Upload 21 files
Browse files- README.md +54 -1
- added_tokens.json +5 -0
- all_results.json +9 -0
- config.json +28 -0
- generation_config.json +6 -0
- llamaboard_config.yaml +63 -0
- main.py +46 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- requirements.txt +0 -0
- running_log.txt +904 -0
- special_tokens_map.json +20 -0
- tokenizer.json +0 -0
- tokenizer_config.json +44 -0
- train_results.json +9 -0
- trainer_log.jsonl +302 -0
- trainer_state.json +2451 -0
- training_args.bin +3 -0
- training_args.yaml +27 -0
- training_loss.png +0 -0
- vocab.json +0 -0
README.md
CHANGED
|
@@ -1,3 +1,56 @@
|
|
| 1 |
---
|
| 2 |
-
license:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
license: other
|
| 3 |
+
base_model: Qwen/Qwen2-0.5B
|
| 4 |
+
tags:
|
| 5 |
+
- llama-factory
|
| 6 |
+
- full
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: train_2024-06-08-23-23-14
|
| 10 |
+
results: []
|
| 11 |
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# train_2024-06-08-23-23-14
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [Qwen/Qwen2-0.5B](https://huggingface.co/Qwen/Qwen2-0.5B) on the longzu dataset.
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 5e-05
|
| 38 |
+
- train_batch_size: 1
|
| 39 |
+
- eval_batch_size: 8
|
| 40 |
+
- seed: 42
|
| 41 |
+
- gradient_accumulation_steps: 8
|
| 42 |
+
- total_train_batch_size: 8
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: cosine
|
| 45 |
+
- num_epochs: 35.0
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
|
| 50 |
+
|
| 51 |
+
### Framework versions
|
| 52 |
+
|
| 53 |
+
- Transformers 4.41.2
|
| 54 |
+
- Pytorch 2.3.0+cu121
|
| 55 |
+
- Datasets 2.19.2
|
| 56 |
+
- Tokenizers 0.19.1
|
added_tokens.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|endoftext|>": 151643,
|
| 3 |
+
"<|im_end|>": 151645,
|
| 4 |
+
"<|im_start|>": 151644
|
| 5 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 34.89855072463768,
|
| 3 |
+
"num_input_tokens_seen": 37412688,
|
| 4 |
+
"total_flos": 8.033958240027034e+16,
|
| 5 |
+
"train_loss": 0.3889684765070578,
|
| 6 |
+
"train_runtime": 37510.9602,
|
| 7 |
+
"train_samples_per_second": 0.322,
|
| 8 |
+
"train_steps_per_second": 0.04
|
| 9 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Qwen2-0.5B-finetuning-by-Dragonraja",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Qwen2ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151643,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 896,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 4864,
|
| 13 |
+
"max_position_embeddings": 131072,
|
| 14 |
+
"max_window_layers": 24,
|
| 15 |
+
"model_type": "qwen2",
|
| 16 |
+
"num_attention_heads": 14,
|
| 17 |
+
"num_hidden_layers": 24,
|
| 18 |
+
"num_key_value_heads": 2,
|
| 19 |
+
"rms_norm_eps": 1e-06,
|
| 20 |
+
"rope_theta": 1000000.0,
|
| 21 |
+
"sliding_window": 131072,
|
| 22 |
+
"tie_word_embeddings": true,
|
| 23 |
+
"torch_dtype": "float32",
|
| 24 |
+
"transformers_version": "4.41.2",
|
| 25 |
+
"use_cache": false,
|
| 26 |
+
"use_sliding_window": false,
|
| 27 |
+
"vocab_size": 151936
|
| 28 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"eos_token_id": 151643,
|
| 4 |
+
"max_new_tokens": 2048,
|
| 5 |
+
"transformers_version": "4.41.2"
|
| 6 |
+
}
|
llamaboard_config.yaml
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
top.booster: none
|
| 2 |
+
top.checkpoint_path: null
|
| 3 |
+
top.finetuning_type: full
|
| 4 |
+
top.model_name: Qwen2-0.5B
|
| 5 |
+
top.quantization_bit: none
|
| 6 |
+
top.rope_scaling: none
|
| 7 |
+
top.template: default
|
| 8 |
+
top.visual_inputs: false
|
| 9 |
+
train.additional_target: ''
|
| 10 |
+
train.badam_mode: layer
|
| 11 |
+
train.badam_switch_interval: 50
|
| 12 |
+
train.badam_switch_mode: ascending
|
| 13 |
+
train.badam_update_ratio: 0.05
|
| 14 |
+
train.batch_size: 1
|
| 15 |
+
train.compute_type: fp32
|
| 16 |
+
train.create_new_adapter: false
|
| 17 |
+
train.cutoff_len: 6100
|
| 18 |
+
train.dataset:
|
| 19 |
+
- longzu
|
| 20 |
+
train.dataset_dir: C:\AI\LLaMA-Factory\data
|
| 21 |
+
train.ds_offload: false
|
| 22 |
+
train.ds_stage: none
|
| 23 |
+
train.freeze_extra_modules: ''
|
| 24 |
+
train.freeze_trainable_layers: 2
|
| 25 |
+
train.freeze_trainable_modules: all
|
| 26 |
+
train.galore_rank: 16
|
| 27 |
+
train.galore_scale: 0.25
|
| 28 |
+
train.galore_target: all
|
| 29 |
+
train.galore_update_interval: 200
|
| 30 |
+
train.gradient_accumulation_steps: 8
|
| 31 |
+
train.learning_rate: 5e-5
|
| 32 |
+
train.logging_steps: 5
|
| 33 |
+
train.lora_alpha: 16
|
| 34 |
+
train.lora_dropout: 0
|
| 35 |
+
train.lora_rank: 8
|
| 36 |
+
train.lora_target: ''
|
| 37 |
+
train.loraplus_lr_ratio: 0
|
| 38 |
+
train.lr_scheduler_type: cosine
|
| 39 |
+
train.max_grad_norm: '1.0'
|
| 40 |
+
train.max_samples: '100000'
|
| 41 |
+
train.neftune_alpha: 0
|
| 42 |
+
train.num_train_epochs: '35'
|
| 43 |
+
train.optim: adamw_torch
|
| 44 |
+
train.packing: false
|
| 45 |
+
train.ppo_score_norm: false
|
| 46 |
+
train.ppo_whiten_rewards: false
|
| 47 |
+
train.pref_beta: 0.1
|
| 48 |
+
train.pref_ftx: 0
|
| 49 |
+
train.pref_loss: sigmoid
|
| 50 |
+
train.report_to: false
|
| 51 |
+
train.resize_vocab: false
|
| 52 |
+
train.reward_model: null
|
| 53 |
+
train.save_steps: 100
|
| 54 |
+
train.shift_attn: false
|
| 55 |
+
train.training_stage: Pre-Training
|
| 56 |
+
train.upcast_layernorm: false
|
| 57 |
+
train.use_badam: false
|
| 58 |
+
train.use_dora: false
|
| 59 |
+
train.use_galore: false
|
| 60 |
+
train.use_llama_pro: false
|
| 61 |
+
train.use_rslora: false
|
| 62 |
+
train.val_size: 0
|
| 63 |
+
train.warmup_steps: 0
|
main.py
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
'''
|
| 2 |
+
Calling example, for reference only
|
| 3 |
+
调用示例，仅供参考
|
| 4 |
+
'''
|
| 5 |
+
import os
|
| 6 |
+
|
| 7 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 8 |
+
|
| 9 |
+
messages = [
|
| 10 |
+
{"role": "system", "content": "你是路明非，你会回答任何问题。"},
|
| 11 |
+
]
|
| 12 |
+
|
| 13 |
+
device = "cuda" # the device to load the model onto
|
| 14 |
+
model_path = os.path.dirname(__file__)
|
| 15 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 16 |
+
model_path,
|
| 17 |
+
torch_dtype="auto",
|
| 18 |
+
device_map="auto"
|
| 19 |
+
)
|
| 20 |
+
tokenizer = AutoTokenizer.from_pretrained(model_path)
|
| 21 |
+
response = ''
|
| 22 |
+
if __name__ == '__main__':
|
| 23 |
+
|
| 24 |
+
while True:
|
| 25 |
+
# prompt = "Give me a short introduction to large language model."
|
| 26 |
+
prompt = input("input:")
|
| 27 |
+
messages.append({"role": "user", "content": prompt})
|
| 28 |
+
text = tokenizer.apply_chat_template(
|
| 29 |
+
messages,
|
| 30 |
+
tokenize=False,
|
| 31 |
+
add_generation_prompt=True
|
| 32 |
+
)
|
| 33 |
+
model_inputs = tokenizer([text], return_tensors="pt").to(device)
|
| 34 |
+
|
| 35 |
+
generated_ids = model.generate(
|
| 36 |
+
model_inputs.input_ids,
|
| 37 |
+
max_new_tokens=768,
|
| 38 |
+
pad_token_id=tokenizer.eos_token_id
|
| 39 |
+
)
|
| 40 |
+
generated_ids = [
|
| 41 |
+
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
|
| 42 |
+
]
|
| 43 |
+
|
| 44 |
+
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
|
| 45 |
+
print(response)
|
| 46 |
+
messages.append({"role": "system", "content": response}, )
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:684a23379925da2510592007f1a4946dc89b0ee00ae970df406ef9f614a3eb6e
|
| 3 |
+
size 1976163472
|
requirements.txt
ADDED
|
Binary file (7.41 kB). View file
|
|
|
running_log.txt
ADDED
|
@@ -0,0 +1,904 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
06/08/2024 23:48:32 - INFO - transformers.tokenization_utils_base - loading file vocab.json
|
| 2 |
+
|
| 3 |
+
06/08/2024 23:48:32 - INFO - transformers.tokenization_utils_base - loading file merges.txt
|
| 4 |
+
|
| 5 |
+
06/08/2024 23:48:32 - INFO - transformers.tokenization_utils_base - loading file tokenizer.json
|
| 6 |
+
|
| 7 |
+
06/08/2024 23:48:32 - INFO - transformers.tokenization_utils_base - loading file added_tokens.json
|
| 8 |
+
|
| 9 |
+
06/08/2024 23:48:32 - INFO - transformers.tokenization_utils_base - loading file special_tokens_map.json
|
| 10 |
+
|
| 11 |
+
06/08/2024 23:48:32 - INFO - transformers.tokenization_utils_base - loading file tokenizer_config.json
|
| 12 |
+
|
| 13 |
+
06/08/2024 23:48:33 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
|
| 14 |
+
|
| 15 |
+
06/08/2024 23:48:33 - INFO - llamafactory.data.loader - Loading dataset longzu.json...
|
| 16 |
+
|
| 17 |
+
06/08/2024 23:48:34 - INFO - transformers.configuration_utils - loading configuration file C:\AI\Qwen2_0.5B\config.json
|
| 18 |
+
|
| 19 |
+
06/08/2024 23:48:34 - INFO - transformers.configuration_utils - Model config Qwen2Config {
|
| 20 |
+
"_name_or_path": "C:\\AI\\Qwen2_0.5B",
|
| 21 |
+
"architectures": [
|
| 22 |
+
"Qwen2ForCausalLM"
|
| 23 |
+
],
|
| 24 |
+
"attention_dropout": 0.0,
|
| 25 |
+
"bos_token_id": 151643,
|
| 26 |
+
"eos_token_id": 151643,
|
| 27 |
+
"hidden_act": "silu",
|
| 28 |
+
"hidden_size": 896,
|
| 29 |
+
"initializer_range": 0.02,
|
| 30 |
+
"intermediate_size": 4864,
|
| 31 |
+
"max_position_embeddings": 131072,
|
| 32 |
+
"max_window_layers": 24,
|
| 33 |
+
"model_type": "qwen2",
|
| 34 |
+
"num_attention_heads": 14,
|
| 35 |
+
"num_hidden_layers": 24,
|
| 36 |
+
"num_key_value_heads": 2,
|
| 37 |
+
"rms_norm_eps": 1e-06,
|
| 38 |
+
"rope_theta": 1000000.0,
|
| 39 |
+
"sliding_window": 131072,
|
| 40 |
+
"tie_word_embeddings": true,
|
| 41 |
+
"torch_dtype": "bfloat16",
|
| 42 |
+
"transformers_version": "4.41.2",
|
| 43 |
+
"use_cache": true,
|
| 44 |
+
"use_sliding_window": false,
|
| 45 |
+
"vocab_size": 151936
|
| 46 |
+
}
|
| 47 |
+
|
| 48 |
+
|
| 49 |
+
06/08/2024 23:48:34 - INFO - transformers.modeling_utils - loading weights file C:\AI\Qwen2_0.5B\model.safetensors
|
| 50 |
+
|
| 51 |
+
06/08/2024 23:48:34 - INFO - transformers.modeling_utils - Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16.
|
| 52 |
+
|
| 53 |
+
06/08/2024 23:48:34 - INFO - transformers.generation.configuration_utils - Generate config GenerationConfig {
|
| 54 |
+
"bos_token_id": 151643,
|
| 55 |
+
"eos_token_id": 151643
|
| 56 |
+
}
|
| 57 |
+
|
| 58 |
+
|
| 59 |
+
06/08/2024 23:48:36 - INFO - transformers.modeling_utils - All model checkpoint weights were used when initializing Qwen2ForCausalLM.
|
| 60 |
+
|
| 61 |
+
|
| 62 |
+
06/08/2024 23:48:36 - INFO - transformers.modeling_utils - All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at C:\AI\Qwen2_0.5B.
|
| 63 |
+
If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training.
|
| 64 |
+
|
| 65 |
+
06/08/2024 23:48:36 - INFO - transformers.generation.configuration_utils - loading configuration file C:\AI\Qwen2_0.5B\generation_config.json
|
| 66 |
+
|
| 67 |
+
06/08/2024 23:48:36 - INFO - transformers.generation.configuration_utils - Generate config GenerationConfig {
|
| 68 |
+
"bos_token_id": 151643,
|
| 69 |
+
"eos_token_id": 151643,
|
| 70 |
+
"max_new_tokens": 2048
|
| 71 |
+
}
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
06/08/2024 23:48:37 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.
|
| 75 |
+
|
| 76 |
+
06/08/2024 23:48:37 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
|
| 77 |
+
|
| 78 |
+
06/08/2024 23:48:37 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.
|
| 79 |
+
|
| 80 |
+
06/08/2024 23:48:37 - INFO - llamafactory.model.adapter - Fine-tuning method: Full
|
| 81 |
+
|
| 82 |
+
06/08/2024 23:48:37 - INFO - llamafactory.model.loader - trainable params: 494032768 || all params: 494032768 || trainable%: 100.0000
|
| 83 |
+
|
| 84 |
+
06/08/2024 23:48:37 - INFO - transformers.trainer - ***** Running training *****
|
| 85 |
+
|
| 86 |
+
06/08/2024 23:48:37 - INFO - transformers.trainer - Num examples = 345
|
| 87 |
+
|
| 88 |
+
06/08/2024 23:48:37 - INFO - transformers.trainer - Num Epochs = 35
|
| 89 |
+
|
| 90 |
+
06/08/2024 23:48:37 - INFO - transformers.trainer - Instantaneous batch size per device = 1
|
| 91 |
+
|
| 92 |
+
06/08/2024 23:48:37 - INFO - transformers.trainer - Total train batch size (w. parallel, distributed & accumulation) = 8
|
| 93 |
+
|
| 94 |
+
06/08/2024 23:48:37 - INFO - transformers.trainer - Gradient Accumulation steps = 8
|
| 95 |
+
|
| 96 |
+
06/08/2024 23:48:37 - INFO - transformers.trainer - Total optimization steps = 1,505
|
| 97 |
+
|
| 98 |
+
06/08/2024 23:48:37 - INFO - transformers.trainer - Number of trainable parameters = 494,032,768
|
| 99 |
+
|
| 100 |
+
06/08/2024 23:50:19 - INFO - llamafactory.extras.callbacks - {'loss': 3.8116, 'learning_rate': 4.9999e-05, 'epoch': 0.12, 'throughput': 1052.64}
|
| 101 |
+
|
| 102 |
+
06/08/2024 23:52:10 - INFO - llamafactory.extras.callbacks - {'loss': 3.6928, 'learning_rate': 4.9995e-05, 'epoch': 0.23, 'throughput': 1060.20}
|
| 103 |
+
|
| 104 |
+
06/08/2024 23:54:31 - INFO - llamafactory.extras.callbacks - {'loss': 3.6227, 'learning_rate': 4.9988e-05, 'epoch': 0.35, 'throughput': 1024.22}
|
| 105 |
+
|
| 106 |
+
06/08/2024 23:56:20 - INFO - llamafactory.extras.callbacks - {'loss': 3.6010, 'learning_rate': 4.9978e-05, 'epoch': 0.46, 'throughput': 1032.88}
|
| 107 |
+
|
| 108 |
+
06/08/2024 23:58:03 - INFO - llamafactory.extras.callbacks - {'loss': 3.5390, 'learning_rate': 4.9966e-05, 'epoch': 0.58, 'throughput': 1040.84}
|
| 109 |
+
|
| 110 |
+
06/08/2024 23:59:56 - INFO - llamafactory.extras.callbacks - {'loss': 3.4956, 'learning_rate': 4.9951e-05, 'epoch': 0.70, 'throughput': 1040.12}
|
| 111 |
+
|
| 112 |
+
06/09/2024 00:02:30 - INFO - llamafactory.extras.callbacks - {'loss': 3.5044, 'learning_rate': 4.9933e-05, 'epoch': 0.81, 'throughput': 1024.54}
|
| 113 |
+
|
| 114 |
+
06/09/2024 00:04:46 - INFO - llamafactory.extras.callbacks - {'loss': 3.4324, 'learning_rate': 4.9913e-05, 'epoch': 0.93, 'throughput': 1022.18}
|
| 115 |
+
|
| 116 |
+
06/09/2024 00:07:00 - INFO - llamafactory.extras.callbacks - {'loss': 3.2542, 'learning_rate': 4.9890e-05, 'epoch': 1.04, 'throughput': 1021.10}
|
| 117 |
+
|
| 118 |
+
06/09/2024 00:08:58 - INFO - llamafactory.extras.callbacks - {'loss': 2.9024, 'learning_rate': 4.9864e-05, 'epoch': 1.16, 'throughput': 1023.49}
|
| 119 |
+
|
| 120 |
+
06/09/2024 00:11:02 - INFO - llamafactory.extras.callbacks - {'loss': 2.8069, 'learning_rate': 4.9835e-05, 'epoch': 1.28, 'throughput': 1022.63}
|
| 121 |
+
|
| 122 |
+
06/09/2024 00:12:57 - INFO - llamafactory.extras.callbacks - {'loss': 2.7500, 'learning_rate': 4.9804e-05, 'epoch': 1.39, 'throughput': 1020.77}
|
| 123 |
+
|
| 124 |
+
06/09/2024 00:14:40 - INFO - llamafactory.extras.callbacks - {'loss': 2.7329, 'learning_rate': 4.9770e-05, 'epoch': 1.51, 'throughput': 1024.15}
|
| 125 |
+
|
| 126 |
+
06/09/2024 00:17:00 - INFO - llamafactory.extras.callbacks - {'loss': 2.8212, 'learning_rate': 4.9734e-05, 'epoch': 1.62, 'throughput': 1016.55}
|
| 127 |
+
|
| 128 |
+
06/09/2024 00:19:05 - INFO - llamafactory.extras.callbacks - {'loss': 2.7935, 'learning_rate': 4.9694e-05, 'epoch': 1.74, 'throughput': 1016.39}
|
| 129 |
+
|
| 130 |
+
06/09/2024 00:21:08 - INFO - llamafactory.extras.callbacks - {'loss': 2.7305, 'learning_rate': 4.9652e-05, 'epoch': 1.86, 'throughput': 1017.05}
|
| 131 |
+
|
| 132 |
+
06/09/2024 00:23:25 - INFO - llamafactory.extras.callbacks - {'loss': 2.6482, 'learning_rate': 4.9608e-05, 'epoch': 1.97, 'throughput': 1010.18}
|
| 133 |
+
|
| 134 |
+
06/09/2024 00:25:46 - INFO - llamafactory.extras.callbacks - {'loss': 2.4292, 'learning_rate': 4.9560e-05, 'epoch': 2.09, 'throughput': 1007.97}
|
| 135 |
+
|
| 136 |
+
06/09/2024 00:28:12 - INFO - llamafactory.extras.callbacks - {'loss': 2.1416, 'learning_rate': 4.9510e-05, 'epoch': 2.20, 'throughput': 1005.24}
|
| 137 |
+
|
| 138 |
+
06/09/2024 00:30:30 - INFO - llamafactory.extras.callbacks - {'loss': 2.2847, 'learning_rate': 4.9457e-05, 'epoch': 2.32, 'throughput': 1003.68}
|
| 139 |
+
|
| 140 |
+
06/09/2024 00:30:30 - INFO - transformers.trainer - Saving model checkpoint to saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-100
|
| 141 |
+
|
| 142 |
+
06/09/2024 00:30:30 - INFO - transformers.configuration_utils - Configuration saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-100\config.json
|
| 143 |
+
|
| 144 |
+
06/09/2024 00:30:30 - INFO - transformers.generation.configuration_utils - Configuration saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-100\generation_config.json
|
| 145 |
+
|
| 146 |
+
06/09/2024 00:30:42 - INFO - transformers.modeling_utils - Model weights saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-100\model.safetensors
|
| 147 |
+
|
| 148 |
+
06/09/2024 00:30:42 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-100\tokenizer_config.json
|
| 149 |
+
|
| 150 |
+
06/09/2024 00:30:42 - INFO - transformers.tokenization_utils_base - Special tokens file saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-100\special_tokens_map.json
|
| 151 |
+
|
| 152 |
+
06/09/2024 00:33:05 - INFO - llamafactory.extras.callbacks - {'loss': 2.0944, 'learning_rate': 4.9402e-05, 'epoch': 2.43, 'throughput': 990.48}
|
| 153 |
+
|
| 154 |
+
06/09/2024 00:35:29 - INFO - llamafactory.extras.callbacks - {'loss': 2.2862, 'learning_rate': 4.9344e-05, 'epoch': 2.55, 'throughput': 988.89}
|
| 155 |
+
|
| 156 |
+
06/09/2024 00:37:04 - INFO - llamafactory.extras.callbacks - {'loss': 2.1050, 'learning_rate': 4.9283e-05, 'epoch': 2.67, 'throughput': 992.54}
|
| 157 |
+
|
| 158 |
+
06/09/2024 00:38:56 - INFO - llamafactory.extras.callbacks - {'loss': 2.0287, 'learning_rate': 4.9220e-05, 'epoch': 2.78, 'throughput': 992.56}
|
| 159 |
+
|
| 160 |
+
06/09/2024 00:40:32 - INFO - llamafactory.extras.callbacks - {'loss': 2.0162, 'learning_rate': 4.9154e-05, 'epoch': 2.90, 'throughput': 995.97}
|
| 161 |
+
|
| 162 |
+
06/09/2024 00:42:39 - INFO - llamafactory.extras.callbacks - {'loss': 2.2464, 'learning_rate': 4.9085e-05, 'epoch': 3.01, 'throughput': 997.54}
|
| 163 |
+
|
| 164 |
+
06/09/2024 00:44:38 - INFO - llamafactory.extras.callbacks - {'loss': 1.6561, 'learning_rate': 4.9014e-05, 'epoch': 3.13, 'throughput': 999.52}
|
| 165 |
+
|
| 166 |
+
06/09/2024 00:46:47 - INFO - llamafactory.extras.callbacks - {'loss': 1.6113, 'learning_rate': 4.8940e-05, 'epoch': 3.25, 'throughput': 1000.08}
|
| 167 |
+
|
| 168 |
+
06/09/2024 00:48:53 - INFO - llamafactory.extras.callbacks - {'loss': 1.6235, 'learning_rate': 4.8864e-05, 'epoch': 3.36, 'throughput': 998.34}
|
| 169 |
+
|
| 170 |
+
06/09/2024 00:51:17 - INFO - llamafactory.extras.callbacks - {'loss': 1.7873, 'learning_rate': 4.8784e-05, 'epoch': 3.48, 'throughput': 997.72}
|
| 171 |
+
|
| 172 |
+
06/09/2024 00:53:20 - INFO - llamafactory.extras.callbacks - {'loss': 1.3723, 'learning_rate': 4.8703e-05, 'epoch': 3.59, 'throughput': 995.58}
|
| 173 |
+
|
| 174 |
+
06/09/2024 00:55:20 - INFO - llamafactory.extras.callbacks - {'loss': 1.6512, 'learning_rate': 4.8619e-05, 'epoch': 3.71, 'throughput': 997.10}
|
| 175 |
+
|
| 176 |
+
06/09/2024 00:57:20 - INFO - llamafactory.extras.callbacks - {'loss': 1.5524, 'learning_rate': 4.8532e-05, 'epoch': 3.83, 'throughput': 997.64}
|
| 177 |
+
|
| 178 |
+
06/09/2024 00:59:17 - INFO - llamafactory.extras.callbacks - {'loss': 1.5954, 'learning_rate': 4.8442e-05, 'epoch': 3.94, 'throughput': 999.10}
|
| 179 |
+
|
| 180 |
+
06/09/2024 01:00:53 - INFO - llamafactory.extras.callbacks - {'loss': 1.1652, 'learning_rate': 4.8350e-05, 'epoch': 4.06, 'throughput': 1001.11}
|
| 181 |
+
|
| 182 |
+
06/09/2024 01:03:08 - INFO - llamafactory.extras.callbacks - {'loss': 1.1995, 'learning_rate': 4.8256e-05, 'epoch': 4.17, 'throughput': 1000.51}
|
| 183 |
+
|
| 184 |
+
06/09/2024 01:05:06 - INFO - llamafactory.extras.callbacks - {'loss': 0.9431, 'learning_rate': 4.8159e-05, 'epoch': 4.29, 'throughput': 999.58}
|
| 185 |
+
|
| 186 |
+
06/09/2024 01:07:07 - INFO - llamafactory.extras.callbacks - {'loss': 1.1136, 'learning_rate': 4.8059e-05, 'epoch': 4.41, 'throughput': 998.32}
|
| 187 |
+
|
| 188 |
+
06/09/2024 01:09:12 - INFO - llamafactory.extras.callbacks - {'loss': 1.1509, 'learning_rate': 4.7957e-05, 'epoch': 4.52, 'throughput': 999.32}
|
| 189 |
+
|
| 190 |
+
06/09/2024 01:10:56 - INFO - llamafactory.extras.callbacks - {'loss': 0.9962, 'learning_rate': 4.7853e-05, 'epoch': 4.64, 'throughput': 1000.59}
|
| 191 |
+
|
| 192 |
+
06/09/2024 01:10:56 - INFO - transformers.trainer - Saving model checkpoint to saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-200
|
| 193 |
+
|
| 194 |
+
06/09/2024 01:10:56 - INFO - transformers.configuration_utils - Configuration saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-200\config.json
|
| 195 |
+
|
| 196 |
+
06/09/2024 01:10:56 - INFO - transformers.generation.configuration_utils - Configuration saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-200\generation_config.json
|
| 197 |
+
|
| 198 |
+
06/09/2024 01:11:07 - INFO - transformers.modeling_utils - Model weights saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-200\model.safetensors
|
| 199 |
+
|
| 200 |
+
06/09/2024 01:11:07 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-200\tokenizer_config.json
|
| 201 |
+
|
| 202 |
+
06/09/2024 01:11:07 - INFO - transformers.tokenization_utils_base - Special tokens file saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-200\special_tokens_map.json
|
| 203 |
+
|
| 204 |
+
06/09/2024 01:13:45 - INFO - llamafactory.extras.callbacks - {'loss': 1.2377, 'learning_rate': 4.7746e-05, 'epoch': 4.75, 'throughput': 996.13}
|
| 205 |
+
|
| 206 |
+
06/09/2024 01:15:55 - INFO - llamafactory.extras.callbacks - {'loss': 1.2340, 'learning_rate': 4.7636e-05, 'epoch': 4.87, 'throughput': 996.52}
|
| 207 |
+
|
| 208 |
+
06/09/2024 01:17:48 - INFO - llamafactory.extras.callbacks - {'loss': 1.1453, 'learning_rate': 4.7524e-05, 'epoch': 4.99, 'throughput': 998.06}
|
| 209 |
+
|
| 210 |
+
06/09/2024 01:20:08 - INFO - llamafactory.extras.callbacks - {'loss': 0.9056, 'learning_rate': 4.7410e-05, 'epoch': 5.10, 'throughput': 997.31}
|
| 211 |
+
|
| 212 |
+
06/09/2024 01:21:58 - INFO - llamafactory.extras.callbacks - {'loss': 0.7349, 'learning_rate': 4.7293e-05, 'epoch': 5.22, 'throughput': 998.01}
|
| 213 |
+
|
| 214 |
+
06/09/2024 01:23:54 - INFO - llamafactory.extras.callbacks - {'loss': 0.6968, 'learning_rate': 4.7174e-05, 'epoch': 5.33, 'throughput': 999.00}
|
| 215 |
+
|
| 216 |
+
06/09/2024 01:26:19 - INFO - llamafactory.extras.callbacks - {'loss': 0.8510, 'learning_rate': 4.7052e-05, 'epoch': 5.45, 'throughput': 998.45}
|
| 217 |
+
|
| 218 |
+
06/09/2024 01:28:14 - INFO - llamafactory.extras.callbacks - {'loss': 0.7160, 'learning_rate': 4.6928e-05, 'epoch': 5.57, 'throughput': 999.21}
|
| 219 |
+
|
| 220 |
+
06/09/2024 01:30:03 - INFO - llamafactory.extras.callbacks - {'loss': 0.6384, 'learning_rate': 4.6801e-05, 'epoch': 5.68, 'throughput': 1000.40}
|
| 221 |
+
|
| 222 |
+
06/09/2024 01:32:24 - INFO - llamafactory.extras.callbacks - {'loss': 0.7799, 'learning_rate': 4.6672e-05, 'epoch': 5.80, 'throughput': 998.13}
|
| 223 |
+
|
| 224 |
+
06/09/2024 01:34:26 - INFO - llamafactory.extras.callbacks - {'loss': 0.7923, 'learning_rate': 4.6541e-05, 'epoch': 5.91, 'throughput': 997.95}
|
| 225 |
+
|
| 226 |
+
06/09/2024 01:36:29 - INFO - llamafactory.extras.callbacks - {'loss': 0.7452, 'learning_rate': 4.6408e-05, 'epoch': 6.03, 'throughput': 998.69}
|
| 227 |
+
|
| 228 |
+
06/09/2024 01:38:14 - INFO - llamafactory.extras.callbacks - {'loss': 0.4085, 'learning_rate': 4.6272e-05, 'epoch': 6.14, 'throughput': 999.98}
|
| 229 |
+
|
| 230 |
+
06/09/2024 01:40:29 - INFO - llamafactory.extras.callbacks - {'loss': 0.5777, 'learning_rate': 4.6133e-05, 'epoch': 6.26, 'throughput': 1000.40}
|
| 231 |
+
|
| 232 |
+
06/09/2024 01:42:32 - INFO - llamafactory.extras.callbacks - {'loss': 0.4718, 'learning_rate': 4.5993e-05, 'epoch': 6.38, 'throughput': 1000.87}
|
| 233 |
+
|
| 234 |
+
06/09/2024 01:44:17 - INFO - llamafactory.extras.callbacks - {'loss': 0.3723, 'learning_rate': 4.5850e-05, 'epoch': 6.49, 'throughput': 1002.09}
|
| 235 |
+
|
| 236 |
+
06/09/2024 01:46:27 - INFO - llamafactory.extras.callbacks - {'loss': 0.4453, 'learning_rate': 4.5705e-05, 'epoch': 6.61, 'throughput': 1000.84}
|
| 237 |
+
|
| 238 |
+
06/09/2024 01:48:29 - INFO - llamafactory.extras.callbacks - {'loss': 0.5742, 'learning_rate': 4.5557e-05, 'epoch': 6.72, 'throughput': 1001.38}
|
| 239 |
+
|
| 240 |
+
06/09/2024 01:50:33 - INFO - llamafactory.extras.callbacks - {'loss': 0.5291, 'learning_rate': 4.5408e-05, 'epoch': 6.84, 'throughput': 1001.95}
|
| 241 |
+
|
| 242 |
+
06/09/2024 01:52:27 - INFO - llamafactory.extras.callbacks - {'loss': 0.4968, 'learning_rate': 4.5256e-05, 'epoch': 6.96, 'throughput': 1002.60}
|
| 243 |
+
|
| 244 |
+
06/09/2024 01:52:27 - INFO - transformers.trainer - Saving model checkpoint to saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-300
|
| 245 |
+
|
| 246 |
+
06/09/2024 01:52:27 - INFO - transformers.configuration_utils - Configuration saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-300\config.json
|
| 247 |
+
|
| 248 |
+
06/09/2024 01:52:27 - INFO - transformers.generation.configuration_utils - Configuration saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-300\generation_config.json
|
| 249 |
+
|
| 250 |
+
06/09/2024 01:52:42 - INFO - transformers.modeling_utils - Model weights saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-300\model.safetensors
|
| 251 |
+
|
| 252 |
+
06/09/2024 01:52:42 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-300\tokenizer_config.json
|
| 253 |
+
|
| 254 |
+
06/09/2024 01:52:42 - INFO - transformers.tokenization_utils_base - Special tokens file saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-300\special_tokens_map.json
|
| 255 |
+
|
| 256 |
+
06/09/2024 01:54:56 - INFO - llamafactory.extras.callbacks - {'loss': 0.4210, 'learning_rate': 4.5102e-05, 'epoch': 7.07, 'throughput': 999.94}
|
| 257 |
+
|
| 258 |
+
06/09/2024 01:57:04 - INFO - llamafactory.extras.callbacks - {'loss': 0.2767, 'learning_rate': 4.4946e-05, 'epoch': 7.19, 'throughput': 998.07}
|
| 259 |
+
|
| 260 |
+
06/09/2024 01:59:02 - INFO - llamafactory.extras.callbacks - {'loss': 0.2922, 'learning_rate': 4.4787e-05, 'epoch': 7.30, 'throughput': 998.79}
|
| 261 |
+
|
| 262 |
+
06/09/2024 02:00:54 - INFO - llamafactory.extras.callbacks - {'loss': 0.2768, 'learning_rate': 4.4627e-05, 'epoch': 7.42, 'throughput': 998.57}
|
| 263 |
+
|
| 264 |
+
06/09/2024 02:03:27 - INFO - llamafactory.extras.callbacks - {'loss': 0.3281, 'learning_rate': 4.4464e-05, 'epoch': 7.54, 'throughput': 995.98}
|
| 265 |
+
|
| 266 |
+
06/09/2024 02:05:38 - INFO - llamafactory.extras.callbacks - {'loss': 0.3374, 'learning_rate': 4.4299e-05, 'epoch': 7.65, 'throughput': 995.98}
|
| 267 |
+
|
| 268 |
+
06/09/2024 02:07:32 - INFO - llamafactory.extras.callbacks - {'loss': 0.2491, 'learning_rate': 4.4132e-05, 'epoch': 7.77, 'throughput': 996.31}
|
| 269 |
+
|
| 270 |
+
06/09/2024 02:09:47 - INFO - llamafactory.extras.callbacks - {'loss': 0.3893, 'learning_rate': 4.3963e-05, 'epoch': 7.88, 'throughput': 996.21}
|
| 271 |
+
|
| 272 |
+
06/09/2024 02:12:03 - INFO - llamafactory.extras.callbacks - {'loss': 0.3761, 'learning_rate': 4.3792e-05, 'epoch': 8.00, 'throughput': 996.14}
|
| 273 |
+
|
| 274 |
+
06/09/2024 02:14:16 - INFO - llamafactory.extras.callbacks - {'loss': 0.2360, 'learning_rate': 4.3619e-05, 'epoch': 8.12, 'throughput': 996.45}
|
| 275 |
+
|
| 276 |
+
06/09/2024 02:16:14 - INFO - llamafactory.extras.callbacks - {'loss': 0.1584, 'learning_rate': 4.3444e-05, 'epoch': 8.23, 'throughput': 996.43}
|
| 277 |
+
|
| 278 |
+
06/09/2024 02:17:54 - INFO - llamafactory.extras.callbacks - {'loss': 0.1481, 'learning_rate': 4.3267e-05, 'epoch': 8.35, 'throughput': 997.27}
|
| 279 |
+
|
| 280 |
+
06/09/2024 02:19:57 - INFO - llamafactory.extras.callbacks - {'loss': 0.1743, 'learning_rate': 4.3088e-05, 'epoch': 8.46, 'throughput': 996.84}
|
| 281 |
+
|
| 282 |
+
06/09/2024 02:22:22 - INFO - llamafactory.extras.callbacks - {'loss': 0.3162, 'learning_rate': 4.2907e-05, 'epoch': 8.58, 'throughput': 996.95}
|
| 283 |
+
|
| 284 |
+
06/09/2024 02:24:19 - INFO - llamafactory.extras.callbacks - {'loss': 0.2235, 'learning_rate': 4.2724e-05, 'epoch': 8.70, 'throughput': 997.40}
|
| 285 |
+
|
| 286 |
+
06/09/2024 02:26:35 - INFO - llamafactory.extras.callbacks - {'loss': 0.2504, 'learning_rate': 4.2539e-05, 'epoch': 8.81, 'throughput': 997.16}
|
| 287 |
+
|
| 288 |
+
06/09/2024 02:28:41 - INFO - llamafactory.extras.callbacks - {'loss': 0.2136, 'learning_rate': 4.2352e-05, 'epoch': 8.93, 'throughput': 997.85}
|
| 289 |
+
|
| 290 |
+
06/09/2024 02:30:12 - INFO - llamafactory.extras.callbacks - {'loss': 0.1047, 'learning_rate': 4.2163e-05, 'epoch': 9.04, 'throughput': 998.27}
|
| 291 |
+
|
| 292 |
+
06/09/2024 02:31:55 - INFO - llamafactory.extras.callbacks - {'loss': 0.1015, 'learning_rate': 4.1972e-05, 'epoch': 9.16, 'throughput': 999.00}
|
| 293 |
+
|
| 294 |
+
06/09/2024 02:34:04 - INFO - llamafactory.extras.callbacks - {'loss': 0.1505, 'learning_rate': 4.1780e-05, 'epoch': 9.28, 'throughput': 998.92}
|
| 295 |
+
|
| 296 |
+
06/09/2024 02:34:04 - INFO - transformers.trainer - Saving model checkpoint to saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-400
|
| 297 |
+
|
| 298 |
+
06/09/2024 02:34:04 - INFO - transformers.configuration_utils - Configuration saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-400\config.json
|
| 299 |
+
|
| 300 |
+
06/09/2024 02:34:04 - INFO - transformers.generation.configuration_utils - Configuration saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-400\generation_config.json
|
| 301 |
+
|
| 302 |
+
06/09/2024 02:34:12 - INFO - transformers.modeling_utils - Model weights saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-400\model.safetensors
|
| 303 |
+
|
| 304 |
+
06/09/2024 02:34:12 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-400\tokenizer_config.json
|
| 305 |
+
|
| 306 |
+
06/09/2024 02:34:12 - INFO - transformers.tokenization_utils_base - Special tokens file saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-400\special_tokens_map.json
|
| 307 |
+
|
| 308 |
+
06/09/2024 02:36:29 - INFO - llamafactory.extras.callbacks - {'loss': 0.1135, 'learning_rate': 4.1586e-05, 'epoch': 9.39, 'throughput': 997.11}
|
| 309 |
+
|
| 310 |
+
06/09/2024 02:38:38 - INFO - llamafactory.extras.callbacks - {'loss': 0.1832, 'learning_rate': 4.1389e-05, 'epoch': 9.51, 'throughput': 997.17}
|
| 311 |
+
|
| 312 |
+
06/09/2024 02:40:19 - INFO - llamafactory.extras.callbacks - {'loss': 0.1178, 'learning_rate': 4.1192e-05, 'epoch': 9.62, 'throughput': 998.04}
|
| 313 |
+
|
| 314 |
+
06/09/2024 02:42:54 - INFO - llamafactory.extras.callbacks - {'loss': 0.1426, 'learning_rate': 4.0992e-05, 'epoch': 9.74, 'throughput': 996.34}
|
| 315 |
+
|
| 316 |
+
06/09/2024 02:45:09 - INFO - llamafactory.extras.callbacks - {'loss': 0.1603, 'learning_rate': 4.0790e-05, 'epoch': 9.86, 'throughput': 996.80}
|
| 317 |
+
|
| 318 |
+
06/09/2024 02:47:19 - INFO - llamafactory.extras.callbacks - {'loss': 0.1548, 'learning_rate': 4.0587e-05, 'epoch': 9.97, 'throughput': 996.01}
|
| 319 |
+
|
| 320 |
+
06/09/2024 02:49:42 - INFO - llamafactory.extras.callbacks - {'loss': 0.1407, 'learning_rate': 4.0382e-05, 'epoch': 10.09, 'throughput': 995.97}
|
| 321 |
+
|
| 322 |
+
06/09/2024 02:51:53 - INFO - llamafactory.extras.callbacks - {'loss': 0.0791, 'learning_rate': 4.0176e-05, 'epoch': 10.20, 'throughput': 995.82}
|
| 323 |
+
|
| 324 |
+
06/09/2024 02:54:04 - INFO - llamafactory.extras.callbacks - {'loss': 0.0722, 'learning_rate': 3.9968e-05, 'epoch': 10.32, 'throughput': 995.11}
|
| 325 |
+
|
| 326 |
+
06/09/2024 02:55:47 - INFO - llamafactory.extras.callbacks - {'loss': 0.0655, 'learning_rate': 3.9758e-05, 'epoch': 10.43, 'throughput': 995.82}
|
| 327 |
+
|
| 328 |
+
06/09/2024 02:57:40 - INFO - llamafactory.extras.callbacks - {'loss': 0.0723, 'learning_rate': 3.9546e-05, 'epoch': 10.55, 'throughput': 996.49}
|
| 329 |
+
|
| 330 |
+
06/09/2024 02:59:24 - INFO - llamafactory.extras.callbacks - {'loss': 0.0655, 'learning_rate': 3.9333e-05, 'epoch': 10.67, 'throughput': 997.33}
|
| 331 |
+
|
| 332 |
+
06/09/2024 03:01:52 - INFO - llamafactory.extras.callbacks - {'loss': 0.1534, 'learning_rate': 3.9119e-05, 'epoch': 10.78, 'throughput': 996.60}
|
| 333 |
+
|
| 334 |
+
06/09/2024 03:03:55 - INFO - llamafactory.extras.callbacks - {'loss': 0.0947, 'learning_rate': 3.8903e-05, 'epoch': 10.90, 'throughput': 996.89}
|
| 335 |
+
|
| 336 |
+
06/09/2024 03:05:59 - INFO - llamafactory.extras.callbacks - {'loss': 0.0868, 'learning_rate': 3.8685e-05, 'epoch': 11.01, 'throughput': 997.29}
|
| 337 |
+
|
| 338 |
+
06/09/2024 03:08:05 - INFO - llamafactory.extras.callbacks - {'loss': 0.0467, 'learning_rate': 3.8466e-05, 'epoch': 11.13, 'throughput': 997.52}
|
| 339 |
+
|
| 340 |
+
06/09/2024 03:09:48 - INFO - llamafactory.extras.callbacks - {'loss': 0.0521, 'learning_rate': 3.8246e-05, 'epoch': 11.25, 'throughput': 998.15}
|
| 341 |
+
|
| 342 |
+
06/09/2024 03:11:59 - INFO - llamafactory.extras.callbacks - {'loss': 0.0510, 'learning_rate': 3.8024e-05, 'epoch': 11.36, 'throughput': 998.66}
|
| 343 |
+
|
| 344 |
+
06/09/2024 03:13:59 - INFO - llamafactory.extras.callbacks - {'loss': 0.0753, 'learning_rate': 3.7800e-05, 'epoch': 11.48, 'throughput': 999.10}
|
| 345 |
+
|
| 346 |
+
06/09/2024 03:16:02 - INFO - llamafactory.extras.callbacks - {'loss': 0.0601, 'learning_rate': 3.7575e-05, 'epoch': 11.59, 'throughput': 999.57}
|
| 347 |
+
|
| 348 |
+
06/09/2024 03:16:02 - INFO - transformers.trainer - Saving model checkpoint to saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-500
|
| 349 |
+
|
| 350 |
+
06/09/2024 03:16:02 - INFO - transformers.configuration_utils - Configuration saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-500\config.json
|
| 351 |
+
|
| 352 |
+
06/09/2024 03:16:02 - INFO - transformers.generation.configuration_utils - Configuration saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-500\generation_config.json
|
| 353 |
+
|
| 354 |
+
06/09/2024 03:16:09 - INFO - transformers.modeling_utils - Model weights saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-500\model.safetensors
|
| 355 |
+
|
| 356 |
+
06/09/2024 03:16:09 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-500\tokenizer_config.json
|
| 357 |
+
|
| 358 |
+
06/09/2024 03:16:09 - INFO - transformers.tokenization_utils_base - Special tokens file saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-500\special_tokens_map.json
|
| 359 |
+
|
| 360 |
+
06/09/2024 03:18:09 - INFO - llamafactory.extras.callbacks - {'loss': 0.0533, 'learning_rate': 3.7349e-05, 'epoch': 11.71, 'throughput': 998.61}
|
| 361 |
+
|
| 362 |
+
06/09/2024 03:20:11 - INFO - llamafactory.extras.callbacks - {'loss': 0.0640, 'learning_rate': 3.7122e-05, 'epoch': 11.83, 'throughput': 999.10}
|
| 363 |
+
|
| 364 |
+
06/09/2024 03:22:03 - INFO - llamafactory.extras.callbacks - {'loss': 0.0755, 'learning_rate': 3.6893e-05, 'epoch': 11.94, 'throughput': 999.59}
|
| 365 |
+
|
| 366 |
+
06/09/2024 03:23:54 - INFO - llamafactory.extras.callbacks - {'loss': 0.0553, 'learning_rate': 3.6662e-05, 'epoch': 12.06, 'throughput': 1000.07}
|
| 367 |
+
|
| 368 |
+
06/09/2024 03:26:08 - INFO - llamafactory.extras.callbacks - {'loss': 0.0355, 'learning_rate': 3.6431e-05, 'epoch': 12.17, 'throughput': 999.57}
|
| 369 |
+
|
| 370 |
+
06/09/2024 03:28:14 - INFO - llamafactory.extras.callbacks - {'loss': 0.0413, 'learning_rate': 3.6198e-05, 'epoch': 12.29, 'throughput': 999.88}
|
| 371 |
+
|
| 372 |
+
06/09/2024 03:30:05 - INFO - llamafactory.extras.callbacks - {'loss': 0.0596, 'learning_rate': 3.5964e-05, 'epoch': 12.41, 'throughput': 1000.36}
|
| 373 |
+
|
| 374 |
+
06/09/2024 03:32:06 - INFO - llamafactory.extras.callbacks - {'loss': 0.0479, 'learning_rate': 3.5729e-05, 'epoch': 12.52, 'throughput': 1000.70}
|
| 375 |
+
|
| 376 |
+
06/09/2024 03:34:19 - INFO - llamafactory.extras.callbacks - {'loss': 0.0470, 'learning_rate': 3.5493e-05, 'epoch': 12.64, 'throughput': 1000.73}
|
| 377 |
+
|
| 378 |
+
06/09/2024 03:36:18 - INFO - llamafactory.extras.callbacks - {'loss': 0.0492, 'learning_rate': 3.5256e-05, 'epoch': 12.75, 'throughput': 1001.04}
|
| 379 |
+
|
| 380 |
+
06/09/2024 03:38:16 - INFO - llamafactory.extras.callbacks - {'loss': 0.0471, 'learning_rate': 3.5017e-05, 'epoch': 12.87, 'throughput': 1001.36}
|
| 381 |
+
|
| 382 |
+
06/09/2024 03:40:25 - INFO - llamafactory.extras.callbacks - {'loss': 0.1041, 'learning_rate': 3.4778e-05, 'epoch': 12.99, 'throughput': 1000.82}
|
| 383 |
+
|
| 384 |
+
06/09/2024 03:42:14 - INFO - llamafactory.extras.callbacks - {'loss': 0.0282, 'learning_rate': 3.4537e-05, 'epoch': 13.10, 'throughput': 1001.50}
|
| 385 |
+
|
| 386 |
+
06/09/2024 03:44:37 - INFO - llamafactory.extras.callbacks - {'loss': 0.0272, 'learning_rate': 3.4295e-05, 'epoch': 13.22, 'throughput': 1000.51}
|
| 387 |
+
|
| 388 |
+
06/09/2024 03:47:00 - INFO - llamafactory.extras.callbacks - {'loss': 0.0342, 'learning_rate': 3.4053e-05, 'epoch': 13.33, 'throughput': 1000.60}
|
| 389 |
+
|
| 390 |
+
06/09/2024 03:48:31 - INFO - llamafactory.extras.callbacks - {'loss': 0.0855, 'learning_rate': 3.3809e-05, 'epoch': 13.45, 'throughput': 1000.75}
|
| 391 |
+
|
| 392 |
+
06/09/2024 03:50:33 - INFO - llamafactory.extras.callbacks - {'loss': 0.0378, 'learning_rate': 3.3564e-05, 'epoch': 13.57, 'throughput': 1001.03}
|
| 393 |
+
|
| 394 |
+
06/09/2024 03:52:10 - INFO - llamafactory.extras.callbacks - {'loss': 0.0457, 'learning_rate': 3.3319e-05, 'epoch': 13.68, 'throughput': 1001.65}
|
| 395 |
+
|
| 396 |
+
06/09/2024 03:54:42 - INFO - llamafactory.extras.callbacks - {'loss': 0.0453, 'learning_rate': 3.3072e-05, 'epoch': 13.80, 'throughput': 1001.53}
|
| 397 |
+
|
| 398 |
+
06/09/2024 03:56:41 - INFO - llamafactory.extras.callbacks - {'loss': 0.0378, 'learning_rate': 3.2825e-05, 'epoch': 13.91, 'throughput': 1001.72}
|
| 399 |
+
|
| 400 |
+
06/09/2024 03:56:41 - INFO - transformers.trainer - Saving model checkpoint to saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-600
|
| 401 |
+
|
| 402 |
+
06/09/2024 03:56:41 - INFO - transformers.configuration_utils - Configuration saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-600\config.json
|
| 403 |
+
|
| 404 |
+
06/09/2024 03:56:41 - INFO - transformers.generation.configuration_utils - Configuration saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-600\generation_config.json
|
| 405 |
+
|
| 406 |
+
06/09/2024 03:57:01 - INFO - transformers.modeling_utils - Model weights saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-600\model.safetensors
|
| 407 |
+
|
| 408 |
+
06/09/2024 03:57:01 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-600\tokenizer_config.json
|
| 409 |
+
|
| 410 |
+
06/09/2024 03:57:01 - INFO - transformers.tokenization_utils_base - Special tokens file saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-600\special_tokens_map.json
|
| 411 |
+
|
| 412 |
+
06/09/2024 03:59:09 - INFO - llamafactory.extras.callbacks - {'loss': 0.0296, 'learning_rate': 3.2576e-05, 'epoch': 14.03, 'throughput': 999.94}
|
| 413 |
+
|
| 414 |
+
06/09/2024 04:01:17 - INFO - llamafactory.extras.callbacks - {'loss': 0.0216, 'learning_rate': 3.2327e-05, 'epoch': 14.14, 'throughput': 999.25}
|
| 415 |
+
|
| 416 |
+
06/09/2024 04:03:35 - INFO - llamafactory.extras.callbacks - {'loss': 0.0299, 'learning_rate': 3.2077e-05, 'epoch': 14.26, 'throughput': 998.89}
|
| 417 |
+
|
| 418 |
+
06/09/2024 04:05:32 - INFO - llamafactory.extras.callbacks - {'loss': 0.0247, 'learning_rate': 3.1827e-05, 'epoch': 14.38, 'throughput': 998.88}
|
| 419 |
+
|
| 420 |
+
06/09/2024 04:08:01 - INFO - llamafactory.extras.callbacks - {'loss': 0.0455, 'learning_rate': 3.1575e-05, 'epoch': 14.49, 'throughput': 997.37}
|
| 421 |
+
|
| 422 |
+
06/09/2024 04:09:49 - INFO - llamafactory.extras.callbacks - {'loss': 0.0262, 'learning_rate': 3.1323e-05, 'epoch': 14.61, 'throughput': 997.84}
|
| 423 |
+
|
| 424 |
+
06/09/2024 04:11:59 - INFO - llamafactory.extras.callbacks - {'loss': 0.0281, 'learning_rate': 3.1071e-05, 'epoch': 14.72, 'throughput': 998.19}
|
| 425 |
+
|
| 426 |
+
06/09/2024 04:13:52 - INFO - llamafactory.extras.callbacks - {'loss': 0.0294, 'learning_rate': 3.0817e-05, 'epoch': 14.84, 'throughput': 998.63}
|
| 427 |
+
|
| 428 |
+
06/09/2024 04:15:58 - INFO - llamafactory.extras.callbacks - {'loss': 0.0291, 'learning_rate': 3.0563e-05, 'epoch': 14.96, 'throughput': 998.97}
|
| 429 |
+
|
| 430 |
+
06/09/2024 04:18:05 - INFO - llamafactory.extras.callbacks - {'loss': 0.0216, 'learning_rate': 3.0308e-05, 'epoch': 15.07, 'throughput': 999.01}
|
| 431 |
+
|
| 432 |
+
06/09/2024 04:20:32 - INFO - llamafactory.extras.callbacks - {'loss': 0.0218, 'learning_rate': 3.0053e-05, 'epoch': 15.19, 'throughput': 997.79}
|
| 433 |
+
|
| 434 |
+
06/09/2024 04:22:51 - INFO - llamafactory.extras.callbacks - {'loss': 0.0283, 'learning_rate': 2.9797e-05, 'epoch': 15.30, 'throughput': 997.64}
|
| 435 |
+
|
| 436 |
+
06/09/2024 04:24:40 - INFO - llamafactory.extras.callbacks - {'loss': 0.0259, 'learning_rate': 2.9541e-05, 'epoch': 15.42, 'throughput': 997.98}
|
| 437 |
+
|
| 438 |
+
06/09/2024 04:26:42 - INFO - llamafactory.extras.callbacks - {'loss': 0.0716, 'learning_rate': 2.9284e-05, 'epoch': 15.54, 'throughput': 998.25}
|
| 439 |
+
|
| 440 |
+
06/09/2024 04:29:05 - INFO - llamafactory.extras.callbacks - {'loss': 0.0250, 'learning_rate': 2.9027e-05, 'epoch': 15.65, 'throughput': 998.26}
|
| 441 |
+
|
| 442 |
+
06/09/2024 04:31:00 - INFO - llamafactory.extras.callbacks - {'loss': 0.0218, 'learning_rate': 2.8769e-05, 'epoch': 15.77, 'throughput': 998.47}
|
| 443 |
+
|
| 444 |
+
06/09/2024 04:32:58 - INFO - llamafactory.extras.callbacks - {'loss': 0.0231, 'learning_rate': 2.8511e-05, 'epoch': 15.88, 'throughput': 998.80}
|
| 445 |
+
|
| 446 |
+
06/09/2024 04:34:35 - INFO - llamafactory.extras.callbacks - {'loss': 0.0228, 'learning_rate': 2.8252e-05, 'epoch': 16.00, 'throughput': 999.30}
|
| 447 |
+
|
| 448 |
+
06/09/2024 04:36:56 - INFO - llamafactory.extras.callbacks - {'loss': 0.0290, 'learning_rate': 2.7993e-05, 'epoch': 16.12, 'throughput': 999.19}
|
| 449 |
+
|
| 450 |
+
06/09/2024 04:39:18 - INFO - llamafactory.extras.callbacks - {'loss': 0.0199, 'learning_rate': 2.7734e-05, 'epoch': 16.23, 'throughput': 999.18}
|
| 451 |
+
|
| 452 |
+
06/09/2024 04:39:18 - INFO - transformers.trainer - Saving model checkpoint to saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-700
|
| 453 |
+
|
| 454 |
+
06/09/2024 04:39:18 - INFO - transformers.configuration_utils - Configuration saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-700\config.json
|
| 455 |
+
|
| 456 |
+
06/09/2024 04:39:18 - INFO - transformers.generation.configuration_utils - Configuration saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-700\generation_config.json
|
| 457 |
+
|
| 458 |
+
06/09/2024 04:39:31 - INFO - transformers.modeling_utils - Model weights saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-700\model.safetensors
|
| 459 |
+
|
| 460 |
+
06/09/2024 04:39:31 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-700\tokenizer_config.json
|
| 461 |
+
|
| 462 |
+
06/09/2024 04:39:31 - INFO - transformers.tokenization_utils_base - Special tokens file saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-700\special_tokens_map.json
|
| 463 |
+
|
| 464 |
+
06/09/2024 04:41:37 - INFO - llamafactory.extras.callbacks - {'loss': 0.0259, 'learning_rate': 2.7475e-05, 'epoch': 16.35, 'throughput': 997.81}
|
| 465 |
+
|
| 466 |
+
06/09/2024 04:43:43 - INFO - llamafactory.extras.callbacks - {'loss': 0.0210, 'learning_rate': 2.7215e-05, 'epoch': 16.46, 'throughput': 997.83}
|
| 467 |
+
|
| 468 |
+
06/09/2024 04:45:37 - INFO - llamafactory.extras.callbacks - {'loss': 0.0199, 'learning_rate': 2.6955e-05, 'epoch': 16.58, 'throughput': 998.23}
|
| 469 |
+
|
| 470 |
+
06/09/2024 04:47:35 - INFO - llamafactory.extras.callbacks - {'loss': 0.0189, 'learning_rate': 2.6695e-05, 'epoch': 16.70, 'throughput': 998.55}
|
| 471 |
+
|
| 472 |
+
06/09/2024 04:49:15 - INFO - llamafactory.extras.callbacks - {'loss': 0.0169, 'learning_rate': 2.6434e-05, 'epoch': 16.81, 'throughput': 998.93}
|
| 473 |
+
|
| 474 |
+
06/09/2024 04:51:09 - INFO - llamafactory.extras.callbacks - {'loss': 0.0209, 'learning_rate': 2.6174e-05, 'epoch': 16.93, 'throughput': 999.34}
|
| 475 |
+
|
| 476 |
+
06/09/2024 04:53:23 - INFO - llamafactory.extras.callbacks - {'loss': 0.0201, 'learning_rate': 2.5913e-05, 'epoch': 17.04, 'throughput': 999.59}
|
| 477 |
+
|
| 478 |
+
06/09/2024 04:55:31 - INFO - llamafactory.extras.callbacks - {'loss': 0.0170, 'learning_rate': 2.5652e-05, 'epoch': 17.16, 'throughput': 999.09}
|
| 479 |
+
|
| 480 |
+
06/09/2024 04:57:15 - INFO - llamafactory.extras.callbacks - {'loss': 0.0187, 'learning_rate': 2.5391e-05, 'epoch': 17.28, 'throughput': 999.36}
|
| 481 |
+
|
| 482 |
+
06/09/2024 04:59:04 - INFO - llamafactory.extras.callbacks - {'loss': 0.0242, 'learning_rate': 2.5130e-05, 'epoch': 17.39, 'throughput': 999.72}
|
| 483 |
+
|
| 484 |
+
06/09/2024 05:01:05 - INFO - llamafactory.extras.callbacks - {'loss': 0.0153, 'learning_rate': 2.4870e-05, 'epoch': 17.51, 'throughput': 1000.04}
|
| 485 |
+
|
| 486 |
+
06/09/2024 05:03:20 - INFO - llamafactory.extras.callbacks - {'loss': 0.0182, 'learning_rate': 2.4609e-05, 'epoch': 17.62, 'throughput': 1000.12}
|
| 487 |
+
|
| 488 |
+
06/09/2024 05:05:14 - INFO - llamafactory.extras.callbacks - {'loss': 0.0143, 'learning_rate': 2.4348e-05, 'epoch': 17.74, 'throughput': 1000.34}
|
| 489 |
+
|
| 490 |
+
06/09/2024 05:07:25 - INFO - llamafactory.extras.callbacks - {'loss': 0.0164, 'learning_rate': 2.4087e-05, 'epoch': 17.86, 'throughput': 1000.46}
|
| 491 |
+
|
| 492 |
+
06/09/2024 05:09:29 - INFO - llamafactory.extras.callbacks - {'loss': 0.0157, 'learning_rate': 2.3826e-05, 'epoch': 17.97, 'throughput': 1000.43}
|
| 493 |
+
|
| 494 |
+
06/09/2024 05:11:39 - INFO - llamafactory.extras.callbacks - {'loss': 0.0304, 'learning_rate': 2.3566e-05, 'epoch': 18.09, 'throughput': 1000.34}
|
| 495 |
+
|
| 496 |
+
06/09/2024 05:14:00 - INFO - llamafactory.extras.callbacks - {'loss': 0.0090, 'learning_rate': 2.3305e-05, 'epoch': 18.20, 'throughput': 1000.45}
|
| 497 |
+
|
| 498 |
+
06/09/2024 05:15:24 - INFO - llamafactory.extras.callbacks - {'loss': 0.0105, 'learning_rate': 2.3045e-05, 'epoch': 18.32, 'throughput': 1000.89}
|
| 499 |
+
|
| 500 |
+
06/09/2024 05:17:37 - INFO - llamafactory.extras.callbacks - {'loss': 0.0104, 'learning_rate': 2.2785e-05, 'epoch': 18.43, 'throughput': 1000.55}
|
| 501 |
+
|
| 502 |
+
06/09/2024 05:19:46 - INFO - llamafactory.extras.callbacks - {'loss': 0.0103, 'learning_rate': 2.2525e-05, 'epoch': 18.55, 'throughput': 1000.55}
|
| 503 |
+
|
| 504 |
+
06/09/2024 05:19:46 - INFO - transformers.trainer - Saving model checkpoint to saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-800
|
| 505 |
+
|
| 506 |
+
06/09/2024 05:19:46 - INFO - transformers.configuration_utils - Configuration saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-800\config.json
|
| 507 |
+
|
| 508 |
+
06/09/2024 05:19:46 - INFO - transformers.generation.configuration_utils - Configuration saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-800\generation_config.json
|
| 509 |
+
|
| 510 |
+
06/09/2024 05:19:58 - INFO - transformers.modeling_utils - Model weights saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-800\model.safetensors
|
| 511 |
+
|
| 512 |
+
06/09/2024 05:19:58 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-800\tokenizer_config.json
|
| 513 |
+
|
| 514 |
+
06/09/2024 05:19:58 - INFO - transformers.tokenization_utils_base - Special tokens file saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-800\special_tokens_map.json
|
| 515 |
+
|
| 516 |
+
06/09/2024 05:22:27 - INFO - llamafactory.extras.callbacks - {'loss': 0.0107, 'learning_rate': 2.2266e-05, 'epoch': 18.67, 'throughput': 999.47}
|
| 517 |
+
|
| 518 |
+
06/09/2024 05:24:25 - INFO - llamafactory.extras.callbacks - {'loss': 0.0269, 'learning_rate': 2.2007e-05, 'epoch': 18.78, 'throughput': 999.49}
|
| 519 |
+
|
| 520 |
+
06/09/2024 05:26:24 - INFO - llamafactory.extras.callbacks - {'loss': 0.0086, 'learning_rate': 2.1748e-05, 'epoch': 18.90, 'throughput': 999.70}
|
| 521 |
+
|
| 522 |
+
06/09/2024 05:28:13 - INFO - llamafactory.extras.callbacks - {'loss': 0.0133, 'learning_rate': 2.1489e-05, 'epoch': 19.01, 'throughput': 999.96}
|
| 523 |
+
|
| 524 |
+
06/09/2024 05:29:46 - INFO - llamafactory.extras.callbacks - {'loss': 0.0114, 'learning_rate': 2.1231e-05, 'epoch': 19.13, 'throughput': 1000.41}
|
| 525 |
+
|
| 526 |
+
06/09/2024 05:31:50 - INFO - llamafactory.extras.callbacks - {'loss': 0.0070, 'learning_rate': 2.0973e-05, 'epoch': 19.25, 'throughput': 1000.64}
|
| 527 |
+
|
| 528 |
+
06/09/2024 05:33:47 - INFO - llamafactory.extras.callbacks - {'loss': 0.0088, 'learning_rate': 2.0716e-05, 'epoch': 19.36, 'throughput': 1000.77}
|
| 529 |
+
|
| 530 |
+
06/09/2024 05:36:12 - INFO - llamafactory.extras.callbacks - {'loss': 0.0070, 'learning_rate': 2.0459e-05, 'epoch': 19.48, 'throughput': 1000.49}
|
| 531 |
+
|
| 532 |
+
06/09/2024 05:37:59 - INFO - llamafactory.extras.callbacks - {'loss': 0.0059, 'learning_rate': 2.0203e-05, 'epoch': 19.59, 'throughput': 1000.78}
|
| 533 |
+
|
| 534 |
+
06/09/2024 05:39:59 - INFO - llamafactory.extras.callbacks - {'loss': 0.0069, 'learning_rate': 1.9947e-05, 'epoch': 19.71, 'throughput': 1000.99}
|
| 535 |
+
|
| 536 |
+
06/09/2024 05:42:18 - INFO - llamafactory.extras.callbacks - {'loss': 0.0080, 'learning_rate': 1.9692e-05, 'epoch': 19.83, 'throughput': 1001.10}
|
| 537 |
+
|
| 538 |
+
06/09/2024 05:44:15 - INFO - llamafactory.extras.callbacks - {'loss': 0.0127, 'learning_rate': 1.9437e-05, 'epoch': 19.94, 'throughput': 1001.23}
|
| 539 |
+
|
| 540 |
+
06/09/2024 05:46:30 - INFO - llamafactory.extras.callbacks - {'loss': 0.0059, 'learning_rate': 1.9183e-05, 'epoch': 20.06, 'throughput': 1001.07}
|
| 541 |
+
|
| 542 |
+
06/09/2024 05:48:17 - INFO - llamafactory.extras.callbacks - {'loss': 0.0046, 'learning_rate': 1.8929e-05, 'epoch': 20.17, 'throughput': 1001.07}
|
| 543 |
+
|
| 544 |
+
06/09/2024 05:50:34 - INFO - llamafactory.extras.callbacks - {'loss': 0.0058, 'learning_rate': 1.8677e-05, 'epoch': 20.29, 'throughput': 1001.15}
|
| 545 |
+
|
| 546 |
+
06/09/2024 05:52:48 - INFO - llamafactory.extras.callbacks - {'loss': 0.0082, 'learning_rate': 1.8425e-05, 'epoch': 20.41, 'throughput': 1000.86}
|
| 547 |
+
|
| 548 |
+
06/09/2024 05:54:46 - INFO - llamafactory.extras.callbacks - {'loss': 0.0148, 'learning_rate': 1.8173e-05, 'epoch': 20.52, 'throughput': 1001.09}
|
| 549 |
+
|
| 550 |
+
06/09/2024 05:56:27 - INFO - llamafactory.extras.callbacks - {'loss': 0.0064, 'learning_rate': 1.7923e-05, 'epoch': 20.64, 'throughput': 1001.43}
|
| 551 |
+
|
| 552 |
+
06/09/2024 05:58:37 - INFO - llamafactory.extras.callbacks - {'loss': 0.0080, 'learning_rate': 1.7673e-05, 'epoch': 20.75, 'throughput': 1001.37}
|
| 553 |
+
|
| 554 |
+
06/09/2024 06:00:59 - INFO - llamafactory.extras.callbacks - {'loss': 0.0053, 'learning_rate': 1.7424e-05, 'epoch': 20.87, 'throughput': 1001.39}
|
| 555 |
+
|
| 556 |
+
06/09/2024 06:00:59 - INFO - transformers.trainer - Saving model checkpoint to saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-900
|
| 557 |
+
|
| 558 |
+
06/09/2024 06:00:59 - INFO - transformers.configuration_utils - Configuration saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-900\config.json
|
| 559 |
+
|
| 560 |
+
06/09/2024 06:00:59 - INFO - transformers.generation.configuration_utils - Configuration saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-900\generation_config.json
|
| 561 |
+
|
| 562 |
+
06/09/2024 06:01:08 - INFO - transformers.modeling_utils - Model weights saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-900\model.safetensors
|
| 563 |
+
|
| 564 |
+
06/09/2024 06:01:08 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-900\tokenizer_config.json
|
| 565 |
+
|
| 566 |
+
06/09/2024 06:01:08 - INFO - transformers.tokenization_utils_base - Special tokens file saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-900\special_tokens_map.json
|
| 567 |
+
|
| 568 |
+
06/09/2024 06:03:11 - INFO - llamafactory.extras.callbacks - {'loss': 0.0054, 'learning_rate': 1.7175e-05, 'epoch': 20.99, 'throughput': 1000.86}
|
| 569 |
+
|
| 570 |
+
06/09/2024 06:05:26 - INFO - llamafactory.extras.callbacks - {'loss': 0.0044, 'learning_rate': 1.6928e-05, 'epoch': 21.10, 'throughput': 1000.89}
|
| 571 |
+
|
| 572 |
+
06/09/2024 06:07:35 - INFO - llamafactory.extras.callbacks - {'loss': 0.0043, 'learning_rate': 1.6681e-05, 'epoch': 21.22, 'throughput': 1000.65}
|
| 573 |
+
|
| 574 |
+
06/09/2024 06:09:39 - INFO - llamafactory.extras.callbacks - {'loss': 0.0035, 'learning_rate': 1.6436e-05, 'epoch': 21.33, 'throughput': 1000.81}
|
| 575 |
+
|
| 576 |
+
06/09/2024 06:11:17 - INFO - llamafactory.extras.callbacks - {'loss': 0.0044, 'learning_rate': 1.6191e-05, 'epoch': 21.45, 'throughput': 1001.21}
|
| 577 |
+
|
| 578 |
+
06/09/2024 06:13:17 - INFO - llamafactory.extras.callbacks - {'loss': 0.0178, 'learning_rate': 1.5947e-05, 'epoch': 21.57, 'throughput': 1001.45}
|
| 579 |
+
|
| 580 |
+
06/09/2024 06:14:58 - INFO - llamafactory.extras.callbacks - {'loss': 0.0089, 'learning_rate': 1.5705e-05, 'epoch': 21.68, 'throughput': 1001.76}
|
| 581 |
+
|
| 582 |
+
06/09/2024 06:17:41 - INFO - llamafactory.extras.callbacks - {'loss': 0.0040, 'learning_rate': 1.5463e-05, 'epoch': 21.80, 'throughput': 1001.09}
|
| 583 |
+
|
| 584 |
+
06/09/2024 06:19:50 - INFO - llamafactory.extras.callbacks - {'loss': 0.0040, 'learning_rate': 1.5222e-05, 'epoch': 21.91, 'throughput': 1000.93}
|
| 585 |
+
|
| 586 |
+
06/09/2024 06:21:39 - INFO - llamafactory.extras.callbacks - {'loss': 0.0034, 'learning_rate': 1.4983e-05, 'epoch': 22.03, 'throughput': 1001.01}
|
| 587 |
+
|
| 588 |
+
06/09/2024 06:23:20 - INFO - llamafactory.extras.callbacks - {'loss': 0.0066, 'learning_rate': 1.4744e-05, 'epoch': 22.14, 'throughput': 1001.40}
|
| 589 |
+
|
| 590 |
+
06/09/2024 06:25:22 - INFO - llamafactory.extras.callbacks - {'loss': 0.0034, 'learning_rate': 1.4507e-05, 'epoch': 22.26, 'throughput': 1001.54}
|
| 591 |
+
|
| 592 |
+
06/09/2024 06:27:14 - INFO - llamafactory.extras.callbacks - {'loss': 0.0032, 'learning_rate': 1.4271e-05, 'epoch': 22.38, 'throughput': 1001.84}
|
| 593 |
+
|
| 594 |
+
06/09/2024 06:29:01 - INFO - llamafactory.extras.callbacks - {'loss': 0.0124, 'learning_rate': 1.4036e-05, 'epoch': 22.49, 'throughput': 1002.12}
|
| 595 |
+
|
| 596 |
+
06/09/2024 06:31:31 - INFO - llamafactory.extras.callbacks - {'loss': 0.0027, 'learning_rate': 1.3802e-05, 'epoch': 22.61, 'throughput': 1001.67}
|
| 597 |
+
|
| 598 |
+
06/09/2024 06:33:18 - INFO - llamafactory.extras.callbacks - {'loss': 0.0037, 'learning_rate': 1.3569e-05, 'epoch': 22.72, 'throughput': 1001.90}
|
| 599 |
+
|
| 600 |
+
06/09/2024 06:35:28 - INFO - llamafactory.extras.callbacks - {'loss': 0.0029, 'learning_rate': 1.3338e-05, 'epoch': 22.84, 'throughput': 1001.88}
|
| 601 |
+
|
| 602 |
+
06/09/2024 06:38:19 - INFO - llamafactory.extras.callbacks - {'loss': 0.0035, 'learning_rate': 1.3107e-05, 'epoch': 22.96, 'throughput': 1001.00}
|
| 603 |
+
|
| 604 |
+
06/09/2024 06:39:55 - INFO - llamafactory.extras.callbacks - {'loss': 0.0020, 'learning_rate': 1.2878e-05, 'epoch': 23.07, 'throughput': 1001.32}
|
| 605 |
+
|
| 606 |
+
06/09/2024 06:41:50 - INFO - llamafactory.extras.callbacks - {'loss': 0.0023, 'learning_rate': 1.2651e-05, 'epoch': 23.19, 'throughput': 1001.57}
|
| 607 |
+
|
| 608 |
+
06/09/2024 06:41:50 - INFO - transformers.trainer - Saving model checkpoint to saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-1000
|
| 609 |
+
|
| 610 |
+
06/09/2024 06:41:50 - INFO - transformers.configuration_utils - Configuration saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-1000\config.json
|
| 611 |
+
|
| 612 |
+
06/09/2024 06:41:50 - INFO - transformers.generation.configuration_utils - Configuration saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-1000\generation_config.json
|
| 613 |
+
|
| 614 |
+
06/09/2024 06:42:07 - INFO - transformers.modeling_utils - Model weights saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-1000\model.safetensors
|
| 615 |
+
|
| 616 |
+
06/09/2024 06:42:07 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-1000\tokenizer_config.json
|
| 617 |
+
|
| 618 |
+
06/09/2024 06:42:07 - INFO - transformers.tokenization_utils_base - Special tokens file saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-1000\special_tokens_map.json
|
| 619 |
+
|
| 620 |
+
06/09/2024 06:44:12 - INFO - llamafactory.extras.callbacks - {'loss': 0.0031, 'learning_rate': 1.2425e-05, 'epoch': 23.30, 'throughput': 1000.67}
|
| 621 |
+
|
| 622 |
+
06/09/2024 06:46:33 - INFO - llamafactory.extras.callbacks - {'loss': 0.0027, 'learning_rate': 1.2200e-05, 'epoch': 23.42, 'throughput': 1000.50}
|
| 623 |
+
|
| 624 |
+
06/09/2024 06:48:36 - INFO - llamafactory.extras.callbacks - {'loss': 0.0124, 'learning_rate': 1.1976e-05, 'epoch': 23.54, 'throughput': 1000.70}
|
| 625 |
+
|
| 626 |
+
06/09/2024 06:50:18 - INFO - llamafactory.extras.callbacks - {'loss': 0.0023, 'learning_rate': 1.1754e-05, 'epoch': 23.65, 'throughput': 1001.02}
|
| 627 |
+
|
| 628 |
+
06/09/2024 06:52:50 - INFO - llamafactory.extras.callbacks - {'loss': 0.0027, 'learning_rate': 1.1534e-05, 'epoch': 23.77, 'throughput': 1000.96}
|
| 629 |
+
|
| 630 |
+
06/09/2024 06:54:48 - INFO - llamafactory.extras.callbacks - {'loss': 0.0041, 'learning_rate': 1.1315e-05, 'epoch': 23.88, 'throughput': 1001.18}
|
| 631 |
+
|
| 632 |
+
06/09/2024 06:56:41 - INFO - llamafactory.extras.callbacks - {'loss': 0.0021, 'learning_rate': 1.1097e-05, 'epoch': 24.00, 'throughput': 1001.39}
|
| 633 |
+
|
| 634 |
+
06/09/2024 06:58:29 - INFO - llamafactory.extras.callbacks - {'loss': 0.0039, 'learning_rate': 1.0881e-05, 'epoch': 24.12, 'throughput': 1001.66}
|
| 635 |
+
|
| 636 |
+
06/09/2024 07:00:50 - INFO - llamafactory.extras.callbacks - {'loss': 0.0025, 'learning_rate': 1.0667e-05, 'epoch': 24.23, 'throughput': 1001.60}
|
| 637 |
+
|
| 638 |
+
06/09/2024 07:02:55 - INFO - llamafactory.extras.callbacks - {'loss': 0.0020, 'learning_rate': 1.0454e-05, 'epoch': 24.35, 'throughput': 1001.79}
|
| 639 |
+
|
| 640 |
+
06/09/2024 07:05:24 - INFO - llamafactory.extras.callbacks - {'loss': 0.0024, 'learning_rate': 1.0242e-05, 'epoch': 24.46, 'throughput': 1001.71}
|
| 641 |
+
|
| 642 |
+
06/09/2024 07:07:13 - INFO - llamafactory.extras.callbacks - {'loss': 0.0031, 'learning_rate': 1.0032e-05, 'epoch': 24.58, 'throughput': 1001.93}
|
| 643 |
+
|
| 644 |
+
06/09/2024 07:09:07 - INFO - llamafactory.extras.callbacks - {'loss': 0.0022, 'learning_rate': 9.8241e-06, 'epoch': 24.70, 'throughput': 1002.12}
|
| 645 |
+
|
| 646 |
+
06/09/2024 07:10:53 - INFO - llamafactory.extras.callbacks - {'loss': 0.0022, 'learning_rate': 9.6176e-06, 'epoch': 24.81, 'throughput': 1002.46}
|
| 647 |
+
|
| 648 |
+
06/09/2024 07:13:23 - INFO - llamafactory.extras.callbacks - {'loss': 0.0109, 'learning_rate': 9.4128e-06, 'epoch': 24.93, 'throughput': 1001.58}
|
| 649 |
+
|
| 650 |
+
06/09/2024 07:15:05 - INFO - llamafactory.extras.callbacks - {'loss': 0.0019, 'learning_rate': 9.2096e-06, 'epoch': 25.04, 'throughput': 1001.78}
|
| 651 |
+
|
| 652 |
+
06/09/2024 07:16:58 - INFO - llamafactory.extras.callbacks - {'loss': 0.0016, 'learning_rate': 9.0082e-06, 'epoch': 25.16, 'throughput': 1002.01}
|
| 653 |
+
|
| 654 |
+
06/09/2024 07:18:57 - INFO - llamafactory.extras.callbacks - {'loss': 0.0020, 'learning_rate': 8.8085e-06, 'epoch': 25.28, 'throughput': 1002.15}
|
| 655 |
+
|
| 656 |
+
06/09/2024 07:20:46 - INFO - llamafactory.extras.callbacks - {'loss': 0.0018, 'learning_rate': 8.6106e-06, 'epoch': 25.39, 'throughput': 1002.35}
|
| 657 |
+
|
| 658 |
+
06/09/2024 07:22:55 - INFO - llamafactory.extras.callbacks - {'loss': 0.0028, 'learning_rate': 8.4144e-06, 'epoch': 25.51, 'throughput': 1002.44}
|
| 659 |
+
|
| 660 |
+
06/09/2024 07:22:55 - INFO - transformers.trainer - Saving model checkpoint to saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-1100
|
| 661 |
+
|
| 662 |
+
06/09/2024 07:22:55 - INFO - transformers.configuration_utils - Configuration saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-1100\config.json
|
| 663 |
+
|
| 664 |
+
06/09/2024 07:22:55 - INFO - transformers.generation.configuration_utils - Configuration saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-1100\generation_config.json
|
| 665 |
+
|
| 666 |
+
06/09/2024 07:23:26 - INFO - transformers.modeling_utils - Model weights saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-1100\model.safetensors
|
| 667 |
+
|
| 668 |
+
06/09/2024 07:23:26 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-1100\tokenizer_config.json
|
| 669 |
+
|
| 670 |
+
06/09/2024 07:23:26 - INFO - transformers.tokenization_utils_base - Special tokens file saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-1100\special_tokens_map.json
|
| 671 |
+
|
| 672 |
+
06/09/2024 07:27:26 - INFO - llamafactory.extras.callbacks - {'loss': 0.0021, 'learning_rate': 8.2201e-06, 'epoch': 25.62, 'throughput': 998.15}
|
| 673 |
+
|
| 674 |
+
06/09/2024 07:29:14 - INFO - llamafactory.extras.callbacks - {'loss': 0.0057, 'learning_rate': 8.0276e-06, 'epoch': 25.74, 'throughput': 998.39}
|
| 675 |
+
|
| 676 |
+
06/09/2024 07:31:09 - INFO - llamafactory.extras.callbacks - {'loss': 0.0067, 'learning_rate': 7.8369e-06, 'epoch': 25.86, 'throughput': 998.59}
|
| 677 |
+
|
| 678 |
+
06/09/2024 07:33:09 - INFO - llamafactory.extras.callbacks - {'loss': 0.0020, 'learning_rate': 7.6481e-06, 'epoch': 25.97, 'throughput': 998.67}
|
| 679 |
+
|
| 680 |
+
06/09/2024 07:35:20 - INFO - llamafactory.extras.callbacks - {'loss': 0.0021, 'learning_rate': 7.4612e-06, 'epoch': 26.09, 'throughput': 998.73}
|
| 681 |
+
|
| 682 |
+
06/09/2024 07:37:21 - INFO - llamafactory.extras.callbacks - {'loss': 0.0020, 'learning_rate': 7.2763e-06, 'epoch': 26.20, 'throughput': 998.92}
|
| 683 |
+
|
| 684 |
+
06/09/2024 07:39:24 - INFO - llamafactory.extras.callbacks - {'loss': 0.0017, 'learning_rate': 7.0932e-06, 'epoch': 26.32, 'throughput': 998.88}
|
| 685 |
+
|
| 686 |
+
06/09/2024 07:41:36 - INFO - llamafactory.extras.callbacks - {'loss': 0.0014, 'learning_rate': 6.9121e-06, 'epoch': 26.43, 'throughput': 998.77}
|
| 687 |
+
|
| 688 |
+
06/09/2024 07:43:49 - INFO - llamafactory.extras.callbacks - {'loss': 0.0022, 'learning_rate': 6.7330e-06, 'epoch': 26.55, 'throughput': 998.82}
|
| 689 |
+
|
| 690 |
+
06/09/2024 07:45:54 - INFO - llamafactory.extras.callbacks - {'loss': 0.0023, 'learning_rate': 6.5558e-06, 'epoch': 26.67, 'throughput': 998.48}
|
| 691 |
+
|
| 692 |
+
06/09/2024 07:47:43 - INFO - llamafactory.extras.callbacks - {'loss': 0.0028, 'learning_rate': 6.3807e-06, 'epoch': 26.78, 'throughput': 998.66}
|
| 693 |
+
|
| 694 |
+
06/09/2024 07:49:50 - INFO - llamafactory.extras.callbacks - {'loss': 0.0060, 'learning_rate': 6.2076e-06, 'epoch': 26.90, 'throughput': 998.69}
|
| 695 |
+
|
| 696 |
+
06/09/2024 07:51:36 - INFO - llamafactory.extras.callbacks - {'loss': 0.0045, 'learning_rate': 6.0365e-06, 'epoch': 27.01, 'throughput': 998.96}
|
| 697 |
+
|
| 698 |
+
06/09/2024 07:53:40 - INFO - llamafactory.extras.callbacks - {'loss': 0.0019, 'learning_rate': 5.8675e-06, 'epoch': 27.13, 'throughput': 999.15}
|
| 699 |
+
|
| 700 |
+
06/09/2024 07:55:56 - INFO - llamafactory.extras.callbacks - {'loss': 0.0020, 'learning_rate': 5.7006e-06, 'epoch': 27.25, 'throughput': 999.08}
|
| 701 |
+
|
| 702 |
+
06/09/2024 07:58:18 - INFO - llamafactory.extras.callbacks - {'loss': 0.0019, 'learning_rate': 5.5358e-06, 'epoch': 27.36, 'throughput': 998.78}
|
| 703 |
+
|
| 704 |
+
06/09/2024 08:00:40 - INFO - llamafactory.extras.callbacks - {'loss': 0.0060, 'learning_rate': 5.3731e-06, 'epoch': 27.48, 'throughput': 998.02}
|
| 705 |
+
|
| 706 |
+
06/09/2024 08:02:32 - INFO - llamafactory.extras.callbacks - {'loss': 0.0043, 'learning_rate': 5.2126e-06, 'epoch': 27.59, 'throughput': 998.17}
|
| 707 |
+
|
| 708 |
+
06/09/2024 08:04:21 - INFO - llamafactory.extras.callbacks - {'loss': 0.0019, 'learning_rate': 5.0542e-06, 'epoch': 27.71, 'throughput': 998.41}
|
| 709 |
+
|
| 710 |
+
06/09/2024 08:06:12 - INFO - llamafactory.extras.callbacks - {'loss': 0.0020, 'learning_rate': 4.8980e-06, 'epoch': 27.83, 'throughput': 998.66}
|
| 711 |
+
|
| 712 |
+
06/09/2024 08:06:12 - INFO - transformers.trainer - Saving model checkpoint to saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-1200
|
| 713 |
+
|
| 714 |
+
06/09/2024 08:06:12 - INFO - transformers.configuration_utils - Configuration saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-1200\config.json
|
| 715 |
+
|
| 716 |
+
06/09/2024 08:06:12 - INFO - transformers.generation.configuration_utils - Configuration saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-1200\generation_config.json
|
| 717 |
+
|
| 718 |
+
06/09/2024 08:06:15 - INFO - transformers.modeling_utils - Model weights saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-1200\model.safetensors
|
| 719 |
+
|
| 720 |
+
06/09/2024 08:06:15 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-1200\tokenizer_config.json
|
| 721 |
+
|
| 722 |
+
06/09/2024 08:06:15 - INFO - transformers.tokenization_utils_base - Special tokens file saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-1200\special_tokens_map.json
|
| 723 |
+
|
| 724 |
+
06/09/2024 08:08:33 - INFO - llamafactory.extras.callbacks - {'loss': 0.0022, 'learning_rate': 4.7439e-06, 'epoch': 27.94, 'throughput': 998.10}
|
| 725 |
+
|
| 726 |
+
06/09/2024 08:11:12 - INFO - llamafactory.extras.callbacks - {'loss': 0.0016, 'learning_rate': 4.5921e-06, 'epoch': 28.06, 'throughput': 997.51}
|
| 727 |
+
|
| 728 |
+
06/09/2024 08:13:00 - INFO - llamafactory.extras.callbacks - {'loss': 0.0033, 'learning_rate': 4.4425e-06, 'epoch': 28.17, 'throughput': 997.65}
|
| 729 |
+
|
| 730 |
+
06/09/2024 08:15:26 - INFO - llamafactory.extras.callbacks - {'loss': 0.0018, 'learning_rate': 4.2952e-06, 'epoch': 28.29, 'throughput': 997.44}
|
| 731 |
+
|
| 732 |
+
06/09/2024 08:17:30 - INFO - llamafactory.extras.callbacks - {'loss': 0.0018, 'learning_rate': 4.1501e-06, 'epoch': 28.41, 'throughput': 997.40}
|
| 733 |
+
|
| 734 |
+
06/09/2024 08:19:21 - INFO - llamafactory.extras.callbacks - {'loss': 0.0078, 'learning_rate': 4.0072e-06, 'epoch': 28.52, 'throughput': 997.56}
|
| 735 |
+
|
| 736 |
+
06/09/2024 08:21:37 - INFO - llamafactory.extras.callbacks - {'loss': 0.0019, 'learning_rate': 3.8667e-06, 'epoch': 28.64, 'throughput': 997.29}
|
| 737 |
+
|
| 738 |
+
06/09/2024 08:24:01 - INFO - llamafactory.extras.callbacks - {'loss': 0.0019, 'learning_rate': 3.7284e-06, 'epoch': 28.75, 'throughput': 996.51}
|
| 739 |
+
|
| 740 |
+
06/09/2024 08:25:32 - INFO - llamafactory.extras.callbacks - {'loss': 0.0027, 'learning_rate': 3.5925e-06, 'epoch': 28.87, 'throughput': 996.81}
|
| 741 |
+
|
| 742 |
+
06/09/2024 08:27:46 - INFO - llamafactory.extras.callbacks - {'loss': 0.0023, 'learning_rate': 3.4589e-06, 'epoch': 28.99, 'throughput': 996.97}
|
| 743 |
+
|
| 744 |
+
06/09/2024 08:30:00 - INFO - llamafactory.extras.callbacks - {'loss': 0.0029, 'learning_rate': 3.3277e-06, 'epoch': 29.10, 'throughput': 997.00}
|
| 745 |
+
|
| 746 |
+
06/09/2024 08:31:58 - INFO - llamafactory.extras.callbacks - {'loss': 0.0018, 'learning_rate': 3.1988e-06, 'epoch': 29.22, 'throughput': 997.14}
|
| 747 |
+
|
| 748 |
+
06/09/2024 08:34:08 - INFO - llamafactory.extras.callbacks - {'loss': 0.0018, 'learning_rate': 3.0723e-06, 'epoch': 29.33, 'throughput': 997.27}
|
| 749 |
+
|
| 750 |
+
06/09/2024 08:36:06 - INFO - llamafactory.extras.callbacks - {'loss': 0.0018, 'learning_rate': 2.9481e-06, 'epoch': 29.45, 'throughput': 997.43}
|
| 751 |
+
|
| 752 |
+
06/09/2024 08:38:28 - INFO - llamafactory.extras.callbacks - {'loss': 0.0019, 'learning_rate': 2.8264e-06, 'epoch': 29.57, 'throughput': 997.05}
|
| 753 |
+
|
| 754 |
+
06/09/2024 08:40:32 - INFO - llamafactory.extras.callbacks - {'loss': 0.0018, 'learning_rate': 2.7071e-06, 'epoch': 29.68, 'throughput': 997.23}
|
| 755 |
+
|
| 756 |
+
06/09/2024 08:42:30 - INFO - llamafactory.extras.callbacks - {'loss': 0.0023, 'learning_rate': 2.5902e-06, 'epoch': 29.80, 'throughput': 997.24}
|
| 757 |
+
|
| 758 |
+
06/09/2024 08:44:29 - INFO - llamafactory.extras.callbacks - {'loss': 0.0078, 'learning_rate': 2.4758e-06, 'epoch': 29.91, 'throughput': 997.37}
|
| 759 |
+
|
| 760 |
+
06/09/2024 08:46:27 - INFO - llamafactory.extras.callbacks - {'loss': 0.0018, 'learning_rate': 2.3638e-06, 'epoch': 30.03, 'throughput': 997.36}
|
| 761 |
+
|
| 762 |
+
06/09/2024 08:48:26 - INFO - llamafactory.extras.callbacks - {'loss': 0.0017, 'learning_rate': 2.2543e-06, 'epoch': 30.14, 'throughput': 997.56}
|
| 763 |
+
|
| 764 |
+
06/09/2024 08:48:26 - INFO - transformers.trainer - Saving model checkpoint to saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-1300
|
| 765 |
+
|
| 766 |
+
06/09/2024 08:48:26 - INFO - transformers.configuration_utils - Configuration saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-1300\config.json
|
| 767 |
+
|
| 768 |
+
06/09/2024 08:48:26 - INFO - transformers.generation.configuration_utils - Configuration saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-1300\generation_config.json
|
| 769 |
+
|
| 770 |
+
06/09/2024 08:48:35 - INFO - transformers.modeling_utils - Model weights saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-1300\model.safetensors
|
| 771 |
+
|
| 772 |
+
06/09/2024 08:48:35 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-1300\tokenizer_config.json
|
| 773 |
+
|
| 774 |
+
06/09/2024 08:48:35 - INFO - transformers.tokenization_utils_base - Special tokens file saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-1300\special_tokens_map.json
|
| 775 |
+
|
| 776 |
+
06/09/2024 08:50:43 - INFO - llamafactory.extras.callbacks - {'loss': 0.0071, 'learning_rate': 2.1472e-06, 'epoch': 30.26, 'throughput': 997.03}
|
| 777 |
+
|
| 778 |
+
06/09/2024 08:52:25 - INFO - llamafactory.extras.callbacks - {'loss': 0.0016, 'learning_rate': 2.0427e-06, 'epoch': 30.38, 'throughput': 997.31}
|
| 779 |
+
|
| 780 |
+
06/09/2024 08:54:28 - INFO - llamafactory.extras.callbacks - {'loss': 0.0018, 'learning_rate': 1.9406e-06, 'epoch': 30.49, 'throughput': 997.40}
|
| 781 |
+
|
| 782 |
+
06/09/2024 08:56:57 - INFO - llamafactory.extras.callbacks - {'loss': 0.0017, 'learning_rate': 1.8411e-06, 'epoch': 30.61, 'throughput': 997.00}
|
| 783 |
+
|
| 784 |
+
06/09/2024 08:59:07 - INFO - llamafactory.extras.callbacks - {'loss': 0.0017, 'learning_rate': 1.7441e-06, 'epoch': 30.72, 'throughput': 996.94}
|
| 785 |
+
|
| 786 |
+
06/09/2024 09:01:08 - INFO - llamafactory.extras.callbacks - {'loss': 0.0019, 'learning_rate': 1.6496e-06, 'epoch': 30.84, 'throughput': 997.09}
|
| 787 |
+
|
| 788 |
+
06/09/2024 09:03:19 - INFO - llamafactory.extras.callbacks - {'loss': 0.0018, 'learning_rate': 1.5577e-06, 'epoch': 30.96, 'throughput': 996.94}
|
| 789 |
+
|
| 790 |
+
06/09/2024 09:05:11 - INFO - llamafactory.extras.callbacks - {'loss': 0.0038, 'learning_rate': 1.4683e-06, 'epoch': 31.07, 'throughput': 997.13}
|
| 791 |
+
|
| 792 |
+
06/09/2024 09:06:56 - INFO - llamafactory.extras.callbacks - {'loss': 0.0052, 'learning_rate': 1.3815e-06, 'epoch': 31.19, 'throughput': 997.30}
|
| 793 |
+
|
| 794 |
+
06/09/2024 09:09:13 - INFO - llamafactory.extras.callbacks - {'loss': 0.0018, 'learning_rate': 1.2972e-06, 'epoch': 31.30, 'throughput': 997.30}
|
| 795 |
+
|
| 796 |
+
06/09/2024 09:10:53 - INFO - llamafactory.extras.callbacks - {'loss': 0.0019, 'learning_rate': 1.2155e-06, 'epoch': 31.42, 'throughput': 997.55}
|
| 797 |
+
|
| 798 |
+
06/09/2024 09:12:40 - INFO - llamafactory.extras.callbacks - {'loss': 0.0019, 'learning_rate': 1.1365e-06, 'epoch': 31.54, 'throughput': 997.81}
|
| 799 |
+
|
| 800 |
+
06/09/2024 09:14:55 - INFO - llamafactory.extras.callbacks - {'loss': 0.0017, 'learning_rate': 1.0600e-06, 'epoch': 31.65, 'throughput': 997.48}
|
| 801 |
+
|
| 802 |
+
06/09/2024 09:16:55 - INFO - llamafactory.extras.callbacks - {'loss': 0.0022, 'learning_rate': 9.8612e-07, 'epoch': 31.77, 'throughput': 997.57}
|
| 803 |
+
|
| 804 |
+
06/09/2024 09:19:26 - INFO - llamafactory.extras.callbacks - {'loss': 0.0037, 'learning_rate': 9.1486e-07, 'epoch': 31.88, 'throughput': 997.25}
|
| 805 |
+
|
| 806 |
+
06/09/2024 09:21:45 - INFO - llamafactory.extras.callbacks - {'loss': 0.0019, 'learning_rate': 8.4624e-07, 'epoch': 32.00, 'throughput': 997.23}
|
| 807 |
+
|
| 808 |
+
06/09/2024 09:23:43 - INFO - llamafactory.extras.callbacks - {'loss': 0.0017, 'learning_rate': 7.8024e-07, 'epoch': 32.12, 'throughput': 997.32}
|
| 809 |
+
|
| 810 |
+
06/09/2024 09:25:59 - INFO - llamafactory.extras.callbacks - {'loss': 0.0018, 'learning_rate': 7.1688e-07, 'epoch': 32.23, 'throughput': 997.25}
|
| 811 |
+
|
| 812 |
+
06/09/2024 09:28:28 - INFO - llamafactory.extras.callbacks - {'loss': 0.0035, 'learning_rate': 6.5617e-07, 'epoch': 32.35, 'throughput': 996.95}
|
| 813 |
+
|
| 814 |
+
06/09/2024 09:30:35 - INFO - llamafactory.extras.callbacks - {'loss': 0.0063, 'learning_rate': 5.9810e-07, 'epoch': 32.46, 'throughput': 996.92}
|
| 815 |
+
|
| 816 |
+
06/09/2024 09:30:35 - INFO - transformers.trainer - Saving model checkpoint to saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-1400
|
| 817 |
+
|
| 818 |
+
06/09/2024 09:30:35 - INFO - transformers.configuration_utils - Configuration saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-1400\config.json
|
| 819 |
+
|
| 820 |
+
06/09/2024 09:30:35 - INFO - transformers.generation.configuration_utils - Configuration saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-1400\generation_config.json
|
| 821 |
+
|
| 822 |
+
06/09/2024 09:30:41 - INFO - transformers.modeling_utils - Model weights saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-1400\model.safetensors
|
| 823 |
+
|
| 824 |
+
06/09/2024 09:30:41 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-1400\tokenizer_config.json
|
| 825 |
+
|
| 826 |
+
06/09/2024 09:30:41 - INFO - transformers.tokenization_utils_base - Special tokens file saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-1400\special_tokens_map.json
|
| 827 |
+
|
| 828 |
+
06/09/2024 09:32:30 - INFO - llamafactory.extras.callbacks - {'loss': 0.0018, 'learning_rate': 5.4270e-07, 'epoch': 32.58, 'throughput': 996.79}
|
| 829 |
+
|
| 830 |
+
06/09/2024 09:34:17 - INFO - llamafactory.extras.callbacks - {'loss': 0.0020, 'learning_rate': 4.8996e-07, 'epoch': 32.70, 'throughput': 997.02}
|
| 831 |
+
|
| 832 |
+
06/09/2024 09:36:26 - INFO - llamafactory.extras.callbacks - {'loss': 0.0017, 'learning_rate': 4.3989e-07, 'epoch': 32.81, 'throughput': 997.12}
|
| 833 |
+
|
| 834 |
+
06/09/2024 09:38:35 - INFO - llamafactory.extras.callbacks - {'loss': 0.0016, 'learning_rate': 3.9250e-07, 'epoch': 32.93, 'throughput': 997.16}
|
| 835 |
+
|
| 836 |
+
06/09/2024 09:40:51 - INFO - llamafactory.extras.callbacks - {'loss': 0.0015, 'learning_rate': 3.4778e-07, 'epoch': 33.04, 'throughput': 997.07}
|
| 837 |
+
|
| 838 |
+
06/09/2024 09:42:47 - INFO - llamafactory.extras.callbacks - {'loss': 0.0057, 'learning_rate': 3.0575e-07, 'epoch': 33.16, 'throughput': 997.25}
|
| 839 |
+
|
| 840 |
+
06/09/2024 09:45:07 - INFO - llamafactory.extras.callbacks - {'loss': 0.0016, 'learning_rate': 2.6642e-07, 'epoch': 33.28, 'throughput': 996.81}
|
| 841 |
+
|
| 842 |
+
06/09/2024 09:46:46 - INFO - llamafactory.extras.callbacks - {'loss': 0.0016, 'learning_rate': 2.2977e-07, 'epoch': 33.39, 'throughput': 997.10}
|
| 843 |
+
|
| 844 |
+
06/09/2024 09:48:52 - INFO - llamafactory.extras.callbacks - {'loss': 0.0019, 'learning_rate': 1.9583e-07, 'epoch': 33.51, 'throughput': 997.13}
|
| 845 |
+
|
| 846 |
+
06/09/2024 09:50:50 - INFO - llamafactory.extras.callbacks - {'loss': 0.0017, 'learning_rate': 1.6458e-07, 'epoch': 33.62, 'throughput': 997.16}
|
| 847 |
+
|
| 848 |
+
06/09/2024 09:52:42 - INFO - llamafactory.extras.callbacks - {'loss': 0.0042, 'learning_rate': 1.3604e-07, 'epoch': 33.74, 'throughput': 997.29}
|
| 849 |
+
|
| 850 |
+
06/09/2024 09:54:48 - INFO - llamafactory.extras.callbacks - {'loss': 0.0017, 'learning_rate': 1.1022e-07, 'epoch': 33.86, 'throughput': 997.47}
|
| 851 |
+
|
| 852 |
+
06/09/2024 09:57:05 - INFO - llamafactory.extras.callbacks - {'loss': 0.0017, 'learning_rate': 8.7097e-08, 'epoch': 33.97, 'throughput': 997.29}
|
| 853 |
+
|
| 854 |
+
06/09/2024 09:59:36 - INFO - llamafactory.extras.callbacks - {'loss': 0.0015, 'learning_rate': 6.6693e-08, 'epoch': 34.09, 'throughput': 997.05}
|
| 855 |
+
|
| 856 |
+
06/09/2024 10:01:03 - INFO - llamafactory.extras.callbacks - {'loss': 0.0018, 'learning_rate': 4.9005e-08, 'epoch': 34.20, 'throughput': 997.33}
|
| 857 |
+
|
| 858 |
+
06/09/2024 10:03:24 - INFO - llamafactory.extras.callbacks - {'loss': 0.0024, 'learning_rate': 3.4034e-08, 'epoch': 34.32, 'throughput': 997.25}
|
| 859 |
+
|
| 860 |
+
06/09/2024 10:05:29 - INFO - llamafactory.extras.callbacks - {'loss': 0.0021, 'learning_rate': 2.1784e-08, 'epoch': 34.43, 'throughput': 997.41}
|
| 861 |
+
|
| 862 |
+
06/09/2024 10:07:24 - INFO - llamafactory.extras.callbacks - {'loss': 0.0035, 'learning_rate': 1.2254e-08, 'epoch': 34.55, 'throughput': 997.57}
|
| 863 |
+
|
| 864 |
+
06/09/2024 10:09:26 - INFO - llamafactory.extras.callbacks - {'loss': 0.0016, 'learning_rate': 5.4465e-09, 'epoch': 34.67, 'throughput': 997.75}
|
| 865 |
+
|
| 866 |
+
06/09/2024 10:11:31 - INFO - llamafactory.extras.callbacks - {'loss': 0.0015, 'learning_rate': 1.3617e-09, 'epoch': 34.78, 'throughput': 997.77}
|
| 867 |
+
|
| 868 |
+
06/09/2024 10:11:31 - INFO - transformers.trainer - Saving model checkpoint to saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-1500
|
| 869 |
+
|
| 870 |
+
06/09/2024 10:11:31 - INFO - transformers.configuration_utils - Configuration saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-1500\config.json
|
| 871 |
+
|
| 872 |
+
06/09/2024 10:11:31 - INFO - transformers.generation.configuration_utils - Configuration saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-1500\generation_config.json
|
| 873 |
+
|
| 874 |
+
06/09/2024 10:11:39 - INFO - transformers.modeling_utils - Model weights saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-1500\model.safetensors
|
| 875 |
+
|
| 876 |
+
06/09/2024 10:11:39 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-1500\tokenizer_config.json
|
| 877 |
+
|
| 878 |
+
06/09/2024 10:11:39 - INFO - transformers.tokenization_utils_base - Special tokens file saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\checkpoint-1500\special_tokens_map.json
|
| 879 |
+
|
| 880 |
+
06/09/2024 10:13:48 - INFO - llamafactory.extras.callbacks - {'loss': 0.0053, 'learning_rate': 0.0000e+00, 'epoch': 34.90, 'throughput': 997.38}
|
| 881 |
+
|
| 882 |
+
06/09/2024 10:13:48 - INFO - transformers.trainer -
|
| 883 |
+
|
| 884 |
+
Training completed. Do not forget to share your model on huggingface.co/models =)
|
| 885 |
+
|
| 886 |
+
|
| 887 |
+
|
| 888 |
+
06/09/2024 10:13:48 - INFO - transformers.trainer - Saving model checkpoint to saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14
|
| 889 |
+
|
| 890 |
+
06/09/2024 10:13:48 - INFO - transformers.configuration_utils - Configuration saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\config.json
|
| 891 |
+
|
| 892 |
+
06/09/2024 10:13:48 - INFO - transformers.generation.configuration_utils - Configuration saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\generation_config.json
|
| 893 |
+
|
| 894 |
+
06/09/2024 10:13:53 - INFO - transformers.modeling_utils - Model weights saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\model.safetensors
|
| 895 |
+
|
| 896 |
+
06/09/2024 10:13:53 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\tokenizer_config.json
|
| 897 |
+
|
| 898 |
+
06/09/2024 10:13:53 - INFO - transformers.tokenization_utils_base - Special tokens file saved in saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14\special_tokens_map.json
|
| 899 |
+
|
| 900 |
+
06/09/2024 10:13:53 - WARNING - llamafactory.extras.ploting - No metric eval_loss to plot.
|
| 901 |
+
|
| 902 |
+
06/09/2024 10:13:53 - INFO - transformers.modelcard - Dropping the following result as it does not have all the necessary fields:
|
| 903 |
+
{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}
|
| 904 |
+
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>"
|
| 5 |
+
],
|
| 6 |
+
"eos_token": {
|
| 7 |
+
"content": "<|endoftext|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false
|
| 12 |
+
},
|
| 13 |
+
"pad_token": {
|
| 14 |
+
"content": "<|endoftext|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
}
|
| 20 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"151643": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"151644": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"151645": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
}
|
| 28 |
+
},
|
| 29 |
+
"additional_special_tokens": [
|
| 30 |
+
"<|im_start|>",
|
| 31 |
+
"<|im_end|>"
|
| 32 |
+
],
|
| 33 |
+
"bos_token": null,
|
| 34 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message + '\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\nAssistant: ' }}{% elif message['role'] == 'assistant' %}{{ content + '<|endoftext|>' + '\n' }}{% endif %}{% endfor %}",
|
| 35 |
+
"clean_up_tokenization_spaces": false,
|
| 36 |
+
"eos_token": "<|endoftext|>",
|
| 37 |
+
"errors": "replace",
|
| 38 |
+
"model_max_length": 32768,
|
| 39 |
+
"pad_token": "<|endoftext|>",
|
| 40 |
+
"padding_side": "right",
|
| 41 |
+
"split_special_tokens": false,
|
| 42 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 43 |
+
"unk_token": null
|
| 44 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 34.89855072463768,
|
| 3 |
+
"num_input_tokens_seen": 37412688,
|
| 4 |
+
"total_flos": 8.033958240027034e+16,
|
| 5 |
+
"train_loss": 0.3889684765070578,
|
| 6 |
+
"train_runtime": 37510.9602,
|
| 7 |
+
"train_samples_per_second": 0.322,
|
| 8 |
+
"train_steps_per_second": 0.04
|
| 9 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,302 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 5, "total_steps": 1505, "loss": 3.8116, "learning_rate": 4.999863832700438e-05, "epoch": 0.11594202898550725, "percentage": 0.33, "elapsed_time": "0:01:41", "remaining_time": "8:27:54", "throughput": "1052.64", "total_tokens": 106929}
|
| 2 |
+
{"current_steps": 10, "total_steps": 1505, "loss": 3.6928, "learning_rate": 4.999455345634978e-05, "epoch": 0.2318840579710145, "percentage": 0.66, "elapsed_time": "0:03:33", "remaining_time": "8:51:03", "throughput": "1060.20", "total_tokens": 225964}
|
| 3 |
+
{"current_steps": 15, "total_steps": 1505, "loss": 3.6227, "learning_rate": 4.9987745833016855e-05, "epoch": 0.34782608695652173, "percentage": 1.0, "elapsed_time": "0:05:53", "remaining_time": "9:45:33", "throughput": "1024.22", "total_tokens": 362264}
|
| 4 |
+
{"current_steps": 20, "total_steps": 1505, "loss": 3.601, "learning_rate": 4.9978216198586135e-05, "epoch": 0.463768115942029, "percentage": 1.33, "elapsed_time": "0:07:42", "remaining_time": "9:32:27", "throughput": "1032.88", "total_tokens": 477807}
|
| 5 |
+
{"current_steps": 25, "total_steps": 1505, "loss": 3.539, "learning_rate": 4.996596559115731e-05, "epoch": 0.5797101449275363, "percentage": 1.66, "elapsed_time": "0:09:25", "remaining_time": "9:18:14", "throughput": "1040.84", "total_tokens": 588900}
|
| 6 |
+
{"current_steps": 30, "total_steps": 1505, "loss": 3.4956, "learning_rate": 4.995099534523607e-05, "epoch": 0.6956521739130435, "percentage": 1.99, "elapsed_time": "0:11:18", "remaining_time": "9:16:16", "throughput": "1040.12", "total_tokens": 706077}
|
| 7 |
+
{"current_steps": 35, "total_steps": 1505, "loss": 3.5044, "learning_rate": 4.9933307091588796e-05, "epoch": 0.8115942028985508, "percentage": 2.33, "elapsed_time": "0:13:53", "remaining_time": "9:43:08", "throughput": "1024.54", "total_tokens": 853504}
|
| 8 |
+
{"current_steps": 40, "total_steps": 1505, "loss": 3.4324, "learning_rate": 4.991290275706486e-05, "epoch": 0.927536231884058, "percentage": 2.66, "elapsed_time": "0:16:08", "remaining_time": "9:51:29", "throughput": "1022.18", "total_tokens": 990472}
|
| 9 |
+
{"current_steps": 45, "total_steps": 1505, "loss": 3.2542, "learning_rate": 4.988978456438678e-05, "epoch": 1.0434782608695652, "percentage": 2.99, "elapsed_time": "0:18:22", "remaining_time": "9:56:13", "throughput": "1021.10", "total_tokens": 1125870}
|
| 10 |
+
{"current_steps": 50, "total_steps": 1505, "loss": 2.9024, "learning_rate": 4.986395503190805e-05, "epoch": 1.1594202898550725, "percentage": 3.32, "elapsed_time": "0:20:21", "remaining_time": "9:52:16", "throughput": "1023.49", "total_tokens": 1249877}
|
| 11 |
+
{"current_steps": 55, "total_steps": 1505, "loss": 2.8069, "learning_rate": 4.983541697333881e-05, "epoch": 1.2753623188405796, "percentage": 3.65, "elapsed_time": "0:22:24", "remaining_time": "9:50:52", "throughput": "1022.63", "total_tokens": 1375193}
|
| 12 |
+
{"current_steps": 60, "total_steps": 1505, "loss": 2.75, "learning_rate": 4.980417349743936e-05, "epoch": 1.391304347826087, "percentage": 3.99, "elapsed_time": "0:24:19", "remaining_time": "9:45:47", "throughput": "1020.77", "total_tokens": 1489716}
|
| 13 |
+
{"current_steps": 65, "total_steps": 1505, "loss": 2.7329, "learning_rate": 4.9770228007681494e-05, "epoch": 1.5072463768115942, "percentage": 4.32, "elapsed_time": "0:26:02", "remaining_time": "9:37:00", "throughput": "1024.15", "total_tokens": 1600483}
|
| 14 |
+
{"current_steps": 70, "total_steps": 1505, "loss": 2.8212, "learning_rate": 4.973358420187776e-05, "epoch": 1.6231884057971016, "percentage": 4.65, "elapsed_time": "0:28:23", "remaining_time": "9:41:54", "throughput": "1016.55", "total_tokens": 1731315}
|
| 15 |
+
{"current_steps": 75, "total_steps": 1505, "loss": 2.7935, "learning_rate": 4.9694246071778604e-05, "epoch": 1.7391304347826086, "percentage": 4.98, "elapsed_time": "0:30:28", "remaining_time": "9:40:59", "throughput": "1016.39", "total_tokens": 1858269}
|
| 16 |
+
{"current_steps": 80, "total_steps": 1505, "loss": 2.7305, "learning_rate": 4.9652217902637596e-05, "epoch": 1.855072463768116, "percentage": 5.32, "elapsed_time": "0:32:31", "remaining_time": "9:39:17", "throughput": "1017.05", "total_tokens": 1984587}
|
| 17 |
+
{"current_steps": 85, "total_steps": 1505, "loss": 2.6482, "learning_rate": 4.9607504272744575e-05, "epoch": 1.971014492753623, "percentage": 5.65, "elapsed_time": "0:34:48", "remaining_time": "9:41:24", "throughput": "1010.18", "total_tokens": 2109391}
|
| 18 |
+
{"current_steps": 90, "total_steps": 1505, "loss": 2.4292, "learning_rate": 4.956011005292692e-05, "epoch": 2.0869565217391304, "percentage": 5.98, "elapsed_time": "0:37:08", "remaining_time": "9:43:59", "throughput": "1007.97", "total_tokens": 2246413}
|
| 19 |
+
{"current_steps": 95, "total_steps": 1505, "loss": 2.1416, "learning_rate": 4.951004040601898e-05, "epoch": 2.2028985507246377, "percentage": 6.31, "elapsed_time": "0:39:34", "remaining_time": "9:47:21", "throughput": "1005.24", "total_tokens": 2386890}
|
| 20 |
+
{"current_steps": 100, "total_steps": 1505, "loss": 2.2847, "learning_rate": 4.945730078629964e-05, "epoch": 2.318840579710145, "percentage": 6.64, "elapsed_time": "0:41:53", "remaining_time": "9:48:28", "throughput": "1003.68", "total_tokens": 2522302}
|
| 21 |
+
{"current_steps": 105, "total_steps": 1505, "loss": 2.0944, "learning_rate": 4.9401896938898185e-05, "epoch": 2.4347826086956523, "percentage": 6.98, "elapsed_time": "0:44:27", "remaining_time": "9:52:47", "throughput": "990.48", "total_tokens": 2642208}
|
| 22 |
+
{"current_steps": 110, "total_steps": 1505, "loss": 2.2862, "learning_rate": 4.934383489916843e-05, "epoch": 2.550724637681159, "percentage": 7.31, "elapsed_time": "0:46:51", "remaining_time": "9:54:19", "throughput": "988.89", "total_tokens": 2780587}
|
| 23 |
+
{"current_steps": 115, "total_steps": 1505, "loss": 2.105, "learning_rate": 4.928312099203131e-05, "epoch": 2.6666666666666665, "percentage": 7.64, "elapsed_time": "0:48:26", "remaining_time": "9:45:36", "throughput": "992.54", "total_tokens": 2885320}
|
| 24 |
+
{"current_steps": 120, "total_steps": 1505, "loss": 2.0287, "learning_rate": 4.921976183128585e-05, "epoch": 2.782608695652174, "percentage": 7.97, "elapsed_time": "0:50:19", "remaining_time": "9:40:48", "throughput": "992.56", "total_tokens": 2996923}
|
| 25 |
+
{"current_steps": 125, "total_steps": 1505, "loss": 2.0162, "learning_rate": 4.9153764318888706e-05, "epoch": 2.898550724637681, "percentage": 8.31, "elapsed_time": "0:51:54", "remaining_time": "9:33:09", "throughput": "995.97", "total_tokens": 3102391}
|
| 26 |
+
{"current_steps": 130, "total_steps": 1505, "loss": 2.2464, "learning_rate": 4.908513564420231e-05, "epoch": 3.0144927536231885, "percentage": 8.64, "elapsed_time": "0:54:01", "remaining_time": "9:31:24", "throughput": "997.54", "total_tokens": 3233443}
|
| 27 |
+
{"current_steps": 135, "total_steps": 1505, "loss": 1.6561, "learning_rate": 4.90138832832117e-05, "epoch": 3.130434782608696, "percentage": 8.97, "elapsed_time": "0:56:00", "remaining_time": "9:28:23", "throughput": "999.52", "total_tokens": 3358966}
|
| 28 |
+
{"current_steps": 140, "total_steps": 1505, "loss": 1.6113, "learning_rate": 4.894001499771015e-05, "epoch": 3.246376811594203, "percentage": 9.3, "elapsed_time": "0:58:09", "remaining_time": "9:27:05", "throughput": "1000.08", "total_tokens": 3490069}
|
| 29 |
+
{"current_steps": 145, "total_steps": 1505, "loss": 1.6235, "learning_rate": 4.886353883445363e-05, "epoch": 3.36231884057971, "percentage": 9.63, "elapsed_time": "1:00:15", "remaining_time": "9:25:14", "throughput": "998.34", "total_tokens": 3609842}
|
| 30 |
+
{"current_steps": 150, "total_steps": 1505, "loss": 1.7873, "learning_rate": 4.878446312428424e-05, "epoch": 3.4782608695652173, "percentage": 9.97, "elapsed_time": "1:02:40", "remaining_time": "9:26:06", "throughput": "997.72", "total_tokens": 3751570}
|
| 31 |
+
{"current_steps": 155, "total_steps": 1505, "loss": 1.3723, "learning_rate": 4.8702796481222714e-05, "epoch": 3.5942028985507246, "percentage": 10.3, "elapsed_time": "1:04:42", "remaining_time": "9:23:34", "throughput": "995.58", "total_tokens": 3865303}
|
| 32 |
+
{"current_steps": 160, "total_steps": 1505, "loss": 1.6512, "learning_rate": 4.861854780153004e-05, "epoch": 3.710144927536232, "percentage": 10.63, "elapsed_time": "1:06:42", "remaining_time": "9:20:49", "throughput": "997.10", "total_tokens": 3991347}
|
| 33 |
+
{"current_steps": 165, "total_steps": 1505, "loss": 1.5524, "learning_rate": 4.853172626273841e-05, "epoch": 3.8260869565217392, "percentage": 10.96, "elapsed_time": "1:08:43", "remaining_time": "9:18:06", "throughput": "997.64", "total_tokens": 4113654}
|
| 34 |
+
{"current_steps": 170, "total_steps": 1505, "loss": 1.5954, "learning_rate": 4.8442341322651385e-05, "epoch": 3.942028985507246, "percentage": 11.3, "elapsed_time": "1:10:40", "remaining_time": "9:14:57", "throughput": "999.10", "total_tokens": 4236348}
|
| 35 |
+
{"current_steps": 175, "total_steps": 1505, "loss": 1.1652, "learning_rate": 4.83504027183137e-05, "epoch": 4.057971014492754, "percentage": 11.63, "elapsed_time": "1:12:15", "remaining_time": "9:09:10", "throughput": "1001.11", "total_tokens": 4340378}
|
| 36 |
+
{"current_steps": 180, "total_steps": 1505, "loss": 1.1995, "learning_rate": 4.825592046495054e-05, "epoch": 4.173913043478261, "percentage": 11.96, "elapsed_time": "1:14:31", "remaining_time": "9:08:33", "throughput": "1000.51", "total_tokens": 4473601}
|
| 37 |
+
{"current_steps": 185, "total_steps": 1505, "loss": 0.9431, "learning_rate": 4.8158904854876555e-05, "epoch": 4.2898550724637685, "percentage": 12.29, "elapsed_time": "1:16:28", "remaining_time": "9:05:42", "throughput": "999.58", "total_tokens": 4586911}
|
| 38 |
+
{"current_steps": 190, "total_steps": 1505, "loss": 1.1136, "learning_rate": 4.805936645637463e-05, "epoch": 4.405797101449275, "percentage": 12.62, "elapsed_time": "1:18:30", "remaining_time": "9:03:20", "throughput": "998.32", "total_tokens": 4702445}
|
| 39 |
+
{"current_steps": 195, "total_steps": 1505, "loss": 1.1509, "learning_rate": 4.795731611254473e-05, "epoch": 4.521739130434782, "percentage": 12.96, "elapsed_time": "1:20:34", "remaining_time": "9:01:18", "throughput": "999.32", "total_tokens": 4831301}
|
| 40 |
+
{"current_steps": 200, "total_steps": 1505, "loss": 0.9962, "learning_rate": 4.785276494012263e-05, "epoch": 4.63768115942029, "percentage": 13.29, "elapsed_time": "1:22:18", "remaining_time": "8:57:05", "throughput": "1000.59", "total_tokens": 4941656}
|
| 41 |
+
{"current_steps": 205, "total_steps": 1505, "loss": 1.2377, "learning_rate": 4.7745724328269e-05, "epoch": 4.753623188405797, "percentage": 13.62, "elapsed_time": "1:25:08", "remaining_time": "8:59:53", "throughput": "996.13", "total_tokens": 5088437}
|
| 42 |
+
{"current_steps": 210, "total_steps": 1505, "loss": 1.234, "learning_rate": 4.763620593732867e-05, "epoch": 4.869565217391305, "percentage": 13.95, "elapsed_time": "1:27:18", "remaining_time": "8:58:21", "throughput": "996.52", "total_tokens": 5219806}
|
| 43 |
+
{"current_steps": 215, "total_steps": 1505, "loss": 1.1453, "learning_rate": 4.752422169756048e-05, "epoch": 4.9855072463768115, "percentage": 14.29, "elapsed_time": "1:29:10", "remaining_time": "8:55:03", "throughput": "998.06", "total_tokens": 5340222}
|
| 44 |
+
{"current_steps": 220, "total_steps": 1505, "loss": 0.9056, "learning_rate": 4.740978380783765e-05, "epoch": 5.101449275362318, "percentage": 14.62, "elapsed_time": "1:31:31", "remaining_time": "8:54:32", "throughput": "997.31", "total_tokens": 5476315}
|
| 45 |
+
{"current_steps": 225, "total_steps": 1505, "loss": 0.7349, "learning_rate": 4.7292904734318924e-05, "epoch": 5.217391304347826, "percentage": 14.95, "elapsed_time": "1:33:21", "remaining_time": "8:51:03", "throughput": "998.01", "total_tokens": 5589951}
|
| 46 |
+
{"current_steps": 230, "total_steps": 1505, "loss": 0.6968, "learning_rate": 4.7173597209090534e-05, "epoch": 5.333333333333333, "percentage": 15.28, "elapsed_time": "1:35:17", "remaining_time": "8:48:13", "throughput": "999.00", "total_tokens": 5711449}
|
| 47 |
+
{"current_steps": 235, "total_steps": 1505, "loss": 0.851, "learning_rate": 4.70518742287793e-05, "epoch": 5.449275362318841, "percentage": 15.61, "elapsed_time": "1:37:41", "remaining_time": "8:47:58", "throughput": "998.45", "total_tokens": 5852650}
|
| 48 |
+
{"current_steps": 240, "total_steps": 1505, "loss": 0.716, "learning_rate": 4.6927749053136866e-05, "epoch": 5.565217391304348, "percentage": 15.95, "elapsed_time": "1:39:37", "remaining_time": "8:45:03", "throughput": "999.21", "total_tokens": 5972289}
|
| 49 |
+
{"current_steps": 245, "total_steps": 1505, "loss": 0.6384, "learning_rate": 4.6801235203595195e-05, "epoch": 5.681159420289855, "percentage": 16.28, "elapsed_time": "1:41:26", "remaining_time": "8:41:40", "throughput": "1000.40", "total_tokens": 6088707}
|
| 50 |
+
{"current_steps": 250, "total_steps": 1505, "loss": 0.7799, "learning_rate": 4.667234646179368e-05, "epoch": 5.797101449275362, "percentage": 16.61, "elapsed_time": "1:43:47", "remaining_time": "8:41:00", "throughput": "998.13", "total_tokens": 6215471}
|
| 51 |
+
{"current_steps": 255, "total_steps": 1505, "loss": 0.7923, "learning_rate": 4.654109686807787e-05, "epoch": 5.913043478260869, "percentage": 16.94, "elapsed_time": "1:45:48", "remaining_time": "8:38:42", "throughput": "997.95", "total_tokens": 6335935}
|
| 52 |
+
{"current_steps": 260, "total_steps": 1505, "loss": 0.7452, "learning_rate": 4.640750071996995e-05, "epoch": 6.028985507246377, "percentage": 17.28, "elapsed_time": "1:47:52", "remaining_time": "8:36:31", "throughput": "998.69", "total_tokens": 6463689}
|
| 53 |
+
{"current_steps": 265, "total_steps": 1505, "loss": 0.4085, "learning_rate": 4.6271572570611296e-05, "epoch": 6.144927536231884, "percentage": 17.61, "elapsed_time": "1:49:37", "remaining_time": "8:32:55", "throughput": "999.98", "total_tokens": 6576954}
|
| 54 |
+
{"current_steps": 270, "total_steps": 1505, "loss": 0.5777, "learning_rate": 4.613332722717714e-05, "epoch": 6.260869565217392, "percentage": 17.94, "elapsed_time": "1:51:51", "remaining_time": "8:31:39", "throughput": "1000.40", "total_tokens": 6714404}
|
| 55 |
+
{"current_steps": 275, "total_steps": 1505, "loss": 0.4718, "learning_rate": 4.5992779749263546e-05, "epoch": 6.3768115942028984, "percentage": 18.27, "elapsed_time": "1:53:54", "remaining_time": "8:29:28", "throughput": "1000.87", "total_tokens": 6840385}
|
| 56 |
+
{"current_steps": 280, "total_steps": 1505, "loss": 0.3723, "learning_rate": 4.584994544724695e-05, "epoch": 6.492753623188406, "percentage": 18.6, "elapsed_time": "1:55:39", "remaining_time": "8:26:01", "throughput": "1002.09", "total_tokens": 6954269}
|
| 57 |
+
{"current_steps": 285, "total_steps": 1505, "loss": 0.4453, "learning_rate": 4.5704839880616296e-05, "epoch": 6.608695652173913, "percentage": 18.94, "elapsed_time": "1:57:50", "remaining_time": "8:24:25", "throughput": "1000.84", "total_tokens": 7076143}
|
| 58 |
+
{"current_steps": 290, "total_steps": 1505, "loss": 0.5742, "learning_rate": 4.5557478856278114e-05, "epoch": 6.72463768115942, "percentage": 19.27, "elapsed_time": "1:59:51", "remaining_time": "8:22:11", "throughput": "1001.38", "total_tokens": 7201833}
|
| 59 |
+
{"current_steps": 295, "total_steps": 1505, "loss": 0.5291, "learning_rate": 4.5407878426834596e-05, "epoch": 6.840579710144928, "percentage": 19.6, "elapsed_time": "2:01:56", "remaining_time": "8:20:09", "throughput": "1001.95", "total_tokens": 7330479}
|
| 60 |
+
{"current_steps": 300, "total_steps": 1505, "loss": 0.4968, "learning_rate": 4.5256054888834934e-05, "epoch": 6.956521739130435, "percentage": 19.93, "elapsed_time": "2:03:49", "remaining_time": "8:17:23", "throughput": "1002.60", "total_tokens": 7449244}
|
| 61 |
+
{"current_steps": 305, "total_steps": 1505, "loss": 0.421, "learning_rate": 4.5102024781000077e-05, "epoch": 7.072463768115942, "percentage": 20.27, "elapsed_time": "2:06:19", "remaining_time": "8:17:00", "throughput": "999.94", "total_tokens": 7578947}
|
| 62 |
+
{"current_steps": 310, "total_steps": 1505, "loss": 0.2767, "learning_rate": 4.4945804882421086e-05, "epoch": 7.188405797101449, "percentage": 20.6, "elapsed_time": "2:08:26", "remaining_time": "8:15:08", "throughput": "998.07", "total_tokens": 7691948}
|
| 63 |
+
{"current_steps": 315, "total_steps": 1505, "loss": 0.2922, "learning_rate": 4.478741221073136e-05, "epoch": 7.304347826086957, "percentage": 20.93, "elapsed_time": "2:10:25", "remaining_time": "8:12:42", "throughput": "998.79", "total_tokens": 7815786}
|
| 64 |
+
{"current_steps": 320, "total_steps": 1505, "loss": 0.2768, "learning_rate": 4.4626864020252774e-05, "epoch": 7.420289855072464, "percentage": 21.26, "elapsed_time": "2:12:16", "remaining_time": "8:09:49", "throughput": "998.57", "total_tokens": 7925106}
|
| 65 |
+
{"current_steps": 325, "total_steps": 1505, "loss": 0.3281, "learning_rate": 4.446417780011618e-05, "epoch": 7.536231884057971, "percentage": 21.59, "elapsed_time": "2:14:49", "remaining_time": "8:09:31", "throughput": "995.98", "total_tokens": 8057202}
|
| 66 |
+
{"current_steps": 330, "total_steps": 1505, "loss": 0.3374, "learning_rate": 4.42993712723562e-05, "epoch": 7.6521739130434785, "percentage": 21.93, "elapsed_time": "2:17:00", "remaining_time": "8:07:51", "throughput": "995.98", "total_tokens": 8187865}
|
| 67 |
+
{"current_steps": 335, "total_steps": 1505, "loss": 0.2491, "learning_rate": 4.413246238998069e-05, "epoch": 7.768115942028985, "percentage": 22.26, "elapsed_time": "2:18:55", "remaining_time": "8:05:11", "throughput": "996.31", "total_tokens": 8304605}
|
| 68 |
+
{"current_steps": 340, "total_steps": 1505, "loss": 0.3893, "learning_rate": 4.3963469335015085e-05, "epoch": 7.884057971014493, "percentage": 22.59, "elapsed_time": "2:21:09", "remaining_time": "8:03:40", "throughput": "996.21", "total_tokens": 8437319}
|
| 69 |
+
{"current_steps": 345, "total_steps": 1505, "loss": 0.3761, "learning_rate": 4.379241051652174e-05, "epoch": 8.0, "percentage": 22.92, "elapsed_time": "2:23:26", "remaining_time": "8:02:17", "throughput": "996.14", "total_tokens": 8573080}
|
| 70 |
+
{"current_steps": 350, "total_steps": 1505, "loss": 0.236, "learning_rate": 4.361930456859456e-05, "epoch": 8.115942028985508, "percentage": 23.26, "elapsed_time": "2:25:38", "remaining_time": "8:00:37", "throughput": "996.45", "total_tokens": 8707741}
|
| 71 |
+
{"current_steps": 355, "total_steps": 1505, "loss": 0.1584, "learning_rate": 4.34441703483291e-05, "epoch": 8.231884057971014, "percentage": 23.59, "elapsed_time": "2:27:37", "remaining_time": "7:58:12", "throughput": "996.43", "total_tokens": 8825774}
|
| 72 |
+
{"current_steps": 360, "total_steps": 1505, "loss": 0.1481, "learning_rate": 4.326702693376844e-05, "epoch": 8.347826086956522, "percentage": 23.92, "elapsed_time": "2:29:16", "remaining_time": "7:54:47", "throughput": "997.27", "total_tokens": 8932249}
|
| 73 |
+
{"current_steps": 365, "total_steps": 1505, "loss": 0.1743, "learning_rate": 4.308789362182492e-05, "epoch": 8.46376811594203, "percentage": 24.25, "elapsed_time": "2:31:20", "remaining_time": "7:52:40", "throughput": "996.84", "total_tokens": 9051548}
|
| 74 |
+
{"current_steps": 370, "total_steps": 1505, "loss": 0.3162, "learning_rate": 4.290678992617798e-05, "epoch": 8.579710144927537, "percentage": 24.58, "elapsed_time": "2:33:45", "remaining_time": "7:51:39", "throughput": "996.95", "total_tokens": 9197232}
|
| 75 |
+
{"current_steps": 375, "total_steps": 1505, "loss": 0.2235, "learning_rate": 4.272373557514858e-05, "epoch": 8.695652173913043, "percentage": 24.92, "elapsed_time": "2:35:41", "remaining_time": "7:49:10", "throughput": "997.40", "total_tokens": 9317650}
|
| 76 |
+
{"current_steps": 380, "total_steps": 1505, "loss": 0.2504, "learning_rate": 4.2538750509550054e-05, "epoch": 8.81159420289855, "percentage": 25.25, "elapsed_time": "2:37:57", "remaining_time": "7:47:39", "throughput": "997.16", "total_tokens": 9450765}
|
| 77 |
+
{"current_steps": 385, "total_steps": 1505, "loss": 0.2136, "learning_rate": 4.235185488051585e-05, "epoch": 8.927536231884059, "percentage": 25.58, "elapsed_time": "2:40:03", "remaining_time": "7:45:37", "throughput": "997.85", "total_tokens": 9582961}
|
| 78 |
+
{"current_steps": 390, "total_steps": 1505, "loss": 0.1047, "learning_rate": 4.216306904730447e-05, "epoch": 9.043478260869565, "percentage": 25.91, "elapsed_time": "2:41:35", "remaining_time": "7:41:58", "throughput": "998.27", "total_tokens": 9678616}
|
| 79 |
+
{"current_steps": 395, "total_steps": 1505, "loss": 0.1015, "learning_rate": 4.1972413575081595e-05, "epoch": 9.159420289855072, "percentage": 26.25, "elapsed_time": "2:43:18", "remaining_time": "7:38:54", "throughput": "999.00", "total_tokens": 9788512}
|
| 80 |
+
{"current_steps": 400, "total_steps": 1505, "loss": 0.1505, "learning_rate": 4.177990923267986e-05, "epoch": 9.27536231884058, "percentage": 26.58, "elapsed_time": "2:45:26", "remaining_time": "7:37:03", "throughput": "998.92", "total_tokens": 9916229}
|
| 81 |
+
{"current_steps": 405, "total_steps": 1505, "loss": 0.1135, "learning_rate": 4.158557699033644e-05, "epoch": 9.391304347826088, "percentage": 26.91, "elapsed_time": "2:47:51", "remaining_time": "7:35:55", "throughput": "997.11", "total_tokens": 10042697}
|
| 82 |
+
{"current_steps": 410, "total_steps": 1505, "loss": 0.1832, "learning_rate": 4.138943801740865e-05, "epoch": 9.507246376811594, "percentage": 27.24, "elapsed_time": "2:50:00", "remaining_time": "7:34:03", "throughput": "997.17", "total_tokens": 10171849}
|
| 83 |
+
{"current_steps": 415, "total_steps": 1505, "loss": 0.1178, "learning_rate": 4.119151368006793e-05, "epoch": 9.623188405797102, "percentage": 27.57, "elapsed_time": "2:51:42", "remaining_time": "7:30:58", "throughput": "998.04", "total_tokens": 10281924}
|
| 84 |
+
{"current_steps": 420, "total_steps": 1505, "loss": 0.1426, "learning_rate": 4.099182553897229e-05, "epoch": 9.73913043478261, "percentage": 27.91, "elapsed_time": "2:54:17", "remaining_time": "7:30:14", "throughput": "996.34", "total_tokens": 10418758}
|
| 85 |
+
{"current_steps": 425, "total_steps": 1505, "loss": 0.1603, "learning_rate": 4.079039534691767e-05, "epoch": 9.855072463768115, "percentage": 28.24, "elapsed_time": "2:56:32", "remaining_time": "7:28:36", "throughput": "996.80", "total_tokens": 10558322}
|
| 86 |
+
{"current_steps": 430, "total_steps": 1505, "loss": 0.1548, "learning_rate": 4.058724504646834e-05, "epoch": 9.971014492753623, "percentage": 28.57, "elapsed_time": "2:58:42", "remaining_time": "7:26:45", "throughput": "996.01", "total_tokens": 10679536}
|
| 87 |
+
{"current_steps": 435, "total_steps": 1505, "loss": 0.1407, "learning_rate": 4.0382396767566536e-05, "epoch": 10.08695652173913, "percentage": 28.9, "elapsed_time": "3:01:04", "remaining_time": "7:25:25", "throughput": "995.97", "total_tokens": 10821076}
|
| 88 |
+
{"current_steps": 440, "total_steps": 1505, "loss": 0.0791, "learning_rate": 4.017587282512181e-05, "epoch": 10.202898550724637, "percentage": 29.24, "elapsed_time": "3:03:15", "remaining_time": "7:23:34", "throughput": "995.82", "total_tokens": 10949771}
|
| 89 |
+
{"current_steps": 445, "total_steps": 1505, "loss": 0.0722, "learning_rate": 3.9967695716580224e-05, "epoch": 10.318840579710145, "percentage": 29.57, "elapsed_time": "3:05:26", "remaining_time": "7:21:43", "throughput": "995.11", "total_tokens": 11072044}
|
| 90 |
+
{"current_steps": 450, "total_steps": 1505, "loss": 0.0655, "learning_rate": 3.975788811947351e-05, "epoch": 10.434782608695652, "percentage": 29.9, "elapsed_time": "3:07:09", "remaining_time": "7:18:47", "throughput": "995.82", "total_tokens": 11182627}
|
| 91 |
+
{"current_steps": 455, "total_steps": 1505, "loss": 0.0723, "learning_rate": 3.954647288894883e-05, "epoch": 10.55072463768116, "percentage": 30.23, "elapsed_time": "3:09:02", "remaining_time": "7:16:15", "throughput": "996.49", "total_tokens": 11303028}
|
| 92 |
+
{"current_steps": 460, "total_steps": 1505, "loss": 0.0655, "learning_rate": 3.933347305527898e-05, "epoch": 10.666666666666666, "percentage": 30.56, "elapsed_time": "3:10:46", "remaining_time": "7:13:23", "throughput": "997.33", "total_tokens": 11415868}
|
| 93 |
+
{"current_steps": 465, "total_steps": 1505, "loss": 0.1534, "learning_rate": 3.911891182135371e-05, "epoch": 10.782608695652174, "percentage": 30.9, "elapsed_time": "3:13:15", "remaining_time": "7:12:13", "throughput": "996.60", "total_tokens": 11555653}
|
| 94 |
+
{"current_steps": 470, "total_steps": 1505, "loss": 0.0947, "learning_rate": 3.8902812560152066e-05, "epoch": 10.898550724637682, "percentage": 31.23, "elapsed_time": "3:15:17", "remaining_time": "7:10:03", "throughput": "996.89", "total_tokens": 11681065}
|
| 95 |
+
{"current_steps": 475, "total_steps": 1505, "loss": 0.0868, "learning_rate": 3.868519881219631e-05, "epoch": 11.014492753623188, "percentage": 31.56, "elapsed_time": "3:17:22", "remaining_time": "7:07:58", "throughput": "997.29", "total_tokens": 11809957}
|
| 96 |
+
{"current_steps": 480, "total_steps": 1505, "loss": 0.0467, "learning_rate": 3.846609428298757e-05, "epoch": 11.130434782608695, "percentage": 31.89, "elapsed_time": "3:19:27", "remaining_time": "7:05:55", "throughput": "997.52", "total_tokens": 11937881}
|
| 97 |
+
{"current_steps": 485, "total_steps": 1505, "loss": 0.0521, "learning_rate": 3.824552284042351e-05, "epoch": 11.246376811594203, "percentage": 32.23, "elapsed_time": "3:21:11", "remaining_time": "7:03:06", "throughput": "998.15", "total_tokens": 12048905}
|
| 98 |
+
{"current_steps": 490, "total_steps": 1505, "loss": 0.051, "learning_rate": 3.8023508512198256e-05, "epoch": 11.36231884057971, "percentage": 32.56, "elapsed_time": "3:23:21", "remaining_time": "7:01:15", "throughput": "998.66", "total_tokens": 12185453}
|
| 99 |
+
{"current_steps": 495, "total_steps": 1505, "loss": 0.0753, "learning_rate": 3.780007548318507e-05, "epoch": 11.478260869565217, "percentage": 32.89, "elapsed_time": "3:25:21", "remaining_time": "6:59:01", "throughput": "999.10", "total_tokens": 12310911}
|
| 100 |
+
{"current_steps": 500, "total_steps": 1505, "loss": 0.0601, "learning_rate": 3.7575248092801686e-05, "epoch": 11.594202898550725, "percentage": 33.22, "elapsed_time": "3:27:25", "remaining_time": "6:56:54", "throughput": "999.57", "total_tokens": 12439708}
|
| 101 |
+
{"current_steps": 505, "total_steps": 1505, "loss": 0.0533, "learning_rate": 3.734905083235901e-05, "epoch": 11.710144927536232, "percentage": 33.55, "elapsed_time": "3:29:31", "remaining_time": "6:54:54", "throughput": "998.61", "total_tokens": 12554467}
|
| 102 |
+
{"current_steps": 510, "total_steps": 1505, "loss": 0.064, "learning_rate": 3.712150834239313e-05, "epoch": 11.826086956521738, "percentage": 33.89, "elapsed_time": "3:31:33", "remaining_time": "6:52:45", "throughput": "999.10", "total_tokens": 12682329}
|
| 103 |
+
{"current_steps": 515, "total_steps": 1505, "loss": 0.0755, "learning_rate": 3.689264540998116e-05, "epoch": 11.942028985507246, "percentage": 34.22, "elapsed_time": "3:33:26", "remaining_time": "6:50:17", "throughput": "999.59", "total_tokens": 12800852}
|
| 104 |
+
{"current_steps": 520, "total_steps": 1505, "loss": 0.0553, "learning_rate": 3.66624869660411e-05, "epoch": 12.057971014492754, "percentage": 34.55, "elapsed_time": "3:35:16", "remaining_time": "6:47:47", "throughput": "1000.07", "total_tokens": 12917527}
|
| 105 |
+
{"current_steps": 525, "total_steps": 1505, "loss": 0.0355, "learning_rate": 3.6431058082615964e-05, "epoch": 12.173913043478262, "percentage": 34.88, "elapsed_time": "3:37:30", "remaining_time": "6:46:00", "throughput": "999.57", "total_tokens": 13044774}
|
| 106 |
+
{"current_steps": 530, "total_steps": 1505, "loss": 0.0413, "learning_rate": 3.619838397014263e-05, "epoch": 12.289855072463768, "percentage": 35.22, "elapsed_time": "3:39:37", "remaining_time": "6:44:01", "throughput": "999.88", "total_tokens": 13175692}
|
| 107 |
+
{"current_steps": 535, "total_steps": 1505, "loss": 0.0596, "learning_rate": 3.5964489974705553e-05, "epoch": 12.405797101449275, "percentage": 35.55, "elapsed_time": "3:41:28", "remaining_time": "6:41:32", "throughput": "1000.36", "total_tokens": 13293164}
|
| 108 |
+
{"current_steps": 540, "total_steps": 1505, "loss": 0.0479, "learning_rate": 3.572940157527572e-05, "epoch": 12.521739130434783, "percentage": 35.88, "elapsed_time": "3:43:28", "remaining_time": "6:39:21", "throughput": "1000.70", "total_tokens": 13417894}
|
| 109 |
+
{"current_steps": 545, "total_steps": 1505, "loss": 0.047, "learning_rate": 3.549314438093515e-05, "epoch": 12.63768115942029, "percentage": 36.21, "elapsed_time": "3:45:42", "remaining_time": "6:37:33", "throughput": "1000.73", "total_tokens": 13551913}
|
| 110 |
+
{"current_steps": 550, "total_steps": 1505, "loss": 0.0492, "learning_rate": 3.525574412808717e-05, "epoch": 12.753623188405797, "percentage": 36.54, "elapsed_time": "3:47:41", "remaining_time": "6:35:20", "throughput": "1001.04", "total_tokens": 13675309}
|
| 111 |
+
{"current_steps": 555, "total_steps": 1505, "loss": 0.0471, "learning_rate": 3.501722667765286e-05, "epoch": 12.869565217391305, "percentage": 36.88, "elapsed_time": "3:49:38", "remaining_time": "6:33:05", "throughput": "1001.36", "total_tokens": 13797691}
|
| 112 |
+
{"current_steps": 560, "total_steps": 1505, "loss": 0.1041, "learning_rate": 3.47776180122539e-05, "epoch": 12.985507246376812, "percentage": 37.21, "elapsed_time": "3:51:48", "remaining_time": "6:31:10", "throughput": "1000.82", "total_tokens": 13919770}
|
| 113 |
+
{"current_steps": 565, "total_steps": 1505, "loss": 0.0282, "learning_rate": 3.453694423338225e-05, "epoch": 13.101449275362318, "percentage": 37.54, "elapsed_time": "3:53:36", "remaining_time": "6:28:39", "throughput": "1001.50", "total_tokens": 14037673}
|
| 114 |
+
{"current_steps": 570, "total_steps": 1505, "loss": 0.0272, "learning_rate": 3.4295231558556715e-05, "epoch": 13.217391304347826, "percentage": 37.87, "elapsed_time": "3:55:59", "remaining_time": "6:27:07", "throughput": "1000.51", "total_tokens": 14167090}
|
| 115 |
+
{"current_steps": 575, "total_steps": 1505, "loss": 0.0342, "learning_rate": 3.4052506318467084e-05, "epoch": 13.333333333333334, "percentage": 38.21, "elapsed_time": "3:58:23", "remaining_time": "6:25:33", "throughput": "1000.60", "total_tokens": 14311710}
|
| 116 |
+
{"current_steps": 580, "total_steps": 1505, "loss": 0.0855, "learning_rate": 3.3808794954105716e-05, "epoch": 13.44927536231884, "percentage": 38.54, "elapsed_time": "3:59:53", "remaining_time": "6:22:35", "throughput": "1000.75", "total_tokens": 14404322}
|
| 117 |
+
{"current_steps": 585, "total_steps": 1505, "loss": 0.0378, "learning_rate": 3.356412401388732e-05, "epoch": 13.565217391304348, "percentage": 38.87, "elapsed_time": "4:01:55", "remaining_time": "6:20:28", "throughput": "1001.03", "total_tokens": 14530794}
|
| 118 |
+
{"current_steps": 590, "total_steps": 1505, "loss": 0.0457, "learning_rate": 3.3318520150756846e-05, "epoch": 13.681159420289855, "percentage": 39.2, "elapsed_time": "4:03:33", "remaining_time": "6:17:42", "throughput": "1001.65", "total_tokens": 14637342}
|
| 119 |
+
{"current_steps": 595, "total_steps": 1505, "loss": 0.0453, "learning_rate": 3.307201011928616e-05, "epoch": 13.797101449275363, "percentage": 39.53, "elapsed_time": "4:06:05", "remaining_time": "6:16:21", "throughput": "1001.53", "total_tokens": 14787534}
|
| 120 |
+
{"current_steps": 600, "total_steps": 1505, "loss": 0.0378, "learning_rate": 3.282462077275947e-05, "epoch": 13.91304347826087, "percentage": 39.87, "elapsed_time": "4:08:03", "remaining_time": "6:14:09", "throughput": "1001.72", "total_tokens": 14909175}
|
| 121 |
+
{"current_steps": 605, "total_steps": 1505, "loss": 0.0296, "learning_rate": 3.257637906024822e-05, "epoch": 14.028985507246377, "percentage": 40.2, "elapsed_time": "4:10:31", "remaining_time": "6:12:40", "throughput": "999.94", "total_tokens": 15030530}
|
| 122 |
+
{"current_steps": 610, "total_steps": 1505, "loss": 0.0216, "learning_rate": 3.2327312023675287e-05, "epoch": 14.144927536231885, "percentage": 40.53, "elapsed_time": "4:12:39", "remaining_time": "6:10:42", "throughput": "999.25", "total_tokens": 15148359}
|
| 123 |
+
{"current_steps": 615, "total_steps": 1505, "loss": 0.0299, "learning_rate": 3.2077446794869295e-05, "epoch": 14.26086956521739, "percentage": 40.86, "elapsed_time": "4:14:57", "remaining_time": "6:08:58", "throughput": "998.89", "total_tokens": 15280749}
|
| 124 |
+
{"current_steps": 620, "total_steps": 1505, "loss": 0.0247, "learning_rate": 3.1826810592609036e-05, "epoch": 14.376811594202898, "percentage": 41.2, "elapsed_time": "4:16:54", "remaining_time": "6:06:42", "throughput": "998.88", "total_tokens": 15397167}
|
| 125 |
+
{"current_steps": 625, "total_steps": 1505, "loss": 0.0455, "learning_rate": 3.157543071965835e-05, "epoch": 14.492753623188406, "percentage": 41.53, "elapsed_time": "4:19:23", "remaining_time": "6:05:13", "throughput": "997.37", "total_tokens": 15522794}
|
| 126 |
+
{"current_steps": 630, "total_steps": 1505, "loss": 0.0262, "learning_rate": 3.132333455979202e-05, "epoch": 14.608695652173914, "percentage": 41.86, "elapsed_time": "4:21:11", "remaining_time": "6:02:46", "throughput": "997.84", "total_tokens": 15637987}
|
| 127 |
+
{"current_steps": 635, "total_steps": 1505, "loss": 0.0281, "learning_rate": 3.107054957481271e-05, "epoch": 14.72463768115942, "percentage": 42.19, "elapsed_time": "4:23:21", "remaining_time": "6:00:49", "throughput": "998.19", "total_tokens": 15773163}
|
| 128 |
+
{"current_steps": 640, "total_steps": 1505, "loss": 0.0294, "learning_rate": 3.081710330155942e-05, "epoch": 14.840579710144928, "percentage": 42.52, "elapsed_time": "4:25:14", "remaining_time": "5:58:29", "throughput": "998.63", "total_tokens": 15892659}
|
| 129 |
+
{"current_steps": 645, "total_steps": 1505, "loss": 0.0291, "learning_rate": 3.056302334890786e-05, "epoch": 14.956521739130435, "percentage": 42.86, "elapsed_time": "4:27:21", "remaining_time": "5:56:28", "throughput": "998.97", "total_tokens": 16024576}
|
| 130 |
+
{"current_steps": 650, "total_steps": 1505, "loss": 0.0216, "learning_rate": 3.030833739476285e-05, "epoch": 15.072463768115941, "percentage": 43.19, "elapsed_time": "4:29:27", "remaining_time": "5:54:27", "throughput": "999.01", "total_tokens": 16151987}
|
| 131 |
+
{"current_steps": 655, "total_steps": 1505, "loss": 0.0218, "learning_rate": 3.0053073183043256e-05, "epoch": 15.18840579710145, "percentage": 43.52, "elapsed_time": "4:31:54", "remaining_time": "5:52:51", "throughput": "997.79", "total_tokens": 16278639}
|
| 132 |
+
{"current_steps": 660, "total_steps": 1505, "loss": 0.0283, "learning_rate": 2.979725852065981e-05, "epoch": 15.304347826086957, "percentage": 43.85, "elapsed_time": "4:34:13", "remaining_time": "5:51:05", "throughput": "997.64", "total_tokens": 16414743}
|
| 133 |
+
{"current_steps": 665, "total_steps": 1505, "loss": 0.0259, "learning_rate": 2.954092127448591e-05, "epoch": 15.420289855072463, "percentage": 44.19, "elapsed_time": "4:36:02", "remaining_time": "5:48:41", "throughput": "997.98", "total_tokens": 16529298}
|
| 134 |
+
{"current_steps": 670, "total_steps": 1505, "loss": 0.0716, "learning_rate": 2.9284089368322045e-05, "epoch": 15.53623188405797, "percentage": 44.52, "elapsed_time": "4:38:05", "remaining_time": "5:46:34", "throughput": "998.25", "total_tokens": 16655909}
|
| 135 |
+
{"current_steps": 675, "total_steps": 1505, "loss": 0.025, "learning_rate": 2.9026790779853874e-05, "epoch": 15.652173913043478, "percentage": 44.85, "elapsed_time": "4:40:27", "remaining_time": "5:44:51", "throughput": "998.26", "total_tokens": 16798263}
|
| 136 |
+
{"current_steps": 680, "total_steps": 1505, "loss": 0.0218, "learning_rate": 2.876905353760459e-05, "epoch": 15.768115942028986, "percentage": 45.18, "elapsed_time": "4:42:22", "remaining_time": "5:42:35", "throughput": "998.47", "total_tokens": 16916827}
|
| 137 |
+
{"current_steps": 685, "total_steps": 1505, "loss": 0.0231, "learning_rate": 2.8510905717881614e-05, "epoch": 15.884057971014492, "percentage": 45.51, "elapsed_time": "4:44:20", "remaining_time": "5:40:23", "throughput": "998.80", "total_tokens": 17040247}
|
| 138 |
+
{"current_steps": 690, "total_steps": 1505, "loss": 0.0228, "learning_rate": 2.8252375441718137e-05, "epoch": 16.0, "percentage": 45.85, "elapsed_time": "4:45:58", "remaining_time": "5:37:46", "throughput": "999.30", "total_tokens": 17146160}
|
| 139 |
+
{"current_steps": 695, "total_steps": 1505, "loss": 0.029, "learning_rate": 2.7993490871809808e-05, "epoch": 16.115942028985508, "percentage": 46.18, "elapsed_time": "4:48:18", "remaining_time": "5:36:01", "throughput": "999.19", "total_tokens": 17284643}
|
| 140 |
+
{"current_steps": 700, "total_steps": 1505, "loss": 0.0199, "learning_rate": 2.7734280209446865e-05, "epoch": 16.231884057971016, "percentage": 46.51, "elapsed_time": "4:50:40", "remaining_time": "5:34:16", "throughput": "999.18", "total_tokens": 17426644}
|
| 141 |
+
{"current_steps": 705, "total_steps": 1505, "loss": 0.0259, "learning_rate": 2.7474771691442018e-05, "epoch": 16.347826086956523, "percentage": 46.84, "elapsed_time": "4:53:00", "remaining_time": "5:32:29", "throughput": "997.81", "total_tokens": 17541812}
|
| 142 |
+
{"current_steps": 710, "total_steps": 1505, "loss": 0.021, "learning_rate": 2.721499358705458e-05, "epoch": 16.463768115942027, "percentage": 47.18, "elapsed_time": "4:55:06", "remaining_time": "5:30:25", "throughput": "997.83", "total_tokens": 17667755}
|
| 143 |
+
{"current_steps": 715, "total_steps": 1505, "loss": 0.0199, "learning_rate": 2.6954974194910888e-05, "epoch": 16.579710144927535, "percentage": 47.51, "elapsed_time": "4:56:59", "remaining_time": "5:28:08", "throughput": "998.23", "total_tokens": 17788162}
|
| 144 |
+
{"current_steps": 720, "total_steps": 1505, "loss": 0.0189, "learning_rate": 2.6694741839921732e-05, "epoch": 16.695652173913043, "percentage": 47.84, "elapsed_time": "4:58:57", "remaining_time": "5:25:57", "throughput": "998.55", "total_tokens": 17911718}
|
| 145 |
+
{"current_steps": 725, "total_steps": 1505, "loss": 0.0169, "learning_rate": 2.6434324870196748e-05, "epoch": 16.81159420289855, "percentage": 48.17, "elapsed_time": "5:00:37", "remaining_time": "5:23:26", "throughput": "998.93", "total_tokens": 18018729}
|
| 146 |
+
{"current_steps": 730, "total_steps": 1505, "loss": 0.0209, "learning_rate": 2.617375165395634e-05, "epoch": 16.92753623188406, "percentage": 48.5, "elapsed_time": "5:02:31", "remaining_time": "5:21:10", "throughput": "999.34", "total_tokens": 18139681}
|
| 147 |
+
{"current_steps": 735, "total_steps": 1505, "loss": 0.0201, "learning_rate": 2.5913050576441477e-05, "epoch": 17.043478260869566, "percentage": 48.84, "elapsed_time": "5:04:46", "remaining_time": "5:19:16", "throughput": "999.59", "total_tokens": 18278544}
|
| 148 |
+
{"current_steps": 740, "total_steps": 1505, "loss": 0.017, "learning_rate": 2.5652250036821523e-05, "epoch": 17.159420289855074, "percentage": 49.17, "elapsed_time": "5:06:53", "remaining_time": "5:17:15", "throughput": "999.09", "total_tokens": 18396700}
|
| 149 |
+
{"current_steps": 745, "total_steps": 1505, "loss": 0.0187, "learning_rate": 2.5391378445100644e-05, "epoch": 17.27536231884058, "percentage": 49.5, "elapsed_time": "5:08:38", "remaining_time": "5:14:50", "throughput": "999.36", "total_tokens": 18506229}
|
| 150 |
+
{"current_steps": 750, "total_steps": 1505, "loss": 0.0242, "learning_rate": 2.5130464219022992e-05, "epoch": 17.391304347826086, "percentage": 49.83, "elapsed_time": "5:10:26", "remaining_time": "5:12:31", "throughput": "999.72", "total_tokens": 18621580}
|
| 151 |
+
{"current_steps": 755, "total_steps": 1505, "loss": 0.0153, "learning_rate": 2.486953578097702e-05, "epoch": 17.507246376811594, "percentage": 50.17, "elapsed_time": "5:12:27", "remaining_time": "5:10:23", "throughput": "1000.04", "total_tokens": 18748382}
|
| 152 |
+
{"current_steps": 760, "total_steps": 1505, "loss": 0.0182, "learning_rate": 2.4608621554899362e-05, "epoch": 17.6231884057971, "percentage": 50.5, "elapsed_time": "5:14:42", "remaining_time": "5:08:29", "throughput": "1000.12", "total_tokens": 18884730}
|
| 153 |
+
{"current_steps": 765, "total_steps": 1505, "loss": 0.0143, "learning_rate": 2.4347749963178486e-05, "epoch": 17.73913043478261, "percentage": 50.83, "elapsed_time": "5:16:37", "remaining_time": "5:06:16", "throughput": "1000.34", "total_tokens": 19003589}
|
| 154 |
+
{"current_steps": 770, "total_steps": 1505, "loss": 0.0164, "learning_rate": 2.4086949423558526e-05, "epoch": 17.855072463768117, "percentage": 51.16, "elapsed_time": "5:18:47", "remaining_time": "5:04:18", "throughput": "1000.46", "total_tokens": 19136411}
|
| 155 |
+
{"current_steps": 775, "total_steps": 1505, "loss": 0.0157, "learning_rate": 2.3826248346043663e-05, "epoch": 17.971014492753625, "percentage": 51.5, "elapsed_time": "5:20:52", "remaining_time": "5:02:14", "throughput": "1000.43", "total_tokens": 19260436}
|
| 156 |
+
{"current_steps": 780, "total_steps": 1505, "loss": 0.0304, "learning_rate": 2.356567512980326e-05, "epoch": 18.08695652173913, "percentage": 51.83, "elapsed_time": "5:23:02", "remaining_time": "5:00:15", "throughput": "1000.34", "total_tokens": 19388733}
|
| 157 |
+
{"current_steps": 785, "total_steps": 1505, "loss": 0.009, "learning_rate": 2.3305258160078274e-05, "epoch": 18.202898550724637, "percentage": 52.16, "elapsed_time": "5:25:22", "remaining_time": "4:58:25", "throughput": "1000.45", "total_tokens": 19531204}
|
| 158 |
+
{"current_steps": 790, "total_steps": 1505, "loss": 0.0105, "learning_rate": 2.3045025805089118e-05, "epoch": 18.318840579710145, "percentage": 52.49, "elapsed_time": "5:26:47", "remaining_time": "4:55:45", "throughput": "1000.89", "total_tokens": 19624608}
|
| 159 |
+
{"current_steps": 795, "total_steps": 1505, "loss": 0.0104, "learning_rate": 2.278500641294543e-05, "epoch": 18.434782608695652, "percentage": 52.82, "elapsed_time": "5:29:00", "remaining_time": "4:53:49", "throughput": "1000.55", "total_tokens": 19751062}
|
| 160 |
+
{"current_steps": 800, "total_steps": 1505, "loss": 0.0103, "learning_rate": 2.252522830855798e-05, "epoch": 18.55072463768116, "percentage": 53.16, "elapsed_time": "5:31:08", "remaining_time": "4:51:49", "throughput": "1000.55", "total_tokens": 19879837}
|
| 161 |
+
{"current_steps": 805, "total_steps": 1505, "loss": 0.0107, "learning_rate": 2.2265719790553147e-05, "epoch": 18.666666666666668, "percentage": 53.49, "elapsed_time": "5:33:50", "remaining_time": "4:50:17", "throughput": "999.47", "total_tokens": 20019385}
|
| 162 |
+
{"current_steps": 810, "total_steps": 1505, "loss": 0.0269, "learning_rate": 2.2006509128190195e-05, "epoch": 18.782608695652176, "percentage": 53.82, "elapsed_time": "5:35:48", "remaining_time": "4:48:07", "throughput": "999.49", "total_tokens": 20138003}
|
| 163 |
+
{"current_steps": 815, "total_steps": 1505, "loss": 0.0086, "learning_rate": 2.174762455828187e-05, "epoch": 18.89855072463768, "percentage": 54.15, "elapsed_time": "5:37:46", "remaining_time": "4:45:58", "throughput": "999.70", "total_tokens": 20260523}
|
| 164 |
+
{"current_steps": 820, "total_steps": 1505, "loss": 0.0133, "learning_rate": 2.1489094282118395e-05, "epoch": 19.014492753623188, "percentage": 54.49, "elapsed_time": "5:39:36", "remaining_time": "4:43:41", "throughput": "999.96", "total_tokens": 20375322}
|
| 165 |
+
{"current_steps": 825, "total_steps": 1505, "loss": 0.0114, "learning_rate": 2.123094646239541e-05, "epoch": 19.130434782608695, "percentage": 54.82, "elapsed_time": "5:41:09", "remaining_time": "4:41:11", "throughput": "1000.41", "total_tokens": 20477407}
|
| 166 |
+
{"current_steps": 830, "total_steps": 1505, "loss": 0.007, "learning_rate": 2.0973209220146135e-05, "epoch": 19.246376811594203, "percentage": 55.15, "elapsed_time": "5:43:12", "remaining_time": "4:39:06", "throughput": "1000.64", "total_tokens": 20605728}
|
| 167 |
+
{"current_steps": 835, "total_steps": 1505, "loss": 0.0088, "learning_rate": 2.0715910631677968e-05, "epoch": 19.36231884057971, "percentage": 55.48, "elapsed_time": "5:45:09", "remaining_time": "4:36:57", "throughput": "1000.77", "total_tokens": 20725799}
|
| 168 |
+
{"current_steps": 840, "total_steps": 1505, "loss": 0.007, "learning_rate": 2.0459078725514092e-05, "epoch": 19.47826086956522, "percentage": 55.81, "elapsed_time": "5:47:35", "remaining_time": "4:35:10", "throughput": "1000.49", "total_tokens": 20865534}
|
| 169 |
+
{"current_steps": 845, "total_steps": 1505, "loss": 0.0059, "learning_rate": 2.020274147934019e-05, "epoch": 19.594202898550726, "percentage": 56.15, "elapsed_time": "5:49:21", "remaining_time": "4:32:52", "throughput": "1000.78", "total_tokens": 20977913}
|
| 170 |
+
{"current_steps": 850, "total_steps": 1505, "loss": 0.0069, "learning_rate": 1.9946926816956743e-05, "epoch": 19.71014492753623, "percentage": 56.48, "elapsed_time": "5:51:21", "remaining_time": "4:30:45", "throughput": "1000.99", "total_tokens": 21102848}
|
| 171 |
+
{"current_steps": 855, "total_steps": 1505, "loss": 0.008, "learning_rate": 1.9691662605237166e-05, "epoch": 19.82608695652174, "percentage": 56.81, "elapsed_time": "5:53:40", "remaining_time": "4:28:52", "throughput": "1001.10", "total_tokens": 21243679}
|
| 172 |
+
{"current_steps": 860, "total_steps": 1505, "loss": 0.0127, "learning_rate": 1.9436976651092144e-05, "epoch": 19.942028985507246, "percentage": 57.14, "elapsed_time": "5:55:37", "remaining_time": "4:26:43", "throughput": "1001.23", "total_tokens": 21364202}
|
| 173 |
+
{"current_steps": 865, "total_steps": 1505, "loss": 0.0059, "learning_rate": 1.9182896698440584e-05, "epoch": 20.057971014492754, "percentage": 57.48, "elapsed_time": "5:57:53", "remaining_time": "4:24:47", "throughput": "1001.07", "total_tokens": 21496089}
|
| 174 |
+
{"current_steps": 870, "total_steps": 1505, "loss": 0.0046, "learning_rate": 1.89294504251873e-05, "epoch": 20.17391304347826, "percentage": 57.81, "elapsed_time": "5:59:40", "remaining_time": "4:22:30", "throughput": "1001.07", "total_tokens": 21603193}
|
| 175 |
+
{"current_steps": 875, "total_steps": 1505, "loss": 0.0058, "learning_rate": 1.867666544020798e-05, "epoch": 20.28985507246377, "percentage": 58.14, "elapsed_time": "6:01:57", "remaining_time": "4:20:36", "throughput": "1001.15", "total_tokens": 21742062}
|
| 176 |
+
{"current_steps": 880, "total_steps": 1505, "loss": 0.0082, "learning_rate": 1.8424569280341653e-05, "epoch": 20.405797101449274, "percentage": 58.47, "elapsed_time": "6:04:10", "remaining_time": "4:18:38", "throughput": "1000.86", "total_tokens": 21869307}
|
| 177 |
+
{"current_steps": 885, "total_steps": 1505, "loss": 0.0148, "learning_rate": 1.817318940739098e-05, "epoch": 20.52173913043478, "percentage": 58.8, "elapsed_time": "6:06:08", "remaining_time": "4:16:30", "throughput": "1001.09", "total_tokens": 21992573}
|
| 178 |
+
{"current_steps": 890, "total_steps": 1505, "loss": 0.0064, "learning_rate": 1.7922553205130707e-05, "epoch": 20.63768115942029, "percentage": 59.14, "elapsed_time": "6:07:50", "remaining_time": "4:14:10", "throughput": "1001.43", "total_tokens": 22101845}
|
| 179 |
+
{"current_steps": 895, "total_steps": 1505, "loss": 0.008, "learning_rate": 1.767268797632472e-05, "epoch": 20.753623188405797, "percentage": 59.47, "elapsed_time": "6:09:59", "remaining_time": "4:12:10", "throughput": "1001.37", "total_tokens": 22230253}
|
| 180 |
+
{"current_steps": 900, "total_steps": 1505, "loss": 0.0053, "learning_rate": 1.7423620939751788e-05, "epoch": 20.869565217391305, "percentage": 59.8, "elapsed_time": "6:12:22", "remaining_time": "4:10:19", "throughput": "1001.39", "total_tokens": 22373454}
|
| 181 |
+
{"current_steps": 905, "total_steps": 1505, "loss": 0.0054, "learning_rate": 1.7175379227240523e-05, "epoch": 20.985507246376812, "percentage": 60.13, "elapsed_time": "6:14:33", "remaining_time": "4:08:19", "throughput": "1000.86", "total_tokens": 22493123}
|
| 182 |
+
{"current_steps": 910, "total_steps": 1505, "loss": 0.0044, "learning_rate": 1.692798988071385e-05, "epoch": 21.10144927536232, "percentage": 60.47, "elapsed_time": "6:16:48", "remaining_time": "4:06:22", "throughput": "1000.89", "total_tokens": 22629005}
|
| 183 |
+
{"current_steps": 915, "total_steps": 1505, "loss": 0.0043, "learning_rate": 1.6681479849243153e-05, "epoch": 21.217391304347824, "percentage": 60.8, "elapsed_time": "6:18:57", "remaining_time": "4:04:21", "throughput": "1000.65", "total_tokens": 22752358}
|
| 184 |
+
{"current_steps": 920, "total_steps": 1505, "loss": 0.0035, "learning_rate": 1.6435875986112685e-05, "epoch": 21.333333333333332, "percentage": 61.13, "elapsed_time": "6:21:01", "remaining_time": "4:02:17", "throughput": "1000.81", "total_tokens": 22880349}
|
| 185 |
+
{"current_steps": 925, "total_steps": 1505, "loss": 0.0044, "learning_rate": 1.6191205045894283e-05, "epoch": 21.44927536231884, "percentage": 61.46, "elapsed_time": "6:22:39", "remaining_time": "3:59:56", "throughput": "1001.21", "total_tokens": 22987343}
|
| 186 |
+
{"current_steps": 930, "total_steps": 1505, "loss": 0.0178, "learning_rate": 1.594749368153292e-05, "epoch": 21.565217391304348, "percentage": 61.79, "elapsed_time": "6:24:39", "remaining_time": "3:57:49", "throughput": "1001.45", "total_tokens": 23113462}
|
| 187 |
+
{"current_steps": 935, "total_steps": 1505, "loss": 0.0089, "learning_rate": 1.570476844144329e-05, "epoch": 21.681159420289855, "percentage": 62.13, "elapsed_time": "6:26:20", "remaining_time": "3:55:31", "throughput": "1001.76", "total_tokens": 23221714}
|
| 188 |
+
{"current_steps": 940, "total_steps": 1505, "loss": 0.004, "learning_rate": 1.546305576661776e-05, "epoch": 21.797101449275363, "percentage": 62.46, "elapsed_time": "6:29:03", "remaining_time": "3:53:50", "throughput": "1001.09", "total_tokens": 23368857}
|
| 189 |
+
{"current_steps": 945, "total_steps": 1505, "loss": 0.004, "learning_rate": 1.5222381987746104e-05, "epoch": 21.91304347826087, "percentage": 62.79, "elapsed_time": "6:31:12", "remaining_time": "3:51:49", "throughput": "1000.93", "total_tokens": 23494483}
|
| 190 |
+
{"current_steps": 950, "total_steps": 1505, "loss": 0.0034, "learning_rate": 1.4982773322347144e-05, "epoch": 22.028985507246375, "percentage": 63.12, "elapsed_time": "6:33:01", "remaining_time": "3:49:36", "throughput": "1001.01", "total_tokens": 23605463}
|
| 191 |
+
{"current_steps": 955, "total_steps": 1505, "loss": 0.0066, "learning_rate": 1.4744255871912823e-05, "epoch": 22.144927536231883, "percentage": 63.46, "elapsed_time": "6:34:42", "remaining_time": "3:47:19", "throughput": "1001.40", "total_tokens": 23715776}
|
| 192 |
+
{"current_steps": 960, "total_steps": 1505, "loss": 0.0034, "learning_rate": 1.4506855619064846e-05, "epoch": 22.26086956521739, "percentage": 63.79, "elapsed_time": "6:36:44", "remaining_time": "3:45:14", "throughput": "1001.54", "total_tokens": 23841669}
|
| 193 |
+
{"current_steps": 965, "total_steps": 1505, "loss": 0.0032, "learning_rate": 1.4270598424724292e-05, "epoch": 22.3768115942029, "percentage": 64.12, "elapsed_time": "6:38:36", "remaining_time": "3:43:03", "throughput": "1001.84", "total_tokens": 23960567}
|
| 194 |
+
{"current_steps": 970, "total_steps": 1505, "loss": 0.0124, "learning_rate": 1.4035510025294462e-05, "epoch": 22.492753623188406, "percentage": 64.45, "elapsed_time": "6:40:23", "remaining_time": "3:40:50", "throughput": "1002.12", "total_tokens": 24074628}
|
| 195 |
+
{"current_steps": 975, "total_steps": 1505, "loss": 0.0027, "learning_rate": 1.3801616029857378e-05, "epoch": 22.608695652173914, "percentage": 64.78, "elapsed_time": "6:42:53", "remaining_time": "3:39:00", "throughput": "1001.67", "total_tokens": 24214324}
|
| 196 |
+
{"current_steps": 980, "total_steps": 1505, "loss": 0.0037, "learning_rate": 1.3568941917384036e-05, "epoch": 22.72463768115942, "percentage": 65.12, "elapsed_time": "6:44:40", "remaining_time": "3:36:47", "throughput": "1001.90", "total_tokens": 24326727}
|
| 197 |
+
{"current_steps": 985, "total_steps": 1505, "loss": 0.0029, "learning_rate": 1.3337513033958904e-05, "epoch": 22.840579710144926, "percentage": 65.45, "elapsed_time": "6:46:51", "remaining_time": "3:34:47", "throughput": "1001.88", "total_tokens": 24456961}
|
| 198 |
+
{"current_steps": 990, "total_steps": 1505, "loss": 0.0035, "learning_rate": 1.310735459001884e-05, "epoch": 22.956521739130434, "percentage": 65.78, "elapsed_time": "6:49:42", "remaining_time": "3:33:07", "throughput": "1001.00", "total_tokens": 24606652}
|
| 199 |
+
{"current_steps": 995, "total_steps": 1505, "loss": 0.002, "learning_rate": 1.2878491657606872e-05, "epoch": 23.07246376811594, "percentage": 66.11, "elapsed_time": "6:51:17", "remaining_time": "3:30:48", "throughput": "1001.32", "total_tokens": 24710410}
|
| 200 |
+
{"current_steps": 1000, "total_steps": 1505, "loss": 0.0023, "learning_rate": 1.2650949167640993e-05, "epoch": 23.18840579710145, "percentage": 66.45, "elapsed_time": "6:53:12", "remaining_time": "3:28:40", "throughput": "1001.57", "total_tokens": 24831908}
|
| 201 |
+
{"current_steps": 1005, "total_steps": 1505, "loss": 0.0031, "learning_rate": 1.2424751907198312e-05, "epoch": 23.304347826086957, "percentage": 66.78, "elapsed_time": "6:55:34", "remaining_time": "3:26:45", "throughput": "1000.67", "total_tokens": 24951342}
|
| 202 |
+
{"current_steps": 1010, "total_steps": 1505, "loss": 0.0027, "learning_rate": 1.2199924516814939e-05, "epoch": 23.420289855072465, "percentage": 67.11, "elapsed_time": "6:57:55", "remaining_time": "3:24:49", "throughput": "1000.50", "total_tokens": 25088309}
|
| 203 |
+
{"current_steps": 1015, "total_steps": 1505, "loss": 0.0124, "learning_rate": 1.1976491487801748e-05, "epoch": 23.536231884057973, "percentage": 67.44, "elapsed_time": "6:59:58", "remaining_time": "3:22:44", "throughput": "1000.70", "total_tokens": 25216080}
|
| 204 |
+
{"current_steps": 1020, "total_steps": 1505, "loss": 0.0023, "learning_rate": 1.1754477159576499e-05, "epoch": 23.652173913043477, "percentage": 67.77, "elapsed_time": "7:01:40", "remaining_time": "3:20:30", "throughput": "1001.02", "total_tokens": 25326581}
|
| 205 |
+
{"current_steps": 1025, "total_steps": 1505, "loss": 0.0027, "learning_rate": 1.1533905717012428e-05, "epoch": 23.768115942028984, "percentage": 68.11, "elapsed_time": "7:04:12", "remaining_time": "3:18:39", "throughput": "1000.96", "total_tokens": 25477500}
|
| 206 |
+
{"current_steps": 1030, "total_steps": 1505, "loss": 0.0041, "learning_rate": 1.1314801187803686e-05, "epoch": 23.884057971014492, "percentage": 68.44, "elapsed_time": "7:06:11", "remaining_time": "3:16:32", "throughput": "1001.18", "total_tokens": 25601354}
|
| 207 |
+
{"current_steps": 1035, "total_steps": 1505, "loss": 0.0021, "learning_rate": 1.1097187439847939e-05, "epoch": 24.0, "percentage": 68.77, "elapsed_time": "7:08:03", "remaining_time": "3:14:23", "throughput": "1001.39", "total_tokens": 25719240}
|
| 208 |
+
{"current_steps": 1040, "total_steps": 1505, "loss": 0.0039, "learning_rate": 1.088108817864629e-05, "epoch": 24.115942028985508, "percentage": 69.1, "elapsed_time": "7:09:52", "remaining_time": "3:12:12", "throughput": "1001.66", "total_tokens": 25834910}
|
| 209 |
+
{"current_steps": 1045, "total_steps": 1505, "loss": 0.0025, "learning_rate": 1.0666526944721016e-05, "epoch": 24.231884057971016, "percentage": 69.44, "elapsed_time": "7:12:13", "remaining_time": "3:10:15", "throughput": "1001.60", "total_tokens": 25974530}
|
| 210 |
+
{"current_steps": 1050, "total_steps": 1505, "loss": 0.002, "learning_rate": 1.0453527111051184e-05, "epoch": 24.347826086956523, "percentage": 69.77, "elapsed_time": "7:14:17", "remaining_time": "3:08:11", "throughput": "1001.79", "total_tokens": 26104464}
|
| 211 |
+
{"current_steps": 1055, "total_steps": 1505, "loss": 0.0024, "learning_rate": 1.0242111880526495e-05, "epoch": 24.463768115942027, "percentage": 70.1, "elapsed_time": "7:16:46", "remaining_time": "3:06:18", "throughput": "1001.71", "total_tokens": 26251334}
|
| 212 |
+
{"current_steps": 1060, "total_steps": 1505, "loss": 0.0031, "learning_rate": 1.003230428341979e-05, "epoch": 24.579710144927535, "percentage": 70.43, "elapsed_time": "7:18:35", "remaining_time": "3:04:07", "throughput": "1001.93", "total_tokens": 26366561}
|
| 213 |
+
{"current_steps": 1065, "total_steps": 1505, "loss": 0.0022, "learning_rate": 9.824127174878195e-06, "epoch": 24.695652173913043, "percentage": 70.76, "elapsed_time": "7:20:30", "remaining_time": "3:01:59", "throughput": "1002.12", "total_tokens": 26486437}
|
| 214 |
+
{"current_steps": 1070, "total_steps": 1505, "loss": 0.0022, "learning_rate": 9.617603232433475e-06, "epoch": 24.81159420289855, "percentage": 71.1, "elapsed_time": "7:22:16", "remaining_time": "2:59:48", "throughput": "1002.46", "total_tokens": 26601526}
|
| 215 |
+
{"current_steps": 1075, "total_steps": 1505, "loss": 0.0109, "learning_rate": 9.412754953531663e-06, "epoch": 24.92753623188406, "percentage": 71.43, "elapsed_time": "7:24:45", "remaining_time": "2:57:54", "throughput": "1001.58", "total_tokens": 26727922}
|
| 216 |
+
{"current_steps": 1080, "total_steps": 1505, "loss": 0.0019, "learning_rate": 9.209604653082326e-06, "epoch": 25.043478260869566, "percentage": 71.76, "elapsed_time": "7:26:27", "remaining_time": "2:55:41", "throughput": "1001.78", "total_tokens": 26835621}
|
| 217 |
+
{"current_steps": 1085, "total_steps": 1505, "loss": 0.0016, "learning_rate": 9.008174461027724e-06, "epoch": 25.159420289855074, "percentage": 72.09, "elapsed_time": "7:28:21", "remaining_time": "2:53:33", "throughput": "1002.01", "total_tokens": 26955101}
|
| 218 |
+
{"current_steps": 1090, "total_steps": 1505, "loss": 0.002, "learning_rate": 8.808486319932083e-06, "epoch": 25.27536231884058, "percentage": 72.43, "elapsed_time": "7:30:19", "remaining_time": "2:51:27", "throughput": "1002.15", "total_tokens": 27077833}
|
| 219 |
+
{"current_steps": 1095, "total_steps": 1505, "loss": 0.0018, "learning_rate": 8.610561982591357e-06, "epoch": 25.391304347826086, "percentage": 72.76, "elapsed_time": "7:32:08", "remaining_time": "2:49:17", "throughput": "1002.35", "total_tokens": 27192758}
|
| 220 |
+
{"current_steps": 1100, "total_steps": 1505, "loss": 0.0028, "learning_rate": 8.414423009663563e-06, "epoch": 25.507246376811594, "percentage": 73.09, "elapsed_time": "7:34:18", "remaining_time": "2:47:16", "throughput": "1002.44", "total_tokens": 27324970}
|
| 221 |
+
{"current_steps": 1105, "total_steps": 1505, "loss": 0.0021, "learning_rate": 8.220090767320137e-06, "epoch": 25.6231884057971, "percentage": 73.42, "elapsed_time": "7:38:48", "remaining_time": "2:46:05", "throughput": "998.15", "total_tokens": 27477531}
|
| 222 |
+
{"current_steps": 1110, "total_steps": 1505, "loss": 0.0057, "learning_rate": 8.027586424918412e-06, "epoch": 25.73913043478261, "percentage": 73.75, "elapsed_time": "7:40:36", "remaining_time": "2:43:54", "throughput": "998.39", "total_tokens": 27592035}
|
| 223 |
+
{"current_steps": 1115, "total_steps": 1505, "loss": 0.0067, "learning_rate": 7.836930952695533e-06, "epoch": 25.855072463768117, "percentage": 74.09, "elapsed_time": "7:42:31", "remaining_time": "2:41:46", "throughput": "998.59", "total_tokens": 27712377}
|
| 224 |
+
{"current_steps": 1120, "total_steps": 1505, "loss": 0.002, "learning_rate": 7.648145119484153e-06, "epoch": 25.971014492753625, "percentage": 74.42, "elapsed_time": "7:44:31", "remaining_time": "2:39:40", "throughput": "998.67", "total_tokens": 27834613}
|
| 225 |
+
{"current_steps": 1125, "total_steps": 1505, "loss": 0.0021, "learning_rate": 7.461249490449954e-06, "epoch": 26.08695652173913, "percentage": 74.75, "elapsed_time": "7:46:42", "remaining_time": "2:37:38", "throughput": "998.73", "total_tokens": 27966996}
|
| 226 |
+
{"current_steps": 1130, "total_steps": 1505, "loss": 0.002, "learning_rate": 7.276264424851423e-06, "epoch": 26.202898550724637, "percentage": 75.08, "elapsed_time": "7:48:44", "remaining_time": "2:35:33", "throughput": "998.92", "total_tokens": 28093538}
|
| 227 |
+
{"current_steps": 1135, "total_steps": 1505, "loss": 0.0017, "learning_rate": 7.0932100738220265e-06, "epoch": 26.318840579710145, "percentage": 75.42, "elapsed_time": "7:50:47", "remaining_time": "2:33:28", "throughput": "998.88", "total_tokens": 28215579}
|
| 228 |
+
{"current_steps": 1140, "total_steps": 1505, "loss": 0.0014, "learning_rate": 6.912106378175098e-06, "epoch": 26.434782608695652, "percentage": 75.75, "elapsed_time": "7:52:59", "remaining_time": "2:31:26", "throughput": "998.77", "total_tokens": 28344144}
|
| 229 |
+
{"current_steps": 1145, "total_steps": 1505, "loss": 0.0022, "learning_rate": 6.732973066231563e-06, "epoch": 26.55072463768116, "percentage": 76.08, "elapsed_time": "7:55:12", "remaining_time": "2:29:24", "throughput": "998.82", "total_tokens": 28478650}
|
| 230 |
+
{"current_steps": 1150, "total_steps": 1505, "loss": 0.0023, "learning_rate": 6.555829651670911e-06, "epoch": 26.666666666666668, "percentage": 76.41, "elapsed_time": "7:57:16", "remaining_time": "2:27:19", "throughput": "998.48", "total_tokens": 28593004}
|
| 231 |
+
{"current_steps": 1155, "total_steps": 1505, "loss": 0.0028, "learning_rate": 6.380695431405456e-06, "epoch": 26.782608695652176, "percentage": 76.74, "elapsed_time": "7:59:05", "remaining_time": "2:25:10", "throughput": "998.66", "total_tokens": 28707392}
|
| 232 |
+
{"current_steps": 1160, "total_steps": 1505, "loss": 0.006, "learning_rate": 6.207589483478266e-06, "epoch": 26.89855072463768, "percentage": 77.08, "elapsed_time": "8:01:12", "remaining_time": "2:23:07", "throughput": "998.69", "total_tokens": 28834902}
|
| 233 |
+
{"current_steps": 1165, "total_steps": 1505, "loss": 0.0045, "learning_rate": 6.0365306649849214e-06, "epoch": 27.014492753623188, "percentage": 77.41, "elapsed_time": "8:02:58", "remaining_time": "2:20:57", "throughput": "998.96", "total_tokens": 28948812}
|
| 234 |
+
{"current_steps": 1170, "total_steps": 1505, "loss": 0.0019, "learning_rate": 5.867537610019317e-06, "epoch": 27.130434782608695, "percentage": 77.74, "elapsed_time": "8:05:02", "remaining_time": "2:18:52", "throughput": "999.15", "total_tokens": 29078309}
|
| 235 |
+
{"current_steps": 1175, "total_steps": 1505, "loss": 0.002, "learning_rate": 5.700628727643806e-06, "epoch": 27.246376811594203, "percentage": 78.07, "elapsed_time": "8:07:18", "remaining_time": "2:16:51", "throughput": "999.08", "total_tokens": 29211503}
|
| 236 |
+
{"current_steps": 1180, "total_steps": 1505, "loss": 0.0019, "learning_rate": 5.53582219988382e-06, "epoch": 27.36231884057971, "percentage": 78.41, "elapsed_time": "8:09:40", "remaining_time": "2:14:52", "throughput": "998.78", "total_tokens": 29344489}
|
| 237 |
+
{"current_steps": 1185, "total_steps": 1505, "loss": 0.006, "learning_rate": 5.373135979747227e-06, "epoch": 27.47826086956522, "percentage": 78.74, "elapsed_time": "8:12:02", "remaining_time": "2:12:52", "throughput": "998.02", "total_tokens": 29464082}
|
| 238 |
+
{"current_steps": 1190, "total_steps": 1505, "loss": 0.0043, "learning_rate": 5.2125877892686496e-06, "epoch": 27.594202898550726, "percentage": 79.07, "elapsed_time": "8:13:55", "remaining_time": "2:10:44", "throughput": "998.17", "total_tokens": 29581124}
|
| 239 |
+
{"current_steps": 1195, "total_steps": 1505, "loss": 0.0019, "learning_rate": 5.054195117578914e-06, "epoch": 27.71014492753623, "percentage": 79.4, "elapsed_time": "8:15:43", "remaining_time": "2:08:35", "throughput": "998.41", "total_tokens": 29696346}
|
| 240 |
+
{"current_steps": 1200, "total_steps": 1505, "loss": 0.002, "learning_rate": 4.897975218999926e-06, "epoch": 27.82608695652174, "percentage": 79.73, "elapsed_time": "8:17:35", "remaining_time": "2:06:28", "throughput": "998.66", "total_tokens": 29815117}
|
| 241 |
+
{"current_steps": 1205, "total_steps": 1505, "loss": 0.0022, "learning_rate": 4.743945111165068e-06, "epoch": 27.942028985507246, "percentage": 80.07, "elapsed_time": "8:19:56", "remaining_time": "2:04:27", "throughput": "998.10", "total_tokens": 29939175}
|
| 242 |
+
{"current_steps": 1210, "total_steps": 1505, "loss": 0.0016, "learning_rate": 4.592121573165414e-06, "epoch": 28.057971014492754, "percentage": 80.4, "elapsed_time": "8:22:34", "remaining_time": "2:02:31", "throughput": "997.51", "total_tokens": 30079840}
|
| 243 |
+
{"current_steps": 1215, "total_steps": 1505, "loss": 0.0033, "learning_rate": 4.442521143721892e-06, "epoch": 28.17391304347826, "percentage": 80.73, "elapsed_time": "8:24:23", "remaining_time": "2:00:23", "throughput": "997.65", "total_tokens": 30192219}
|
| 244 |
+
{"current_steps": 1220, "total_steps": 1505, "loss": 0.0018, "learning_rate": 4.295160119383712e-06, "epoch": 28.28985507246377, "percentage": 81.06, "elapsed_time": "8:26:48", "remaining_time": "1:58:23", "throughput": "997.44", "total_tokens": 30330969}
|
| 245 |
+
{"current_steps": 1225, "total_steps": 1505, "loss": 0.0018, "learning_rate": 4.150054552753055e-06, "epoch": 28.405797101449274, "percentage": 81.4, "elapsed_time": "8:28:52", "remaining_time": "1:56:18", "throughput": "997.40", "total_tokens": 30453302}
|
| 246 |
+
{"current_steps": 1230, "total_steps": 1505, "loss": 0.0078, "learning_rate": 4.007220250736454e-06, "epoch": 28.52173913043478, "percentage": 81.73, "elapsed_time": "8:30:43", "remaining_time": "1:54:11", "throughput": "997.56", "total_tokens": 30568943}
|
| 247 |
+
{"current_steps": 1235, "total_steps": 1505, "loss": 0.0019, "learning_rate": 3.866672772822863e-06, "epoch": 28.63768115942029, "percentage": 82.06, "elapsed_time": "8:32:59", "remaining_time": "1:52:09", "throughput": "997.29", "total_tokens": 30696057}
|
| 248 |
+
{"current_steps": 1240, "total_steps": 1505, "loss": 0.0019, "learning_rate": 3.7284274293887115e-06, "epoch": 28.753623188405797, "percentage": 82.39, "elapsed_time": "8:35:23", "remaining_time": "1:50:08", "throughput": "996.51", "total_tokens": 30815506}
|
| 249 |
+
{"current_steps": 1245, "total_steps": 1505, "loss": 0.0027, "learning_rate": 3.592499280030057e-06, "epoch": 28.869565217391305, "percentage": 82.72, "elapsed_time": "8:36:55", "remaining_time": "1:47:57", "throughput": "996.81", "total_tokens": 30916446}
|
| 250 |
+
{"current_steps": 1250, "total_steps": 1505, "loss": 0.0023, "learning_rate": 3.458903131922134e-06, "epoch": 28.985507246376812, "percentage": 83.06, "elapsed_time": "8:39:08", "remaining_time": "1:45:54", "throughput": "996.97", "total_tokens": 31054242}
|
| 251 |
+
{"current_steps": 1255, "total_steps": 1505, "loss": 0.0029, "learning_rate": 3.3276535382063213e-06, "epoch": 29.10144927536232, "percentage": 83.39, "elapsed_time": "8:41:22", "remaining_time": "1:43:51", "throughput": "997.00", "total_tokens": 31189078}
|
| 252 |
+
{"current_steps": 1260, "total_steps": 1505, "loss": 0.0018, "learning_rate": 3.198764796404807e-06, "epoch": 29.217391304347824, "percentage": 83.72, "elapsed_time": "8:43:21", "remaining_time": "1:41:45", "throughput": "997.14", "total_tokens": 31311374}
|
| 253 |
+
{"current_steps": 1265, "total_steps": 1505, "loss": 0.0018, "learning_rate": 3.0722509468631392e-06, "epoch": 29.333333333333332, "percentage": 84.05, "elapsed_time": "8:45:30", "remaining_time": "1:39:42", "throughput": "997.27", "total_tokens": 31444681}
|
| 254 |
+
{"current_steps": 1270, "total_steps": 1505, "loss": 0.0018, "learning_rate": 2.948125771220697e-06, "epoch": 29.44927536231884, "percentage": 84.39, "elapsed_time": "8:47:28", "remaining_time": "1:37:36", "throughput": "997.43", "total_tokens": 31567569}
|
| 255 |
+
{"current_steps": 1275, "total_steps": 1505, "loss": 0.0019, "learning_rate": 2.8264027909094715e-06, "epoch": 29.565217391304348, "percentage": 84.72, "elapsed_time": "8:49:51", "remaining_time": "1:35:34", "throughput": "997.05", "total_tokens": 31697338}
|
| 256 |
+
{"current_steps": 1280, "total_steps": 1505, "loss": 0.0018, "learning_rate": 2.707095265681081e-06, "epoch": 29.681159420289855, "percentage": 85.05, "elapsed_time": "8:51:55", "remaining_time": "1:33:30", "throughput": "997.23", "total_tokens": 31826661}
|
| 257 |
+
{"current_steps": 1285, "total_steps": 1505, "loss": 0.0023, "learning_rate": 2.5902161921623454e-06, "epoch": 29.797101449275363, "percentage": 85.38, "elapsed_time": "8:53:53", "remaining_time": "1:31:24", "throughput": "997.24", "total_tokens": 31944680}
|
| 258 |
+
{"current_steps": 1290, "total_steps": 1505, "loss": 0.0078, "learning_rate": 2.475778302439524e-06, "epoch": 29.91304347826087, "percentage": 85.71, "elapsed_time": "8:55:51", "remaining_time": "1:29:18", "throughput": "997.37", "total_tokens": 32067106}
|
| 259 |
+
{"current_steps": 1295, "total_steps": 1505, "loss": 0.0018, "learning_rate": 2.3637940626713346e-06, "epoch": 30.028985507246375, "percentage": 86.05, "elapsed_time": "8:57:49", "remaining_time": "1:27:12", "throughput": "997.36", "total_tokens": 32184526}
|
| 260 |
+
{"current_steps": 1300, "total_steps": 1505, "loss": 0.0017, "learning_rate": 2.254275671731007e-06, "epoch": 30.144927536231883, "percentage": 86.38, "elapsed_time": "8:59:48", "remaining_time": "1:25:07", "throughput": "997.56", "total_tokens": 32309423}
|
| 261 |
+
{"current_steps": 1305, "total_steps": 1505, "loss": 0.0071, "learning_rate": 2.14723505987737e-06, "epoch": 30.26086956521739, "percentage": 86.71, "elapsed_time": "9:02:06", "remaining_time": "1:23:04", "throughput": "997.03", "total_tokens": 32429445}
|
| 262 |
+
{"current_steps": 1310, "total_steps": 1505, "loss": 0.0016, "learning_rate": 2.0426838874552714e-06, "epoch": 30.3768115942029, "percentage": 87.04, "elapsed_time": "9:03:48", "remaining_time": "1:20:56", "throughput": "997.31", "total_tokens": 32540571}
|
| 263 |
+
{"current_steps": 1315, "total_steps": 1505, "loss": 0.0018, "learning_rate": 1.9406335436253724e-06, "epoch": 30.492753623188406, "percentage": 87.38, "elapsed_time": "9:05:50", "remaining_time": "1:18:52", "throughput": "997.40", "total_tokens": 32665528}
|
| 264 |
+
{"current_steps": 1320, "total_steps": 1505, "loss": 0.0017, "learning_rate": 1.8410951451234533e-06, "epoch": 30.608695652173914, "percentage": 87.71, "elapsed_time": "9:08:19", "remaining_time": "1:16:50", "throughput": "997.00", "total_tokens": 32800773}
|
| 265 |
+
{"current_steps": 1325, "total_steps": 1505, "loss": 0.0017, "learning_rate": 1.7440795350494588e-06, "epoch": 30.72463768115942, "percentage": 88.04, "elapsed_time": "9:10:29", "remaining_time": "1:14:47", "throughput": "996.94", "total_tokens": 32928397}
|
| 266 |
+
{"current_steps": 1330, "total_steps": 1505, "loss": 0.0019, "learning_rate": 1.649597281686302e-06, "epoch": 30.840579710144926, "percentage": 88.37, "elapsed_time": "9:12:31", "remaining_time": "1:12:41", "throughput": "997.09", "total_tokens": 33054819}
|
| 267 |
+
{"current_steps": 1335, "total_steps": 1505, "loss": 0.0018, "learning_rate": 1.5576586773486195e-06, "epoch": 30.956521739130434, "percentage": 88.7, "elapsed_time": "9:14:42", "remaining_time": "1:10:38", "throughput": "996.94", "total_tokens": 33180616}
|
| 268 |
+
{"current_steps": 1340, "total_steps": 1505, "loss": 0.0038, "learning_rate": 1.4682737372615967e-06, "epoch": 31.07246376811594, "percentage": 89.04, "elapsed_time": "9:16:33", "remaining_time": "1:08:31", "throughput": "997.13", "total_tokens": 33298041}
|
| 269 |
+
{"current_steps": 1345, "total_steps": 1505, "loss": 0.0052, "learning_rate": 1.3814521984699596e-06, "epoch": 31.18840579710145, "percentage": 89.37, "elapsed_time": "9:18:18", "remaining_time": "1:06:24", "throughput": "997.30", "total_tokens": 33408343}
|
| 270 |
+
{"current_steps": 1350, "total_steps": 1505, "loss": 0.0018, "learning_rate": 1.297203518777293e-06, "epoch": 31.304347826086957, "percentage": 89.7, "elapsed_time": "9:20:36", "remaining_time": "1:04:21", "throughput": "997.30", "total_tokens": 33545364}
|
| 271 |
+
{"current_steps": 1355, "total_steps": 1505, "loss": 0.0019, "learning_rate": 1.2155368757157643e-06, "epoch": 31.420289855072465, "percentage": 90.03, "elapsed_time": "9:22:15", "remaining_time": "1:02:14", "throughput": "997.55", "total_tokens": 33652900}
|
| 272 |
+
{"current_steps": 1360, "total_steps": 1505, "loss": 0.0019, "learning_rate": 1.1364611655463736e-06, "epoch": 31.536231884057973, "percentage": 90.37, "elapsed_time": "9:24:02", "remaining_time": "1:00:08", "throughput": "997.81", "total_tokens": 33768791}
|
| 273 |
+
{"current_steps": 1365, "total_steps": 1505, "loss": 0.0017, "learning_rate": 1.0599850022898539e-06, "epoch": 31.652173913043477, "percentage": 90.7, "elapsed_time": "9:26:18", "remaining_time": "0:58:04", "throughput": "997.48", "total_tokens": 33892837}
|
| 274 |
+
{"current_steps": 1370, "total_steps": 1505, "loss": 0.0022, "learning_rate": 9.861167167883046e-07, "epoch": 31.768115942028984, "percentage": 91.03, "elapsed_time": "9:28:18", "remaining_time": "0:56:00", "throughput": "997.57", "total_tokens": 34015288}
|
| 275 |
+
{"current_steps": 1375, "total_steps": 1505, "loss": 0.0037, "learning_rate": 9.148643557976955e-07, "epoch": 31.884057971014492, "percentage": 91.36, "elapsed_time": "9:30:49", "remaining_time": "0:53:58", "throughput": "997.25", "total_tokens": 34154884}
|
| 276 |
+
{"current_steps": 1380, "total_steps": 1505, "loss": 0.0019, "learning_rate": 8.462356811112987e-07, "epoch": 32.0, "percentage": 91.69, "elapsed_time": "9:33:07", "remaining_time": "0:51:54", "throughput": "997.23", "total_tokens": 34292320}
|
| 277 |
+
{"current_steps": 1385, "total_steps": 1505, "loss": 0.0017, "learning_rate": 7.802381687141535e-07, "epoch": 32.11594202898551, "percentage": 92.03, "elapsed_time": "9:35:06", "remaining_time": "0:49:49", "throughput": "997.32", "total_tokens": 34413850}
|
| 278 |
+
{"current_steps": 1390, "total_steps": 1505, "loss": 0.0018, "learning_rate": 7.168790079686932e-07, "epoch": 32.231884057971016, "percentage": 92.36, "elapsed_time": "9:37:22", "remaining_time": "0:47:46", "throughput": "997.25", "total_tokens": 34547127}
|
| 279 |
+
{"current_steps": 1395, "total_steps": 1505, "loss": 0.0035, "learning_rate": 6.561651008315738e-07, "epoch": 32.34782608695652, "percentage": 92.69, "elapsed_time": "9:39:51", "remaining_time": "0:45:43", "throughput": "996.95", "total_tokens": 34685112}
|
| 280 |
+
{"current_steps": 1400, "total_steps": 1505, "loss": 0.0063, "learning_rate": 5.981030611018234e-07, "epoch": 32.46376811594203, "percentage": 93.02, "elapsed_time": "9:41:58", "remaining_time": "0:43:38", "throughput": "996.92", "total_tokens": 34810484}
|
| 281 |
+
{"current_steps": 1405, "total_steps": 1505, "loss": 0.0018, "learning_rate": 5.426992137003622e-07, "epoch": 32.57971014492754, "percentage": 93.36, "elapsed_time": "9:43:53", "remaining_time": "0:41:33", "throughput": "996.79", "total_tokens": 34920531}
|
| 282 |
+
{"current_steps": 1410, "total_steps": 1505, "loss": 0.002, "learning_rate": 4.899595939810236e-07, "epoch": 32.69565217391305, "percentage": 93.69, "elapsed_time": "9:45:40", "remaining_time": "0:39:27", "throughput": "997.02", "total_tokens": 35035657}
|
| 283 |
+
{"current_steps": 1415, "total_steps": 1505, "loss": 0.0017, "learning_rate": 4.398899470730827e-07, "epoch": 32.81159420289855, "percentage": 94.02, "elapsed_time": "9:47:49", "remaining_time": "0:37:23", "throughput": "997.12", "total_tokens": 35167466}
|
| 284 |
+
{"current_steps": 1420, "total_steps": 1505, "loss": 0.0016, "learning_rate": 3.9249572725543196e-07, "epoch": 32.927536231884055, "percentage": 94.35, "elapsed_time": "9:49:57", "remaining_time": "0:35:18", "throughput": "997.16", "total_tokens": 35296818}
|
| 285 |
+
{"current_steps": 1425, "total_steps": 1505, "loss": 0.0015, "learning_rate": 3.477820973624063e-07, "epoch": 33.04347826086956, "percentage": 94.68, "elapsed_time": "9:52:14", "remaining_time": "0:33:14", "throughput": "997.07", "total_tokens": 35430399}
|
| 286 |
+
{"current_steps": 1430, "total_steps": 1505, "loss": 0.0057, "learning_rate": 3.0575392822139726e-07, "epoch": 33.15942028985507, "percentage": 95.02, "elapsed_time": "9:54:09", "remaining_time": "0:31:09", "throughput": "997.25", "total_tokens": 35551540}
|
| 287 |
+
{"current_steps": 1435, "total_steps": 1505, "loss": 0.0016, "learning_rate": 2.664157981222437e-07, "epoch": 33.27536231884058, "percentage": 95.35, "elapsed_time": "9:56:30", "remaining_time": "0:29:05", "throughput": "996.81", "total_tokens": 35676077}
|
| 288 |
+
{"current_steps": 1440, "total_steps": 1505, "loss": 0.0016, "learning_rate": 2.297719923185032e-07, "epoch": 33.391304347826086, "percentage": 95.68, "elapsed_time": "9:58:09", "remaining_time": "0:27:00", "throughput": "997.10", "total_tokens": 35785127}
|
| 289 |
+
{"current_steps": 1445, "total_steps": 1505, "loss": 0.0019, "learning_rate": 1.9582650256064205e-07, "epoch": 33.507246376811594, "percentage": 96.01, "elapsed_time": "10:00:15", "remaining_time": "0:24:55", "throughput": "997.13", "total_tokens": 35911682}
|
| 290 |
+
{"current_steps": 1450, "total_steps": 1505, "loss": 0.0017, "learning_rate": 1.645830266611914e-07, "epoch": 33.6231884057971, "percentage": 96.35, "elapsed_time": "10:02:13", "remaining_time": "0:22:50", "throughput": "997.16", "total_tokens": 36030754}
|
| 291 |
+
{"current_steps": 1455, "total_steps": 1505, "loss": 0.0042, "learning_rate": 1.3604496809195288e-07, "epoch": 33.73913043478261, "percentage": 96.68, "elapsed_time": "10:04:04", "remaining_time": "0:20:45", "throughput": "997.29", "total_tokens": 36146749}
|
| 292 |
+
{"current_steps": 1460, "total_steps": 1505, "loss": 0.0017, "learning_rate": 1.1021543561322012e-07, "epoch": 33.85507246376812, "percentage": 97.01, "elapsed_time": "10:06:10", "remaining_time": "0:18:41", "throughput": "997.47", "total_tokens": 36278454}
|
| 293 |
+
{"current_steps": 1465, "total_steps": 1505, "loss": 0.0017, "learning_rate": 8.709724293513854e-08, "epoch": 33.971014492753625, "percentage": 97.34, "elapsed_time": "10:08:27", "remaining_time": "0:16:36", "throughput": "997.29", "total_tokens": 36408834}
|
| 294 |
+
{"current_steps": 1470, "total_steps": 1505, "loss": 0.0015, "learning_rate": 6.66929084112089e-08, "epoch": 34.08695652173913, "percentage": 97.67, "elapsed_time": "10:10:58", "remaining_time": "0:14:32", "throughput": "997.05", "total_tokens": 36550538}
|
| 295 |
+
{"current_steps": 1475, "total_steps": 1505, "loss": 0.0018, "learning_rate": 4.900465476393168e-08, "epoch": 34.20289855072464, "percentage": 98.01, "elapsed_time": "10:12:25", "remaining_time": "0:12:27", "throughput": "997.33", "total_tokens": 36647436}
|
| 296 |
+
{"current_steps": 1480, "total_steps": 1505, "loss": 0.0024, "learning_rate": 3.403440884269526e-08, "epoch": 34.31884057971015, "percentage": 98.34, "elapsed_time": "10:14:46", "remaining_time": "0:10:23", "throughput": "997.25", "total_tokens": 36785387}
|
| 297 |
+
{"current_steps": 1485, "total_steps": 1505, "loss": 0.0021, "learning_rate": 2.1783801413866046e-08, "epoch": 34.43478260869565, "percentage": 98.67, "elapsed_time": "10:16:51", "remaining_time": "0:08:18", "throughput": "997.41", "total_tokens": 36915606}
|
| 298 |
+
{"current_steps": 1490, "total_steps": 1505, "loss": 0.0035, "learning_rate": 1.2254166983152737e-08, "epoch": 34.55072463768116, "percentage": 99.0, "elapsed_time": "10:18:46", "remaining_time": "0:06:13", "throughput": "997.57", "total_tokens": 37036117}
|
| 299 |
+
{"current_steps": 1495, "total_steps": 1505, "loss": 0.0016, "learning_rate": 5.446543650219904e-09, "epoch": 34.666666666666664, "percentage": 99.34, "elapsed_time": "10:20:49", "remaining_time": "0:04:09", "throughput": "997.75", "total_tokens": 37165587}
|
| 300 |
+
{"current_steps": 1500, "total_steps": 1505, "loss": 0.0015, "learning_rate": 1.3616729956228425e-09, "epoch": 34.78260869565217, "percentage": 99.67, "elapsed_time": "10:22:54", "remaining_time": "0:02:04", "throughput": "997.77", "total_tokens": 37290827}
|
| 301 |
+
{"current_steps": 1505, "total_steps": 1505, "loss": 0.0053, "learning_rate": 0.0, "epoch": 34.89855072463768, "percentage": 100.0, "elapsed_time": "10:25:10", "remaining_time": "0:00:00", "throughput": "997.38", "total_tokens": 37412688}
|
| 302 |
+
{"current_steps": 1505, "total_steps": 1505, "epoch": 34.89855072463768, "percentage": 100.0, "elapsed_time": "10:25:10", "remaining_time": "0:00:00", "throughput": "997.38", "total_tokens": 37412688}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2451 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 34.89855072463768,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1505,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.11594202898550725,
|
| 13 |
+
"grad_norm": 7.532149791717529,
|
| 14 |
+
"learning_rate": 4.999863832700438e-05,
|
| 15 |
+
"loss": 3.8116,
|
| 16 |
+
"num_input_tokens_seen": 106929,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.2318840579710145,
|
| 21 |
+
"grad_norm": 4.141716480255127,
|
| 22 |
+
"learning_rate": 4.999455345634978e-05,
|
| 23 |
+
"loss": 3.6928,
|
| 24 |
+
"num_input_tokens_seen": 225964,
|
| 25 |
+
"step": 10
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.34782608695652173,
|
| 29 |
+
"grad_norm": 3.470097780227661,
|
| 30 |
+
"learning_rate": 4.9987745833016855e-05,
|
| 31 |
+
"loss": 3.6227,
|
| 32 |
+
"num_input_tokens_seen": 362264,
|
| 33 |
+
"step": 15
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.463768115942029,
|
| 37 |
+
"grad_norm": 3.4544646739959717,
|
| 38 |
+
"learning_rate": 4.9978216198586135e-05,
|
| 39 |
+
"loss": 3.601,
|
| 40 |
+
"num_input_tokens_seen": 477807,
|
| 41 |
+
"step": 20
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.5797101449275363,
|
| 45 |
+
"grad_norm": 3.249224901199341,
|
| 46 |
+
"learning_rate": 4.996596559115731e-05,
|
| 47 |
+
"loss": 3.539,
|
| 48 |
+
"num_input_tokens_seen": 588900,
|
| 49 |
+
"step": 25
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.6956521739130435,
|
| 53 |
+
"grad_norm": 3.395056962966919,
|
| 54 |
+
"learning_rate": 4.995099534523607e-05,
|
| 55 |
+
"loss": 3.4956,
|
| 56 |
+
"num_input_tokens_seen": 706077,
|
| 57 |
+
"step": 30
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.8115942028985508,
|
| 61 |
+
"grad_norm": 3.997875213623047,
|
| 62 |
+
"learning_rate": 4.9933307091588796e-05,
|
| 63 |
+
"loss": 3.5044,
|
| 64 |
+
"num_input_tokens_seen": 853504,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.927536231884058,
|
| 69 |
+
"grad_norm": 3.5168681144714355,
|
| 70 |
+
"learning_rate": 4.991290275706486e-05,
|
| 71 |
+
"loss": 3.4324,
|
| 72 |
+
"num_input_tokens_seen": 990472,
|
| 73 |
+
"step": 40
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 1.0434782608695652,
|
| 77 |
+
"grad_norm": 7.144646167755127,
|
| 78 |
+
"learning_rate": 4.988978456438678e-05,
|
| 79 |
+
"loss": 3.2542,
|
| 80 |
+
"num_input_tokens_seen": 1125870,
|
| 81 |
+
"step": 45
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.1594202898550725,
|
| 85 |
+
"grad_norm": 3.257103681564331,
|
| 86 |
+
"learning_rate": 4.986395503190805e-05,
|
| 87 |
+
"loss": 2.9024,
|
| 88 |
+
"num_input_tokens_seen": 1249877,
|
| 89 |
+
"step": 50
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.2753623188405796,
|
| 93 |
+
"grad_norm": 3.3208603858947754,
|
| 94 |
+
"learning_rate": 4.983541697333881e-05,
|
| 95 |
+
"loss": 2.8069,
|
| 96 |
+
"num_input_tokens_seen": 1375193,
|
| 97 |
+
"step": 55
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 1.391304347826087,
|
| 101 |
+
"grad_norm": 4.378167629241943,
|
| 102 |
+
"learning_rate": 4.980417349743936e-05,
|
| 103 |
+
"loss": 2.75,
|
| 104 |
+
"num_input_tokens_seen": 1489716,
|
| 105 |
+
"step": 60
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 1.5072463768115942,
|
| 109 |
+
"grad_norm": 4.321849822998047,
|
| 110 |
+
"learning_rate": 4.9770228007681494e-05,
|
| 111 |
+
"loss": 2.7329,
|
| 112 |
+
"num_input_tokens_seen": 1600483,
|
| 113 |
+
"step": 65
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.6231884057971016,
|
| 117 |
+
"grad_norm": 3.6365067958831787,
|
| 118 |
+
"learning_rate": 4.973358420187776e-05,
|
| 119 |
+
"loss": 2.8212,
|
| 120 |
+
"num_input_tokens_seen": 1731315,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.7391304347826086,
|
| 125 |
+
"grad_norm": 3.74035906791687,
|
| 126 |
+
"learning_rate": 4.9694246071778604e-05,
|
| 127 |
+
"loss": 2.7935,
|
| 128 |
+
"num_input_tokens_seen": 1858269,
|
| 129 |
+
"step": 75
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.855072463768116,
|
| 133 |
+
"grad_norm": 23.26426124572754,
|
| 134 |
+
"learning_rate": 4.9652217902637596e-05,
|
| 135 |
+
"loss": 2.7305,
|
| 136 |
+
"num_input_tokens_seen": 1984587,
|
| 137 |
+
"step": 80
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.971014492753623,
|
| 141 |
+
"grad_norm": 4.870578289031982,
|
| 142 |
+
"learning_rate": 4.9607504272744575e-05,
|
| 143 |
+
"loss": 2.6482,
|
| 144 |
+
"num_input_tokens_seen": 2109391,
|
| 145 |
+
"step": 85
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 2.0869565217391304,
|
| 149 |
+
"grad_norm": 4.419096946716309,
|
| 150 |
+
"learning_rate": 4.956011005292692e-05,
|
| 151 |
+
"loss": 2.4292,
|
| 152 |
+
"num_input_tokens_seen": 2246413,
|
| 153 |
+
"step": 90
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 2.2028985507246377,
|
| 157 |
+
"grad_norm": 18.216915130615234,
|
| 158 |
+
"learning_rate": 4.951004040601898e-05,
|
| 159 |
+
"loss": 2.1416,
|
| 160 |
+
"num_input_tokens_seen": 2386890,
|
| 161 |
+
"step": 95
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 2.318840579710145,
|
| 165 |
+
"grad_norm": 4.4814581871032715,
|
| 166 |
+
"learning_rate": 4.945730078629964e-05,
|
| 167 |
+
"loss": 2.2847,
|
| 168 |
+
"num_input_tokens_seen": 2522302,
|
| 169 |
+
"step": 100
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 2.4347826086956523,
|
| 173 |
+
"grad_norm": 406.9701232910156,
|
| 174 |
+
"learning_rate": 4.9401896938898185e-05,
|
| 175 |
+
"loss": 2.0944,
|
| 176 |
+
"num_input_tokens_seen": 2642208,
|
| 177 |
+
"step": 105
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 2.550724637681159,
|
| 181 |
+
"grad_norm": 3.5890581607818604,
|
| 182 |
+
"learning_rate": 4.934383489916843e-05,
|
| 183 |
+
"loss": 2.2862,
|
| 184 |
+
"num_input_tokens_seen": 2780587,
|
| 185 |
+
"step": 110
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 2.6666666666666665,
|
| 189 |
+
"grad_norm": 5.334541320800781,
|
| 190 |
+
"learning_rate": 4.928312099203131e-05,
|
| 191 |
+
"loss": 2.105,
|
| 192 |
+
"num_input_tokens_seen": 2885320,
|
| 193 |
+
"step": 115
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 2.782608695652174,
|
| 197 |
+
"grad_norm": 5.464664936065674,
|
| 198 |
+
"learning_rate": 4.921976183128585e-05,
|
| 199 |
+
"loss": 2.0287,
|
| 200 |
+
"num_input_tokens_seen": 2996923,
|
| 201 |
+
"step": 120
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 2.898550724637681,
|
| 205 |
+
"grad_norm": 4.113780975341797,
|
| 206 |
+
"learning_rate": 4.9153764318888706e-05,
|
| 207 |
+
"loss": 2.0162,
|
| 208 |
+
"num_input_tokens_seen": 3102391,
|
| 209 |
+
"step": 125
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 3.0144927536231885,
|
| 213 |
+
"grad_norm": 6.009971618652344,
|
| 214 |
+
"learning_rate": 4.908513564420231e-05,
|
| 215 |
+
"loss": 2.2464,
|
| 216 |
+
"num_input_tokens_seen": 3233443,
|
| 217 |
+
"step": 130
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 3.130434782608696,
|
| 221 |
+
"grad_norm": 10.397327423095703,
|
| 222 |
+
"learning_rate": 4.90138832832117e-05,
|
| 223 |
+
"loss": 1.6561,
|
| 224 |
+
"num_input_tokens_seen": 3358966,
|
| 225 |
+
"step": 135
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 3.246376811594203,
|
| 229 |
+
"grad_norm": 4.9139556884765625,
|
| 230 |
+
"learning_rate": 4.894001499771015e-05,
|
| 231 |
+
"loss": 1.6113,
|
| 232 |
+
"num_input_tokens_seen": 3490069,
|
| 233 |
+
"step": 140
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 3.36231884057971,
|
| 237 |
+
"grad_norm": 4.146034240722656,
|
| 238 |
+
"learning_rate": 4.886353883445363e-05,
|
| 239 |
+
"loss": 1.6235,
|
| 240 |
+
"num_input_tokens_seen": 3609842,
|
| 241 |
+
"step": 145
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 3.4782608695652173,
|
| 245 |
+
"grad_norm": 4.301880359649658,
|
| 246 |
+
"learning_rate": 4.878446312428424e-05,
|
| 247 |
+
"loss": 1.7873,
|
| 248 |
+
"num_input_tokens_seen": 3751570,
|
| 249 |
+
"step": 150
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 3.5942028985507246,
|
| 253 |
+
"grad_norm": 3.9485158920288086,
|
| 254 |
+
"learning_rate": 4.8702796481222714e-05,
|
| 255 |
+
"loss": 1.3723,
|
| 256 |
+
"num_input_tokens_seen": 3865303,
|
| 257 |
+
"step": 155
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 3.710144927536232,
|
| 261 |
+
"grad_norm": 4.183668613433838,
|
| 262 |
+
"learning_rate": 4.861854780153004e-05,
|
| 263 |
+
"loss": 1.6512,
|
| 264 |
+
"num_input_tokens_seen": 3991347,
|
| 265 |
+
"step": 160
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 3.8260869565217392,
|
| 269 |
+
"grad_norm": 5.1000471115112305,
|
| 270 |
+
"learning_rate": 4.853172626273841e-05,
|
| 271 |
+
"loss": 1.5524,
|
| 272 |
+
"num_input_tokens_seen": 4113654,
|
| 273 |
+
"step": 165
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 3.942028985507246,
|
| 277 |
+
"grad_norm": 4.142239570617676,
|
| 278 |
+
"learning_rate": 4.8442341322651385e-05,
|
| 279 |
+
"loss": 1.5954,
|
| 280 |
+
"num_input_tokens_seen": 4236348,
|
| 281 |
+
"step": 170
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 4.057971014492754,
|
| 285 |
+
"grad_norm": 3.8976669311523438,
|
| 286 |
+
"learning_rate": 4.83504027183137e-05,
|
| 287 |
+
"loss": 1.1652,
|
| 288 |
+
"num_input_tokens_seen": 4340378,
|
| 289 |
+
"step": 175
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 4.173913043478261,
|
| 293 |
+
"grad_norm": 5.923389911651611,
|
| 294 |
+
"learning_rate": 4.825592046495054e-05,
|
| 295 |
+
"loss": 1.1995,
|
| 296 |
+
"num_input_tokens_seen": 4473601,
|
| 297 |
+
"step": 180
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 4.2898550724637685,
|
| 301 |
+
"grad_norm": 4.220530033111572,
|
| 302 |
+
"learning_rate": 4.8158904854876555e-05,
|
| 303 |
+
"loss": 0.9431,
|
| 304 |
+
"num_input_tokens_seen": 4586911,
|
| 305 |
+
"step": 185
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 4.405797101449275,
|
| 309 |
+
"grad_norm": 5.896139144897461,
|
| 310 |
+
"learning_rate": 4.805936645637463e-05,
|
| 311 |
+
"loss": 1.1136,
|
| 312 |
+
"num_input_tokens_seen": 4702445,
|
| 313 |
+
"step": 190
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 4.521739130434782,
|
| 317 |
+
"grad_norm": 4.467094421386719,
|
| 318 |
+
"learning_rate": 4.795731611254473e-05,
|
| 319 |
+
"loss": 1.1509,
|
| 320 |
+
"num_input_tokens_seen": 4831301,
|
| 321 |
+
"step": 195
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 4.63768115942029,
|
| 325 |
+
"grad_norm": 4.232386112213135,
|
| 326 |
+
"learning_rate": 4.785276494012263e-05,
|
| 327 |
+
"loss": 0.9962,
|
| 328 |
+
"num_input_tokens_seen": 4941656,
|
| 329 |
+
"step": 200
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 4.753623188405797,
|
| 333 |
+
"grad_norm": 4.829892635345459,
|
| 334 |
+
"learning_rate": 4.7745724328269e-05,
|
| 335 |
+
"loss": 1.2377,
|
| 336 |
+
"num_input_tokens_seen": 5088437,
|
| 337 |
+
"step": 205
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 4.869565217391305,
|
| 341 |
+
"grad_norm": 4.1343913078308105,
|
| 342 |
+
"learning_rate": 4.763620593732867e-05,
|
| 343 |
+
"loss": 1.234,
|
| 344 |
+
"num_input_tokens_seen": 5219806,
|
| 345 |
+
"step": 210
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 4.9855072463768115,
|
| 349 |
+
"grad_norm": 4.9217729568481445,
|
| 350 |
+
"learning_rate": 4.752422169756048e-05,
|
| 351 |
+
"loss": 1.1453,
|
| 352 |
+
"num_input_tokens_seen": 5340222,
|
| 353 |
+
"step": 215
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 5.101449275362318,
|
| 357 |
+
"grad_norm": 4.4605865478515625,
|
| 358 |
+
"learning_rate": 4.740978380783765e-05,
|
| 359 |
+
"loss": 0.9056,
|
| 360 |
+
"num_input_tokens_seen": 5476315,
|
| 361 |
+
"step": 220
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 5.217391304347826,
|
| 365 |
+
"grad_norm": 4.396484375,
|
| 366 |
+
"learning_rate": 4.7292904734318924e-05,
|
| 367 |
+
"loss": 0.7349,
|
| 368 |
+
"num_input_tokens_seen": 5589951,
|
| 369 |
+
"step": 225
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 5.333333333333333,
|
| 373 |
+
"grad_norm": 4.053436279296875,
|
| 374 |
+
"learning_rate": 4.7173597209090534e-05,
|
| 375 |
+
"loss": 0.6968,
|
| 376 |
+
"num_input_tokens_seen": 5711449,
|
| 377 |
+
"step": 230
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 5.449275362318841,
|
| 381 |
+
"grad_norm": 5.303736209869385,
|
| 382 |
+
"learning_rate": 4.70518742287793e-05,
|
| 383 |
+
"loss": 0.851,
|
| 384 |
+
"num_input_tokens_seen": 5852650,
|
| 385 |
+
"step": 235
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 5.565217391304348,
|
| 389 |
+
"grad_norm": 3.70810866355896,
|
| 390 |
+
"learning_rate": 4.6927749053136866e-05,
|
| 391 |
+
"loss": 0.716,
|
| 392 |
+
"num_input_tokens_seen": 5972289,
|
| 393 |
+
"step": 240
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 5.681159420289855,
|
| 397 |
+
"grad_norm": 3.9204599857330322,
|
| 398 |
+
"learning_rate": 4.6801235203595195e-05,
|
| 399 |
+
"loss": 0.6384,
|
| 400 |
+
"num_input_tokens_seen": 6088707,
|
| 401 |
+
"step": 245
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 5.797101449275362,
|
| 405 |
+
"grad_norm": 4.06931209564209,
|
| 406 |
+
"learning_rate": 4.667234646179368e-05,
|
| 407 |
+
"loss": 0.7799,
|
| 408 |
+
"num_input_tokens_seen": 6215471,
|
| 409 |
+
"step": 250
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 5.913043478260869,
|
| 413 |
+
"grad_norm": 4.283618450164795,
|
| 414 |
+
"learning_rate": 4.654109686807787e-05,
|
| 415 |
+
"loss": 0.7923,
|
| 416 |
+
"num_input_tokens_seen": 6335935,
|
| 417 |
+
"step": 255
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 6.028985507246377,
|
| 421 |
+
"grad_norm": 4.719886302947998,
|
| 422 |
+
"learning_rate": 4.640750071996995e-05,
|
| 423 |
+
"loss": 0.7452,
|
| 424 |
+
"num_input_tokens_seen": 6463689,
|
| 425 |
+
"step": 260
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 6.144927536231884,
|
| 429 |
+
"grad_norm": 3.8415334224700928,
|
| 430 |
+
"learning_rate": 4.6271572570611296e-05,
|
| 431 |
+
"loss": 0.4085,
|
| 432 |
+
"num_input_tokens_seen": 6576954,
|
| 433 |
+
"step": 265
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 6.260869565217392,
|
| 437 |
+
"grad_norm": 4.19309663772583,
|
| 438 |
+
"learning_rate": 4.613332722717714e-05,
|
| 439 |
+
"loss": 0.5777,
|
| 440 |
+
"num_input_tokens_seen": 6714404,
|
| 441 |
+
"step": 270
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 6.3768115942028984,
|
| 445 |
+
"grad_norm": 5.686235427856445,
|
| 446 |
+
"learning_rate": 4.5992779749263546e-05,
|
| 447 |
+
"loss": 0.4718,
|
| 448 |
+
"num_input_tokens_seen": 6840385,
|
| 449 |
+
"step": 275
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 6.492753623188406,
|
| 453 |
+
"grad_norm": 3.2365808486938477,
|
| 454 |
+
"learning_rate": 4.584994544724695e-05,
|
| 455 |
+
"loss": 0.3723,
|
| 456 |
+
"num_input_tokens_seen": 6954269,
|
| 457 |
+
"step": 280
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 6.608695652173913,
|
| 461 |
+
"grad_norm": 3.530801296234131,
|
| 462 |
+
"learning_rate": 4.5704839880616296e-05,
|
| 463 |
+
"loss": 0.4453,
|
| 464 |
+
"num_input_tokens_seen": 7076143,
|
| 465 |
+
"step": 285
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 6.72463768115942,
|
| 469 |
+
"grad_norm": 3.2134931087493896,
|
| 470 |
+
"learning_rate": 4.5557478856278114e-05,
|
| 471 |
+
"loss": 0.5742,
|
| 472 |
+
"num_input_tokens_seen": 7201833,
|
| 473 |
+
"step": 290
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 6.840579710144928,
|
| 477 |
+
"grad_norm": 6.281985282897949,
|
| 478 |
+
"learning_rate": 4.5407878426834596e-05,
|
| 479 |
+
"loss": 0.5291,
|
| 480 |
+
"num_input_tokens_seen": 7330479,
|
| 481 |
+
"step": 295
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 6.956521739130435,
|
| 485 |
+
"grad_norm": 17.072542190551758,
|
| 486 |
+
"learning_rate": 4.5256054888834934e-05,
|
| 487 |
+
"loss": 0.4968,
|
| 488 |
+
"num_input_tokens_seen": 7449244,
|
| 489 |
+
"step": 300
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 7.072463768115942,
|
| 493 |
+
"grad_norm": 3.737456798553467,
|
| 494 |
+
"learning_rate": 4.5102024781000077e-05,
|
| 495 |
+
"loss": 0.421,
|
| 496 |
+
"num_input_tokens_seen": 7578947,
|
| 497 |
+
"step": 305
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 7.188405797101449,
|
| 501 |
+
"grad_norm": 2.6586523056030273,
|
| 502 |
+
"learning_rate": 4.4945804882421086e-05,
|
| 503 |
+
"loss": 0.2767,
|
| 504 |
+
"num_input_tokens_seen": 7691948,
|
| 505 |
+
"step": 310
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 7.304347826086957,
|
| 509 |
+
"grad_norm": 2.027702808380127,
|
| 510 |
+
"learning_rate": 4.478741221073136e-05,
|
| 511 |
+
"loss": 0.2922,
|
| 512 |
+
"num_input_tokens_seen": 7815786,
|
| 513 |
+
"step": 315
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 7.420289855072464,
|
| 517 |
+
"grad_norm": 3.4651787281036377,
|
| 518 |
+
"learning_rate": 4.4626864020252774e-05,
|
| 519 |
+
"loss": 0.2768,
|
| 520 |
+
"num_input_tokens_seen": 7925106,
|
| 521 |
+
"step": 320
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 7.536231884057971,
|
| 525 |
+
"grad_norm": 4.559577941894531,
|
| 526 |
+
"learning_rate": 4.446417780011618e-05,
|
| 527 |
+
"loss": 0.3281,
|
| 528 |
+
"num_input_tokens_seen": 8057202,
|
| 529 |
+
"step": 325
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 7.6521739130434785,
|
| 533 |
+
"grad_norm": 2.5885751247406006,
|
| 534 |
+
"learning_rate": 4.42993712723562e-05,
|
| 535 |
+
"loss": 0.3374,
|
| 536 |
+
"num_input_tokens_seen": 8187865,
|
| 537 |
+
"step": 330
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 7.768115942028985,
|
| 541 |
+
"grad_norm": 2.792222023010254,
|
| 542 |
+
"learning_rate": 4.413246238998069e-05,
|
| 543 |
+
"loss": 0.2491,
|
| 544 |
+
"num_input_tokens_seen": 8304605,
|
| 545 |
+
"step": 335
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 7.884057971014493,
|
| 549 |
+
"grad_norm": 3.610206127166748,
|
| 550 |
+
"learning_rate": 4.3963469335015085e-05,
|
| 551 |
+
"loss": 0.3893,
|
| 552 |
+
"num_input_tokens_seen": 8437319,
|
| 553 |
+
"step": 340
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 8.0,
|
| 557 |
+
"grad_norm": 4.31643533706665,
|
| 558 |
+
"learning_rate": 4.379241051652174e-05,
|
| 559 |
+
"loss": 0.3761,
|
| 560 |
+
"num_input_tokens_seen": 8573080,
|
| 561 |
+
"step": 345
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 8.115942028985508,
|
| 565 |
+
"grad_norm": 2.2834160327911377,
|
| 566 |
+
"learning_rate": 4.361930456859456e-05,
|
| 567 |
+
"loss": 0.236,
|
| 568 |
+
"num_input_tokens_seen": 8707741,
|
| 569 |
+
"step": 350
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 8.231884057971014,
|
| 573 |
+
"grad_norm": 2.6929121017456055,
|
| 574 |
+
"learning_rate": 4.34441703483291e-05,
|
| 575 |
+
"loss": 0.1584,
|
| 576 |
+
"num_input_tokens_seen": 8825774,
|
| 577 |
+
"step": 355
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 8.347826086956522,
|
| 581 |
+
"grad_norm": 3.8095011711120605,
|
| 582 |
+
"learning_rate": 4.326702693376844e-05,
|
| 583 |
+
"loss": 0.1481,
|
| 584 |
+
"num_input_tokens_seen": 8932249,
|
| 585 |
+
"step": 360
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 8.46376811594203,
|
| 589 |
+
"grad_norm": 2.6493489742279053,
|
| 590 |
+
"learning_rate": 4.308789362182492e-05,
|
| 591 |
+
"loss": 0.1743,
|
| 592 |
+
"num_input_tokens_seen": 9051548,
|
| 593 |
+
"step": 365
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 8.579710144927537,
|
| 597 |
+
"grad_norm": 30.796459197998047,
|
| 598 |
+
"learning_rate": 4.290678992617798e-05,
|
| 599 |
+
"loss": 0.3162,
|
| 600 |
+
"num_input_tokens_seen": 9197232,
|
| 601 |
+
"step": 370
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 8.695652173913043,
|
| 605 |
+
"grad_norm": 3.3164985179901123,
|
| 606 |
+
"learning_rate": 4.272373557514858e-05,
|
| 607 |
+
"loss": 0.2235,
|
| 608 |
+
"num_input_tokens_seen": 9317650,
|
| 609 |
+
"step": 375
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 8.81159420289855,
|
| 613 |
+
"grad_norm": 3.1515417098999023,
|
| 614 |
+
"learning_rate": 4.2538750509550054e-05,
|
| 615 |
+
"loss": 0.2504,
|
| 616 |
+
"num_input_tokens_seen": 9450765,
|
| 617 |
+
"step": 380
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 8.927536231884059,
|
| 621 |
+
"grad_norm": 3.3926901817321777,
|
| 622 |
+
"learning_rate": 4.235185488051585e-05,
|
| 623 |
+
"loss": 0.2136,
|
| 624 |
+
"num_input_tokens_seen": 9582961,
|
| 625 |
+
"step": 385
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 9.043478260869565,
|
| 629 |
+
"grad_norm": 4.670753002166748,
|
| 630 |
+
"learning_rate": 4.216306904730447e-05,
|
| 631 |
+
"loss": 0.1047,
|
| 632 |
+
"num_input_tokens_seen": 9678616,
|
| 633 |
+
"step": 390
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 9.159420289855072,
|
| 637 |
+
"grad_norm": 2.166652202606201,
|
| 638 |
+
"learning_rate": 4.1972413575081595e-05,
|
| 639 |
+
"loss": 0.1015,
|
| 640 |
+
"num_input_tokens_seen": 9788512,
|
| 641 |
+
"step": 395
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 9.27536231884058,
|
| 645 |
+
"grad_norm": 2.1161272525787354,
|
| 646 |
+
"learning_rate": 4.177990923267986e-05,
|
| 647 |
+
"loss": 0.1505,
|
| 648 |
+
"num_input_tokens_seen": 9916229,
|
| 649 |
+
"step": 400
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 9.391304347826088,
|
| 653 |
+
"grad_norm": 2.378105401992798,
|
| 654 |
+
"learning_rate": 4.158557699033644e-05,
|
| 655 |
+
"loss": 0.1135,
|
| 656 |
+
"num_input_tokens_seen": 10042697,
|
| 657 |
+
"step": 405
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 9.507246376811594,
|
| 661 |
+
"grad_norm": 2.5567331314086914,
|
| 662 |
+
"learning_rate": 4.138943801740865e-05,
|
| 663 |
+
"loss": 0.1832,
|
| 664 |
+
"num_input_tokens_seen": 10171849,
|
| 665 |
+
"step": 410
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 9.623188405797102,
|
| 669 |
+
"grad_norm": 2.022610902786255,
|
| 670 |
+
"learning_rate": 4.119151368006793e-05,
|
| 671 |
+
"loss": 0.1178,
|
| 672 |
+
"num_input_tokens_seen": 10281924,
|
| 673 |
+
"step": 415
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 9.73913043478261,
|
| 677 |
+
"grad_norm": 2.5578079223632812,
|
| 678 |
+
"learning_rate": 4.099182553897229e-05,
|
| 679 |
+
"loss": 0.1426,
|
| 680 |
+
"num_input_tokens_seen": 10418758,
|
| 681 |
+
"step": 420
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 9.855072463768115,
|
| 685 |
+
"grad_norm": 2.7287228107452393,
|
| 686 |
+
"learning_rate": 4.079039534691767e-05,
|
| 687 |
+
"loss": 0.1603,
|
| 688 |
+
"num_input_tokens_seen": 10558322,
|
| 689 |
+
"step": 425
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 9.971014492753623,
|
| 693 |
+
"grad_norm": 2.361532688140869,
|
| 694 |
+
"learning_rate": 4.058724504646834e-05,
|
| 695 |
+
"loss": 0.1548,
|
| 696 |
+
"num_input_tokens_seen": 10679536,
|
| 697 |
+
"step": 430
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 10.08695652173913,
|
| 701 |
+
"grad_norm": 1.8757002353668213,
|
| 702 |
+
"learning_rate": 4.0382396767566536e-05,
|
| 703 |
+
"loss": 0.1407,
|
| 704 |
+
"num_input_tokens_seen": 10821076,
|
| 705 |
+
"step": 435
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 10.202898550724637,
|
| 709 |
+
"grad_norm": 2.352725028991699,
|
| 710 |
+
"learning_rate": 4.017587282512181e-05,
|
| 711 |
+
"loss": 0.0791,
|
| 712 |
+
"num_input_tokens_seen": 10949771,
|
| 713 |
+
"step": 440
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 10.318840579710145,
|
| 717 |
+
"grad_norm": 1.7948939800262451,
|
| 718 |
+
"learning_rate": 3.9967695716580224e-05,
|
| 719 |
+
"loss": 0.0722,
|
| 720 |
+
"num_input_tokens_seen": 11072044,
|
| 721 |
+
"step": 445
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 10.434782608695652,
|
| 725 |
+
"grad_norm": 1.954727292060852,
|
| 726 |
+
"learning_rate": 3.975788811947351e-05,
|
| 727 |
+
"loss": 0.0655,
|
| 728 |
+
"num_input_tokens_seen": 11182627,
|
| 729 |
+
"step": 450
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 10.55072463768116,
|
| 733 |
+
"grad_norm": 2.143941640853882,
|
| 734 |
+
"learning_rate": 3.954647288894883e-05,
|
| 735 |
+
"loss": 0.0723,
|
| 736 |
+
"num_input_tokens_seen": 11303028,
|
| 737 |
+
"step": 455
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 10.666666666666666,
|
| 741 |
+
"grad_norm": 2.0527164936065674,
|
| 742 |
+
"learning_rate": 3.933347305527898e-05,
|
| 743 |
+
"loss": 0.0655,
|
| 744 |
+
"num_input_tokens_seen": 11415868,
|
| 745 |
+
"step": 460
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 10.782608695652174,
|
| 749 |
+
"grad_norm": 1.6390535831451416,
|
| 750 |
+
"learning_rate": 3.911891182135371e-05,
|
| 751 |
+
"loss": 0.1534,
|
| 752 |
+
"num_input_tokens_seen": 11555653,
|
| 753 |
+
"step": 465
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 10.898550724637682,
|
| 757 |
+
"grad_norm": 2.3848719596862793,
|
| 758 |
+
"learning_rate": 3.8902812560152066e-05,
|
| 759 |
+
"loss": 0.0947,
|
| 760 |
+
"num_input_tokens_seen": 11681065,
|
| 761 |
+
"step": 470
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 11.014492753623188,
|
| 765 |
+
"grad_norm": 2.2094757556915283,
|
| 766 |
+
"learning_rate": 3.868519881219631e-05,
|
| 767 |
+
"loss": 0.0868,
|
| 768 |
+
"num_input_tokens_seen": 11809957,
|
| 769 |
+
"step": 475
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 11.130434782608695,
|
| 773 |
+
"grad_norm": 4.137216567993164,
|
| 774 |
+
"learning_rate": 3.846609428298757e-05,
|
| 775 |
+
"loss": 0.0467,
|
| 776 |
+
"num_input_tokens_seen": 11937881,
|
| 777 |
+
"step": 480
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 11.246376811594203,
|
| 781 |
+
"grad_norm": 1.6658189296722412,
|
| 782 |
+
"learning_rate": 3.824552284042351e-05,
|
| 783 |
+
"loss": 0.0521,
|
| 784 |
+
"num_input_tokens_seen": 12048905,
|
| 785 |
+
"step": 485
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 11.36231884057971,
|
| 789 |
+
"grad_norm": 1.5732171535491943,
|
| 790 |
+
"learning_rate": 3.8023508512198256e-05,
|
| 791 |
+
"loss": 0.051,
|
| 792 |
+
"num_input_tokens_seen": 12185453,
|
| 793 |
+
"step": 490
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 11.478260869565217,
|
| 797 |
+
"grad_norm": 1.8459701538085938,
|
| 798 |
+
"learning_rate": 3.780007548318507e-05,
|
| 799 |
+
"loss": 0.0753,
|
| 800 |
+
"num_input_tokens_seen": 12310911,
|
| 801 |
+
"step": 495
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 11.594202898550725,
|
| 805 |
+
"grad_norm": 1.4724109172821045,
|
| 806 |
+
"learning_rate": 3.7575248092801686e-05,
|
| 807 |
+
"loss": 0.0601,
|
| 808 |
+
"num_input_tokens_seen": 12439708,
|
| 809 |
+
"step": 500
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 11.710144927536232,
|
| 813 |
+
"grad_norm": 2.4690322875976562,
|
| 814 |
+
"learning_rate": 3.734905083235901e-05,
|
| 815 |
+
"loss": 0.0533,
|
| 816 |
+
"num_input_tokens_seen": 12554467,
|
| 817 |
+
"step": 505
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 11.826086956521738,
|
| 821 |
+
"grad_norm": 2.369218111038208,
|
| 822 |
+
"learning_rate": 3.712150834239313e-05,
|
| 823 |
+
"loss": 0.064,
|
| 824 |
+
"num_input_tokens_seen": 12682329,
|
| 825 |
+
"step": 510
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 11.942028985507246,
|
| 829 |
+
"grad_norm": 1.6901100873947144,
|
| 830 |
+
"learning_rate": 3.689264540998116e-05,
|
| 831 |
+
"loss": 0.0755,
|
| 832 |
+
"num_input_tokens_seen": 12800852,
|
| 833 |
+
"step": 515
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 12.057971014492754,
|
| 837 |
+
"grad_norm": 1.303114414215088,
|
| 838 |
+
"learning_rate": 3.66624869660411e-05,
|
| 839 |
+
"loss": 0.0553,
|
| 840 |
+
"num_input_tokens_seen": 12917527,
|
| 841 |
+
"step": 520
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 12.173913043478262,
|
| 845 |
+
"grad_norm": 1.1986353397369385,
|
| 846 |
+
"learning_rate": 3.6431058082615964e-05,
|
| 847 |
+
"loss": 0.0355,
|
| 848 |
+
"num_input_tokens_seen": 13044774,
|
| 849 |
+
"step": 525
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 12.289855072463768,
|
| 853 |
+
"grad_norm": 1.5653026103973389,
|
| 854 |
+
"learning_rate": 3.619838397014263e-05,
|
| 855 |
+
"loss": 0.0413,
|
| 856 |
+
"num_input_tokens_seen": 13175692,
|
| 857 |
+
"step": 530
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 12.405797101449275,
|
| 861 |
+
"grad_norm": 1.0767664909362793,
|
| 862 |
+
"learning_rate": 3.5964489974705553e-05,
|
| 863 |
+
"loss": 0.0596,
|
| 864 |
+
"num_input_tokens_seen": 13293164,
|
| 865 |
+
"step": 535
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 12.521739130434783,
|
| 869 |
+
"grad_norm": 1.6005312204360962,
|
| 870 |
+
"learning_rate": 3.572940157527572e-05,
|
| 871 |
+
"loss": 0.0479,
|
| 872 |
+
"num_input_tokens_seen": 13417894,
|
| 873 |
+
"step": 540
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 12.63768115942029,
|
| 877 |
+
"grad_norm": 1.627121925354004,
|
| 878 |
+
"learning_rate": 3.549314438093515e-05,
|
| 879 |
+
"loss": 0.047,
|
| 880 |
+
"num_input_tokens_seen": 13551913,
|
| 881 |
+
"step": 545
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 12.753623188405797,
|
| 885 |
+
"grad_norm": 2.239276647567749,
|
| 886 |
+
"learning_rate": 3.525574412808717e-05,
|
| 887 |
+
"loss": 0.0492,
|
| 888 |
+
"num_input_tokens_seen": 13675309,
|
| 889 |
+
"step": 550
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 12.869565217391305,
|
| 893 |
+
"grad_norm": 1.5702998638153076,
|
| 894 |
+
"learning_rate": 3.501722667765286e-05,
|
| 895 |
+
"loss": 0.0471,
|
| 896 |
+
"num_input_tokens_seen": 13797691,
|
| 897 |
+
"step": 555
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 12.985507246376812,
|
| 901 |
+
"grad_norm": 1.8216972351074219,
|
| 902 |
+
"learning_rate": 3.47776180122539e-05,
|
| 903 |
+
"loss": 0.1041,
|
| 904 |
+
"num_input_tokens_seen": 13919770,
|
| 905 |
+
"step": 560
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 13.101449275362318,
|
| 909 |
+
"grad_norm": 0.9026144742965698,
|
| 910 |
+
"learning_rate": 3.453694423338225e-05,
|
| 911 |
+
"loss": 0.0282,
|
| 912 |
+
"num_input_tokens_seen": 14037673,
|
| 913 |
+
"step": 565
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 13.217391304347826,
|
| 917 |
+
"grad_norm": 1.4504765272140503,
|
| 918 |
+
"learning_rate": 3.4295231558556715e-05,
|
| 919 |
+
"loss": 0.0272,
|
| 920 |
+
"num_input_tokens_seen": 14167090,
|
| 921 |
+
"step": 570
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 13.333333333333334,
|
| 925 |
+
"grad_norm": 1.4278969764709473,
|
| 926 |
+
"learning_rate": 3.4052506318467084e-05,
|
| 927 |
+
"loss": 0.0342,
|
| 928 |
+
"num_input_tokens_seen": 14311710,
|
| 929 |
+
"step": 575
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 13.44927536231884,
|
| 933 |
+
"grad_norm": 1.1284997463226318,
|
| 934 |
+
"learning_rate": 3.3808794954105716e-05,
|
| 935 |
+
"loss": 0.0855,
|
| 936 |
+
"num_input_tokens_seen": 14404322,
|
| 937 |
+
"step": 580
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 13.565217391304348,
|
| 941 |
+
"grad_norm": 1.4915614128112793,
|
| 942 |
+
"learning_rate": 3.356412401388732e-05,
|
| 943 |
+
"loss": 0.0378,
|
| 944 |
+
"num_input_tokens_seen": 14530794,
|
| 945 |
+
"step": 585
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 13.681159420289855,
|
| 949 |
+
"grad_norm": 1.372157096862793,
|
| 950 |
+
"learning_rate": 3.3318520150756846e-05,
|
| 951 |
+
"loss": 0.0457,
|
| 952 |
+
"num_input_tokens_seen": 14637342,
|
| 953 |
+
"step": 590
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 13.797101449275363,
|
| 957 |
+
"grad_norm": 1.6492116451263428,
|
| 958 |
+
"learning_rate": 3.307201011928616e-05,
|
| 959 |
+
"loss": 0.0453,
|
| 960 |
+
"num_input_tokens_seen": 14787534,
|
| 961 |
+
"step": 595
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 13.91304347826087,
|
| 965 |
+
"grad_norm": 1.3583859205245972,
|
| 966 |
+
"learning_rate": 3.282462077275947e-05,
|
| 967 |
+
"loss": 0.0378,
|
| 968 |
+
"num_input_tokens_seen": 14909175,
|
| 969 |
+
"step": 600
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 14.028985507246377,
|
| 973 |
+
"grad_norm": 1.0751795768737793,
|
| 974 |
+
"learning_rate": 3.257637906024822e-05,
|
| 975 |
+
"loss": 0.0296,
|
| 976 |
+
"num_input_tokens_seen": 15030530,
|
| 977 |
+
"step": 605
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 14.144927536231885,
|
| 981 |
+
"grad_norm": 1.474602222442627,
|
| 982 |
+
"learning_rate": 3.2327312023675287e-05,
|
| 983 |
+
"loss": 0.0216,
|
| 984 |
+
"num_input_tokens_seen": 15148359,
|
| 985 |
+
"step": 610
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 14.26086956521739,
|
| 989 |
+
"grad_norm": 1.0749961137771606,
|
| 990 |
+
"learning_rate": 3.2077446794869295e-05,
|
| 991 |
+
"loss": 0.0299,
|
| 992 |
+
"num_input_tokens_seen": 15280749,
|
| 993 |
+
"step": 615
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 14.376811594202898,
|
| 997 |
+
"grad_norm": 1.4042794704437256,
|
| 998 |
+
"learning_rate": 3.1826810592609036e-05,
|
| 999 |
+
"loss": 0.0247,
|
| 1000 |
+
"num_input_tokens_seen": 15397167,
|
| 1001 |
+
"step": 620
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 14.492753623188406,
|
| 1005 |
+
"grad_norm": 1.2280118465423584,
|
| 1006 |
+
"learning_rate": 3.157543071965835e-05,
|
| 1007 |
+
"loss": 0.0455,
|
| 1008 |
+
"num_input_tokens_seen": 15522794,
|
| 1009 |
+
"step": 625
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 14.608695652173914,
|
| 1013 |
+
"grad_norm": 1.2819784879684448,
|
| 1014 |
+
"learning_rate": 3.132333455979202e-05,
|
| 1015 |
+
"loss": 0.0262,
|
| 1016 |
+
"num_input_tokens_seen": 15637987,
|
| 1017 |
+
"step": 630
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 14.72463768115942,
|
| 1021 |
+
"grad_norm": 1.2691748142242432,
|
| 1022 |
+
"learning_rate": 3.107054957481271e-05,
|
| 1023 |
+
"loss": 0.0281,
|
| 1024 |
+
"num_input_tokens_seen": 15773163,
|
| 1025 |
+
"step": 635
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 14.840579710144928,
|
| 1029 |
+
"grad_norm": 1.2752504348754883,
|
| 1030 |
+
"learning_rate": 3.081710330155942e-05,
|
| 1031 |
+
"loss": 0.0294,
|
| 1032 |
+
"num_input_tokens_seen": 15892659,
|
| 1033 |
+
"step": 640
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 14.956521739130435,
|
| 1037 |
+
"grad_norm": 1.3479197025299072,
|
| 1038 |
+
"learning_rate": 3.056302334890786e-05,
|
| 1039 |
+
"loss": 0.0291,
|
| 1040 |
+
"num_input_tokens_seen": 16024576,
|
| 1041 |
+
"step": 645
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 15.072463768115941,
|
| 1045 |
+
"grad_norm": 1.3151382207870483,
|
| 1046 |
+
"learning_rate": 3.030833739476285e-05,
|
| 1047 |
+
"loss": 0.0216,
|
| 1048 |
+
"num_input_tokens_seen": 16151987,
|
| 1049 |
+
"step": 650
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 15.18840579710145,
|
| 1053 |
+
"grad_norm": 2.3882877826690674,
|
| 1054 |
+
"learning_rate": 3.0053073183043256e-05,
|
| 1055 |
+
"loss": 0.0218,
|
| 1056 |
+
"num_input_tokens_seen": 16278639,
|
| 1057 |
+
"step": 655
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 15.304347826086957,
|
| 1061 |
+
"grad_norm": 0.9794278144836426,
|
| 1062 |
+
"learning_rate": 2.979725852065981e-05,
|
| 1063 |
+
"loss": 0.0283,
|
| 1064 |
+
"num_input_tokens_seen": 16414743,
|
| 1065 |
+
"step": 660
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 15.420289855072463,
|
| 1069 |
+
"grad_norm": 0.8964869976043701,
|
| 1070 |
+
"learning_rate": 2.954092127448591e-05,
|
| 1071 |
+
"loss": 0.0259,
|
| 1072 |
+
"num_input_tokens_seen": 16529298,
|
| 1073 |
+
"step": 665
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 15.53623188405797,
|
| 1077 |
+
"grad_norm": 1.1441810131072998,
|
| 1078 |
+
"learning_rate": 2.9284089368322045e-05,
|
| 1079 |
+
"loss": 0.0716,
|
| 1080 |
+
"num_input_tokens_seen": 16655909,
|
| 1081 |
+
"step": 670
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 15.652173913043478,
|
| 1085 |
+
"grad_norm": 1.0959213972091675,
|
| 1086 |
+
"learning_rate": 2.9026790779853874e-05,
|
| 1087 |
+
"loss": 0.025,
|
| 1088 |
+
"num_input_tokens_seen": 16798263,
|
| 1089 |
+
"step": 675
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 15.768115942028986,
|
| 1093 |
+
"grad_norm": 1.0119343996047974,
|
| 1094 |
+
"learning_rate": 2.876905353760459e-05,
|
| 1095 |
+
"loss": 0.0218,
|
| 1096 |
+
"num_input_tokens_seen": 16916827,
|
| 1097 |
+
"step": 680
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 15.884057971014492,
|
| 1101 |
+
"grad_norm": 1.1373978853225708,
|
| 1102 |
+
"learning_rate": 2.8510905717881614e-05,
|
| 1103 |
+
"loss": 0.0231,
|
| 1104 |
+
"num_input_tokens_seen": 17040247,
|
| 1105 |
+
"step": 685
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 16.0,
|
| 1109 |
+
"grad_norm": 1.2512497901916504,
|
| 1110 |
+
"learning_rate": 2.8252375441718137e-05,
|
| 1111 |
+
"loss": 0.0228,
|
| 1112 |
+
"num_input_tokens_seen": 17146160,
|
| 1113 |
+
"step": 690
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 16.115942028985508,
|
| 1117 |
+
"grad_norm": 0.7410117387771606,
|
| 1118 |
+
"learning_rate": 2.7993490871809808e-05,
|
| 1119 |
+
"loss": 0.029,
|
| 1120 |
+
"num_input_tokens_seen": 17284643,
|
| 1121 |
+
"step": 695
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 16.231884057971016,
|
| 1125 |
+
"grad_norm": 1.0934263467788696,
|
| 1126 |
+
"learning_rate": 2.7734280209446865e-05,
|
| 1127 |
+
"loss": 0.0199,
|
| 1128 |
+
"num_input_tokens_seen": 17426644,
|
| 1129 |
+
"step": 700
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 16.347826086956523,
|
| 1133 |
+
"grad_norm": 1.0034395456314087,
|
| 1134 |
+
"learning_rate": 2.7474771691442018e-05,
|
| 1135 |
+
"loss": 0.0259,
|
| 1136 |
+
"num_input_tokens_seen": 17541812,
|
| 1137 |
+
"step": 705
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 16.463768115942027,
|
| 1141 |
+
"grad_norm": 1.4287781715393066,
|
| 1142 |
+
"learning_rate": 2.721499358705458e-05,
|
| 1143 |
+
"loss": 0.021,
|
| 1144 |
+
"num_input_tokens_seen": 17667755,
|
| 1145 |
+
"step": 710
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 16.579710144927535,
|
| 1149 |
+
"grad_norm": 1.0989606380462646,
|
| 1150 |
+
"learning_rate": 2.6954974194910888e-05,
|
| 1151 |
+
"loss": 0.0199,
|
| 1152 |
+
"num_input_tokens_seen": 17788162,
|
| 1153 |
+
"step": 715
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 16.695652173913043,
|
| 1157 |
+
"grad_norm": 0.9687130451202393,
|
| 1158 |
+
"learning_rate": 2.6694741839921732e-05,
|
| 1159 |
+
"loss": 0.0189,
|
| 1160 |
+
"num_input_tokens_seen": 17911718,
|
| 1161 |
+
"step": 720
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 16.81159420289855,
|
| 1165 |
+
"grad_norm": 1.143617033958435,
|
| 1166 |
+
"learning_rate": 2.6434324870196748e-05,
|
| 1167 |
+
"loss": 0.0169,
|
| 1168 |
+
"num_input_tokens_seen": 18018729,
|
| 1169 |
+
"step": 725
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 16.92753623188406,
|
| 1173 |
+
"grad_norm": 1.1395140886306763,
|
| 1174 |
+
"learning_rate": 2.617375165395634e-05,
|
| 1175 |
+
"loss": 0.0209,
|
| 1176 |
+
"num_input_tokens_seen": 18139681,
|
| 1177 |
+
"step": 730
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 17.043478260869566,
|
| 1181 |
+
"grad_norm": 0.881986677646637,
|
| 1182 |
+
"learning_rate": 2.5913050576441477e-05,
|
| 1183 |
+
"loss": 0.0201,
|
| 1184 |
+
"num_input_tokens_seen": 18278544,
|
| 1185 |
+
"step": 735
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 17.159420289855074,
|
| 1189 |
+
"grad_norm": 0.8654409050941467,
|
| 1190 |
+
"learning_rate": 2.5652250036821523e-05,
|
| 1191 |
+
"loss": 0.017,
|
| 1192 |
+
"num_input_tokens_seen": 18396700,
|
| 1193 |
+
"step": 740
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 17.27536231884058,
|
| 1197 |
+
"grad_norm": 0.9699842929840088,
|
| 1198 |
+
"learning_rate": 2.5391378445100644e-05,
|
| 1199 |
+
"loss": 0.0187,
|
| 1200 |
+
"num_input_tokens_seen": 18506229,
|
| 1201 |
+
"step": 745
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 17.391304347826086,
|
| 1205 |
+
"grad_norm": 0.8799194693565369,
|
| 1206 |
+
"learning_rate": 2.5130464219022992e-05,
|
| 1207 |
+
"loss": 0.0242,
|
| 1208 |
+
"num_input_tokens_seen": 18621580,
|
| 1209 |
+
"step": 750
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 17.507246376811594,
|
| 1213 |
+
"grad_norm": 0.9715821146965027,
|
| 1214 |
+
"learning_rate": 2.486953578097702e-05,
|
| 1215 |
+
"loss": 0.0153,
|
| 1216 |
+
"num_input_tokens_seen": 18748382,
|
| 1217 |
+
"step": 755
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 17.6231884057971,
|
| 1221 |
+
"grad_norm": 0.8819458484649658,
|
| 1222 |
+
"learning_rate": 2.4608621554899362e-05,
|
| 1223 |
+
"loss": 0.0182,
|
| 1224 |
+
"num_input_tokens_seen": 18884730,
|
| 1225 |
+
"step": 760
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 17.73913043478261,
|
| 1229 |
+
"grad_norm": 0.8835431933403015,
|
| 1230 |
+
"learning_rate": 2.4347749963178486e-05,
|
| 1231 |
+
"loss": 0.0143,
|
| 1232 |
+
"num_input_tokens_seen": 19003589,
|
| 1233 |
+
"step": 765
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 17.855072463768117,
|
| 1237 |
+
"grad_norm": 0.780754566192627,
|
| 1238 |
+
"learning_rate": 2.4086949423558526e-05,
|
| 1239 |
+
"loss": 0.0164,
|
| 1240 |
+
"num_input_tokens_seen": 19136411,
|
| 1241 |
+
"step": 770
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 17.971014492753625,
|
| 1245 |
+
"grad_norm": 0.7591371536254883,
|
| 1246 |
+
"learning_rate": 2.3826248346043663e-05,
|
| 1247 |
+
"loss": 0.0157,
|
| 1248 |
+
"num_input_tokens_seen": 19260436,
|
| 1249 |
+
"step": 775
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 18.08695652173913,
|
| 1253 |
+
"grad_norm": 0.673797070980072,
|
| 1254 |
+
"learning_rate": 2.356567512980326e-05,
|
| 1255 |
+
"loss": 0.0304,
|
| 1256 |
+
"num_input_tokens_seen": 19388733,
|
| 1257 |
+
"step": 780
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 18.202898550724637,
|
| 1261 |
+
"grad_norm": 0.4008718729019165,
|
| 1262 |
+
"learning_rate": 2.3305258160078274e-05,
|
| 1263 |
+
"loss": 0.009,
|
| 1264 |
+
"num_input_tokens_seen": 19531204,
|
| 1265 |
+
"step": 785
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 18.318840579710145,
|
| 1269 |
+
"grad_norm": 0.6676005125045776,
|
| 1270 |
+
"learning_rate": 2.3045025805089118e-05,
|
| 1271 |
+
"loss": 0.0105,
|
| 1272 |
+
"num_input_tokens_seen": 19624608,
|
| 1273 |
+
"step": 790
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 18.434782608695652,
|
| 1277 |
+
"grad_norm": 0.6956990957260132,
|
| 1278 |
+
"learning_rate": 2.278500641294543e-05,
|
| 1279 |
+
"loss": 0.0104,
|
| 1280 |
+
"num_input_tokens_seen": 19751062,
|
| 1281 |
+
"step": 795
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 18.55072463768116,
|
| 1285 |
+
"grad_norm": 0.80479896068573,
|
| 1286 |
+
"learning_rate": 2.252522830855798e-05,
|
| 1287 |
+
"loss": 0.0103,
|
| 1288 |
+
"num_input_tokens_seen": 19879837,
|
| 1289 |
+
"step": 800
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 18.666666666666668,
|
| 1293 |
+
"grad_norm": 0.7206840515136719,
|
| 1294 |
+
"learning_rate": 2.2265719790553147e-05,
|
| 1295 |
+
"loss": 0.0107,
|
| 1296 |
+
"num_input_tokens_seen": 20019385,
|
| 1297 |
+
"step": 805
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 18.782608695652176,
|
| 1301 |
+
"grad_norm": 0.6994977593421936,
|
| 1302 |
+
"learning_rate": 2.2006509128190195e-05,
|
| 1303 |
+
"loss": 0.0269,
|
| 1304 |
+
"num_input_tokens_seen": 20138003,
|
| 1305 |
+
"step": 810
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 18.89855072463768,
|
| 1309 |
+
"grad_norm": 0.5642988681793213,
|
| 1310 |
+
"learning_rate": 2.174762455828187e-05,
|
| 1311 |
+
"loss": 0.0086,
|
| 1312 |
+
"num_input_tokens_seen": 20260523,
|
| 1313 |
+
"step": 815
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 19.014492753623188,
|
| 1317 |
+
"grad_norm": 0.5547834038734436,
|
| 1318 |
+
"learning_rate": 2.1489094282118395e-05,
|
| 1319 |
+
"loss": 0.0133,
|
| 1320 |
+
"num_input_tokens_seen": 20375322,
|
| 1321 |
+
"step": 820
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 19.130434782608695,
|
| 1325 |
+
"grad_norm": 0.48678871989250183,
|
| 1326 |
+
"learning_rate": 2.123094646239541e-05,
|
| 1327 |
+
"loss": 0.0114,
|
| 1328 |
+
"num_input_tokens_seen": 20477407,
|
| 1329 |
+
"step": 825
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 19.246376811594203,
|
| 1333 |
+
"grad_norm": 0.4791460633277893,
|
| 1334 |
+
"learning_rate": 2.0973209220146135e-05,
|
| 1335 |
+
"loss": 0.007,
|
| 1336 |
+
"num_input_tokens_seen": 20605728,
|
| 1337 |
+
"step": 830
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 19.36231884057971,
|
| 1341 |
+
"grad_norm": 1.1198338270187378,
|
| 1342 |
+
"learning_rate": 2.0715910631677968e-05,
|
| 1343 |
+
"loss": 0.0088,
|
| 1344 |
+
"num_input_tokens_seen": 20725799,
|
| 1345 |
+
"step": 835
|
| 1346 |
+
},
|
| 1347 |
+
{
|
| 1348 |
+
"epoch": 19.47826086956522,
|
| 1349 |
+
"grad_norm": 0.6645247936248779,
|
| 1350 |
+
"learning_rate": 2.0459078725514092e-05,
|
| 1351 |
+
"loss": 0.007,
|
| 1352 |
+
"num_input_tokens_seen": 20865534,
|
| 1353 |
+
"step": 840
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 19.594202898550726,
|
| 1357 |
+
"grad_norm": 0.5324479341506958,
|
| 1358 |
+
"learning_rate": 2.020274147934019e-05,
|
| 1359 |
+
"loss": 0.0059,
|
| 1360 |
+
"num_input_tokens_seen": 20977913,
|
| 1361 |
+
"step": 845
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 19.71014492753623,
|
| 1365 |
+
"grad_norm": 0.6183504462242126,
|
| 1366 |
+
"learning_rate": 1.9946926816956743e-05,
|
| 1367 |
+
"loss": 0.0069,
|
| 1368 |
+
"num_input_tokens_seen": 21102848,
|
| 1369 |
+
"step": 850
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 19.82608695652174,
|
| 1373 |
+
"grad_norm": 0.6665703058242798,
|
| 1374 |
+
"learning_rate": 1.9691662605237166e-05,
|
| 1375 |
+
"loss": 0.008,
|
| 1376 |
+
"num_input_tokens_seen": 21243679,
|
| 1377 |
+
"step": 855
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 19.942028985507246,
|
| 1381 |
+
"grad_norm": 0.3298584222793579,
|
| 1382 |
+
"learning_rate": 1.9436976651092144e-05,
|
| 1383 |
+
"loss": 0.0127,
|
| 1384 |
+
"num_input_tokens_seen": 21364202,
|
| 1385 |
+
"step": 860
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 20.057971014492754,
|
| 1389 |
+
"grad_norm": 0.2818591296672821,
|
| 1390 |
+
"learning_rate": 1.9182896698440584e-05,
|
| 1391 |
+
"loss": 0.0059,
|
| 1392 |
+
"num_input_tokens_seen": 21496089,
|
| 1393 |
+
"step": 865
|
| 1394 |
+
},
|
| 1395 |
+
{
|
| 1396 |
+
"epoch": 20.17391304347826,
|
| 1397 |
+
"grad_norm": 0.6906440258026123,
|
| 1398 |
+
"learning_rate": 1.89294504251873e-05,
|
| 1399 |
+
"loss": 0.0046,
|
| 1400 |
+
"num_input_tokens_seen": 21603193,
|
| 1401 |
+
"step": 870
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 20.28985507246377,
|
| 1405 |
+
"grad_norm": 0.33482542634010315,
|
| 1406 |
+
"learning_rate": 1.867666544020798e-05,
|
| 1407 |
+
"loss": 0.0058,
|
| 1408 |
+
"num_input_tokens_seen": 21742062,
|
| 1409 |
+
"step": 875
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 20.405797101449274,
|
| 1413 |
+
"grad_norm": 2.443847417831421,
|
| 1414 |
+
"learning_rate": 1.8424569280341653e-05,
|
| 1415 |
+
"loss": 0.0082,
|
| 1416 |
+
"num_input_tokens_seen": 21869307,
|
| 1417 |
+
"step": 880
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 20.52173913043478,
|
| 1421 |
+
"grad_norm": 0.43886587023735046,
|
| 1422 |
+
"learning_rate": 1.817318940739098e-05,
|
| 1423 |
+
"loss": 0.0148,
|
| 1424 |
+
"num_input_tokens_seen": 21992573,
|
| 1425 |
+
"step": 885
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 20.63768115942029,
|
| 1429 |
+
"grad_norm": 0.93570876121521,
|
| 1430 |
+
"learning_rate": 1.7922553205130707e-05,
|
| 1431 |
+
"loss": 0.0064,
|
| 1432 |
+
"num_input_tokens_seen": 22101845,
|
| 1433 |
+
"step": 890
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 20.753623188405797,
|
| 1437 |
+
"grad_norm": 1176.9595947265625,
|
| 1438 |
+
"learning_rate": 1.767268797632472e-05,
|
| 1439 |
+
"loss": 0.008,
|
| 1440 |
+
"num_input_tokens_seen": 22230253,
|
| 1441 |
+
"step": 895
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 20.869565217391305,
|
| 1445 |
+
"grad_norm": 0.35642215609550476,
|
| 1446 |
+
"learning_rate": 1.7423620939751788e-05,
|
| 1447 |
+
"loss": 0.0053,
|
| 1448 |
+
"num_input_tokens_seen": 22373454,
|
| 1449 |
+
"step": 900
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 20.985507246376812,
|
| 1453 |
+
"grad_norm": 0.39736178517341614,
|
| 1454 |
+
"learning_rate": 1.7175379227240523e-05,
|
| 1455 |
+
"loss": 0.0054,
|
| 1456 |
+
"num_input_tokens_seen": 22493123,
|
| 1457 |
+
"step": 905
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 21.10144927536232,
|
| 1461 |
+
"grad_norm": 0.5092463493347168,
|
| 1462 |
+
"learning_rate": 1.692798988071385e-05,
|
| 1463 |
+
"loss": 0.0044,
|
| 1464 |
+
"num_input_tokens_seen": 22629005,
|
| 1465 |
+
"step": 910
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 21.217391304347824,
|
| 1469 |
+
"grad_norm": 0.26361697912216187,
|
| 1470 |
+
"learning_rate": 1.6681479849243153e-05,
|
| 1471 |
+
"loss": 0.0043,
|
| 1472 |
+
"num_input_tokens_seen": 22752358,
|
| 1473 |
+
"step": 915
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 21.333333333333332,
|
| 1477 |
+
"grad_norm": 0.19933666288852692,
|
| 1478 |
+
"learning_rate": 1.6435875986112685e-05,
|
| 1479 |
+
"loss": 0.0035,
|
| 1480 |
+
"num_input_tokens_seen": 22880349,
|
| 1481 |
+
"step": 920
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 21.44927536231884,
|
| 1485 |
+
"grad_norm": 0.22622954845428467,
|
| 1486 |
+
"learning_rate": 1.6191205045894283e-05,
|
| 1487 |
+
"loss": 0.0044,
|
| 1488 |
+
"num_input_tokens_seen": 22987343,
|
| 1489 |
+
"step": 925
|
| 1490 |
+
},
|
| 1491 |
+
{
|
| 1492 |
+
"epoch": 21.565217391304348,
|
| 1493 |
+
"grad_norm": 0.30199098587036133,
|
| 1494 |
+
"learning_rate": 1.594749368153292e-05,
|
| 1495 |
+
"loss": 0.0178,
|
| 1496 |
+
"num_input_tokens_seen": 23113462,
|
| 1497 |
+
"step": 930
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 21.681159420289855,
|
| 1501 |
+
"grad_norm": 0.9627483487129211,
|
| 1502 |
+
"learning_rate": 1.570476844144329e-05,
|
| 1503 |
+
"loss": 0.0089,
|
| 1504 |
+
"num_input_tokens_seen": 23221714,
|
| 1505 |
+
"step": 935
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 21.797101449275363,
|
| 1509 |
+
"grad_norm": 0.27791452407836914,
|
| 1510 |
+
"learning_rate": 1.546305576661776e-05,
|
| 1511 |
+
"loss": 0.004,
|
| 1512 |
+
"num_input_tokens_seen": 23368857,
|
| 1513 |
+
"step": 940
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 21.91304347826087,
|
| 1517 |
+
"grad_norm": 0.3269965648651123,
|
| 1518 |
+
"learning_rate": 1.5222381987746104e-05,
|
| 1519 |
+
"loss": 0.004,
|
| 1520 |
+
"num_input_tokens_seen": 23494483,
|
| 1521 |
+
"step": 945
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 22.028985507246375,
|
| 1525 |
+
"grad_norm": 0.15966826677322388,
|
| 1526 |
+
"learning_rate": 1.4982773322347144e-05,
|
| 1527 |
+
"loss": 0.0034,
|
| 1528 |
+
"num_input_tokens_seen": 23605463,
|
| 1529 |
+
"step": 950
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 22.144927536231883,
|
| 1533 |
+
"grad_norm": 0.3009255826473236,
|
| 1534 |
+
"learning_rate": 1.4744255871912823e-05,
|
| 1535 |
+
"loss": 0.0066,
|
| 1536 |
+
"num_input_tokens_seen": 23715776,
|
| 1537 |
+
"step": 955
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 22.26086956521739,
|
| 1541 |
+
"grad_norm": 0.4215935170650482,
|
| 1542 |
+
"learning_rate": 1.4506855619064846e-05,
|
| 1543 |
+
"loss": 0.0034,
|
| 1544 |
+
"num_input_tokens_seen": 23841669,
|
| 1545 |
+
"step": 960
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 22.3768115942029,
|
| 1549 |
+
"grad_norm": 0.20214155316352844,
|
| 1550 |
+
"learning_rate": 1.4270598424724292e-05,
|
| 1551 |
+
"loss": 0.0032,
|
| 1552 |
+
"num_input_tokens_seen": 23960567,
|
| 1553 |
+
"step": 965
|
| 1554 |
+
},
|
| 1555 |
+
{
|
| 1556 |
+
"epoch": 22.492753623188406,
|
| 1557 |
+
"grad_norm": 7.0683207511901855,
|
| 1558 |
+
"learning_rate": 1.4035510025294462e-05,
|
| 1559 |
+
"loss": 0.0124,
|
| 1560 |
+
"num_input_tokens_seen": 24074628,
|
| 1561 |
+
"step": 970
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 22.608695652173914,
|
| 1565 |
+
"grad_norm": 0.20178793370723724,
|
| 1566 |
+
"learning_rate": 1.3801616029857378e-05,
|
| 1567 |
+
"loss": 0.0027,
|
| 1568 |
+
"num_input_tokens_seen": 24214324,
|
| 1569 |
+
"step": 975
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 22.72463768115942,
|
| 1573 |
+
"grad_norm": 1.3855236768722534,
|
| 1574 |
+
"learning_rate": 1.3568941917384036e-05,
|
| 1575 |
+
"loss": 0.0037,
|
| 1576 |
+
"num_input_tokens_seen": 24326727,
|
| 1577 |
+
"step": 980
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 22.840579710144926,
|
| 1581 |
+
"grad_norm": 0.18420317769050598,
|
| 1582 |
+
"learning_rate": 1.3337513033958904e-05,
|
| 1583 |
+
"loss": 0.0029,
|
| 1584 |
+
"num_input_tokens_seen": 24456961,
|
| 1585 |
+
"step": 985
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 22.956521739130434,
|
| 1589 |
+
"grad_norm": 0.15907694399356842,
|
| 1590 |
+
"learning_rate": 1.310735459001884e-05,
|
| 1591 |
+
"loss": 0.0035,
|
| 1592 |
+
"num_input_tokens_seen": 24606652,
|
| 1593 |
+
"step": 990
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 23.07246376811594,
|
| 1597 |
+
"grad_norm": 0.2548115849494934,
|
| 1598 |
+
"learning_rate": 1.2878491657606872e-05,
|
| 1599 |
+
"loss": 0.002,
|
| 1600 |
+
"num_input_tokens_seen": 24710410,
|
| 1601 |
+
"step": 995
|
| 1602 |
+
},
|
| 1603 |
+
{
|
| 1604 |
+
"epoch": 23.18840579710145,
|
| 1605 |
+
"grad_norm": 0.36587971448898315,
|
| 1606 |
+
"learning_rate": 1.2650949167640993e-05,
|
| 1607 |
+
"loss": 0.0023,
|
| 1608 |
+
"num_input_tokens_seen": 24831908,
|
| 1609 |
+
"step": 1000
|
| 1610 |
+
},
|
| 1611 |
+
{
|
| 1612 |
+
"epoch": 23.304347826086957,
|
| 1613 |
+
"grad_norm": 0.13662408292293549,
|
| 1614 |
+
"learning_rate": 1.2424751907198312e-05,
|
| 1615 |
+
"loss": 0.0031,
|
| 1616 |
+
"num_input_tokens_seen": 24951342,
|
| 1617 |
+
"step": 1005
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 23.420289855072465,
|
| 1621 |
+
"grad_norm": 0.19979843497276306,
|
| 1622 |
+
"learning_rate": 1.2199924516814939e-05,
|
| 1623 |
+
"loss": 0.0027,
|
| 1624 |
+
"num_input_tokens_seen": 25088309,
|
| 1625 |
+
"step": 1010
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 23.536231884057973,
|
| 1629 |
+
"grad_norm": 0.14170995354652405,
|
| 1630 |
+
"learning_rate": 1.1976491487801748e-05,
|
| 1631 |
+
"loss": 0.0124,
|
| 1632 |
+
"num_input_tokens_seen": 25216080,
|
| 1633 |
+
"step": 1015
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 23.652173913043477,
|
| 1637 |
+
"grad_norm": 0.06863216310739517,
|
| 1638 |
+
"learning_rate": 1.1754477159576499e-05,
|
| 1639 |
+
"loss": 0.0023,
|
| 1640 |
+
"num_input_tokens_seen": 25326581,
|
| 1641 |
+
"step": 1020
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 23.768115942028984,
|
| 1645 |
+
"grad_norm": 0.25133436918258667,
|
| 1646 |
+
"learning_rate": 1.1533905717012428e-05,
|
| 1647 |
+
"loss": 0.0027,
|
| 1648 |
+
"num_input_tokens_seen": 25477500,
|
| 1649 |
+
"step": 1025
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 23.884057971014492,
|
| 1653 |
+
"grad_norm": 0.28348398208618164,
|
| 1654 |
+
"learning_rate": 1.1314801187803686e-05,
|
| 1655 |
+
"loss": 0.0041,
|
| 1656 |
+
"num_input_tokens_seen": 25601354,
|
| 1657 |
+
"step": 1030
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 24.0,
|
| 1661 |
+
"grad_norm": 0.5024954676628113,
|
| 1662 |
+
"learning_rate": 1.1097187439847939e-05,
|
| 1663 |
+
"loss": 0.0021,
|
| 1664 |
+
"num_input_tokens_seen": 25719240,
|
| 1665 |
+
"step": 1035
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 24.115942028985508,
|
| 1669 |
+
"grad_norm": 0.1774568408727646,
|
| 1670 |
+
"learning_rate": 1.088108817864629e-05,
|
| 1671 |
+
"loss": 0.0039,
|
| 1672 |
+
"num_input_tokens_seen": 25834910,
|
| 1673 |
+
"step": 1040
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 24.231884057971016,
|
| 1677 |
+
"grad_norm": 0.08105342090129852,
|
| 1678 |
+
"learning_rate": 1.0666526944721016e-05,
|
| 1679 |
+
"loss": 0.0025,
|
| 1680 |
+
"num_input_tokens_seen": 25974530,
|
| 1681 |
+
"step": 1045
|
| 1682 |
+
},
|
| 1683 |
+
{
|
| 1684 |
+
"epoch": 24.347826086956523,
|
| 1685 |
+
"grad_norm": 0.13048779964447021,
|
| 1686 |
+
"learning_rate": 1.0453527111051184e-05,
|
| 1687 |
+
"loss": 0.002,
|
| 1688 |
+
"num_input_tokens_seen": 26104464,
|
| 1689 |
+
"step": 1050
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 24.463768115942027,
|
| 1693 |
+
"grad_norm": 0.10774020105600357,
|
| 1694 |
+
"learning_rate": 1.0242111880526495e-05,
|
| 1695 |
+
"loss": 0.0024,
|
| 1696 |
+
"num_input_tokens_seen": 26251334,
|
| 1697 |
+
"step": 1055
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 24.579710144927535,
|
| 1701 |
+
"grad_norm": 0.7494776248931885,
|
| 1702 |
+
"learning_rate": 1.003230428341979e-05,
|
| 1703 |
+
"loss": 0.0031,
|
| 1704 |
+
"num_input_tokens_seen": 26366561,
|
| 1705 |
+
"step": 1060
|
| 1706 |
+
},
|
| 1707 |
+
{
|
| 1708 |
+
"epoch": 24.695652173913043,
|
| 1709 |
+
"grad_norm": 0.3580308258533478,
|
| 1710 |
+
"learning_rate": 9.824127174878195e-06,
|
| 1711 |
+
"loss": 0.0022,
|
| 1712 |
+
"num_input_tokens_seen": 26486437,
|
| 1713 |
+
"step": 1065
|
| 1714 |
+
},
|
| 1715 |
+
{
|
| 1716 |
+
"epoch": 24.81159420289855,
|
| 1717 |
+
"grad_norm": 0.1473228931427002,
|
| 1718 |
+
"learning_rate": 9.617603232433475e-06,
|
| 1719 |
+
"loss": 0.0022,
|
| 1720 |
+
"num_input_tokens_seen": 26601526,
|
| 1721 |
+
"step": 1070
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 24.92753623188406,
|
| 1725 |
+
"grad_norm": 0.11716706305742264,
|
| 1726 |
+
"learning_rate": 9.412754953531663e-06,
|
| 1727 |
+
"loss": 0.0109,
|
| 1728 |
+
"num_input_tokens_seen": 26727922,
|
| 1729 |
+
"step": 1075
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 25.043478260869566,
|
| 1733 |
+
"grad_norm": 0.12043190747499466,
|
| 1734 |
+
"learning_rate": 9.209604653082326e-06,
|
| 1735 |
+
"loss": 0.0019,
|
| 1736 |
+
"num_input_tokens_seen": 26835621,
|
| 1737 |
+
"step": 1080
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 25.159420289855074,
|
| 1741 |
+
"grad_norm": 0.1277165412902832,
|
| 1742 |
+
"learning_rate": 9.008174461027724e-06,
|
| 1743 |
+
"loss": 0.0016,
|
| 1744 |
+
"num_input_tokens_seen": 26955101,
|
| 1745 |
+
"step": 1085
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 25.27536231884058,
|
| 1749 |
+
"grad_norm": 0.08892516791820526,
|
| 1750 |
+
"learning_rate": 8.808486319932083e-06,
|
| 1751 |
+
"loss": 0.002,
|
| 1752 |
+
"num_input_tokens_seen": 27077833,
|
| 1753 |
+
"step": 1090
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 25.391304347826086,
|
| 1757 |
+
"grad_norm": 0.30754807591438293,
|
| 1758 |
+
"learning_rate": 8.610561982591357e-06,
|
| 1759 |
+
"loss": 0.0018,
|
| 1760 |
+
"num_input_tokens_seen": 27192758,
|
| 1761 |
+
"step": 1095
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 25.507246376811594,
|
| 1765 |
+
"grad_norm": 0.7194050550460815,
|
| 1766 |
+
"learning_rate": 8.414423009663563e-06,
|
| 1767 |
+
"loss": 0.0028,
|
| 1768 |
+
"num_input_tokens_seen": 27324970,
|
| 1769 |
+
"step": 1100
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"epoch": 25.6231884057971,
|
| 1773 |
+
"grad_norm": 4777.61328125,
|
| 1774 |
+
"learning_rate": 8.220090767320137e-06,
|
| 1775 |
+
"loss": 0.0021,
|
| 1776 |
+
"num_input_tokens_seen": 27477531,
|
| 1777 |
+
"step": 1105
|
| 1778 |
+
},
|
| 1779 |
+
{
|
| 1780 |
+
"epoch": 25.73913043478261,
|
| 1781 |
+
"grad_norm": 2.280327081680298,
|
| 1782 |
+
"learning_rate": 8.027586424918412e-06,
|
| 1783 |
+
"loss": 0.0057,
|
| 1784 |
+
"num_input_tokens_seen": 27592035,
|
| 1785 |
+
"step": 1110
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"epoch": 25.855072463768117,
|
| 1789 |
+
"grad_norm": 0.13882993161678314,
|
| 1790 |
+
"learning_rate": 7.836930952695533e-06,
|
| 1791 |
+
"loss": 0.0067,
|
| 1792 |
+
"num_input_tokens_seen": 27712377,
|
| 1793 |
+
"step": 1115
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 25.971014492753625,
|
| 1797 |
+
"grad_norm": 0.20987676084041595,
|
| 1798 |
+
"learning_rate": 7.648145119484153e-06,
|
| 1799 |
+
"loss": 0.002,
|
| 1800 |
+
"num_input_tokens_seen": 27834613,
|
| 1801 |
+
"step": 1120
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 26.08695652173913,
|
| 1805 |
+
"grad_norm": 0.09795770049095154,
|
| 1806 |
+
"learning_rate": 7.461249490449954e-06,
|
| 1807 |
+
"loss": 0.0021,
|
| 1808 |
+
"num_input_tokens_seen": 27966996,
|
| 1809 |
+
"step": 1125
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 26.202898550724637,
|
| 1813 |
+
"grad_norm": 0.14506971836090088,
|
| 1814 |
+
"learning_rate": 7.276264424851423e-06,
|
| 1815 |
+
"loss": 0.002,
|
| 1816 |
+
"num_input_tokens_seen": 28093538,
|
| 1817 |
+
"step": 1130
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 26.318840579710145,
|
| 1821 |
+
"grad_norm": 0.08091314136981964,
|
| 1822 |
+
"learning_rate": 7.0932100738220265e-06,
|
| 1823 |
+
"loss": 0.0017,
|
| 1824 |
+
"num_input_tokens_seen": 28215579,
|
| 1825 |
+
"step": 1135
|
| 1826 |
+
},
|
| 1827 |
+
{
|
| 1828 |
+
"epoch": 26.434782608695652,
|
| 1829 |
+
"grad_norm": 0.22550061345100403,
|
| 1830 |
+
"learning_rate": 6.912106378175098e-06,
|
| 1831 |
+
"loss": 0.0014,
|
| 1832 |
+
"num_input_tokens_seen": 28344144,
|
| 1833 |
+
"step": 1140
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 26.55072463768116,
|
| 1837 |
+
"grad_norm": 0.23987355828285217,
|
| 1838 |
+
"learning_rate": 6.732973066231563e-06,
|
| 1839 |
+
"loss": 0.0022,
|
| 1840 |
+
"num_input_tokens_seen": 28478650,
|
| 1841 |
+
"step": 1145
|
| 1842 |
+
},
|
| 1843 |
+
{
|
| 1844 |
+
"epoch": 26.666666666666668,
|
| 1845 |
+
"grad_norm": 0.1993756741285324,
|
| 1846 |
+
"learning_rate": 6.555829651670911e-06,
|
| 1847 |
+
"loss": 0.0023,
|
| 1848 |
+
"num_input_tokens_seen": 28593004,
|
| 1849 |
+
"step": 1150
|
| 1850 |
+
},
|
| 1851 |
+
{
|
| 1852 |
+
"epoch": 26.782608695652176,
|
| 1853 |
+
"grad_norm": 0.7184757590293884,
|
| 1854 |
+
"learning_rate": 6.380695431405456e-06,
|
| 1855 |
+
"loss": 0.0028,
|
| 1856 |
+
"num_input_tokens_seen": 28707392,
|
| 1857 |
+
"step": 1155
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 26.89855072463768,
|
| 1861 |
+
"grad_norm": 0.06247011199593544,
|
| 1862 |
+
"learning_rate": 6.207589483478266e-06,
|
| 1863 |
+
"loss": 0.006,
|
| 1864 |
+
"num_input_tokens_seen": 28834902,
|
| 1865 |
+
"step": 1160
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 27.014492753623188,
|
| 1869 |
+
"grad_norm": 0.11046591401100159,
|
| 1870 |
+
"learning_rate": 6.0365306649849214e-06,
|
| 1871 |
+
"loss": 0.0045,
|
| 1872 |
+
"num_input_tokens_seen": 28948812,
|
| 1873 |
+
"step": 1165
|
| 1874 |
+
},
|
| 1875 |
+
{
|
| 1876 |
+
"epoch": 27.130434782608695,
|
| 1877 |
+
"grad_norm": 0.12309098988771439,
|
| 1878 |
+
"learning_rate": 5.867537610019317e-06,
|
| 1879 |
+
"loss": 0.0019,
|
| 1880 |
+
"num_input_tokens_seen": 29078309,
|
| 1881 |
+
"step": 1170
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"epoch": 27.246376811594203,
|
| 1885 |
+
"grad_norm": 0.11428932845592499,
|
| 1886 |
+
"learning_rate": 5.700628727643806e-06,
|
| 1887 |
+
"loss": 0.002,
|
| 1888 |
+
"num_input_tokens_seen": 29211503,
|
| 1889 |
+
"step": 1175
|
| 1890 |
+
},
|
| 1891 |
+
{
|
| 1892 |
+
"epoch": 27.36231884057971,
|
| 1893 |
+
"grad_norm": 0.1093268170952797,
|
| 1894 |
+
"learning_rate": 5.53582219988382e-06,
|
| 1895 |
+
"loss": 0.0019,
|
| 1896 |
+
"num_input_tokens_seen": 29344489,
|
| 1897 |
+
"step": 1180
|
| 1898 |
+
},
|
| 1899 |
+
{
|
| 1900 |
+
"epoch": 27.47826086956522,
|
| 1901 |
+
"grad_norm": 0.2166384607553482,
|
| 1902 |
+
"learning_rate": 5.373135979747227e-06,
|
| 1903 |
+
"loss": 0.006,
|
| 1904 |
+
"num_input_tokens_seen": 29464082,
|
| 1905 |
+
"step": 1185
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 27.594202898550726,
|
| 1909 |
+
"grad_norm": 0.15387850999832153,
|
| 1910 |
+
"learning_rate": 5.2125877892686496e-06,
|
| 1911 |
+
"loss": 0.0043,
|
| 1912 |
+
"num_input_tokens_seen": 29581124,
|
| 1913 |
+
"step": 1190
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 27.71014492753623,
|
| 1917 |
+
"grad_norm": 0.11962082982063293,
|
| 1918 |
+
"learning_rate": 5.054195117578914e-06,
|
| 1919 |
+
"loss": 0.0019,
|
| 1920 |
+
"num_input_tokens_seen": 29696346,
|
| 1921 |
+
"step": 1195
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 27.82608695652174,
|
| 1925 |
+
"grad_norm": 0.18724732100963593,
|
| 1926 |
+
"learning_rate": 4.897975218999926e-06,
|
| 1927 |
+
"loss": 0.002,
|
| 1928 |
+
"num_input_tokens_seen": 29815117,
|
| 1929 |
+
"step": 1200
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 27.942028985507246,
|
| 1933 |
+
"grad_norm": 0.09917350113391876,
|
| 1934 |
+
"learning_rate": 4.743945111165068e-06,
|
| 1935 |
+
"loss": 0.0022,
|
| 1936 |
+
"num_input_tokens_seen": 29939175,
|
| 1937 |
+
"step": 1205
|
| 1938 |
+
},
|
| 1939 |
+
{
|
| 1940 |
+
"epoch": 28.057971014492754,
|
| 1941 |
+
"grad_norm": 0.08235369622707367,
|
| 1942 |
+
"learning_rate": 4.592121573165414e-06,
|
| 1943 |
+
"loss": 0.0016,
|
| 1944 |
+
"num_input_tokens_seen": 30079840,
|
| 1945 |
+
"step": 1210
|
| 1946 |
+
},
|
| 1947 |
+
{
|
| 1948 |
+
"epoch": 28.17391304347826,
|
| 1949 |
+
"grad_norm": 0.20488996803760529,
|
| 1950 |
+
"learning_rate": 4.442521143721892e-06,
|
| 1951 |
+
"loss": 0.0033,
|
| 1952 |
+
"num_input_tokens_seen": 30192219,
|
| 1953 |
+
"step": 1215
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"epoch": 28.28985507246377,
|
| 1957 |
+
"grad_norm": 0.05383768677711487,
|
| 1958 |
+
"learning_rate": 4.295160119383712e-06,
|
| 1959 |
+
"loss": 0.0018,
|
| 1960 |
+
"num_input_tokens_seen": 30330969,
|
| 1961 |
+
"step": 1220
|
| 1962 |
+
},
|
| 1963 |
+
{
|
| 1964 |
+
"epoch": 28.405797101449274,
|
| 1965 |
+
"grad_norm": 0.14237363636493683,
|
| 1966 |
+
"learning_rate": 4.150054552753055e-06,
|
| 1967 |
+
"loss": 0.0018,
|
| 1968 |
+
"num_input_tokens_seen": 30453302,
|
| 1969 |
+
"step": 1225
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 28.52173913043478,
|
| 1973 |
+
"grad_norm": 0.12487669289112091,
|
| 1974 |
+
"learning_rate": 4.007220250736454e-06,
|
| 1975 |
+
"loss": 0.0078,
|
| 1976 |
+
"num_input_tokens_seen": 30568943,
|
| 1977 |
+
"step": 1230
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 28.63768115942029,
|
| 1981 |
+
"grad_norm": 0.1423855572938919,
|
| 1982 |
+
"learning_rate": 3.866672772822863e-06,
|
| 1983 |
+
"loss": 0.0019,
|
| 1984 |
+
"num_input_tokens_seen": 30696057,
|
| 1985 |
+
"step": 1235
|
| 1986 |
+
},
|
| 1987 |
+
{
|
| 1988 |
+
"epoch": 28.753623188405797,
|
| 1989 |
+
"grad_norm": 0.1543101817369461,
|
| 1990 |
+
"learning_rate": 3.7284274293887115e-06,
|
| 1991 |
+
"loss": 0.0019,
|
| 1992 |
+
"num_input_tokens_seen": 30815506,
|
| 1993 |
+
"step": 1240
|
| 1994 |
+
},
|
| 1995 |
+
{
|
| 1996 |
+
"epoch": 28.869565217391305,
|
| 1997 |
+
"grad_norm": 0.1402539610862732,
|
| 1998 |
+
"learning_rate": 3.592499280030057e-06,
|
| 1999 |
+
"loss": 0.0027,
|
| 2000 |
+
"num_input_tokens_seen": 30916446,
|
| 2001 |
+
"step": 1245
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 28.985507246376812,
|
| 2005 |
+
"grad_norm": 0.26191645860671997,
|
| 2006 |
+
"learning_rate": 3.458903131922134e-06,
|
| 2007 |
+
"loss": 0.0023,
|
| 2008 |
+
"num_input_tokens_seen": 31054242,
|
| 2009 |
+
"step": 1250
|
| 2010 |
+
},
|
| 2011 |
+
{
|
| 2012 |
+
"epoch": 29.10144927536232,
|
| 2013 |
+
"grad_norm": 0.09874732792377472,
|
| 2014 |
+
"learning_rate": 3.3276535382063213e-06,
|
| 2015 |
+
"loss": 0.0029,
|
| 2016 |
+
"num_input_tokens_seen": 31189078,
|
| 2017 |
+
"step": 1255
|
| 2018 |
+
},
|
| 2019 |
+
{
|
| 2020 |
+
"epoch": 29.217391304347824,
|
| 2021 |
+
"grad_norm": 0.11677820980548859,
|
| 2022 |
+
"learning_rate": 3.198764796404807e-06,
|
| 2023 |
+
"loss": 0.0018,
|
| 2024 |
+
"num_input_tokens_seen": 31311374,
|
| 2025 |
+
"step": 1260
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 29.333333333333332,
|
| 2029 |
+
"grad_norm": 0.05459802597761154,
|
| 2030 |
+
"learning_rate": 3.0722509468631392e-06,
|
| 2031 |
+
"loss": 0.0018,
|
| 2032 |
+
"num_input_tokens_seen": 31444681,
|
| 2033 |
+
"step": 1265
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 29.44927536231884,
|
| 2037 |
+
"grad_norm": 0.1113714948296547,
|
| 2038 |
+
"learning_rate": 2.948125771220697e-06,
|
| 2039 |
+
"loss": 0.0018,
|
| 2040 |
+
"num_input_tokens_seen": 31567569,
|
| 2041 |
+
"step": 1270
|
| 2042 |
+
},
|
| 2043 |
+
{
|
| 2044 |
+
"epoch": 29.565217391304348,
|
| 2045 |
+
"grad_norm": 0.1816156655550003,
|
| 2046 |
+
"learning_rate": 2.8264027909094715e-06,
|
| 2047 |
+
"loss": 0.0019,
|
| 2048 |
+
"num_input_tokens_seen": 31697338,
|
| 2049 |
+
"step": 1275
|
| 2050 |
+
},
|
| 2051 |
+
{
|
| 2052 |
+
"epoch": 29.681159420289855,
|
| 2053 |
+
"grad_norm": 0.13639949262142181,
|
| 2054 |
+
"learning_rate": 2.707095265681081e-06,
|
| 2055 |
+
"loss": 0.0018,
|
| 2056 |
+
"num_input_tokens_seen": 31826661,
|
| 2057 |
+
"step": 1280
|
| 2058 |
+
},
|
| 2059 |
+
{
|
| 2060 |
+
"epoch": 29.797101449275363,
|
| 2061 |
+
"grad_norm": 0.05292365327477455,
|
| 2062 |
+
"learning_rate": 2.5902161921623454e-06,
|
| 2063 |
+
"loss": 0.0023,
|
| 2064 |
+
"num_input_tokens_seen": 31944680,
|
| 2065 |
+
"step": 1285
|
| 2066 |
+
},
|
| 2067 |
+
{
|
| 2068 |
+
"epoch": 29.91304347826087,
|
| 2069 |
+
"grad_norm": 0.16608740389347076,
|
| 2070 |
+
"learning_rate": 2.475778302439524e-06,
|
| 2071 |
+
"loss": 0.0078,
|
| 2072 |
+
"num_input_tokens_seen": 32067106,
|
| 2073 |
+
"step": 1290
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 30.028985507246375,
|
| 2077 |
+
"grad_norm": 0.09277443587779999,
|
| 2078 |
+
"learning_rate": 2.3637940626713346e-06,
|
| 2079 |
+
"loss": 0.0018,
|
| 2080 |
+
"num_input_tokens_seen": 32184526,
|
| 2081 |
+
"step": 1295
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 30.144927536231883,
|
| 2085 |
+
"grad_norm": 0.18832191824913025,
|
| 2086 |
+
"learning_rate": 2.254275671731007e-06,
|
| 2087 |
+
"loss": 0.0017,
|
| 2088 |
+
"num_input_tokens_seen": 32309423,
|
| 2089 |
+
"step": 1300
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 30.26086956521739,
|
| 2093 |
+
"grad_norm": 0.1828456073999405,
|
| 2094 |
+
"learning_rate": 2.14723505987737e-06,
|
| 2095 |
+
"loss": 0.0071,
|
| 2096 |
+
"num_input_tokens_seen": 32429445,
|
| 2097 |
+
"step": 1305
|
| 2098 |
+
},
|
| 2099 |
+
{
|
| 2100 |
+
"epoch": 30.3768115942029,
|
| 2101 |
+
"grad_norm": 0.07503814995288849,
|
| 2102 |
+
"learning_rate": 2.0426838874552714e-06,
|
| 2103 |
+
"loss": 0.0016,
|
| 2104 |
+
"num_input_tokens_seen": 32540571,
|
| 2105 |
+
"step": 1310
|
| 2106 |
+
},
|
| 2107 |
+
{
|
| 2108 |
+
"epoch": 30.492753623188406,
|
| 2109 |
+
"grad_norm": 0.19047732651233673,
|
| 2110 |
+
"learning_rate": 1.9406335436253724e-06,
|
| 2111 |
+
"loss": 0.0018,
|
| 2112 |
+
"num_input_tokens_seen": 32665528,
|
| 2113 |
+
"step": 1315
|
| 2114 |
+
},
|
| 2115 |
+
{
|
| 2116 |
+
"epoch": 30.608695652173914,
|
| 2117 |
+
"grad_norm": 0.17791509628295898,
|
| 2118 |
+
"learning_rate": 1.8410951451234533e-06,
|
| 2119 |
+
"loss": 0.0017,
|
| 2120 |
+
"num_input_tokens_seen": 32800773,
|
| 2121 |
+
"step": 1320
|
| 2122 |
+
},
|
| 2123 |
+
{
|
| 2124 |
+
"epoch": 30.72463768115942,
|
| 2125 |
+
"grad_norm": 0.10698456317186356,
|
| 2126 |
+
"learning_rate": 1.7440795350494588e-06,
|
| 2127 |
+
"loss": 0.0017,
|
| 2128 |
+
"num_input_tokens_seen": 32928397,
|
| 2129 |
+
"step": 1325
|
| 2130 |
+
},
|
| 2131 |
+
{
|
| 2132 |
+
"epoch": 30.840579710144926,
|
| 2133 |
+
"grad_norm": 0.0963551327586174,
|
| 2134 |
+
"learning_rate": 1.649597281686302e-06,
|
| 2135 |
+
"loss": 0.0019,
|
| 2136 |
+
"num_input_tokens_seen": 33054819,
|
| 2137 |
+
"step": 1330
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 30.956521739130434,
|
| 2141 |
+
"grad_norm": 0.24703514575958252,
|
| 2142 |
+
"learning_rate": 1.5576586773486195e-06,
|
| 2143 |
+
"loss": 0.0018,
|
| 2144 |
+
"num_input_tokens_seen": 33180616,
|
| 2145 |
+
"step": 1335
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 31.07246376811594,
|
| 2149 |
+
"grad_norm": 0.12497910857200623,
|
| 2150 |
+
"learning_rate": 1.4682737372615967e-06,
|
| 2151 |
+
"loss": 0.0038,
|
| 2152 |
+
"num_input_tokens_seen": 33298041,
|
| 2153 |
+
"step": 1340
|
| 2154 |
+
},
|
| 2155 |
+
{
|
| 2156 |
+
"epoch": 31.18840579710145,
|
| 2157 |
+
"grad_norm": 0.18260960280895233,
|
| 2158 |
+
"learning_rate": 1.3814521984699596e-06,
|
| 2159 |
+
"loss": 0.0052,
|
| 2160 |
+
"num_input_tokens_seen": 33408343,
|
| 2161 |
+
"step": 1345
|
| 2162 |
+
},
|
| 2163 |
+
{
|
| 2164 |
+
"epoch": 31.304347826086957,
|
| 2165 |
+
"grad_norm": 0.13422255218029022,
|
| 2166 |
+
"learning_rate": 1.297203518777293e-06,
|
| 2167 |
+
"loss": 0.0018,
|
| 2168 |
+
"num_input_tokens_seen": 33545364,
|
| 2169 |
+
"step": 1350
|
| 2170 |
+
},
|
| 2171 |
+
{
|
| 2172 |
+
"epoch": 31.420289855072465,
|
| 2173 |
+
"grad_norm": 0.1285027116537094,
|
| 2174 |
+
"learning_rate": 1.2155368757157643e-06,
|
| 2175 |
+
"loss": 0.0019,
|
| 2176 |
+
"num_input_tokens_seen": 33652900,
|
| 2177 |
+
"step": 1355
|
| 2178 |
+
},
|
| 2179 |
+
{
|
| 2180 |
+
"epoch": 31.536231884057973,
|
| 2181 |
+
"grad_norm": 0.12832242250442505,
|
| 2182 |
+
"learning_rate": 1.1364611655463736e-06,
|
| 2183 |
+
"loss": 0.0019,
|
| 2184 |
+
"num_input_tokens_seen": 33768791,
|
| 2185 |
+
"step": 1360
|
| 2186 |
+
},
|
| 2187 |
+
{
|
| 2188 |
+
"epoch": 31.652173913043477,
|
| 2189 |
+
"grad_norm": 0.12093157321214676,
|
| 2190 |
+
"learning_rate": 1.0599850022898539e-06,
|
| 2191 |
+
"loss": 0.0017,
|
| 2192 |
+
"num_input_tokens_seen": 33892837,
|
| 2193 |
+
"step": 1365
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 31.768115942028984,
|
| 2197 |
+
"grad_norm": 0.7227018475532532,
|
| 2198 |
+
"learning_rate": 9.861167167883046e-07,
|
| 2199 |
+
"loss": 0.0022,
|
| 2200 |
+
"num_input_tokens_seen": 34015288,
|
| 2201 |
+
"step": 1370
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 31.884057971014492,
|
| 2205 |
+
"grad_norm": 2.143653631210327,
|
| 2206 |
+
"learning_rate": 9.148643557976955e-07,
|
| 2207 |
+
"loss": 0.0037,
|
| 2208 |
+
"num_input_tokens_seen": 34154884,
|
| 2209 |
+
"step": 1375
|
| 2210 |
+
},
|
| 2211 |
+
{
|
| 2212 |
+
"epoch": 32.0,
|
| 2213 |
+
"grad_norm": 0.17518474161624908,
|
| 2214 |
+
"learning_rate": 8.462356811112987e-07,
|
| 2215 |
+
"loss": 0.0019,
|
| 2216 |
+
"num_input_tokens_seen": 34292320,
|
| 2217 |
+
"step": 1380
|
| 2218 |
+
},
|
| 2219 |
+
{
|
| 2220 |
+
"epoch": 32.11594202898551,
|
| 2221 |
+
"grad_norm": 0.1274159997701645,
|
| 2222 |
+
"learning_rate": 7.802381687141535e-07,
|
| 2223 |
+
"loss": 0.0017,
|
| 2224 |
+
"num_input_tokens_seen": 34413850,
|
| 2225 |
+
"step": 1385
|
| 2226 |
+
},
|
| 2227 |
+
{
|
| 2228 |
+
"epoch": 32.231884057971016,
|
| 2229 |
+
"grad_norm": 0.11443401873111725,
|
| 2230 |
+
"learning_rate": 7.168790079686932e-07,
|
| 2231 |
+
"loss": 0.0018,
|
| 2232 |
+
"num_input_tokens_seen": 34547127,
|
| 2233 |
+
"step": 1390
|
| 2234 |
+
},
|
| 2235 |
+
{
|
| 2236 |
+
"epoch": 32.34782608695652,
|
| 2237 |
+
"grad_norm": 0.08239752799272537,
|
| 2238 |
+
"learning_rate": 6.561651008315738e-07,
|
| 2239 |
+
"loss": 0.0035,
|
| 2240 |
+
"num_input_tokens_seen": 34685112,
|
| 2241 |
+
"step": 1395
|
| 2242 |
+
},
|
| 2243 |
+
{
|
| 2244 |
+
"epoch": 32.46376811594203,
|
| 2245 |
+
"grad_norm": 0.7361220717430115,
|
| 2246 |
+
"learning_rate": 5.981030611018234e-07,
|
| 2247 |
+
"loss": 0.0063,
|
| 2248 |
+
"num_input_tokens_seen": 34810484,
|
| 2249 |
+
"step": 1400
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 32.57971014492754,
|
| 2253 |
+
"grad_norm": 0.20323431491851807,
|
| 2254 |
+
"learning_rate": 5.426992137003622e-07,
|
| 2255 |
+
"loss": 0.0018,
|
| 2256 |
+
"num_input_tokens_seen": 34920531,
|
| 2257 |
+
"step": 1405
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 32.69565217391305,
|
| 2261 |
+
"grad_norm": 0.11165229231119156,
|
| 2262 |
+
"learning_rate": 4.899595939810236e-07,
|
| 2263 |
+
"loss": 0.002,
|
| 2264 |
+
"num_input_tokens_seen": 35035657,
|
| 2265 |
+
"step": 1410
|
| 2266 |
+
},
|
| 2267 |
+
{
|
| 2268 |
+
"epoch": 32.81159420289855,
|
| 2269 |
+
"grad_norm": 0.15023387968540192,
|
| 2270 |
+
"learning_rate": 4.398899470730827e-07,
|
| 2271 |
+
"loss": 0.0017,
|
| 2272 |
+
"num_input_tokens_seen": 35167466,
|
| 2273 |
+
"step": 1415
|
| 2274 |
+
},
|
| 2275 |
+
{
|
| 2276 |
+
"epoch": 32.927536231884055,
|
| 2277 |
+
"grad_norm": 0.18479810655117035,
|
| 2278 |
+
"learning_rate": 3.9249572725543196e-07,
|
| 2279 |
+
"loss": 0.0016,
|
| 2280 |
+
"num_input_tokens_seen": 35296818,
|
| 2281 |
+
"step": 1420
|
| 2282 |
+
},
|
| 2283 |
+
{
|
| 2284 |
+
"epoch": 33.04347826086956,
|
| 2285 |
+
"grad_norm": 0.08527754247188568,
|
| 2286 |
+
"learning_rate": 3.477820973624063e-07,
|
| 2287 |
+
"loss": 0.0015,
|
| 2288 |
+
"num_input_tokens_seen": 35430399,
|
| 2289 |
+
"step": 1425
|
| 2290 |
+
},
|
| 2291 |
+
{
|
| 2292 |
+
"epoch": 33.15942028985507,
|
| 2293 |
+
"grad_norm": 0.16888481378555298,
|
| 2294 |
+
"learning_rate": 3.0575392822139726e-07,
|
| 2295 |
+
"loss": 0.0057,
|
| 2296 |
+
"num_input_tokens_seen": 35551540,
|
| 2297 |
+
"step": 1430
|
| 2298 |
+
},
|
| 2299 |
+
{
|
| 2300 |
+
"epoch": 33.27536231884058,
|
| 2301 |
+
"grad_norm": 0.18187086284160614,
|
| 2302 |
+
"learning_rate": 2.664157981222437e-07,
|
| 2303 |
+
"loss": 0.0016,
|
| 2304 |
+
"num_input_tokens_seen": 35676077,
|
| 2305 |
+
"step": 1435
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 33.391304347826086,
|
| 2309 |
+
"grad_norm": 0.15047162771224976,
|
| 2310 |
+
"learning_rate": 2.297719923185032e-07,
|
| 2311 |
+
"loss": 0.0016,
|
| 2312 |
+
"num_input_tokens_seen": 35785127,
|
| 2313 |
+
"step": 1440
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 33.507246376811594,
|
| 2317 |
+
"grad_norm": 0.12288761883974075,
|
| 2318 |
+
"learning_rate": 1.9582650256064205e-07,
|
| 2319 |
+
"loss": 0.0019,
|
| 2320 |
+
"num_input_tokens_seen": 35911682,
|
| 2321 |
+
"step": 1445
|
| 2322 |
+
},
|
| 2323 |
+
{
|
| 2324 |
+
"epoch": 33.6231884057971,
|
| 2325 |
+
"grad_norm": 0.22509098052978516,
|
| 2326 |
+
"learning_rate": 1.645830266611914e-07,
|
| 2327 |
+
"loss": 0.0017,
|
| 2328 |
+
"num_input_tokens_seen": 36030754,
|
| 2329 |
+
"step": 1450
|
| 2330 |
+
},
|
| 2331 |
+
{
|
| 2332 |
+
"epoch": 33.73913043478261,
|
| 2333 |
+
"grad_norm": 2.0408618450164795,
|
| 2334 |
+
"learning_rate": 1.3604496809195288e-07,
|
| 2335 |
+
"loss": 0.0042,
|
| 2336 |
+
"num_input_tokens_seen": 36146749,
|
| 2337 |
+
"step": 1455
|
| 2338 |
+
},
|
| 2339 |
+
{
|
| 2340 |
+
"epoch": 33.85507246376812,
|
| 2341 |
+
"grad_norm": 0.10705255717039108,
|
| 2342 |
+
"learning_rate": 1.1021543561322012e-07,
|
| 2343 |
+
"loss": 0.0017,
|
| 2344 |
+
"num_input_tokens_seen": 36278454,
|
| 2345 |
+
"step": 1460
|
| 2346 |
+
},
|
| 2347 |
+
{
|
| 2348 |
+
"epoch": 33.971014492753625,
|
| 2349 |
+
"grad_norm": 1876.0384521484375,
|
| 2350 |
+
"learning_rate": 8.709724293513854e-08,
|
| 2351 |
+
"loss": 0.0017,
|
| 2352 |
+
"num_input_tokens_seen": 36408834,
|
| 2353 |
+
"step": 1465
|
| 2354 |
+
},
|
| 2355 |
+
{
|
| 2356 |
+
"epoch": 34.08695652173913,
|
| 2357 |
+
"grad_norm": 0.1927630454301834,
|
| 2358 |
+
"learning_rate": 6.66929084112089e-08,
|
| 2359 |
+
"loss": 0.0015,
|
| 2360 |
+
"num_input_tokens_seen": 36550538,
|
| 2361 |
+
"step": 1470
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 34.20289855072464,
|
| 2365 |
+
"grad_norm": 0.1668202131986618,
|
| 2366 |
+
"learning_rate": 4.900465476393168e-08,
|
| 2367 |
+
"loss": 0.0018,
|
| 2368 |
+
"num_input_tokens_seen": 36647436,
|
| 2369 |
+
"step": 1475
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 34.31884057971015,
|
| 2373 |
+
"grad_norm": 0.7123565673828125,
|
| 2374 |
+
"learning_rate": 3.403440884269526e-08,
|
| 2375 |
+
"loss": 0.0024,
|
| 2376 |
+
"num_input_tokens_seen": 36785387,
|
| 2377 |
+
"step": 1480
|
| 2378 |
+
},
|
| 2379 |
+
{
|
| 2380 |
+
"epoch": 34.43478260869565,
|
| 2381 |
+
"grad_norm": 0.16973845660686493,
|
| 2382 |
+
"learning_rate": 2.1783801413866046e-08,
|
| 2383 |
+
"loss": 0.0021,
|
| 2384 |
+
"num_input_tokens_seen": 36915606,
|
| 2385 |
+
"step": 1485
|
| 2386 |
+
},
|
| 2387 |
+
{
|
| 2388 |
+
"epoch": 34.55072463768116,
|
| 2389 |
+
"grad_norm": 2.034724473953247,
|
| 2390 |
+
"learning_rate": 1.2254166983152737e-08,
|
| 2391 |
+
"loss": 0.0035,
|
| 2392 |
+
"num_input_tokens_seen": 37036117,
|
| 2393 |
+
"step": 1490
|
| 2394 |
+
},
|
| 2395 |
+
{
|
| 2396 |
+
"epoch": 34.666666666666664,
|
| 2397 |
+
"grad_norm": 0.155415877699852,
|
| 2398 |
+
"learning_rate": 5.446543650219904e-09,
|
| 2399 |
+
"loss": 0.0016,
|
| 2400 |
+
"num_input_tokens_seen": 37165587,
|
| 2401 |
+
"step": 1495
|
| 2402 |
+
},
|
| 2403 |
+
{
|
| 2404 |
+
"epoch": 34.78260869565217,
|
| 2405 |
+
"grad_norm": 0.10199662297964096,
|
| 2406 |
+
"learning_rate": 1.3616729956228425e-09,
|
| 2407 |
+
"loss": 0.0015,
|
| 2408 |
+
"num_input_tokens_seen": 37290827,
|
| 2409 |
+
"step": 1500
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 34.89855072463768,
|
| 2413 |
+
"grad_norm": 0.14740267395973206,
|
| 2414 |
+
"learning_rate": 0.0,
|
| 2415 |
+
"loss": 0.0053,
|
| 2416 |
+
"num_input_tokens_seen": 37412688,
|
| 2417 |
+
"step": 1505
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 34.89855072463768,
|
| 2421 |
+
"num_input_tokens_seen": 37412688,
|
| 2422 |
+
"step": 1505,
|
| 2423 |
+
"total_flos": 8.033958240027034e+16,
|
| 2424 |
+
"train_loss": 0.3889684765070578,
|
| 2425 |
+
"train_runtime": 37510.9602,
|
| 2426 |
+
"train_samples_per_second": 0.322,
|
| 2427 |
+
"train_steps_per_second": 0.04
|
| 2428 |
+
}
|
| 2429 |
+
],
|
| 2430 |
+
"logging_steps": 5,
|
| 2431 |
+
"max_steps": 1505,
|
| 2432 |
+
"num_input_tokens_seen": 37412688,
|
| 2433 |
+
"num_train_epochs": 35,
|
| 2434 |
+
"save_steps": 100,
|
| 2435 |
+
"stateful_callbacks": {
|
| 2436 |
+
"TrainerControl": {
|
| 2437 |
+
"args": {
|
| 2438 |
+
"should_epoch_stop": false,
|
| 2439 |
+
"should_evaluate": false,
|
| 2440 |
+
"should_log": false,
|
| 2441 |
+
"should_save": true,
|
| 2442 |
+
"should_training_stop": false
|
| 2443 |
+
},
|
| 2444 |
+
"attributes": {}
|
| 2445 |
+
}
|
| 2446 |
+
},
|
| 2447 |
+
"total_flos": 8.033958240027034e+16,
|
| 2448 |
+
"train_batch_size": 1,
|
| 2449 |
+
"trial_name": null,
|
| 2450 |
+
"trial_params": null
|
| 2451 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d1bf7e450e4a6d37229f59b5902ed4c9f65d4b8a73fe748056cfd0dc9b1d2f6
|
| 3 |
+
size 5304
|
training_args.yaml
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
cutoff_len: 6100
|
| 2 |
+
dataset: longzu
|
| 3 |
+
dataset_dir: C:\AI\LLaMA-Factory\data
|
| 4 |
+
ddp_timeout: 180000000
|
| 5 |
+
do_train: true
|
| 6 |
+
finetuning_type: full
|
| 7 |
+
flash_attn: auto
|
| 8 |
+
gradient_accumulation_steps: 8
|
| 9 |
+
include_num_input_tokens_seen: true
|
| 10 |
+
learning_rate: 5.0e-05
|
| 11 |
+
logging_steps: 5
|
| 12 |
+
lr_scheduler_type: cosine
|
| 13 |
+
max_grad_norm: 1.0
|
| 14 |
+
max_samples: 100000
|
| 15 |
+
model_name_or_path: C:\AI\Qwen2_0.5B
|
| 16 |
+
num_train_epochs: 35.0
|
| 17 |
+
optim: adamw_torch
|
| 18 |
+
output_dir: saves\Qwen2-0.5B\full\train_2024-06-08-23-23-14
|
| 19 |
+
packing: false
|
| 20 |
+
per_device_train_batch_size: 1
|
| 21 |
+
plot_loss: true
|
| 22 |
+
preprocessing_num_workers: 16
|
| 23 |
+
report_to: none
|
| 24 |
+
save_steps: 100
|
| 25 |
+
stage: pt
|
| 26 |
+
template: default
|
| 27 |
+
warmup_steps: 0
|
training_loss.png
ADDED
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|