Upload folder using huggingface_hub
Browse files- README.md +96 -0
- config.json +37 -0
- model.safetensors +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +219 -0
- trainer_state.json +1518 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: kykim0/pythia-1b-tulu-v2-mix
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
datasets:
|
| 8 |
+
- allenai/ultrafeedback_binarized_cleaned
|
| 9 |
+
metrics:
|
| 10 |
+
- accuracy
|
| 11 |
+
model-index:
|
| 12 |
+
- name: b32-lr1.41e-05-s0-e2-btbinf-seed42
|
| 13 |
+
results:
|
| 14 |
+
- task:
|
| 15 |
+
name: Text Classification
|
| 16 |
+
type: text-classification
|
| 17 |
+
dataset:
|
| 18 |
+
name: allenai/ultrafeedback_binarized_cleaned
|
| 19 |
+
type: allenai/ultrafeedback_binarized_cleaned
|
| 20 |
+
metrics:
|
| 21 |
+
- name: Accuracy
|
| 22 |
+
type: accuracy
|
| 23 |
+
value: 0.7427109974424553
|
| 24 |
+
---
|
| 25 |
+
|
| 26 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 27 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 28 |
+
|
| 29 |
+
# b32-lr1.41e-05-s0-e2-btbinf-seed42
|
| 30 |
+
|
| 31 |
+
This model is a fine-tuned version of [kykim0/pythia-1b-tulu-v2-mix](https://huggingface.co/kykim0/pythia-1b-tulu-v2-mix) on the allenai/ultrafeedback_binarized_cleaned dataset.
|
| 32 |
+
It achieves the following results on the evaluation set:
|
| 33 |
+
- Loss: 0.5040
|
| 34 |
+
- Accuracy: 0.7458
|
| 35 |
+
|
| 36 |
+
## Model description
|
| 37 |
+
|
| 38 |
+
More information needed
|
| 39 |
+
|
| 40 |
+
## Intended uses & limitations
|
| 41 |
+
|
| 42 |
+
More information needed
|
| 43 |
+
|
| 44 |
+
## Training and evaluation data
|
| 45 |
+
|
| 46 |
+
More information needed
|
| 47 |
+
|
| 48 |
+
## Training procedure
|
| 49 |
+
|
| 50 |
+
### Training hyperparameters
|
| 51 |
+
|
| 52 |
+
The following hyperparameters were used during training:
|
| 53 |
+
- learning_rate: 1.41e-05
|
| 54 |
+
- train_batch_size: 1
|
| 55 |
+
- eval_batch_size: 8
|
| 56 |
+
- seed: 42
|
| 57 |
+
- distributed_type: multi-GPU
|
| 58 |
+
- num_devices: 4
|
| 59 |
+
- gradient_accumulation_steps: 8
|
| 60 |
+
- total_train_batch_size: 32
|
| 61 |
+
- total_eval_batch_size: 32
|
| 62 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 63 |
+
- lr_scheduler_type: linear
|
| 64 |
+
- num_epochs: 1
|
| 65 |
+
|
| 66 |
+
### Training results
|
| 67 |
+
|
| 68 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 69 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|
|
| 70 |
+
| 0.6627 | 0.0527 | 100 | 0.6306 | 0.6675 |
|
| 71 |
+
| 0.5604 | 0.1055 | 200 | 0.5954 | 0.6890 |
|
| 72 |
+
| 0.5743 | 0.1582 | 300 | 0.5773 | 0.6880 |
|
| 73 |
+
| 0.573 | 0.2110 | 400 | 0.5408 | 0.7182 |
|
| 74 |
+
| 0.5644 | 0.2637 | 500 | 0.5285 | 0.7361 |
|
| 75 |
+
| 0.5482 | 0.3165 | 600 | 0.5251 | 0.7366 |
|
| 76 |
+
| 0.5673 | 0.3692 | 700 | 0.5267 | 0.7279 |
|
| 77 |
+
| 0.5701 | 0.4219 | 800 | 0.5123 | 0.7453 |
|
| 78 |
+
| 0.5199 | 0.4747 | 900 | 0.5148 | 0.7376 |
|
| 79 |
+
| 0.5525 | 0.5274 | 1000 | 0.5133 | 0.7494 |
|
| 80 |
+
| 0.5197 | 0.5802 | 1100 | 0.5085 | 0.7488 |
|
| 81 |
+
| 0.4977 | 0.6329 | 1200 | 0.5146 | 0.7412 |
|
| 82 |
+
| 0.492 | 0.6857 | 1300 | 0.5116 | 0.7417 |
|
| 83 |
+
| 0.5046 | 0.7384 | 1400 | 0.5069 | 0.7453 |
|
| 84 |
+
| 0.5476 | 0.7911 | 1500 | 0.5044 | 0.7478 |
|
| 85 |
+
| 0.5247 | 0.8439 | 1600 | 0.5038 | 0.7468 |
|
| 86 |
+
| 0.5591 | 0.8966 | 1700 | 0.5079 | 0.7453 |
|
| 87 |
+
| 0.5228 | 0.9494 | 1800 | 0.5040 | 0.7458 |
|
| 88 |
+
| 0.5336 | 1.0021 | 1900 | 0.5045 | 0.7488 |
|
| 89 |
+
|
| 90 |
+
|
| 91 |
+
### Framework versions
|
| 92 |
+
|
| 93 |
+
- Transformers 4.44.2
|
| 94 |
+
- Pytorch 2.1.2+cu121
|
| 95 |
+
- Datasets 2.14.6
|
| 96 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "kykim0/pythia-1b-tulu-v2-mix",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPTNeoXForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": true,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"classifier_dropout": 0.1,
|
| 10 |
+
"eos_token_id": 0,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout": 0.0,
|
| 13 |
+
"hidden_size": 2048,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "LABEL_0"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 8192,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"LABEL_0": 0
|
| 21 |
+
},
|
| 22 |
+
"layer_norm_eps": 1e-05,
|
| 23 |
+
"max_position_embeddings": 2048,
|
| 24 |
+
"model_type": "gpt_neox",
|
| 25 |
+
"num_attention_heads": 8,
|
| 26 |
+
"num_hidden_layers": 16,
|
| 27 |
+
"pad_token_id": 1,
|
| 28 |
+
"rope_scaling": null,
|
| 29 |
+
"rotary_emb_base": 10000,
|
| 30 |
+
"rotary_pct": 0.25,
|
| 31 |
+
"tie_word_embeddings": false,
|
| 32 |
+
"torch_dtype": "bfloat16",
|
| 33 |
+
"transformers_version": "4.44.2",
|
| 34 |
+
"use_cache": false,
|
| 35 |
+
"use_parallel_residual": true,
|
| 36 |
+
"vocab_size": 50304
|
| 37 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d5e03ef03e2826ad8c3137e282404ffc28ed6c1d803095099beef0be1373743
|
| 3 |
+
size 1817545248
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|padding|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,219 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": false,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<|endoftext|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<|padding|>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"50254": {
|
| 23 |
+
"content": " ",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": true,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"50255": {
|
| 31 |
+
"content": " ",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": false
|
| 37 |
+
},
|
| 38 |
+
"50256": {
|
| 39 |
+
"content": " ",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": true,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
},
|
| 46 |
+
"50257": {
|
| 47 |
+
"content": " ",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": true,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
+
},
|
| 54 |
+
"50258": {
|
| 55 |
+
"content": " ",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": true,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"50259": {
|
| 63 |
+
"content": " ",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": true,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": false
|
| 69 |
+
},
|
| 70 |
+
"50260": {
|
| 71 |
+
"content": " ",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": true,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": false
|
| 77 |
+
},
|
| 78 |
+
"50261": {
|
| 79 |
+
"content": " ",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": true,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": false
|
| 85 |
+
},
|
| 86 |
+
"50262": {
|
| 87 |
+
"content": " ",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": true,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": false
|
| 93 |
+
},
|
| 94 |
+
"50263": {
|
| 95 |
+
"content": " ",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": true,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": false
|
| 101 |
+
},
|
| 102 |
+
"50264": {
|
| 103 |
+
"content": " ",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": true,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": false
|
| 109 |
+
},
|
| 110 |
+
"50265": {
|
| 111 |
+
"content": " ",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": true,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": false
|
| 117 |
+
},
|
| 118 |
+
"50266": {
|
| 119 |
+
"content": " ",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": true,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": false
|
| 125 |
+
},
|
| 126 |
+
"50267": {
|
| 127 |
+
"content": " ",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": true,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"50268": {
|
| 135 |
+
"content": " ",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": true,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"50269": {
|
| 143 |
+
"content": " ",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": true,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"50270": {
|
| 151 |
+
"content": " ",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": true,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"50271": {
|
| 159 |
+
"content": " ",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": true,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"50272": {
|
| 167 |
+
"content": " ",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": true,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"50273": {
|
| 175 |
+
"content": " ",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": true,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": false
|
| 181 |
+
},
|
| 182 |
+
"50274": {
|
| 183 |
+
"content": " ",
|
| 184 |
+
"lstrip": false,
|
| 185 |
+
"normalized": true,
|
| 186 |
+
"rstrip": false,
|
| 187 |
+
"single_word": false,
|
| 188 |
+
"special": false
|
| 189 |
+
},
|
| 190 |
+
"50275": {
|
| 191 |
+
"content": " ",
|
| 192 |
+
"lstrip": false,
|
| 193 |
+
"normalized": true,
|
| 194 |
+
"rstrip": false,
|
| 195 |
+
"single_word": false,
|
| 196 |
+
"special": false
|
| 197 |
+
},
|
| 198 |
+
"50276": {
|
| 199 |
+
"content": " ",
|
| 200 |
+
"lstrip": false,
|
| 201 |
+
"normalized": true,
|
| 202 |
+
"rstrip": false,
|
| 203 |
+
"single_word": false,
|
| 204 |
+
"special": false
|
| 205 |
+
}
|
| 206 |
+
},
|
| 207 |
+
"bos_token": "<|endoftext|>",
|
| 208 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
| 209 |
+
"clean_up_tokenization_spaces": true,
|
| 210 |
+
"eos_token": "<|endoftext|>",
|
| 211 |
+
"max_length": 2048,
|
| 212 |
+
"model_max_length": 2048,
|
| 213 |
+
"pad_token": "<|padding|>",
|
| 214 |
+
"stride": 0,
|
| 215 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
| 216 |
+
"truncation_side": "right",
|
| 217 |
+
"truncation_strategy": "longest_first",
|
| 218 |
+
"unk_token": "<|endoftext|>"
|
| 219 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1518 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 1896,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.005274261603375527,
|
| 13 |
+
"grad_norm": 43.75,
|
| 14 |
+
"learning_rate": 1.4062816455696203e-05,
|
| 15 |
+
"loss": 0.8954,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.010548523206751054,
|
| 20 |
+
"grad_norm": 29.0,
|
| 21 |
+
"learning_rate": 1.4025632911392405e-05,
|
| 22 |
+
"loss": 0.7418,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.015822784810126583,
|
| 27 |
+
"grad_norm": 27.5,
|
| 28 |
+
"learning_rate": 1.3988449367088608e-05,
|
| 29 |
+
"loss": 0.793,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.02109704641350211,
|
| 34 |
+
"grad_norm": 31.25,
|
| 35 |
+
"learning_rate": 1.395126582278481e-05,
|
| 36 |
+
"loss": 0.6991,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.026371308016877638,
|
| 41 |
+
"grad_norm": 26.625,
|
| 42 |
+
"learning_rate": 1.3914082278481013e-05,
|
| 43 |
+
"loss": 0.7284,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.03164556962025317,
|
| 48 |
+
"grad_norm": 32.75,
|
| 49 |
+
"learning_rate": 1.3876898734177215e-05,
|
| 50 |
+
"loss": 0.7174,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03691983122362869,
|
| 55 |
+
"grad_norm": 25.25,
|
| 56 |
+
"learning_rate": 1.3839715189873418e-05,
|
| 57 |
+
"loss": 0.7091,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.04219409282700422,
|
| 62 |
+
"grad_norm": 21.375,
|
| 63 |
+
"learning_rate": 1.3802531645569622e-05,
|
| 64 |
+
"loss": 0.6764,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.04746835443037975,
|
| 69 |
+
"grad_norm": 23.75,
|
| 70 |
+
"learning_rate": 1.3765348101265823e-05,
|
| 71 |
+
"loss": 0.6988,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.052742616033755275,
|
| 76 |
+
"grad_norm": 21.625,
|
| 77 |
+
"learning_rate": 1.3728164556962027e-05,
|
| 78 |
+
"loss": 0.6627,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.052742616033755275,
|
| 83 |
+
"eval_accuracy": 0.6675191815856778,
|
| 84 |
+
"eval_loss": 0.6305665969848633,
|
| 85 |
+
"eval_runtime": 31.833,
|
| 86 |
+
"eval_samples_per_second": 61.414,
|
| 87 |
+
"eval_steps_per_second": 1.948,
|
| 88 |
+
"step": 100
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.0580168776371308,
|
| 92 |
+
"grad_norm": 22.125,
|
| 93 |
+
"learning_rate": 1.3690981012658228e-05,
|
| 94 |
+
"loss": 0.5756,
|
| 95 |
+
"step": 110
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.06329113924050633,
|
| 99 |
+
"grad_norm": 17.5,
|
| 100 |
+
"learning_rate": 1.3653797468354432e-05,
|
| 101 |
+
"loss": 0.5999,
|
| 102 |
+
"step": 120
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.06856540084388185,
|
| 106 |
+
"grad_norm": 24.125,
|
| 107 |
+
"learning_rate": 1.3616613924050634e-05,
|
| 108 |
+
"loss": 0.6658,
|
| 109 |
+
"step": 130
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.07383966244725738,
|
| 113 |
+
"grad_norm": 17.5,
|
| 114 |
+
"learning_rate": 1.3579430379746835e-05,
|
| 115 |
+
"loss": 0.5995,
|
| 116 |
+
"step": 140
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.07911392405063292,
|
| 120 |
+
"grad_norm": 18.0,
|
| 121 |
+
"learning_rate": 1.354224683544304e-05,
|
| 122 |
+
"loss": 0.5795,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.08438818565400844,
|
| 127 |
+
"grad_norm": 14.75,
|
| 128 |
+
"learning_rate": 1.350506329113924e-05,
|
| 129 |
+
"loss": 0.5548,
|
| 130 |
+
"step": 160
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.08966244725738397,
|
| 134 |
+
"grad_norm": 16.125,
|
| 135 |
+
"learning_rate": 1.3467879746835444e-05,
|
| 136 |
+
"loss": 0.6347,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.0949367088607595,
|
| 141 |
+
"grad_norm": 17.0,
|
| 142 |
+
"learning_rate": 1.3430696202531645e-05,
|
| 143 |
+
"loss": 0.5786,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.10021097046413502,
|
| 148 |
+
"grad_norm": 16.625,
|
| 149 |
+
"learning_rate": 1.3393512658227849e-05,
|
| 150 |
+
"loss": 0.5929,
|
| 151 |
+
"step": 190
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.10548523206751055,
|
| 155 |
+
"grad_norm": 13.3125,
|
| 156 |
+
"learning_rate": 1.3356329113924052e-05,
|
| 157 |
+
"loss": 0.5604,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.10548523206751055,
|
| 162 |
+
"eval_accuracy": 0.689002557544757,
|
| 163 |
+
"eval_loss": 0.5953558087348938,
|
| 164 |
+
"eval_runtime": 31.9307,
|
| 165 |
+
"eval_samples_per_second": 61.226,
|
| 166 |
+
"eval_steps_per_second": 1.942,
|
| 167 |
+
"step": 200
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.11075949367088607,
|
| 171 |
+
"grad_norm": 12.3125,
|
| 172 |
+
"learning_rate": 1.3319145569620254e-05,
|
| 173 |
+
"loss": 0.5708,
|
| 174 |
+
"step": 210
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.1160337552742616,
|
| 178 |
+
"grad_norm": 20.625,
|
| 179 |
+
"learning_rate": 1.3281962025316456e-05,
|
| 180 |
+
"loss": 0.6226,
|
| 181 |
+
"step": 220
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.12130801687763713,
|
| 185 |
+
"grad_norm": 10.625,
|
| 186 |
+
"learning_rate": 1.3244778481012659e-05,
|
| 187 |
+
"loss": 0.5384,
|
| 188 |
+
"step": 230
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.12658227848101267,
|
| 192 |
+
"grad_norm": 14.5625,
|
| 193 |
+
"learning_rate": 1.3207594936708861e-05,
|
| 194 |
+
"loss": 0.6306,
|
| 195 |
+
"step": 240
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.13185654008438819,
|
| 199 |
+
"grad_norm": 12.0,
|
| 200 |
+
"learning_rate": 1.3170411392405064e-05,
|
| 201 |
+
"loss": 0.556,
|
| 202 |
+
"step": 250
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.1371308016877637,
|
| 206 |
+
"grad_norm": 11.0625,
|
| 207 |
+
"learning_rate": 1.3133227848101266e-05,
|
| 208 |
+
"loss": 0.5659,
|
| 209 |
+
"step": 260
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.14240506329113925,
|
| 213 |
+
"grad_norm": 14.3125,
|
| 214 |
+
"learning_rate": 1.3096044303797469e-05,
|
| 215 |
+
"loss": 0.6133,
|
| 216 |
+
"step": 270
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.14767932489451477,
|
| 220 |
+
"grad_norm": 15.125,
|
| 221 |
+
"learning_rate": 1.3058860759493671e-05,
|
| 222 |
+
"loss": 0.59,
|
| 223 |
+
"step": 280
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 0.1529535864978903,
|
| 227 |
+
"grad_norm": 12.9375,
|
| 228 |
+
"learning_rate": 1.3021677215189874e-05,
|
| 229 |
+
"loss": 0.5685,
|
| 230 |
+
"step": 290
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.15822784810126583,
|
| 234 |
+
"grad_norm": 13.25,
|
| 235 |
+
"learning_rate": 1.2984493670886076e-05,
|
| 236 |
+
"loss": 0.5743,
|
| 237 |
+
"step": 300
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.15822784810126583,
|
| 241 |
+
"eval_accuracy": 0.6879795396419437,
|
| 242 |
+
"eval_loss": 0.5773088932037354,
|
| 243 |
+
"eval_runtime": 31.9222,
|
| 244 |
+
"eval_samples_per_second": 61.243,
|
| 245 |
+
"eval_steps_per_second": 1.942,
|
| 246 |
+
"step": 300
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.16350210970464135,
|
| 250 |
+
"grad_norm": 12.0,
|
| 251 |
+
"learning_rate": 1.2947310126582279e-05,
|
| 252 |
+
"loss": 0.5435,
|
| 253 |
+
"step": 310
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.16877637130801687,
|
| 257 |
+
"grad_norm": 12.1875,
|
| 258 |
+
"learning_rate": 1.2910126582278483e-05,
|
| 259 |
+
"loss": 0.5873,
|
| 260 |
+
"step": 320
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.17405063291139242,
|
| 264 |
+
"grad_norm": 13.125,
|
| 265 |
+
"learning_rate": 1.2872943037974684e-05,
|
| 266 |
+
"loss": 0.5687,
|
| 267 |
+
"step": 330
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.17932489451476794,
|
| 271 |
+
"grad_norm": 10.9375,
|
| 272 |
+
"learning_rate": 1.2835759493670888e-05,
|
| 273 |
+
"loss": 0.5496,
|
| 274 |
+
"step": 340
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.18459915611814345,
|
| 278 |
+
"grad_norm": 8.0625,
|
| 279 |
+
"learning_rate": 1.2798575949367088e-05,
|
| 280 |
+
"loss": 0.5872,
|
| 281 |
+
"step": 350
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.189873417721519,
|
| 285 |
+
"grad_norm": 8.6875,
|
| 286 |
+
"learning_rate": 1.2761392405063293e-05,
|
| 287 |
+
"loss": 0.557,
|
| 288 |
+
"step": 360
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.19514767932489452,
|
| 292 |
+
"grad_norm": 11.625,
|
| 293 |
+
"learning_rate": 1.2724208860759493e-05,
|
| 294 |
+
"loss": 0.5815,
|
| 295 |
+
"step": 370
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.20042194092827004,
|
| 299 |
+
"grad_norm": 10.5,
|
| 300 |
+
"learning_rate": 1.2687025316455696e-05,
|
| 301 |
+
"loss": 0.5662,
|
| 302 |
+
"step": 380
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.20569620253164558,
|
| 306 |
+
"grad_norm": 10.5,
|
| 307 |
+
"learning_rate": 1.26498417721519e-05,
|
| 308 |
+
"loss": 0.5674,
|
| 309 |
+
"step": 390
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.2109704641350211,
|
| 313 |
+
"grad_norm": 9.4375,
|
| 314 |
+
"learning_rate": 1.26126582278481e-05,
|
| 315 |
+
"loss": 0.573,
|
| 316 |
+
"step": 400
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.2109704641350211,
|
| 320 |
+
"eval_accuracy": 0.718158567774936,
|
| 321 |
+
"eval_loss": 0.5407843589782715,
|
| 322 |
+
"eval_runtime": 31.895,
|
| 323 |
+
"eval_samples_per_second": 61.295,
|
| 324 |
+
"eval_steps_per_second": 1.944,
|
| 325 |
+
"step": 400
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.21624472573839662,
|
| 329 |
+
"grad_norm": 8.375,
|
| 330 |
+
"learning_rate": 1.2575474683544305e-05,
|
| 331 |
+
"loss": 0.5875,
|
| 332 |
+
"step": 410
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.22151898734177214,
|
| 336 |
+
"grad_norm": 9.25,
|
| 337 |
+
"learning_rate": 1.2538291139240506e-05,
|
| 338 |
+
"loss": 0.5336,
|
| 339 |
+
"step": 420
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.22679324894514769,
|
| 343 |
+
"grad_norm": 9.875,
|
| 344 |
+
"learning_rate": 1.250110759493671e-05,
|
| 345 |
+
"loss": 0.509,
|
| 346 |
+
"step": 430
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.2320675105485232,
|
| 350 |
+
"grad_norm": 11.625,
|
| 351 |
+
"learning_rate": 1.246392405063291e-05,
|
| 352 |
+
"loss": 0.5688,
|
| 353 |
+
"step": 440
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.23734177215189872,
|
| 357 |
+
"grad_norm": 8.625,
|
| 358 |
+
"learning_rate": 1.2426740506329115e-05,
|
| 359 |
+
"loss": 0.5802,
|
| 360 |
+
"step": 450
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.24261603375527427,
|
| 364 |
+
"grad_norm": 8.75,
|
| 365 |
+
"learning_rate": 1.2389556962025317e-05,
|
| 366 |
+
"loss": 0.5117,
|
| 367 |
+
"step": 460
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.2478902953586498,
|
| 371 |
+
"grad_norm": 10.25,
|
| 372 |
+
"learning_rate": 1.235237341772152e-05,
|
| 373 |
+
"loss": 0.5687,
|
| 374 |
+
"step": 470
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.25316455696202533,
|
| 378 |
+
"grad_norm": 7.53125,
|
| 379 |
+
"learning_rate": 1.2315189873417722e-05,
|
| 380 |
+
"loss": 0.5465,
|
| 381 |
+
"step": 480
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.25843881856540085,
|
| 385 |
+
"grad_norm": 9.8125,
|
| 386 |
+
"learning_rate": 1.2278006329113925e-05,
|
| 387 |
+
"loss": 0.585,
|
| 388 |
+
"step": 490
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.26371308016877637,
|
| 392 |
+
"grad_norm": 9.1875,
|
| 393 |
+
"learning_rate": 1.2240822784810127e-05,
|
| 394 |
+
"loss": 0.5644,
|
| 395 |
+
"step": 500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.26371308016877637,
|
| 399 |
+
"eval_accuracy": 0.7360613810741689,
|
| 400 |
+
"eval_loss": 0.5284575819969177,
|
| 401 |
+
"eval_runtime": 31.9441,
|
| 402 |
+
"eval_samples_per_second": 61.201,
|
| 403 |
+
"eval_steps_per_second": 1.941,
|
| 404 |
+
"step": 500
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.2689873417721519,
|
| 408 |
+
"grad_norm": 8.375,
|
| 409 |
+
"learning_rate": 1.220363924050633e-05,
|
| 410 |
+
"loss": 0.5357,
|
| 411 |
+
"step": 510
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.2742616033755274,
|
| 415 |
+
"grad_norm": 8.375,
|
| 416 |
+
"learning_rate": 1.2166455696202532e-05,
|
| 417 |
+
"loss": 0.5818,
|
| 418 |
+
"step": 520
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.2795358649789029,
|
| 422 |
+
"grad_norm": 9.8125,
|
| 423 |
+
"learning_rate": 1.2129272151898735e-05,
|
| 424 |
+
"loss": 0.5275,
|
| 425 |
+
"step": 530
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.2848101265822785,
|
| 429 |
+
"grad_norm": 9.0,
|
| 430 |
+
"learning_rate": 1.2092088607594937e-05,
|
| 431 |
+
"loss": 0.5201,
|
| 432 |
+
"step": 540
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.290084388185654,
|
| 436 |
+
"grad_norm": 9.75,
|
| 437 |
+
"learning_rate": 1.205490506329114e-05,
|
| 438 |
+
"loss": 0.5351,
|
| 439 |
+
"step": 550
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.29535864978902954,
|
| 443 |
+
"grad_norm": 10.625,
|
| 444 |
+
"learning_rate": 1.2017721518987342e-05,
|
| 445 |
+
"loss": 0.5406,
|
| 446 |
+
"step": 560
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.30063291139240506,
|
| 450 |
+
"grad_norm": 11.625,
|
| 451 |
+
"learning_rate": 1.1980537974683544e-05,
|
| 452 |
+
"loss": 0.5758,
|
| 453 |
+
"step": 570
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.3059071729957806,
|
| 457 |
+
"grad_norm": 9.4375,
|
| 458 |
+
"learning_rate": 1.1943354430379749e-05,
|
| 459 |
+
"loss": 0.5494,
|
| 460 |
+
"step": 580
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.3111814345991561,
|
| 464 |
+
"grad_norm": 7.4375,
|
| 465 |
+
"learning_rate": 1.190617088607595e-05,
|
| 466 |
+
"loss": 0.5516,
|
| 467 |
+
"step": 590
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.31645569620253167,
|
| 471 |
+
"grad_norm": 10.375,
|
| 472 |
+
"learning_rate": 1.1868987341772153e-05,
|
| 473 |
+
"loss": 0.5482,
|
| 474 |
+
"step": 600
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.31645569620253167,
|
| 478 |
+
"eval_accuracy": 0.7365728900255755,
|
| 479 |
+
"eval_loss": 0.5250852704048157,
|
| 480 |
+
"eval_runtime": 31.8662,
|
| 481 |
+
"eval_samples_per_second": 61.35,
|
| 482 |
+
"eval_steps_per_second": 1.946,
|
| 483 |
+
"step": 600
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.3217299578059072,
|
| 487 |
+
"grad_norm": 8.25,
|
| 488 |
+
"learning_rate": 1.1831803797468354e-05,
|
| 489 |
+
"loss": 0.5412,
|
| 490 |
+
"step": 610
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.3270042194092827,
|
| 494 |
+
"grad_norm": 8.25,
|
| 495 |
+
"learning_rate": 1.1794620253164558e-05,
|
| 496 |
+
"loss": 0.5614,
|
| 497 |
+
"step": 620
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 0.3322784810126582,
|
| 501 |
+
"grad_norm": 7.84375,
|
| 502 |
+
"learning_rate": 1.175743670886076e-05,
|
| 503 |
+
"loss": 0.5152,
|
| 504 |
+
"step": 630
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.33755274261603374,
|
| 508 |
+
"grad_norm": 8.3125,
|
| 509 |
+
"learning_rate": 1.1720253164556962e-05,
|
| 510 |
+
"loss": 0.5914,
|
| 511 |
+
"step": 640
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 0.34282700421940926,
|
| 515 |
+
"grad_norm": 7.71875,
|
| 516 |
+
"learning_rate": 1.1683069620253166e-05,
|
| 517 |
+
"loss": 0.5333,
|
| 518 |
+
"step": 650
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.34810126582278483,
|
| 522 |
+
"grad_norm": 7.5,
|
| 523 |
+
"learning_rate": 1.1645886075949367e-05,
|
| 524 |
+
"loss": 0.5196,
|
| 525 |
+
"step": 660
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.35337552742616035,
|
| 529 |
+
"grad_norm": 8.75,
|
| 530 |
+
"learning_rate": 1.160870253164557e-05,
|
| 531 |
+
"loss": 0.5901,
|
| 532 |
+
"step": 670
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.35864978902953587,
|
| 536 |
+
"grad_norm": 9.75,
|
| 537 |
+
"learning_rate": 1.1571518987341771e-05,
|
| 538 |
+
"loss": 0.5537,
|
| 539 |
+
"step": 680
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.3639240506329114,
|
| 543 |
+
"grad_norm": 10.4375,
|
| 544 |
+
"learning_rate": 1.1534335443037976e-05,
|
| 545 |
+
"loss": 0.5316,
|
| 546 |
+
"step": 690
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.3691983122362869,
|
| 550 |
+
"grad_norm": 8.375,
|
| 551 |
+
"learning_rate": 1.1497151898734178e-05,
|
| 552 |
+
"loss": 0.5673,
|
| 553 |
+
"step": 700
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.3691983122362869,
|
| 557 |
+
"eval_accuracy": 0.7278772378516624,
|
| 558 |
+
"eval_loss": 0.5267060399055481,
|
| 559 |
+
"eval_runtime": 31.9212,
|
| 560 |
+
"eval_samples_per_second": 61.245,
|
| 561 |
+
"eval_steps_per_second": 1.942,
|
| 562 |
+
"step": 700
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.3744725738396624,
|
| 566 |
+
"grad_norm": 9.4375,
|
| 567 |
+
"learning_rate": 1.145996835443038e-05,
|
| 568 |
+
"loss": 0.6081,
|
| 569 |
+
"step": 710
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.379746835443038,
|
| 573 |
+
"grad_norm": 8.5,
|
| 574 |
+
"learning_rate": 1.1422784810126583e-05,
|
| 575 |
+
"loss": 0.5328,
|
| 576 |
+
"step": 720
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.3850210970464135,
|
| 580 |
+
"grad_norm": 8.6875,
|
| 581 |
+
"learning_rate": 1.1385601265822785e-05,
|
| 582 |
+
"loss": 0.5353,
|
| 583 |
+
"step": 730
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.39029535864978904,
|
| 587 |
+
"grad_norm": 7.96875,
|
| 588 |
+
"learning_rate": 1.1348417721518988e-05,
|
| 589 |
+
"loss": 0.5502,
|
| 590 |
+
"step": 740
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.39556962025316456,
|
| 594 |
+
"grad_norm": 9.0625,
|
| 595 |
+
"learning_rate": 1.1311234177215189e-05,
|
| 596 |
+
"loss": 0.5072,
|
| 597 |
+
"step": 750
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.4008438818565401,
|
| 601 |
+
"grad_norm": 8.4375,
|
| 602 |
+
"learning_rate": 1.1274050632911393e-05,
|
| 603 |
+
"loss": 0.5366,
|
| 604 |
+
"step": 760
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.4061181434599156,
|
| 608 |
+
"grad_norm": 9.8125,
|
| 609 |
+
"learning_rate": 1.1236867088607595e-05,
|
| 610 |
+
"loss": 0.5221,
|
| 611 |
+
"step": 770
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.41139240506329117,
|
| 615 |
+
"grad_norm": 7.84375,
|
| 616 |
+
"learning_rate": 1.1199683544303798e-05,
|
| 617 |
+
"loss": 0.5226,
|
| 618 |
+
"step": 780
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.4166666666666667,
|
| 622 |
+
"grad_norm": 8.9375,
|
| 623 |
+
"learning_rate": 1.11625e-05,
|
| 624 |
+
"loss": 0.5562,
|
| 625 |
+
"step": 790
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.4219409282700422,
|
| 629 |
+
"grad_norm": 8.4375,
|
| 630 |
+
"learning_rate": 1.1125316455696203e-05,
|
| 631 |
+
"loss": 0.5701,
|
| 632 |
+
"step": 800
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.4219409282700422,
|
| 636 |
+
"eval_accuracy": 0.7452685421994885,
|
| 637 |
+
"eval_loss": 0.5122529864311218,
|
| 638 |
+
"eval_runtime": 31.8853,
|
| 639 |
+
"eval_samples_per_second": 61.314,
|
| 640 |
+
"eval_steps_per_second": 1.944,
|
| 641 |
+
"step": 800
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.4272151898734177,
|
| 645 |
+
"grad_norm": 8.875,
|
| 646 |
+
"learning_rate": 1.1088132911392405e-05,
|
| 647 |
+
"loss": 0.5108,
|
| 648 |
+
"step": 810
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.43248945147679324,
|
| 652 |
+
"grad_norm": 7.375,
|
| 653 |
+
"learning_rate": 1.1050949367088608e-05,
|
| 654 |
+
"loss": 0.5223,
|
| 655 |
+
"step": 820
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.43776371308016876,
|
| 659 |
+
"grad_norm": 9.0,
|
| 660 |
+
"learning_rate": 1.101376582278481e-05,
|
| 661 |
+
"loss": 0.5463,
|
| 662 |
+
"step": 830
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.4430379746835443,
|
| 666 |
+
"grad_norm": 7.09375,
|
| 667 |
+
"learning_rate": 1.0976582278481014e-05,
|
| 668 |
+
"loss": 0.5222,
|
| 669 |
+
"step": 840
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.44831223628691985,
|
| 673 |
+
"grad_norm": 7.5,
|
| 674 |
+
"learning_rate": 1.0939398734177215e-05,
|
| 675 |
+
"loss": 0.593,
|
| 676 |
+
"step": 850
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.45358649789029537,
|
| 680 |
+
"grad_norm": 10.9375,
|
| 681 |
+
"learning_rate": 1.090221518987342e-05,
|
| 682 |
+
"loss": 0.5828,
|
| 683 |
+
"step": 860
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.4588607594936709,
|
| 687 |
+
"grad_norm": 7.5625,
|
| 688 |
+
"learning_rate": 1.086503164556962e-05,
|
| 689 |
+
"loss": 0.5251,
|
| 690 |
+
"step": 870
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.4641350210970464,
|
| 694 |
+
"grad_norm": 9.0625,
|
| 695 |
+
"learning_rate": 1.0827848101265822e-05,
|
| 696 |
+
"loss": 0.5284,
|
| 697 |
+
"step": 880
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.4694092827004219,
|
| 701 |
+
"grad_norm": 7.25,
|
| 702 |
+
"learning_rate": 1.0790664556962027e-05,
|
| 703 |
+
"loss": 0.5502,
|
| 704 |
+
"step": 890
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.47468354430379744,
|
| 708 |
+
"grad_norm": 6.90625,
|
| 709 |
+
"learning_rate": 1.0753481012658227e-05,
|
| 710 |
+
"loss": 0.5199,
|
| 711 |
+
"step": 900
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.47468354430379744,
|
| 715 |
+
"eval_accuracy": 0.7375959079283887,
|
| 716 |
+
"eval_loss": 0.514769971370697,
|
| 717 |
+
"eval_runtime": 31.9299,
|
| 718 |
+
"eval_samples_per_second": 61.228,
|
| 719 |
+
"eval_steps_per_second": 1.942,
|
| 720 |
+
"step": 900
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.479957805907173,
|
| 724 |
+
"grad_norm": 8.0,
|
| 725 |
+
"learning_rate": 1.0716297468354432e-05,
|
| 726 |
+
"loss": 0.5431,
|
| 727 |
+
"step": 910
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 0.48523206751054854,
|
| 731 |
+
"grad_norm": 6.78125,
|
| 732 |
+
"learning_rate": 1.0679113924050632e-05,
|
| 733 |
+
"loss": 0.5744,
|
| 734 |
+
"step": 920
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.49050632911392406,
|
| 738 |
+
"grad_norm": 6.59375,
|
| 739 |
+
"learning_rate": 1.0641930379746836e-05,
|
| 740 |
+
"loss": 0.5749,
|
| 741 |
+
"step": 930
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.4957805907172996,
|
| 745 |
+
"grad_norm": 8.3125,
|
| 746 |
+
"learning_rate": 1.0604746835443037e-05,
|
| 747 |
+
"loss": 0.5595,
|
| 748 |
+
"step": 940
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 0.5010548523206751,
|
| 752 |
+
"grad_norm": 6.875,
|
| 753 |
+
"learning_rate": 1.0567563291139241e-05,
|
| 754 |
+
"loss": 0.5198,
|
| 755 |
+
"step": 950
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 0.5063291139240507,
|
| 759 |
+
"grad_norm": 10.5,
|
| 760 |
+
"learning_rate": 1.0530379746835444e-05,
|
| 761 |
+
"loss": 0.57,
|
| 762 |
+
"step": 960
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 0.5116033755274262,
|
| 766 |
+
"grad_norm": 7.03125,
|
| 767 |
+
"learning_rate": 1.0493196202531646e-05,
|
| 768 |
+
"loss": 0.5725,
|
| 769 |
+
"step": 970
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 0.5168776371308017,
|
| 773 |
+
"grad_norm": 8.125,
|
| 774 |
+
"learning_rate": 1.0456012658227849e-05,
|
| 775 |
+
"loss": 0.5162,
|
| 776 |
+
"step": 980
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 0.5221518987341772,
|
| 780 |
+
"grad_norm": 8.125,
|
| 781 |
+
"learning_rate": 1.0418829113924051e-05,
|
| 782 |
+
"loss": 0.4939,
|
| 783 |
+
"step": 990
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.5274261603375527,
|
| 787 |
+
"grad_norm": 7.5625,
|
| 788 |
+
"learning_rate": 1.0381645569620254e-05,
|
| 789 |
+
"loss": 0.5525,
|
| 790 |
+
"step": 1000
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.5274261603375527,
|
| 794 |
+
"eval_accuracy": 0.7493606138107417,
|
| 795 |
+
"eval_loss": 0.5132544040679932,
|
| 796 |
+
"eval_runtime": 31.9116,
|
| 797 |
+
"eval_samples_per_second": 61.263,
|
| 798 |
+
"eval_steps_per_second": 1.943,
|
| 799 |
+
"step": 1000
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 0.5327004219409283,
|
| 803 |
+
"grad_norm": 7.125,
|
| 804 |
+
"learning_rate": 1.0344462025316456e-05,
|
| 805 |
+
"loss": 0.5266,
|
| 806 |
+
"step": 1010
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 0.5379746835443038,
|
| 810 |
+
"grad_norm": 5.90625,
|
| 811 |
+
"learning_rate": 1.0307278481012659e-05,
|
| 812 |
+
"loss": 0.5283,
|
| 813 |
+
"step": 1020
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.5432489451476793,
|
| 817 |
+
"grad_norm": 7.0625,
|
| 818 |
+
"learning_rate": 1.0270094936708861e-05,
|
| 819 |
+
"loss": 0.5323,
|
| 820 |
+
"step": 1030
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 0.5485232067510548,
|
| 824 |
+
"grad_norm": 7.0,
|
| 825 |
+
"learning_rate": 1.0232911392405064e-05,
|
| 826 |
+
"loss": 0.4994,
|
| 827 |
+
"step": 1040
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 0.5537974683544303,
|
| 831 |
+
"grad_norm": 6.34375,
|
| 832 |
+
"learning_rate": 1.0195727848101266e-05,
|
| 833 |
+
"loss": 0.5333,
|
| 834 |
+
"step": 1050
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 0.5590717299578059,
|
| 838 |
+
"grad_norm": 8.4375,
|
| 839 |
+
"learning_rate": 1.0158544303797469e-05,
|
| 840 |
+
"loss": 0.5548,
|
| 841 |
+
"step": 1060
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 0.5643459915611815,
|
| 845 |
+
"grad_norm": 6.46875,
|
| 846 |
+
"learning_rate": 1.0121360759493671e-05,
|
| 847 |
+
"loss": 0.5212,
|
| 848 |
+
"step": 1070
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 0.569620253164557,
|
| 852 |
+
"grad_norm": 7.28125,
|
| 853 |
+
"learning_rate": 1.0084177215189875e-05,
|
| 854 |
+
"loss": 0.5402,
|
| 855 |
+
"step": 1080
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.5748945147679325,
|
| 859 |
+
"grad_norm": 8.625,
|
| 860 |
+
"learning_rate": 1.0046993670886076e-05,
|
| 861 |
+
"loss": 0.5508,
|
| 862 |
+
"step": 1090
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 0.580168776371308,
|
| 866 |
+
"grad_norm": 7.21875,
|
| 867 |
+
"learning_rate": 1.000981012658228e-05,
|
| 868 |
+
"loss": 0.5197,
|
| 869 |
+
"step": 1100
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 0.580168776371308,
|
| 873 |
+
"eval_accuracy": 0.7488491048593351,
|
| 874 |
+
"eval_loss": 0.5085062980651855,
|
| 875 |
+
"eval_runtime": 31.9268,
|
| 876 |
+
"eval_samples_per_second": 61.234,
|
| 877 |
+
"eval_steps_per_second": 1.942,
|
| 878 |
+
"step": 1100
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.5854430379746836,
|
| 882 |
+
"grad_norm": 7.53125,
|
| 883 |
+
"learning_rate": 9.97262658227848e-06,
|
| 884 |
+
"loss": 0.5004,
|
| 885 |
+
"step": 1110
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.5907172995780591,
|
| 889 |
+
"grad_norm": 8.75,
|
| 890 |
+
"learning_rate": 9.935443037974685e-06,
|
| 891 |
+
"loss": 0.5404,
|
| 892 |
+
"step": 1120
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.5959915611814346,
|
| 896 |
+
"grad_norm": 10.9375,
|
| 897 |
+
"learning_rate": 9.898259493670886e-06,
|
| 898 |
+
"loss": 0.5352,
|
| 899 |
+
"step": 1130
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.6012658227848101,
|
| 903 |
+
"grad_norm": 6.6875,
|
| 904 |
+
"learning_rate": 9.861075949367088e-06,
|
| 905 |
+
"loss": 0.4879,
|
| 906 |
+
"step": 1140
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.6065400843881856,
|
| 910 |
+
"grad_norm": 9.5,
|
| 911 |
+
"learning_rate": 9.823892405063292e-06,
|
| 912 |
+
"loss": 0.5985,
|
| 913 |
+
"step": 1150
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.6118143459915611,
|
| 917 |
+
"grad_norm": 6.28125,
|
| 918 |
+
"learning_rate": 9.786708860759493e-06,
|
| 919 |
+
"loss": 0.5321,
|
| 920 |
+
"step": 1160
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.6170886075949367,
|
| 924 |
+
"grad_norm": 6.09375,
|
| 925 |
+
"learning_rate": 9.749525316455697e-06,
|
| 926 |
+
"loss": 0.5005,
|
| 927 |
+
"step": 1170
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.6223628691983122,
|
| 931 |
+
"grad_norm": 6.625,
|
| 932 |
+
"learning_rate": 9.712341772151898e-06,
|
| 933 |
+
"loss": 0.4947,
|
| 934 |
+
"step": 1180
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.6276371308016878,
|
| 938 |
+
"grad_norm": 7.78125,
|
| 939 |
+
"learning_rate": 9.675158227848102e-06,
|
| 940 |
+
"loss": 0.4745,
|
| 941 |
+
"step": 1190
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.6329113924050633,
|
| 945 |
+
"grad_norm": 7.71875,
|
| 946 |
+
"learning_rate": 9.637974683544305e-06,
|
| 947 |
+
"loss": 0.4977,
|
| 948 |
+
"step": 1200
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.6329113924050633,
|
| 952 |
+
"eval_accuracy": 0.7411764705882353,
|
| 953 |
+
"eval_loss": 0.5146331787109375,
|
| 954 |
+
"eval_runtime": 31.9288,
|
| 955 |
+
"eval_samples_per_second": 61.23,
|
| 956 |
+
"eval_steps_per_second": 1.942,
|
| 957 |
+
"step": 1200
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.6381856540084389,
|
| 961 |
+
"grad_norm": 10.9375,
|
| 962 |
+
"learning_rate": 9.600791139240507e-06,
|
| 963 |
+
"loss": 0.5176,
|
| 964 |
+
"step": 1210
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.6434599156118144,
|
| 968 |
+
"grad_norm": 8.3125,
|
| 969 |
+
"learning_rate": 9.56360759493671e-06,
|
| 970 |
+
"loss": 0.5472,
|
| 971 |
+
"step": 1220
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.6487341772151899,
|
| 975 |
+
"grad_norm": 6.90625,
|
| 976 |
+
"learning_rate": 9.526424050632912e-06,
|
| 977 |
+
"loss": 0.4825,
|
| 978 |
+
"step": 1230
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.6540084388185654,
|
| 982 |
+
"grad_norm": 7.40625,
|
| 983 |
+
"learning_rate": 9.489240506329115e-06,
|
| 984 |
+
"loss": 0.4956,
|
| 985 |
+
"step": 1240
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.6592827004219409,
|
| 989 |
+
"grad_norm": 6.75,
|
| 990 |
+
"learning_rate": 9.452056962025315e-06,
|
| 991 |
+
"loss": 0.5199,
|
| 992 |
+
"step": 1250
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.6645569620253164,
|
| 996 |
+
"grad_norm": 9.25,
|
| 997 |
+
"learning_rate": 9.41487341772152e-06,
|
| 998 |
+
"loss": 0.5871,
|
| 999 |
+
"step": 1260
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.669831223628692,
|
| 1003 |
+
"grad_norm": 7.75,
|
| 1004 |
+
"learning_rate": 9.377689873417722e-06,
|
| 1005 |
+
"loss": 0.5269,
|
| 1006 |
+
"step": 1270
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.6751054852320675,
|
| 1010 |
+
"grad_norm": 7.71875,
|
| 1011 |
+
"learning_rate": 9.340506329113924e-06,
|
| 1012 |
+
"loss": 0.4983,
|
| 1013 |
+
"step": 1280
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.680379746835443,
|
| 1017 |
+
"grad_norm": 7.5625,
|
| 1018 |
+
"learning_rate": 9.303322784810127e-06,
|
| 1019 |
+
"loss": 0.5544,
|
| 1020 |
+
"step": 1290
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.6856540084388185,
|
| 1024 |
+
"grad_norm": 7.59375,
|
| 1025 |
+
"learning_rate": 9.26613924050633e-06,
|
| 1026 |
+
"loss": 0.492,
|
| 1027 |
+
"step": 1300
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.6856540084388185,
|
| 1031 |
+
"eval_accuracy": 0.7416879795396419,
|
| 1032 |
+
"eval_loss": 0.511603593826294,
|
| 1033 |
+
"eval_runtime": 31.9424,
|
| 1034 |
+
"eval_samples_per_second": 61.204,
|
| 1035 |
+
"eval_steps_per_second": 1.941,
|
| 1036 |
+
"step": 1300
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 0.6909282700421941,
|
| 1040 |
+
"grad_norm": 8.0,
|
| 1041 |
+
"learning_rate": 9.228955696202532e-06,
|
| 1042 |
+
"loss": 0.5052,
|
| 1043 |
+
"step": 1310
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 0.6962025316455697,
|
| 1047 |
+
"grad_norm": 8.5625,
|
| 1048 |
+
"learning_rate": 9.191772151898734e-06,
|
| 1049 |
+
"loss": 0.5295,
|
| 1050 |
+
"step": 1320
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 0.7014767932489452,
|
| 1054 |
+
"grad_norm": 9.0,
|
| 1055 |
+
"learning_rate": 9.154588607594937e-06,
|
| 1056 |
+
"loss": 0.5589,
|
| 1057 |
+
"step": 1330
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 0.7067510548523207,
|
| 1061 |
+
"grad_norm": 7.1875,
|
| 1062 |
+
"learning_rate": 9.117405063291141e-06,
|
| 1063 |
+
"loss": 0.536,
|
| 1064 |
+
"step": 1340
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 0.7120253164556962,
|
| 1068 |
+
"grad_norm": 6.3125,
|
| 1069 |
+
"learning_rate": 9.080221518987342e-06,
|
| 1070 |
+
"loss": 0.473,
|
| 1071 |
+
"step": 1350
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 0.7172995780590717,
|
| 1075 |
+
"grad_norm": 9.25,
|
| 1076 |
+
"learning_rate": 9.043037974683546e-06,
|
| 1077 |
+
"loss": 0.503,
|
| 1078 |
+
"step": 1360
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 0.7225738396624473,
|
| 1082 |
+
"grad_norm": 7.34375,
|
| 1083 |
+
"learning_rate": 9.005854430379747e-06,
|
| 1084 |
+
"loss": 0.4972,
|
| 1085 |
+
"step": 1370
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 0.7278481012658228,
|
| 1089 |
+
"grad_norm": 8.875,
|
| 1090 |
+
"learning_rate": 8.968670886075949e-06,
|
| 1091 |
+
"loss": 0.5291,
|
| 1092 |
+
"step": 1380
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 0.7331223628691983,
|
| 1096 |
+
"grad_norm": 7.625,
|
| 1097 |
+
"learning_rate": 8.931487341772152e-06,
|
| 1098 |
+
"loss": 0.5637,
|
| 1099 |
+
"step": 1390
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 0.7383966244725738,
|
| 1103 |
+
"grad_norm": 7.25,
|
| 1104 |
+
"learning_rate": 8.894303797468354e-06,
|
| 1105 |
+
"loss": 0.5046,
|
| 1106 |
+
"step": 1400
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 0.7383966244725738,
|
| 1110 |
+
"eval_accuracy": 0.7452685421994885,
|
| 1111 |
+
"eval_loss": 0.5069195628166199,
|
| 1112 |
+
"eval_runtime": 31.9183,
|
| 1113 |
+
"eval_samples_per_second": 61.25,
|
| 1114 |
+
"eval_steps_per_second": 1.942,
|
| 1115 |
+
"step": 1400
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.7436708860759493,
|
| 1119 |
+
"grad_norm": 10.625,
|
| 1120 |
+
"learning_rate": 8.857120253164558e-06,
|
| 1121 |
+
"loss": 0.587,
|
| 1122 |
+
"step": 1410
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.7489451476793249,
|
| 1126 |
+
"grad_norm": 7.28125,
|
| 1127 |
+
"learning_rate": 8.819936708860759e-06,
|
| 1128 |
+
"loss": 0.5255,
|
| 1129 |
+
"step": 1420
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.7542194092827004,
|
| 1133 |
+
"grad_norm": 7.59375,
|
| 1134 |
+
"learning_rate": 8.782753164556963e-06,
|
| 1135 |
+
"loss": 0.532,
|
| 1136 |
+
"step": 1430
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.759493670886076,
|
| 1140 |
+
"grad_norm": 7.96875,
|
| 1141 |
+
"learning_rate": 8.745569620253164e-06,
|
| 1142 |
+
"loss": 0.4791,
|
| 1143 |
+
"step": 1440
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.7647679324894515,
|
| 1147 |
+
"grad_norm": 8.6875,
|
| 1148 |
+
"learning_rate": 8.708386075949368e-06,
|
| 1149 |
+
"loss": 0.5277,
|
| 1150 |
+
"step": 1450
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.770042194092827,
|
| 1154 |
+
"grad_norm": 9.5,
|
| 1155 |
+
"learning_rate": 8.67120253164557e-06,
|
| 1156 |
+
"loss": 0.5335,
|
| 1157 |
+
"step": 1460
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.7753164556962026,
|
| 1161 |
+
"grad_norm": 9.1875,
|
| 1162 |
+
"learning_rate": 8.634018987341773e-06,
|
| 1163 |
+
"loss": 0.5746,
|
| 1164 |
+
"step": 1470
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.7805907172995781,
|
| 1168 |
+
"grad_norm": 10.125,
|
| 1169 |
+
"learning_rate": 8.596835443037975e-06,
|
| 1170 |
+
"loss": 0.5555,
|
| 1171 |
+
"step": 1480
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.7858649789029536,
|
| 1175 |
+
"grad_norm": 7.84375,
|
| 1176 |
+
"learning_rate": 8.559651898734178e-06,
|
| 1177 |
+
"loss": 0.4913,
|
| 1178 |
+
"step": 1490
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.7911392405063291,
|
| 1182 |
+
"grad_norm": 7.9375,
|
| 1183 |
+
"learning_rate": 8.52246835443038e-06,
|
| 1184 |
+
"loss": 0.5476,
|
| 1185 |
+
"step": 1500
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.7911392405063291,
|
| 1189 |
+
"eval_accuracy": 0.7478260869565218,
|
| 1190 |
+
"eval_loss": 0.504403293132782,
|
| 1191 |
+
"eval_runtime": 31.9252,
|
| 1192 |
+
"eval_samples_per_second": 61.237,
|
| 1193 |
+
"eval_steps_per_second": 1.942,
|
| 1194 |
+
"step": 1500
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 0.7964135021097046,
|
| 1198 |
+
"grad_norm": 8.1875,
|
| 1199 |
+
"learning_rate": 8.485284810126581e-06,
|
| 1200 |
+
"loss": 0.5078,
|
| 1201 |
+
"step": 1510
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 0.8016877637130801,
|
| 1205 |
+
"grad_norm": 6.75,
|
| 1206 |
+
"learning_rate": 8.448101265822785e-06,
|
| 1207 |
+
"loss": 0.4789,
|
| 1208 |
+
"step": 1520
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 0.8069620253164557,
|
| 1212 |
+
"grad_norm": 9.5,
|
| 1213 |
+
"learning_rate": 8.410917721518988e-06,
|
| 1214 |
+
"loss": 0.5122,
|
| 1215 |
+
"step": 1530
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 0.8122362869198312,
|
| 1219 |
+
"grad_norm": 7.59375,
|
| 1220 |
+
"learning_rate": 8.37373417721519e-06,
|
| 1221 |
+
"loss": 0.5184,
|
| 1222 |
+
"step": 1540
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 0.8175105485232067,
|
| 1226 |
+
"grad_norm": 8.6875,
|
| 1227 |
+
"learning_rate": 8.336550632911393e-06,
|
| 1228 |
+
"loss": 0.5303,
|
| 1229 |
+
"step": 1550
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 0.8227848101265823,
|
| 1233 |
+
"grad_norm": 7.125,
|
| 1234 |
+
"learning_rate": 8.299367088607595e-06,
|
| 1235 |
+
"loss": 0.5199,
|
| 1236 |
+
"step": 1560
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 0.8280590717299579,
|
| 1240 |
+
"grad_norm": 6.96875,
|
| 1241 |
+
"learning_rate": 8.262183544303798e-06,
|
| 1242 |
+
"loss": 0.4956,
|
| 1243 |
+
"step": 1570
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 0.8333333333333334,
|
| 1247 |
+
"grad_norm": 7.84375,
|
| 1248 |
+
"learning_rate": 8.225e-06,
|
| 1249 |
+
"loss": 0.4543,
|
| 1250 |
+
"step": 1580
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 0.8386075949367089,
|
| 1254 |
+
"grad_norm": 8.3125,
|
| 1255 |
+
"learning_rate": 8.187816455696202e-06,
|
| 1256 |
+
"loss": 0.5797,
|
| 1257 |
+
"step": 1590
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 0.8438818565400844,
|
| 1261 |
+
"grad_norm": 6.53125,
|
| 1262 |
+
"learning_rate": 8.150632911392407e-06,
|
| 1263 |
+
"loss": 0.5247,
|
| 1264 |
+
"step": 1600
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 0.8438818565400844,
|
| 1268 |
+
"eval_accuracy": 0.7468030690537084,
|
| 1269 |
+
"eval_loss": 0.5038452744483948,
|
| 1270 |
+
"eval_runtime": 31.9203,
|
| 1271 |
+
"eval_samples_per_second": 61.246,
|
| 1272 |
+
"eval_steps_per_second": 1.942,
|
| 1273 |
+
"step": 1600
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.8491561181434599,
|
| 1277 |
+
"grad_norm": 7.625,
|
| 1278 |
+
"learning_rate": 8.113449367088607e-06,
|
| 1279 |
+
"loss": 0.5348,
|
| 1280 |
+
"step": 1610
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.8544303797468354,
|
| 1284 |
+
"grad_norm": 6.3125,
|
| 1285 |
+
"learning_rate": 8.076265822784812e-06,
|
| 1286 |
+
"loss": 0.5507,
|
| 1287 |
+
"step": 1620
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.859704641350211,
|
| 1291 |
+
"grad_norm": 6.03125,
|
| 1292 |
+
"learning_rate": 8.039082278481012e-06,
|
| 1293 |
+
"loss": 0.4819,
|
| 1294 |
+
"step": 1630
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.8649789029535865,
|
| 1298 |
+
"grad_norm": 6.875,
|
| 1299 |
+
"learning_rate": 8.001898734177215e-06,
|
| 1300 |
+
"loss": 0.4581,
|
| 1301 |
+
"step": 1640
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.870253164556962,
|
| 1305 |
+
"grad_norm": 7.53125,
|
| 1306 |
+
"learning_rate": 7.964715189873419e-06,
|
| 1307 |
+
"loss": 0.4928,
|
| 1308 |
+
"step": 1650
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.8755274261603375,
|
| 1312 |
+
"grad_norm": 8.75,
|
| 1313 |
+
"learning_rate": 7.92753164556962e-06,
|
| 1314 |
+
"loss": 0.5144,
|
| 1315 |
+
"step": 1660
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.880801687763713,
|
| 1319 |
+
"grad_norm": 9.0625,
|
| 1320 |
+
"learning_rate": 7.890348101265824e-06,
|
| 1321 |
+
"loss": 0.5475,
|
| 1322 |
+
"step": 1670
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.8860759493670886,
|
| 1326 |
+
"grad_norm": 7.8125,
|
| 1327 |
+
"learning_rate": 7.853164556962025e-06,
|
| 1328 |
+
"loss": 0.5443,
|
| 1329 |
+
"step": 1680
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.8913502109704642,
|
| 1333 |
+
"grad_norm": 5.5625,
|
| 1334 |
+
"learning_rate": 7.815981012658229e-06,
|
| 1335 |
+
"loss": 0.4987,
|
| 1336 |
+
"step": 1690
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.8966244725738397,
|
| 1340 |
+
"grad_norm": 7.5625,
|
| 1341 |
+
"learning_rate": 7.77879746835443e-06,
|
| 1342 |
+
"loss": 0.5591,
|
| 1343 |
+
"step": 1700
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.8966244725738397,
|
| 1347 |
+
"eval_accuracy": 0.7452685421994885,
|
| 1348 |
+
"eval_loss": 0.507918119430542,
|
| 1349 |
+
"eval_runtime": 31.9838,
|
| 1350 |
+
"eval_samples_per_second": 61.125,
|
| 1351 |
+
"eval_steps_per_second": 1.938,
|
| 1352 |
+
"step": 1700
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 0.9018987341772152,
|
| 1356 |
+
"grad_norm": 8.3125,
|
| 1357 |
+
"learning_rate": 7.741613924050634e-06,
|
| 1358 |
+
"loss": 0.4957,
|
| 1359 |
+
"step": 1710
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 0.9071729957805907,
|
| 1363 |
+
"grad_norm": 6.71875,
|
| 1364 |
+
"learning_rate": 7.704430379746836e-06,
|
| 1365 |
+
"loss": 0.5035,
|
| 1366 |
+
"step": 1720
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 0.9124472573839663,
|
| 1370 |
+
"grad_norm": 8.1875,
|
| 1371 |
+
"learning_rate": 7.667246835443039e-06,
|
| 1372 |
+
"loss": 0.5108,
|
| 1373 |
+
"step": 1730
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 0.9177215189873418,
|
| 1377 |
+
"grad_norm": 7.5,
|
| 1378 |
+
"learning_rate": 7.630063291139241e-06,
|
| 1379 |
+
"loss": 0.5288,
|
| 1380 |
+
"step": 1740
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 0.9229957805907173,
|
| 1384 |
+
"grad_norm": 6.5625,
|
| 1385 |
+
"learning_rate": 7.592879746835443e-06,
|
| 1386 |
+
"loss": 0.4739,
|
| 1387 |
+
"step": 1750
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"epoch": 0.9282700421940928,
|
| 1391 |
+
"grad_norm": 7.28125,
|
| 1392 |
+
"learning_rate": 7.555696202531646e-06,
|
| 1393 |
+
"loss": 0.49,
|
| 1394 |
+
"step": 1760
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 0.9335443037974683,
|
| 1398 |
+
"grad_norm": 6.75,
|
| 1399 |
+
"learning_rate": 7.518512658227848e-06,
|
| 1400 |
+
"loss": 0.4745,
|
| 1401 |
+
"step": 1770
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 0.9388185654008439,
|
| 1405 |
+
"grad_norm": 8.375,
|
| 1406 |
+
"learning_rate": 7.481329113924051e-06,
|
| 1407 |
+
"loss": 0.4974,
|
| 1408 |
+
"step": 1780
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"epoch": 0.9440928270042194,
|
| 1412 |
+
"grad_norm": 6.90625,
|
| 1413 |
+
"learning_rate": 7.444145569620253e-06,
|
| 1414 |
+
"loss": 0.5397,
|
| 1415 |
+
"step": 1790
|
| 1416 |
+
},
|
| 1417 |
+
{
|
| 1418 |
+
"epoch": 0.9493670886075949,
|
| 1419 |
+
"grad_norm": 6.78125,
|
| 1420 |
+
"learning_rate": 7.406962025316456e-06,
|
| 1421 |
+
"loss": 0.5228,
|
| 1422 |
+
"step": 1800
|
| 1423 |
+
},
|
| 1424 |
+
{
|
| 1425 |
+
"epoch": 0.9493670886075949,
|
| 1426 |
+
"eval_accuracy": 0.7457800511508952,
|
| 1427 |
+
"eval_loss": 0.5040280222892761,
|
| 1428 |
+
"eval_runtime": 31.9049,
|
| 1429 |
+
"eval_samples_per_second": 61.276,
|
| 1430 |
+
"eval_steps_per_second": 1.943,
|
| 1431 |
+
"step": 1800
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.9546413502109705,
|
| 1435 |
+
"grad_norm": 9.8125,
|
| 1436 |
+
"learning_rate": 7.369778481012658e-06,
|
| 1437 |
+
"loss": 0.4839,
|
| 1438 |
+
"step": 1810
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.959915611814346,
|
| 1442 |
+
"grad_norm": 7.34375,
|
| 1443 |
+
"learning_rate": 7.332594936708862e-06,
|
| 1444 |
+
"loss": 0.4897,
|
| 1445 |
+
"step": 1820
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.9651898734177216,
|
| 1449 |
+
"grad_norm": 9.0625,
|
| 1450 |
+
"learning_rate": 7.295411392405063e-06,
|
| 1451 |
+
"loss": 0.5778,
|
| 1452 |
+
"step": 1830
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.9704641350210971,
|
| 1456 |
+
"grad_norm": 8.5,
|
| 1457 |
+
"learning_rate": 7.258227848101267e-06,
|
| 1458 |
+
"loss": 0.5402,
|
| 1459 |
+
"step": 1840
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.9757383966244726,
|
| 1463 |
+
"grad_norm": 10.75,
|
| 1464 |
+
"learning_rate": 7.221044303797468e-06,
|
| 1465 |
+
"loss": 0.5665,
|
| 1466 |
+
"step": 1850
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.9810126582278481,
|
| 1470 |
+
"grad_norm": 5.59375,
|
| 1471 |
+
"learning_rate": 7.1838607594936716e-06,
|
| 1472 |
+
"loss": 0.5238,
|
| 1473 |
+
"step": 1860
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.9862869198312236,
|
| 1477 |
+
"grad_norm": 8.875,
|
| 1478 |
+
"learning_rate": 7.146677215189874e-06,
|
| 1479 |
+
"loss": 0.5707,
|
| 1480 |
+
"step": 1870
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.9915611814345991,
|
| 1484 |
+
"grad_norm": 7.8125,
|
| 1485 |
+
"learning_rate": 7.109493670886076e-06,
|
| 1486 |
+
"loss": 0.5202,
|
| 1487 |
+
"step": 1880
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.9968354430379747,
|
| 1491 |
+
"grad_norm": 8.0,
|
| 1492 |
+
"learning_rate": 7.072310126582279e-06,
|
| 1493 |
+
"loss": 0.5018,
|
| 1494 |
+
"step": 1890
|
| 1495 |
+
}
|
| 1496 |
+
],
|
| 1497 |
+
"logging_steps": 10,
|
| 1498 |
+
"max_steps": 3792,
|
| 1499 |
+
"num_input_tokens_seen": 0,
|
| 1500 |
+
"num_train_epochs": 2,
|
| 1501 |
+
"save_steps": 500,
|
| 1502 |
+
"stateful_callbacks": {
|
| 1503 |
+
"TrainerControl": {
|
| 1504 |
+
"args": {
|
| 1505 |
+
"should_epoch_stop": false,
|
| 1506 |
+
"should_evaluate": false,
|
| 1507 |
+
"should_log": false,
|
| 1508 |
+
"should_save": true,
|
| 1509 |
+
"should_training_stop": false
|
| 1510 |
+
},
|
| 1511 |
+
"attributes": {}
|
| 1512 |
+
}
|
| 1513 |
+
},
|
| 1514 |
+
"total_flos": 0.0,
|
| 1515 |
+
"train_batch_size": 1,
|
| 1516 |
+
"trial_name": null,
|
| 1517 |
+
"trial_params": null
|
| 1518 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e6097da4220b50e111db1a14cacea507cfb00b6002e5bad2b745620266b2c0b1
|
| 3 |
+
size 5496
|