Model save
Browse files- README.md +78 -0
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +3155 -0
README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- sft
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
datasets:
|
| 9 |
+
- generator
|
| 10 |
+
base_model: meta-llama/Meta-Llama-3-8B-Instruct
|
| 11 |
+
model-index:
|
| 12 |
+
- name: Meta-Llama-3-8B-Instruct-miracl-mix-raft-sft-25th-apr-v1.0
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# Meta-Llama-3-8B-Instruct-miracl-mix-raft-sft-25th-apr-v1.0
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the generator dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 1.3064
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 1e-05
|
| 43 |
+
- train_batch_size: 2
|
| 44 |
+
- eval_batch_size: 2
|
| 45 |
+
- seed: 42
|
| 46 |
+
- distributed_type: multi-GPU
|
| 47 |
+
- num_devices: 4
|
| 48 |
+
- gradient_accumulation_steps: 4
|
| 49 |
+
- total_train_batch_size: 32
|
| 50 |
+
- total_eval_batch_size: 8
|
| 51 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 52 |
+
- lr_scheduler_type: cosine
|
| 53 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 54 |
+
- num_epochs: 1
|
| 55 |
+
|
| 56 |
+
### Training results
|
| 57 |
+
|
| 58 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 59 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 60 |
+
| 1.4903 | 0.09 | 200 | 1.3961 |
|
| 61 |
+
| 1.465 | 0.18 | 400 | 1.3499 |
|
| 62 |
+
| 1.4193 | 0.28 | 600 | 1.3330 |
|
| 63 |
+
| 1.3593 | 0.37 | 800 | 1.3232 |
|
| 64 |
+
| 1.3552 | 0.46 | 1000 | 1.3166 |
|
| 65 |
+
| 1.3685 | 0.55 | 1200 | 1.3123 |
|
| 66 |
+
| 1.3487 | 0.64 | 1400 | 1.3094 |
|
| 67 |
+
| 1.3891 | 0.74 | 1600 | 1.3076 |
|
| 68 |
+
| 1.3858 | 0.83 | 1800 | 1.3067 |
|
| 69 |
+
| 1.3635 | 0.92 | 2000 | 1.3064 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
### Framework versions
|
| 73 |
+
|
| 74 |
+
- PEFT 0.10.0
|
| 75 |
+
- Transformers 4.39.0.dev0
|
| 76 |
+
- Pytorch 2.1.2+cu121
|
| 77 |
+
- Datasets 2.18.0
|
| 78 |
+
- Tokenizers 0.15.2
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 1.4133363889659056,
|
| 4 |
+
"train_runtime": 112943.9974,
|
| 5 |
+
"train_samples": 239934,
|
| 6 |
+
"train_samples_per_second": 0.615,
|
| 7 |
+
"train_steps_per_second": 0.019
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 1.4133363889659056,
|
| 4 |
+
"train_runtime": 112943.9974,
|
| 5 |
+
"train_samples": 239934,
|
| 6 |
+
"train_samples_per_second": 0.615,
|
| 7 |
+
"train_steps_per_second": 0.019
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3155 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.3063520193099976,
|
| 3 |
+
"best_model_checkpoint": "/mnt/users/n3thakur/vectara/huggingface-dpo/trained_models/v3/Meta-Llama-3-8B-Instruct-miracl-mix-raft-sft-25th-apr-v1.0/checkpoint-2000",
|
| 4 |
+
"epoch": 0.9996544972935621,
|
| 5 |
+
"eval_steps": 200,
|
| 6 |
+
"global_step": 2170,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"grad_norm": 1.0262953847325709,
|
| 14 |
+
"learning_rate": 4.608294930875576e-08,
|
| 15 |
+
"loss": 1.7621,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0,
|
| 20 |
+
"grad_norm": 0.954880939596983,
|
| 21 |
+
"learning_rate": 2.3041474654377884e-07,
|
| 22 |
+
"loss": 1.7602,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.0,
|
| 27 |
+
"grad_norm": 1.0004644202041775,
|
| 28 |
+
"learning_rate": 4.608294930875577e-07,
|
| 29 |
+
"loss": 1.8162,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.01,
|
| 34 |
+
"grad_norm": 1.0280115397490373,
|
| 35 |
+
"learning_rate": 6.912442396313365e-07,
|
| 36 |
+
"loss": 1.7724,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.01,
|
| 41 |
+
"grad_norm": 0.8732665912953524,
|
| 42 |
+
"learning_rate": 9.216589861751154e-07,
|
| 43 |
+
"loss": 1.7378,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.01,
|
| 48 |
+
"grad_norm": 0.9441885280056963,
|
| 49 |
+
"learning_rate": 1.1520737327188942e-06,
|
| 50 |
+
"loss": 1.7507,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.01,
|
| 55 |
+
"grad_norm": 0.9845213443275476,
|
| 56 |
+
"learning_rate": 1.382488479262673e-06,
|
| 57 |
+
"loss": 1.7561,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.02,
|
| 62 |
+
"grad_norm": 0.9521516823054887,
|
| 63 |
+
"learning_rate": 1.6129032258064516e-06,
|
| 64 |
+
"loss": 1.7479,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.02,
|
| 69 |
+
"grad_norm": 1.0047303931298321,
|
| 70 |
+
"learning_rate": 1.8433179723502307e-06,
|
| 71 |
+
"loss": 1.7773,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.02,
|
| 76 |
+
"grad_norm": 0.9230639224993269,
|
| 77 |
+
"learning_rate": 2.0737327188940094e-06,
|
| 78 |
+
"loss": 1.7752,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.02,
|
| 83 |
+
"grad_norm": 0.9112137084493539,
|
| 84 |
+
"learning_rate": 2.3041474654377884e-06,
|
| 85 |
+
"loss": 1.7213,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.03,
|
| 90 |
+
"grad_norm": 0.8909029043612109,
|
| 91 |
+
"learning_rate": 2.5345622119815673e-06,
|
| 92 |
+
"loss": 1.7881,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.03,
|
| 97 |
+
"grad_norm": 0.7189360071641709,
|
| 98 |
+
"learning_rate": 2.764976958525346e-06,
|
| 99 |
+
"loss": 1.6636,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.03,
|
| 104 |
+
"grad_norm": 0.6692633878715751,
|
| 105 |
+
"learning_rate": 2.9953917050691243e-06,
|
| 106 |
+
"loss": 1.6508,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.03,
|
| 111 |
+
"grad_norm": 0.6188511577538577,
|
| 112 |
+
"learning_rate": 3.225806451612903e-06,
|
| 113 |
+
"loss": 1.7011,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.03,
|
| 118 |
+
"grad_norm": 0.6279410712564498,
|
| 119 |
+
"learning_rate": 3.4562211981566825e-06,
|
| 120 |
+
"loss": 1.6403,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.04,
|
| 125 |
+
"grad_norm": 0.5342697084988228,
|
| 126 |
+
"learning_rate": 3.6866359447004615e-06,
|
| 127 |
+
"loss": 1.656,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.04,
|
| 132 |
+
"grad_norm": 0.44402512139023,
|
| 133 |
+
"learning_rate": 3.91705069124424e-06,
|
| 134 |
+
"loss": 1.6617,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.04,
|
| 139 |
+
"grad_norm": 0.4644619191475398,
|
| 140 |
+
"learning_rate": 4.147465437788019e-06,
|
| 141 |
+
"loss": 1.6303,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.04,
|
| 146 |
+
"grad_norm": 0.371289417426217,
|
| 147 |
+
"learning_rate": 4.377880184331797e-06,
|
| 148 |
+
"loss": 1.6453,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.05,
|
| 153 |
+
"grad_norm": 0.3309787275557066,
|
| 154 |
+
"learning_rate": 4.608294930875577e-06,
|
| 155 |
+
"loss": 1.5851,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.05,
|
| 160 |
+
"grad_norm": 0.31477252449769144,
|
| 161 |
+
"learning_rate": 4.838709677419355e-06,
|
| 162 |
+
"loss": 1.604,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.05,
|
| 167 |
+
"grad_norm": 0.2612544823481869,
|
| 168 |
+
"learning_rate": 5.0691244239631346e-06,
|
| 169 |
+
"loss": 1.5725,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.05,
|
| 174 |
+
"grad_norm": 0.2605484332821398,
|
| 175 |
+
"learning_rate": 5.299539170506913e-06,
|
| 176 |
+
"loss": 1.5644,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.06,
|
| 181 |
+
"grad_norm": 0.25148232016385397,
|
| 182 |
+
"learning_rate": 5.529953917050692e-06,
|
| 183 |
+
"loss": 1.5467,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.06,
|
| 188 |
+
"grad_norm": 0.2601998287824473,
|
| 189 |
+
"learning_rate": 5.76036866359447e-06,
|
| 190 |
+
"loss": 1.589,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.06,
|
| 195 |
+
"grad_norm": 0.2385121609938763,
|
| 196 |
+
"learning_rate": 5.9907834101382485e-06,
|
| 197 |
+
"loss": 1.6055,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.06,
|
| 202 |
+
"grad_norm": 0.24629649793790628,
|
| 203 |
+
"learning_rate": 6.221198156682028e-06,
|
| 204 |
+
"loss": 1.5373,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.06,
|
| 209 |
+
"grad_norm": 0.2468655185850127,
|
| 210 |
+
"learning_rate": 6.451612903225806e-06,
|
| 211 |
+
"loss": 1.5614,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.07,
|
| 216 |
+
"grad_norm": 0.22223391970377232,
|
| 217 |
+
"learning_rate": 6.682027649769586e-06,
|
| 218 |
+
"loss": 1.5624,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.07,
|
| 223 |
+
"grad_norm": 0.2062049955510628,
|
| 224 |
+
"learning_rate": 6.912442396313365e-06,
|
| 225 |
+
"loss": 1.5013,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.07,
|
| 230 |
+
"grad_norm": 0.19876212655323225,
|
| 231 |
+
"learning_rate": 7.1428571428571436e-06,
|
| 232 |
+
"loss": 1.575,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.07,
|
| 237 |
+
"grad_norm": 0.19765238479942285,
|
| 238 |
+
"learning_rate": 7.373271889400923e-06,
|
| 239 |
+
"loss": 1.5167,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.08,
|
| 244 |
+
"grad_norm": 0.19240215611308686,
|
| 245 |
+
"learning_rate": 7.603686635944701e-06,
|
| 246 |
+
"loss": 1.5071,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.08,
|
| 251 |
+
"grad_norm": 0.2001053295395004,
|
| 252 |
+
"learning_rate": 7.83410138248848e-06,
|
| 253 |
+
"loss": 1.4932,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.08,
|
| 258 |
+
"grad_norm": 0.20863957442778325,
|
| 259 |
+
"learning_rate": 8.064516129032258e-06,
|
| 260 |
+
"loss": 1.5371,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.08,
|
| 265 |
+
"grad_norm": 0.1880073967302754,
|
| 266 |
+
"learning_rate": 8.294930875576038e-06,
|
| 267 |
+
"loss": 1.492,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.09,
|
| 272 |
+
"grad_norm": 0.18052519991071567,
|
| 273 |
+
"learning_rate": 8.525345622119815e-06,
|
| 274 |
+
"loss": 1.5039,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.09,
|
| 279 |
+
"grad_norm": 0.17252733686762506,
|
| 280 |
+
"learning_rate": 8.755760368663595e-06,
|
| 281 |
+
"loss": 1.492,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.09,
|
| 286 |
+
"grad_norm": 0.1754856007551659,
|
| 287 |
+
"learning_rate": 8.986175115207374e-06,
|
| 288 |
+
"loss": 1.4926,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.09,
|
| 293 |
+
"grad_norm": 0.16521189205999245,
|
| 294 |
+
"learning_rate": 9.216589861751153e-06,
|
| 295 |
+
"loss": 1.4903,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.09,
|
| 300 |
+
"eval_loss": 1.3960996866226196,
|
| 301 |
+
"eval_runtime": 1753.0374,
|
| 302 |
+
"eval_samples_per_second": 2.162,
|
| 303 |
+
"eval_steps_per_second": 0.27,
|
| 304 |
+
"step": 200
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.09,
|
| 308 |
+
"grad_norm": 0.1618648599795676,
|
| 309 |
+
"learning_rate": 9.447004608294931e-06,
|
| 310 |
+
"loss": 1.4499,
|
| 311 |
+
"step": 205
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.1,
|
| 315 |
+
"grad_norm": 0.1609921643942943,
|
| 316 |
+
"learning_rate": 9.67741935483871e-06,
|
| 317 |
+
"loss": 1.4775,
|
| 318 |
+
"step": 210
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.1,
|
| 322 |
+
"grad_norm": 0.161807092383862,
|
| 323 |
+
"learning_rate": 9.90783410138249e-06,
|
| 324 |
+
"loss": 1.4779,
|
| 325 |
+
"step": 215
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.1,
|
| 329 |
+
"grad_norm": 0.15789342984068674,
|
| 330 |
+
"learning_rate": 9.999941779365509e-06,
|
| 331 |
+
"loss": 1.4064,
|
| 332 |
+
"step": 220
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.1,
|
| 336 |
+
"grad_norm": 0.17953421611953463,
|
| 337 |
+
"learning_rate": 9.99958599150926e-06,
|
| 338 |
+
"loss": 1.4216,
|
| 339 |
+
"step": 225
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.11,
|
| 343 |
+
"grad_norm": 0.17033046165043145,
|
| 344 |
+
"learning_rate": 9.998906783581494e-06,
|
| 345 |
+
"loss": 1.4872,
|
| 346 |
+
"step": 230
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.11,
|
| 350 |
+
"grad_norm": 0.15935058975437466,
|
| 351 |
+
"learning_rate": 9.997904199519748e-06,
|
| 352 |
+
"loss": 1.4473,
|
| 353 |
+
"step": 235
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.11,
|
| 357 |
+
"grad_norm": 0.16188090301066688,
|
| 358 |
+
"learning_rate": 9.996578304180551e-06,
|
| 359 |
+
"loss": 1.4484,
|
| 360 |
+
"step": 240
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.11,
|
| 364 |
+
"grad_norm": 0.1692826467439708,
|
| 365 |
+
"learning_rate": 9.994929183335237e-06,
|
| 366 |
+
"loss": 1.4576,
|
| 367 |
+
"step": 245
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.12,
|
| 371 |
+
"grad_norm": 0.16233371930510018,
|
| 372 |
+
"learning_rate": 9.992956943664401e-06,
|
| 373 |
+
"loss": 1.4674,
|
| 374 |
+
"step": 250
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.12,
|
| 378 |
+
"grad_norm": 0.1601701723529579,
|
| 379 |
+
"learning_rate": 9.99066171275098e-06,
|
| 380 |
+
"loss": 1.434,
|
| 381 |
+
"step": 255
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.12,
|
| 385 |
+
"grad_norm": 0.1515934744211598,
|
| 386 |
+
"learning_rate": 9.988043639072021e-06,
|
| 387 |
+
"loss": 1.469,
|
| 388 |
+
"step": 260
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.12,
|
| 392 |
+
"grad_norm": 0.1558360755989006,
|
| 393 |
+
"learning_rate": 9.985102891989063e-06,
|
| 394 |
+
"loss": 1.4688,
|
| 395 |
+
"step": 265
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.12,
|
| 399 |
+
"grad_norm": 0.20565866787405954,
|
| 400 |
+
"learning_rate": 9.98183966173718e-06,
|
| 401 |
+
"loss": 1.4794,
|
| 402 |
+
"step": 270
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.13,
|
| 406 |
+
"grad_norm": 0.16589082756750548,
|
| 407 |
+
"learning_rate": 9.97825415941269e-06,
|
| 408 |
+
"loss": 1.4514,
|
| 409 |
+
"step": 275
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.13,
|
| 413 |
+
"grad_norm": 0.16179243903344054,
|
| 414 |
+
"learning_rate": 9.974346616959476e-06,
|
| 415 |
+
"loss": 1.4802,
|
| 416 |
+
"step": 280
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.13,
|
| 420 |
+
"grad_norm": 0.15782689090886812,
|
| 421 |
+
"learning_rate": 9.970117287154004e-06,
|
| 422 |
+
"loss": 1.4356,
|
| 423 |
+
"step": 285
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.13,
|
| 427 |
+
"grad_norm": 0.15954652235182576,
|
| 428 |
+
"learning_rate": 9.965566443588956e-06,
|
| 429 |
+
"loss": 1.3886,
|
| 430 |
+
"step": 290
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.14,
|
| 434 |
+
"grad_norm": 0.16253218390477409,
|
| 435 |
+
"learning_rate": 9.960694380655539e-06,
|
| 436 |
+
"loss": 1.456,
|
| 437 |
+
"step": 295
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.14,
|
| 441 |
+
"grad_norm": 0.15571215758010262,
|
| 442 |
+
"learning_rate": 9.955501413524438e-06,
|
| 443 |
+
"loss": 1.4038,
|
| 444 |
+
"step": 300
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.14,
|
| 448 |
+
"grad_norm": 0.15764668416666167,
|
| 449 |
+
"learning_rate": 9.949987878125427e-06,
|
| 450 |
+
"loss": 1.4292,
|
| 451 |
+
"step": 305
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.14,
|
| 455 |
+
"grad_norm": 0.15565461047093965,
|
| 456 |
+
"learning_rate": 9.944154131125643e-06,
|
| 457 |
+
"loss": 1.3845,
|
| 458 |
+
"step": 310
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.15,
|
| 462 |
+
"grad_norm": 0.16274505869667716,
|
| 463 |
+
"learning_rate": 9.938000549906509e-06,
|
| 464 |
+
"loss": 1.4143,
|
| 465 |
+
"step": 315
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.15,
|
| 469 |
+
"grad_norm": 0.15771377018169355,
|
| 470 |
+
"learning_rate": 9.93152753253932e-06,
|
| 471 |
+
"loss": 1.414,
|
| 472 |
+
"step": 320
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.15,
|
| 476 |
+
"grad_norm": 0.15819595549860918,
|
| 477 |
+
"learning_rate": 9.924735497759497e-06,
|
| 478 |
+
"loss": 1.398,
|
| 479 |
+
"step": 325
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.15,
|
| 483 |
+
"grad_norm": 0.16836842547624103,
|
| 484 |
+
"learning_rate": 9.917624884939495e-06,
|
| 485 |
+
"loss": 1.415,
|
| 486 |
+
"step": 330
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.15,
|
| 490 |
+
"grad_norm": 0.16454346246919038,
|
| 491 |
+
"learning_rate": 9.910196154060381e-06,
|
| 492 |
+
"loss": 1.5025,
|
| 493 |
+
"step": 335
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.16,
|
| 497 |
+
"grad_norm": 0.15952712351687925,
|
| 498 |
+
"learning_rate": 9.902449785682084e-06,
|
| 499 |
+
"loss": 1.4602,
|
| 500 |
+
"step": 340
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.16,
|
| 504 |
+
"grad_norm": 0.15913354058980336,
|
| 505 |
+
"learning_rate": 9.894386280912298e-06,
|
| 506 |
+
"loss": 1.4437,
|
| 507 |
+
"step": 345
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.16,
|
| 511 |
+
"grad_norm": 0.16526633029775475,
|
| 512 |
+
"learning_rate": 9.88600616137407e-06,
|
| 513 |
+
"loss": 1.443,
|
| 514 |
+
"step": 350
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.16,
|
| 518 |
+
"grad_norm": 0.1570973278965336,
|
| 519 |
+
"learning_rate": 9.877309969172065e-06,
|
| 520 |
+
"loss": 1.4001,
|
| 521 |
+
"step": 355
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.17,
|
| 525 |
+
"grad_norm": 0.16323401596231638,
|
| 526 |
+
"learning_rate": 9.868298266857477e-06,
|
| 527 |
+
"loss": 1.4115,
|
| 528 |
+
"step": 360
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.17,
|
| 532 |
+
"grad_norm": 0.16999252145703372,
|
| 533 |
+
"learning_rate": 9.858971637391662e-06,
|
| 534 |
+
"loss": 1.431,
|
| 535 |
+
"step": 365
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.17,
|
| 539 |
+
"grad_norm": 0.1598876979960763,
|
| 540 |
+
"learning_rate": 9.849330684108409e-06,
|
| 541 |
+
"loss": 1.3925,
|
| 542 |
+
"step": 370
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.17,
|
| 546 |
+
"grad_norm": 0.16716694688842804,
|
| 547 |
+
"learning_rate": 9.83937603067492e-06,
|
| 548 |
+
"loss": 1.4369,
|
| 549 |
+
"step": 375
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.18,
|
| 553 |
+
"grad_norm": 0.17160997265475317,
|
| 554 |
+
"learning_rate": 9.829108321051461e-06,
|
| 555 |
+
"loss": 1.4236,
|
| 556 |
+
"step": 380
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.18,
|
| 560 |
+
"grad_norm": 0.1709419213466886,
|
| 561 |
+
"learning_rate": 9.818528219449705e-06,
|
| 562 |
+
"loss": 1.4156,
|
| 563 |
+
"step": 385
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.18,
|
| 567 |
+
"grad_norm": 0.1706660498176678,
|
| 568 |
+
"learning_rate": 9.807636410289767e-06,
|
| 569 |
+
"loss": 1.3531,
|
| 570 |
+
"step": 390
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.18,
|
| 574 |
+
"grad_norm": 0.1654207117166432,
|
| 575 |
+
"learning_rate": 9.796433598155928e-06,
|
| 576 |
+
"loss": 1.4282,
|
| 577 |
+
"step": 395
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.18,
|
| 581 |
+
"grad_norm": 0.17005569486504588,
|
| 582 |
+
"learning_rate": 9.784920507751052e-06,
|
| 583 |
+
"loss": 1.465,
|
| 584 |
+
"step": 400
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.18,
|
| 588 |
+
"eval_loss": 1.3499208688735962,
|
| 589 |
+
"eval_runtime": 1761.5948,
|
| 590 |
+
"eval_samples_per_second": 2.151,
|
| 591 |
+
"eval_steps_per_second": 0.269,
|
| 592 |
+
"step": 400
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.19,
|
| 596 |
+
"grad_norm": 0.16465910018813473,
|
| 597 |
+
"learning_rate": 9.773097883849715e-06,
|
| 598 |
+
"loss": 1.4856,
|
| 599 |
+
"step": 405
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.19,
|
| 603 |
+
"grad_norm": 0.1687241699251977,
|
| 604 |
+
"learning_rate": 9.760966491250018e-06,
|
| 605 |
+
"loss": 1.4448,
|
| 606 |
+
"step": 410
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.19,
|
| 610 |
+
"grad_norm": 0.173826161389088,
|
| 611 |
+
"learning_rate": 9.748527114724111e-06,
|
| 612 |
+
"loss": 1.4588,
|
| 613 |
+
"step": 415
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.19,
|
| 617 |
+
"grad_norm": 0.1664583424134419,
|
| 618 |
+
"learning_rate": 9.735780558967434e-06,
|
| 619 |
+
"loss": 1.3651,
|
| 620 |
+
"step": 420
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.2,
|
| 624 |
+
"grad_norm": 0.16305809613976227,
|
| 625 |
+
"learning_rate": 9.72272764854666e-06,
|
| 626 |
+
"loss": 1.386,
|
| 627 |
+
"step": 425
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.2,
|
| 631 |
+
"grad_norm": 0.16712240916605367,
|
| 632 |
+
"learning_rate": 9.709369227846346e-06,
|
| 633 |
+
"loss": 1.4249,
|
| 634 |
+
"step": 430
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.2,
|
| 638 |
+
"grad_norm": 0.1685889272801495,
|
| 639 |
+
"learning_rate": 9.695706161014322e-06,
|
| 640 |
+
"loss": 1.4629,
|
| 641 |
+
"step": 435
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.2,
|
| 645 |
+
"grad_norm": 0.16213828032523545,
|
| 646 |
+
"learning_rate": 9.681739331905784e-06,
|
| 647 |
+
"loss": 1.4633,
|
| 648 |
+
"step": 440
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.2,
|
| 652 |
+
"grad_norm": 0.1722162760562697,
|
| 653 |
+
"learning_rate": 9.667469644026118e-06,
|
| 654 |
+
"loss": 1.4147,
|
| 655 |
+
"step": 445
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.21,
|
| 659 |
+
"grad_norm": 0.16634245789106444,
|
| 660 |
+
"learning_rate": 9.652898020472449e-06,
|
| 661 |
+
"loss": 1.4254,
|
| 662 |
+
"step": 450
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.21,
|
| 666 |
+
"grad_norm": 0.17414333030226264,
|
| 667 |
+
"learning_rate": 9.638025403873939e-06,
|
| 668 |
+
"loss": 1.3734,
|
| 669 |
+
"step": 455
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.21,
|
| 673 |
+
"grad_norm": 0.17078620575685172,
|
| 674 |
+
"learning_rate": 9.622852756330797e-06,
|
| 675 |
+
"loss": 1.4313,
|
| 676 |
+
"step": 460
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.21,
|
| 680 |
+
"grad_norm": 0.17201073443780537,
|
| 681 |
+
"learning_rate": 9.60738105935204e-06,
|
| 682 |
+
"loss": 1.4412,
|
| 683 |
+
"step": 465
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.22,
|
| 687 |
+
"grad_norm": 0.1781118635582674,
|
| 688 |
+
"learning_rate": 9.59161131379201e-06,
|
| 689 |
+
"loss": 1.4102,
|
| 690 |
+
"step": 470
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.22,
|
| 694 |
+
"grad_norm": 0.17417835939253798,
|
| 695 |
+
"learning_rate": 9.575544539785626e-06,
|
| 696 |
+
"loss": 1.4311,
|
| 697 |
+
"step": 475
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.22,
|
| 701 |
+
"grad_norm": 0.17050610923384396,
|
| 702 |
+
"learning_rate": 9.559181776682387e-06,
|
| 703 |
+
"loss": 1.4627,
|
| 704 |
+
"step": 480
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.22,
|
| 708 |
+
"grad_norm": 0.176092363473546,
|
| 709 |
+
"learning_rate": 9.542524082979138e-06,
|
| 710 |
+
"loss": 1.4517,
|
| 711 |
+
"step": 485
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.23,
|
| 715 |
+
"grad_norm": 0.17498193119749225,
|
| 716 |
+
"learning_rate": 9.525572536251608e-06,
|
| 717 |
+
"loss": 1.3956,
|
| 718 |
+
"step": 490
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.23,
|
| 722 |
+
"grad_norm": 0.17003085925682157,
|
| 723 |
+
"learning_rate": 9.50832823308468e-06,
|
| 724 |
+
"loss": 1.4012,
|
| 725 |
+
"step": 495
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.23,
|
| 729 |
+
"grad_norm": 0.17064790853058265,
|
| 730 |
+
"learning_rate": 9.490792289001476e-06,
|
| 731 |
+
"loss": 1.3523,
|
| 732 |
+
"step": 500
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.23,
|
| 736 |
+
"grad_norm": 0.1799693810618531,
|
| 737 |
+
"learning_rate": 9.472965838391187e-06,
|
| 738 |
+
"loss": 1.4446,
|
| 739 |
+
"step": 505
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 0.23,
|
| 743 |
+
"grad_norm": 0.16868170325096435,
|
| 744 |
+
"learning_rate": 9.454850034435679e-06,
|
| 745 |
+
"loss": 1.3912,
|
| 746 |
+
"step": 510
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.24,
|
| 750 |
+
"grad_norm": 0.16981991686336434,
|
| 751 |
+
"learning_rate": 9.436446049034913e-06,
|
| 752 |
+
"loss": 1.3986,
|
| 753 |
+
"step": 515
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.24,
|
| 757 |
+
"grad_norm": 0.1755120644725739,
|
| 758 |
+
"learning_rate": 9.417755072731121e-06,
|
| 759 |
+
"loss": 1.4117,
|
| 760 |
+
"step": 520
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 0.24,
|
| 764 |
+
"grad_norm": 0.1757934575464805,
|
| 765 |
+
"learning_rate": 9.398778314631801e-06,
|
| 766 |
+
"loss": 1.3587,
|
| 767 |
+
"step": 525
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 0.24,
|
| 771 |
+
"grad_norm": 0.173876963970309,
|
| 772 |
+
"learning_rate": 9.379517002331489e-06,
|
| 773 |
+
"loss": 1.3862,
|
| 774 |
+
"step": 530
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.25,
|
| 778 |
+
"grad_norm": 0.17746114421749437,
|
| 779 |
+
"learning_rate": 9.359972381832358e-06,
|
| 780 |
+
"loss": 1.4309,
|
| 781 |
+
"step": 535
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 0.25,
|
| 785 |
+
"grad_norm": 0.16869333613216586,
|
| 786 |
+
"learning_rate": 9.340145717463609e-06,
|
| 787 |
+
"loss": 1.4118,
|
| 788 |
+
"step": 540
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.25,
|
| 792 |
+
"grad_norm": 0.17746743334088458,
|
| 793 |
+
"learning_rate": 9.320038291799679e-06,
|
| 794 |
+
"loss": 1.4433,
|
| 795 |
+
"step": 545
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.25,
|
| 799 |
+
"grad_norm": 0.17587914404814756,
|
| 800 |
+
"learning_rate": 9.299651405577286e-06,
|
| 801 |
+
"loss": 1.4421,
|
| 802 |
+
"step": 550
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 0.26,
|
| 806 |
+
"grad_norm": 0.18048857244310448,
|
| 807 |
+
"learning_rate": 9.278986377611266e-06,
|
| 808 |
+
"loss": 1.4221,
|
| 809 |
+
"step": 555
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 0.26,
|
| 813 |
+
"grad_norm": 0.17371693231140117,
|
| 814 |
+
"learning_rate": 9.258044544709276e-06,
|
| 815 |
+
"loss": 1.4131,
|
| 816 |
+
"step": 560
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 0.26,
|
| 820 |
+
"grad_norm": 0.17693122935797964,
|
| 821 |
+
"learning_rate": 9.236827261585306e-06,
|
| 822 |
+
"loss": 1.4205,
|
| 823 |
+
"step": 565
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 0.26,
|
| 827 |
+
"grad_norm": 0.18630601640696606,
|
| 828 |
+
"learning_rate": 9.215335900772048e-06,
|
| 829 |
+
"loss": 1.4067,
|
| 830 |
+
"step": 570
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.26,
|
| 834 |
+
"grad_norm": 0.17220695844147543,
|
| 835 |
+
"learning_rate": 9.193571852532112e-06,
|
| 836 |
+
"loss": 1.3834,
|
| 837 |
+
"step": 575
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.27,
|
| 841 |
+
"grad_norm": 0.18435801453629633,
|
| 842 |
+
"learning_rate": 9.17153652476808e-06,
|
| 843 |
+
"loss": 1.3485,
|
| 844 |
+
"step": 580
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 0.27,
|
| 848 |
+
"grad_norm": 0.1719982815834864,
|
| 849 |
+
"learning_rate": 9.14923134293144e-06,
|
| 850 |
+
"loss": 1.4265,
|
| 851 |
+
"step": 585
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 0.27,
|
| 855 |
+
"grad_norm": 0.17622887749418029,
|
| 856 |
+
"learning_rate": 9.126657749930365e-06,
|
| 857 |
+
"loss": 1.4242,
|
| 858 |
+
"step": 590
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 0.27,
|
| 862 |
+
"grad_norm": 0.1772303960409497,
|
| 863 |
+
"learning_rate": 9.103817206036383e-06,
|
| 864 |
+
"loss": 1.3901,
|
| 865 |
+
"step": 595
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 0.28,
|
| 869 |
+
"grad_norm": 0.18039291853040396,
|
| 870 |
+
"learning_rate": 9.080711188789903e-06,
|
| 871 |
+
"loss": 1.4193,
|
| 872 |
+
"step": 600
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 0.28,
|
| 876 |
+
"eval_loss": 1.333003282546997,
|
| 877 |
+
"eval_runtime": 1759.7499,
|
| 878 |
+
"eval_samples_per_second": 2.154,
|
| 879 |
+
"eval_steps_per_second": 0.269,
|
| 880 |
+
"step": 600
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.28,
|
| 884 |
+
"grad_norm": 0.18468507528075692,
|
| 885 |
+
"learning_rate": 9.057341192904641e-06,
|
| 886 |
+
"loss": 1.4663,
|
| 887 |
+
"step": 605
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.28,
|
| 891 |
+
"grad_norm": 0.17990669625911423,
|
| 892 |
+
"learning_rate": 9.033708730170925e-06,
|
| 893 |
+
"loss": 1.4289,
|
| 894 |
+
"step": 610
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.28,
|
| 898 |
+
"grad_norm": 0.17925115015014306,
|
| 899 |
+
"learning_rate": 9.009815329357893e-06,
|
| 900 |
+
"loss": 1.4337,
|
| 901 |
+
"step": 615
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.29,
|
| 905 |
+
"grad_norm": 0.1742038025383068,
|
| 906 |
+
"learning_rate": 8.985662536114614e-06,
|
| 907 |
+
"loss": 1.4156,
|
| 908 |
+
"step": 620
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.29,
|
| 912 |
+
"grad_norm": 0.18266353155608991,
|
| 913 |
+
"learning_rate": 8.961251912870077e-06,
|
| 914 |
+
"loss": 1.3896,
|
| 915 |
+
"step": 625
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.29,
|
| 919 |
+
"grad_norm": 0.18057511349721395,
|
| 920 |
+
"learning_rate": 8.936585038732143e-06,
|
| 921 |
+
"loss": 1.3764,
|
| 922 |
+
"step": 630
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.29,
|
| 926 |
+
"grad_norm": 0.18596859871805246,
|
| 927 |
+
"learning_rate": 8.91166350938537e-06,
|
| 928 |
+
"loss": 1.4193,
|
| 929 |
+
"step": 635
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.29,
|
| 933 |
+
"grad_norm": 0.18986971270095016,
|
| 934 |
+
"learning_rate": 8.886488936987817e-06,
|
| 935 |
+
"loss": 1.3955,
|
| 936 |
+
"step": 640
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.3,
|
| 940 |
+
"grad_norm": 0.17418454140586195,
|
| 941 |
+
"learning_rate": 8.861062950066723e-06,
|
| 942 |
+
"loss": 1.427,
|
| 943 |
+
"step": 645
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.3,
|
| 947 |
+
"grad_norm": 0.18149732001872015,
|
| 948 |
+
"learning_rate": 8.835387193413185e-06,
|
| 949 |
+
"loss": 1.4046,
|
| 950 |
+
"step": 650
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.3,
|
| 954 |
+
"grad_norm": 0.18147198520857166,
|
| 955 |
+
"learning_rate": 8.809463327975741e-06,
|
| 956 |
+
"loss": 1.4058,
|
| 957 |
+
"step": 655
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.3,
|
| 961 |
+
"grad_norm": 0.18099108296498378,
|
| 962 |
+
"learning_rate": 8.783293030752932e-06,
|
| 963 |
+
"loss": 1.4066,
|
| 964 |
+
"step": 660
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.31,
|
| 968 |
+
"grad_norm": 0.1794240687483909,
|
| 969 |
+
"learning_rate": 8.756877994684818e-06,
|
| 970 |
+
"loss": 1.3921,
|
| 971 |
+
"step": 665
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.31,
|
| 975 |
+
"grad_norm": 0.1839307276635119,
|
| 976 |
+
"learning_rate": 8.730219928543458e-06,
|
| 977 |
+
"loss": 1.4054,
|
| 978 |
+
"step": 670
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.31,
|
| 982 |
+
"grad_norm": 0.18145863325096048,
|
| 983 |
+
"learning_rate": 8.703320556822375e-06,
|
| 984 |
+
"loss": 1.4053,
|
| 985 |
+
"step": 675
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.31,
|
| 989 |
+
"grad_norm": 0.1808487553528171,
|
| 990 |
+
"learning_rate": 8.676181619624996e-06,
|
| 991 |
+
"loss": 1.4055,
|
| 992 |
+
"step": 680
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.32,
|
| 996 |
+
"grad_norm": 0.1862476804387168,
|
| 997 |
+
"learning_rate": 8.648804872552092e-06,
|
| 998 |
+
"loss": 1.3841,
|
| 999 |
+
"step": 685
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.32,
|
| 1003 |
+
"grad_norm": 0.19563150015616995,
|
| 1004 |
+
"learning_rate": 8.6211920865882e-06,
|
| 1005 |
+
"loss": 1.371,
|
| 1006 |
+
"step": 690
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.32,
|
| 1010 |
+
"grad_norm": 0.18923848385153544,
|
| 1011 |
+
"learning_rate": 8.593345047987069e-06,
|
| 1012 |
+
"loss": 1.3988,
|
| 1013 |
+
"step": 695
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.32,
|
| 1017 |
+
"grad_norm": 0.18078263758464272,
|
| 1018 |
+
"learning_rate": 8.565265558156101e-06,
|
| 1019 |
+
"loss": 1.4024,
|
| 1020 |
+
"step": 700
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.32,
|
| 1024 |
+
"grad_norm": 0.18258637947544226,
|
| 1025 |
+
"learning_rate": 8.536955433539824e-06,
|
| 1026 |
+
"loss": 1.371,
|
| 1027 |
+
"step": 705
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.33,
|
| 1031 |
+
"grad_norm": 0.19116331272141834,
|
| 1032 |
+
"learning_rate": 8.508416505502383e-06,
|
| 1033 |
+
"loss": 1.4456,
|
| 1034 |
+
"step": 710
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.33,
|
| 1038 |
+
"grad_norm": 0.17469959227839357,
|
| 1039 |
+
"learning_rate": 8.479650620209072e-06,
|
| 1040 |
+
"loss": 1.385,
|
| 1041 |
+
"step": 715
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.33,
|
| 1045 |
+
"grad_norm": 0.18410741548679613,
|
| 1046 |
+
"learning_rate": 8.450659638506908e-06,
|
| 1047 |
+
"loss": 1.4095,
|
| 1048 |
+
"step": 720
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.33,
|
| 1052 |
+
"grad_norm": 0.19634261946282605,
|
| 1053 |
+
"learning_rate": 8.421445435804255e-06,
|
| 1054 |
+
"loss": 1.3513,
|
| 1055 |
+
"step": 725
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.34,
|
| 1059 |
+
"grad_norm": 0.17826721350047323,
|
| 1060 |
+
"learning_rate": 8.3920099019495e-06,
|
| 1061 |
+
"loss": 1.3792,
|
| 1062 |
+
"step": 730
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.34,
|
| 1066 |
+
"grad_norm": 0.1826653979119606,
|
| 1067 |
+
"learning_rate": 8.362354941108803e-06,
|
| 1068 |
+
"loss": 1.4448,
|
| 1069 |
+
"step": 735
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.34,
|
| 1073 |
+
"grad_norm": 0.18664731594802075,
|
| 1074 |
+
"learning_rate": 8.33248247164292e-06,
|
| 1075 |
+
"loss": 1.3751,
|
| 1076 |
+
"step": 740
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.34,
|
| 1080 |
+
"grad_norm": 0.18231556377003602,
|
| 1081 |
+
"learning_rate": 8.3023944259831e-06,
|
| 1082 |
+
"loss": 1.3773,
|
| 1083 |
+
"step": 745
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.35,
|
| 1087 |
+
"grad_norm": 0.18711137034484868,
|
| 1088 |
+
"learning_rate": 8.272092750506084e-06,
|
| 1089 |
+
"loss": 1.4096,
|
| 1090 |
+
"step": 750
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 0.35,
|
| 1094 |
+
"grad_norm": 0.1877955269203901,
|
| 1095 |
+
"learning_rate": 8.241579405408192e-06,
|
| 1096 |
+
"loss": 1.3902,
|
| 1097 |
+
"step": 755
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 0.35,
|
| 1101 |
+
"grad_norm": 0.18482019451091206,
|
| 1102 |
+
"learning_rate": 8.21085636457851e-06,
|
| 1103 |
+
"loss": 1.3734,
|
| 1104 |
+
"step": 760
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 0.35,
|
| 1108 |
+
"grad_norm": 0.19891330231660218,
|
| 1109 |
+
"learning_rate": 8.179925615471218e-06,
|
| 1110 |
+
"loss": 1.4061,
|
| 1111 |
+
"step": 765
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 0.35,
|
| 1115 |
+
"grad_norm": 0.18663983192529415,
|
| 1116 |
+
"learning_rate": 8.148789158977012e-06,
|
| 1117 |
+
"loss": 1.3326,
|
| 1118 |
+
"step": 770
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 0.36,
|
| 1122 |
+
"grad_norm": 0.1874487096476331,
|
| 1123 |
+
"learning_rate": 8.117449009293668e-06,
|
| 1124 |
+
"loss": 1.3384,
|
| 1125 |
+
"step": 775
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 0.36,
|
| 1129 |
+
"grad_norm": 0.18710305973456598,
|
| 1130 |
+
"learning_rate": 8.085907193795745e-06,
|
| 1131 |
+
"loss": 1.3828,
|
| 1132 |
+
"step": 780
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 0.36,
|
| 1136 |
+
"grad_norm": 0.18416014945175566,
|
| 1137 |
+
"learning_rate": 8.05416575290344e-06,
|
| 1138 |
+
"loss": 1.3737,
|
| 1139 |
+
"step": 785
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 0.36,
|
| 1143 |
+
"grad_norm": 0.18615555988464447,
|
| 1144 |
+
"learning_rate": 8.022226739950587e-06,
|
| 1145 |
+
"loss": 1.4359,
|
| 1146 |
+
"step": 790
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 0.37,
|
| 1150 |
+
"grad_norm": 0.18594902983475312,
|
| 1151 |
+
"learning_rate": 7.990092221051835e-06,
|
| 1152 |
+
"loss": 1.389,
|
| 1153 |
+
"step": 795
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 0.37,
|
| 1157 |
+
"grad_norm": 0.18537070852284854,
|
| 1158 |
+
"learning_rate": 7.95776427496899e-06,
|
| 1159 |
+
"loss": 1.3593,
|
| 1160 |
+
"step": 800
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 0.37,
|
| 1164 |
+
"eval_loss": 1.323183298110962,
|
| 1165 |
+
"eval_runtime": 1742.9319,
|
| 1166 |
+
"eval_samples_per_second": 2.174,
|
| 1167 |
+
"eval_steps_per_second": 0.272,
|
| 1168 |
+
"step": 800
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.37,
|
| 1172 |
+
"grad_norm": 0.1908169492182471,
|
| 1173 |
+
"learning_rate": 7.925244992976538e-06,
|
| 1174 |
+
"loss": 1.3406,
|
| 1175 |
+
"step": 805
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.37,
|
| 1179 |
+
"grad_norm": 0.18784810075497232,
|
| 1180 |
+
"learning_rate": 7.89253647872637e-06,
|
| 1181 |
+
"loss": 1.3842,
|
| 1182 |
+
"step": 810
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.38,
|
| 1186 |
+
"grad_norm": 0.19406647113841424,
|
| 1187 |
+
"learning_rate": 7.859640848111686e-06,
|
| 1188 |
+
"loss": 1.4286,
|
| 1189 |
+
"step": 815
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.38,
|
| 1193 |
+
"grad_norm": 0.19197603494160256,
|
| 1194 |
+
"learning_rate": 7.826560229130132e-06,
|
| 1195 |
+
"loss": 1.3928,
|
| 1196 |
+
"step": 820
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.38,
|
| 1200 |
+
"grad_norm": 0.19099716433921685,
|
| 1201 |
+
"learning_rate": 7.793296761746126e-06,
|
| 1202 |
+
"loss": 1.362,
|
| 1203 |
+
"step": 825
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.38,
|
| 1207 |
+
"grad_norm": 0.18788356013356616,
|
| 1208 |
+
"learning_rate": 7.759852597752447e-06,
|
| 1209 |
+
"loss": 1.4034,
|
| 1210 |
+
"step": 830
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.38,
|
| 1214 |
+
"grad_norm": 0.1921444320557867,
|
| 1215 |
+
"learning_rate": 7.726229900631015e-06,
|
| 1216 |
+
"loss": 1.3793,
|
| 1217 |
+
"step": 835
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.39,
|
| 1221 |
+
"grad_norm": 0.20734046130350145,
|
| 1222 |
+
"learning_rate": 7.692430845412946e-06,
|
| 1223 |
+
"loss": 1.4203,
|
| 1224 |
+
"step": 840
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.39,
|
| 1228 |
+
"grad_norm": 0.19179256662995678,
|
| 1229 |
+
"learning_rate": 7.658457618537853e-06,
|
| 1230 |
+
"loss": 1.4021,
|
| 1231 |
+
"step": 845
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.39,
|
| 1235 |
+
"grad_norm": 0.18555040743415147,
|
| 1236 |
+
"learning_rate": 7.624312417712403e-06,
|
| 1237 |
+
"loss": 1.423,
|
| 1238 |
+
"step": 850
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.39,
|
| 1242 |
+
"grad_norm": 0.19398963612254347,
|
| 1243 |
+
"learning_rate": 7.58999745176815e-06,
|
| 1244 |
+
"loss": 1.4367,
|
| 1245 |
+
"step": 855
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.4,
|
| 1249 |
+
"grad_norm": 0.19074855950766817,
|
| 1250 |
+
"learning_rate": 7.555514940518647e-06,
|
| 1251 |
+
"loss": 1.3695,
|
| 1252 |
+
"step": 860
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.4,
|
| 1256 |
+
"grad_norm": 0.1893550054117395,
|
| 1257 |
+
"learning_rate": 7.520867114615844e-06,
|
| 1258 |
+
"loss": 1.3939,
|
| 1259 |
+
"step": 865
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.4,
|
| 1263 |
+
"grad_norm": 0.19196726666071628,
|
| 1264 |
+
"learning_rate": 7.486056215405797e-06,
|
| 1265 |
+
"loss": 1.3964,
|
| 1266 |
+
"step": 870
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.4,
|
| 1270 |
+
"grad_norm": 0.2100904294893222,
|
| 1271 |
+
"learning_rate": 7.451084494783668e-06,
|
| 1272 |
+
"loss": 1.3753,
|
| 1273 |
+
"step": 875
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.41,
|
| 1277 |
+
"grad_norm": 0.1870023533707271,
|
| 1278 |
+
"learning_rate": 7.415954215048057e-06,
|
| 1279 |
+
"loss": 1.379,
|
| 1280 |
+
"step": 880
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.41,
|
| 1284 |
+
"grad_norm": 0.19635898208120364,
|
| 1285 |
+
"learning_rate": 7.38066764875465e-06,
|
| 1286 |
+
"loss": 1.4329,
|
| 1287 |
+
"step": 885
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.41,
|
| 1291 |
+
"grad_norm": 0.1896615635850299,
|
| 1292 |
+
"learning_rate": 7.345227078569218e-06,
|
| 1293 |
+
"loss": 1.357,
|
| 1294 |
+
"step": 890
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.41,
|
| 1298 |
+
"grad_norm": 0.19424130426015207,
|
| 1299 |
+
"learning_rate": 7.309634797119941e-06,
|
| 1300 |
+
"loss": 1.3774,
|
| 1301 |
+
"step": 895
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.41,
|
| 1305 |
+
"grad_norm": 0.22888693201104138,
|
| 1306 |
+
"learning_rate": 7.273893106849108e-06,
|
| 1307 |
+
"loss": 1.3976,
|
| 1308 |
+
"step": 900
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.42,
|
| 1312 |
+
"grad_norm": 0.1919456484613934,
|
| 1313 |
+
"learning_rate": 7.23800431986417e-06,
|
| 1314 |
+
"loss": 1.378,
|
| 1315 |
+
"step": 905
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.42,
|
| 1319 |
+
"grad_norm": 0.19241540158105003,
|
| 1320 |
+
"learning_rate": 7.201970757788172e-06,
|
| 1321 |
+
"loss": 1.4094,
|
| 1322 |
+
"step": 910
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.42,
|
| 1326 |
+
"grad_norm": 0.19333437065467562,
|
| 1327 |
+
"learning_rate": 7.165794751609569e-06,
|
| 1328 |
+
"loss": 1.3971,
|
| 1329 |
+
"step": 915
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.42,
|
| 1333 |
+
"grad_norm": 0.19460601771644864,
|
| 1334 |
+
"learning_rate": 7.1294786415314336e-06,
|
| 1335 |
+
"loss": 1.3879,
|
| 1336 |
+
"step": 920
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.43,
|
| 1340 |
+
"grad_norm": 0.18754355788787921,
|
| 1341 |
+
"learning_rate": 7.093024776820076e-06,
|
| 1342 |
+
"loss": 1.3534,
|
| 1343 |
+
"step": 925
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.43,
|
| 1347 |
+
"grad_norm": 0.18648196033472134,
|
| 1348 |
+
"learning_rate": 7.056435515653059e-06,
|
| 1349 |
+
"loss": 1.3969,
|
| 1350 |
+
"step": 930
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.43,
|
| 1354 |
+
"grad_norm": 0.18580702737411495,
|
| 1355 |
+
"learning_rate": 7.019713224966664e-06,
|
| 1356 |
+
"loss": 1.4416,
|
| 1357 |
+
"step": 935
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.43,
|
| 1361 |
+
"grad_norm": 0.24918096880464727,
|
| 1362 |
+
"learning_rate": 6.9828602803027664e-06,
|
| 1363 |
+
"loss": 1.3814,
|
| 1364 |
+
"step": 940
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.44,
|
| 1368 |
+
"grad_norm": 0.19003799001704857,
|
| 1369 |
+
"learning_rate": 6.945879065655164e-06,
|
| 1370 |
+
"loss": 1.3581,
|
| 1371 |
+
"step": 945
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.44,
|
| 1375 |
+
"grad_norm": 0.19777328354162663,
|
| 1376 |
+
"learning_rate": 6.90877197331536e-06,
|
| 1377 |
+
"loss": 1.3883,
|
| 1378 |
+
"step": 950
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.44,
|
| 1382 |
+
"grad_norm": 0.1978053982444075,
|
| 1383 |
+
"learning_rate": 6.871541403717808e-06,
|
| 1384 |
+
"loss": 1.4298,
|
| 1385 |
+
"step": 955
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.44,
|
| 1389 |
+
"grad_norm": 0.19360877663534273,
|
| 1390 |
+
"learning_rate": 6.83418976528462e-06,
|
| 1391 |
+
"loss": 1.3623,
|
| 1392 |
+
"step": 960
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.44,
|
| 1396 |
+
"grad_norm": 0.19124472077513613,
|
| 1397 |
+
"learning_rate": 6.7967194742697866e-06,
|
| 1398 |
+
"loss": 1.3965,
|
| 1399 |
+
"step": 965
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.45,
|
| 1403 |
+
"grad_norm": 0.2026314484251062,
|
| 1404 |
+
"learning_rate": 6.759132954602852e-06,
|
| 1405 |
+
"loss": 1.3889,
|
| 1406 |
+
"step": 970
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.45,
|
| 1410 |
+
"grad_norm": 0.20177996042623167,
|
| 1411 |
+
"learning_rate": 6.721432637732117e-06,
|
| 1412 |
+
"loss": 1.3987,
|
| 1413 |
+
"step": 975
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.45,
|
| 1417 |
+
"grad_norm": 0.19199095023199664,
|
| 1418 |
+
"learning_rate": 6.6836209624673575e-06,
|
| 1419 |
+
"loss": 1.3658,
|
| 1420 |
+
"step": 980
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.45,
|
| 1424 |
+
"grad_norm": 0.19092380360827313,
|
| 1425 |
+
"learning_rate": 6.64570037482205e-06,
|
| 1426 |
+
"loss": 1.3601,
|
| 1427 |
+
"step": 985
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.46,
|
| 1431 |
+
"grad_norm": 0.21156775391897173,
|
| 1432 |
+
"learning_rate": 6.607673327855149e-06,
|
| 1433 |
+
"loss": 1.4427,
|
| 1434 |
+
"step": 990
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.46,
|
| 1438 |
+
"grad_norm": 0.19213500215723073,
|
| 1439 |
+
"learning_rate": 6.569542281512388e-06,
|
| 1440 |
+
"loss": 1.3934,
|
| 1441 |
+
"step": 995
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.46,
|
| 1445 |
+
"grad_norm": 0.19675677797230362,
|
| 1446 |
+
"learning_rate": 6.531309702467159e-06,
|
| 1447 |
+
"loss": 1.3552,
|
| 1448 |
+
"step": 1000
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 0.46,
|
| 1452 |
+
"eval_loss": 1.3166489601135254,
|
| 1453 |
+
"eval_runtime": 1748.0429,
|
| 1454 |
+
"eval_samples_per_second": 2.168,
|
| 1455 |
+
"eval_steps_per_second": 0.271,
|
| 1456 |
+
"step": 1000
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 0.46,
|
| 1460 |
+
"grad_norm": 0.18781337537819495,
|
| 1461 |
+
"learning_rate": 6.492978063960942e-06,
|
| 1462 |
+
"loss": 1.3937,
|
| 1463 |
+
"step": 1005
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 0.47,
|
| 1467 |
+
"grad_norm": 0.1935060574506341,
|
| 1468 |
+
"learning_rate": 6.45454984564331e-06,
|
| 1469 |
+
"loss": 1.4284,
|
| 1470 |
+
"step": 1010
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 0.47,
|
| 1474 |
+
"grad_norm": 0.1936429054806515,
|
| 1475 |
+
"learning_rate": 6.41602753341152e-06,
|
| 1476 |
+
"loss": 1.3618,
|
| 1477 |
+
"step": 1015
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 0.47,
|
| 1481 |
+
"grad_norm": 0.19582370428755932,
|
| 1482 |
+
"learning_rate": 6.377413619249713e-06,
|
| 1483 |
+
"loss": 1.3822,
|
| 1484 |
+
"step": 1020
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 0.47,
|
| 1488 |
+
"grad_norm": 0.18931877193304708,
|
| 1489 |
+
"learning_rate": 6.338710601067691e-06,
|
| 1490 |
+
"loss": 1.3473,
|
| 1491 |
+
"step": 1025
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 0.47,
|
| 1495 |
+
"grad_norm": 0.1952618362908433,
|
| 1496 |
+
"learning_rate": 6.2999209825393445e-06,
|
| 1497 |
+
"loss": 1.369,
|
| 1498 |
+
"step": 1030
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 0.48,
|
| 1502 |
+
"grad_norm": 0.196265797323174,
|
| 1503 |
+
"learning_rate": 6.2610472729406905e-06,
|
| 1504 |
+
"loss": 1.3679,
|
| 1505 |
+
"step": 1035
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 0.48,
|
| 1509 |
+
"grad_norm": 0.1909001830769802,
|
| 1510 |
+
"learning_rate": 6.222091986987534e-06,
|
| 1511 |
+
"loss": 1.3939,
|
| 1512 |
+
"step": 1040
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 0.48,
|
| 1516 |
+
"grad_norm": 0.1974314278029084,
|
| 1517 |
+
"learning_rate": 6.18305764467281e-06,
|
| 1518 |
+
"loss": 1.4111,
|
| 1519 |
+
"step": 1045
|
| 1520 |
+
},
|
| 1521 |
+
{
|
| 1522 |
+
"epoch": 0.48,
|
| 1523 |
+
"grad_norm": 0.19874201405315123,
|
| 1524 |
+
"learning_rate": 6.143946771103561e-06,
|
| 1525 |
+
"loss": 1.383,
|
| 1526 |
+
"step": 1050
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 0.49,
|
| 1530 |
+
"grad_norm": 0.20109125948229767,
|
| 1531 |
+
"learning_rate": 6.104761896337581e-06,
|
| 1532 |
+
"loss": 1.3548,
|
| 1533 |
+
"step": 1055
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 0.49,
|
| 1537 |
+
"grad_norm": 0.18937099603698346,
|
| 1538 |
+
"learning_rate": 6.0655055552197616e-06,
|
| 1539 |
+
"loss": 1.4427,
|
| 1540 |
+
"step": 1060
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"epoch": 0.49,
|
| 1544 |
+
"grad_norm": 0.20257668978871882,
|
| 1545 |
+
"learning_rate": 6.026180287218106e-06,
|
| 1546 |
+
"loss": 1.3773,
|
| 1547 |
+
"step": 1065
|
| 1548 |
+
},
|
| 1549 |
+
{
|
| 1550 |
+
"epoch": 0.49,
|
| 1551 |
+
"grad_norm": 0.19836764097355777,
|
| 1552 |
+
"learning_rate": 5.986788636259453e-06,
|
| 1553 |
+
"loss": 1.3945,
|
| 1554 |
+
"step": 1070
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 0.5,
|
| 1558 |
+
"grad_norm": 0.19345413549116036,
|
| 1559 |
+
"learning_rate": 5.9473331505649125e-06,
|
| 1560 |
+
"loss": 1.4439,
|
| 1561 |
+
"step": 1075
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 0.5,
|
| 1565 |
+
"grad_norm": 0.19576415671480885,
|
| 1566 |
+
"learning_rate": 5.907816382485026e-06,
|
| 1567 |
+
"loss": 1.3432,
|
| 1568 |
+
"step": 1080
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 0.5,
|
| 1572 |
+
"grad_norm": 0.19643295445396305,
|
| 1573 |
+
"learning_rate": 5.8682408883346535e-06,
|
| 1574 |
+
"loss": 1.3459,
|
| 1575 |
+
"step": 1085
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 0.5,
|
| 1579 |
+
"grad_norm": 0.19760654138918068,
|
| 1580 |
+
"learning_rate": 5.828609228227603e-06,
|
| 1581 |
+
"loss": 1.4334,
|
| 1582 |
+
"step": 1090
|
| 1583 |
+
},
|
| 1584 |
+
{
|
| 1585 |
+
"epoch": 0.5,
|
| 1586 |
+
"grad_norm": 0.1907622356589435,
|
| 1587 |
+
"learning_rate": 5.788923965911028e-06,
|
| 1588 |
+
"loss": 1.3195,
|
| 1589 |
+
"step": 1095
|
| 1590 |
+
},
|
| 1591 |
+
{
|
| 1592 |
+
"epoch": 0.51,
|
| 1593 |
+
"grad_norm": 0.19974010922162466,
|
| 1594 |
+
"learning_rate": 5.749187668599574e-06,
|
| 1595 |
+
"loss": 1.3973,
|
| 1596 |
+
"step": 1100
|
| 1597 |
+
},
|
| 1598 |
+
{
|
| 1599 |
+
"epoch": 0.51,
|
| 1600 |
+
"grad_norm": 0.1899811113208983,
|
| 1601 |
+
"learning_rate": 5.709402906809307e-06,
|
| 1602 |
+
"loss": 1.3788,
|
| 1603 |
+
"step": 1105
|
| 1604 |
+
},
|
| 1605 |
+
{
|
| 1606 |
+
"epoch": 0.51,
|
| 1607 |
+
"grad_norm": 0.19125136139691074,
|
| 1608 |
+
"learning_rate": 5.669572254191431e-06,
|
| 1609 |
+
"loss": 1.3749,
|
| 1610 |
+
"step": 1110
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 0.51,
|
| 1614 |
+
"grad_norm": 0.19773999696793723,
|
| 1615 |
+
"learning_rate": 5.6296982873658e-06,
|
| 1616 |
+
"loss": 1.3812,
|
| 1617 |
+
"step": 1115
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 0.52,
|
| 1621 |
+
"grad_norm": 0.19522230435252472,
|
| 1622 |
+
"learning_rate": 5.5897835857542315e-06,
|
| 1623 |
+
"loss": 1.3639,
|
| 1624 |
+
"step": 1120
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"epoch": 0.52,
|
| 1628 |
+
"grad_norm": 0.19203158758627778,
|
| 1629 |
+
"learning_rate": 5.549830731413655e-06,
|
| 1630 |
+
"loss": 1.3988,
|
| 1631 |
+
"step": 1125
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 0.52,
|
| 1635 |
+
"grad_norm": 0.19785365288187984,
|
| 1636 |
+
"learning_rate": 5.509842308869075e-06,
|
| 1637 |
+
"loss": 1.4031,
|
| 1638 |
+
"step": 1130
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 0.52,
|
| 1642 |
+
"grad_norm": 0.20110593532241236,
|
| 1643 |
+
"learning_rate": 5.469820904946383e-06,
|
| 1644 |
+
"loss": 1.3447,
|
| 1645 |
+
"step": 1135
|
| 1646 |
+
},
|
| 1647 |
+
{
|
| 1648 |
+
"epoch": 0.53,
|
| 1649 |
+
"grad_norm": 0.20730230846403253,
|
| 1650 |
+
"learning_rate": 5.429769108605013e-06,
|
| 1651 |
+
"loss": 1.433,
|
| 1652 |
+
"step": 1140
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 0.53,
|
| 1656 |
+
"grad_norm": 0.19538915157122386,
|
| 1657 |
+
"learning_rate": 5.389689510770462e-06,
|
| 1658 |
+
"loss": 1.3751,
|
| 1659 |
+
"step": 1145
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 0.53,
|
| 1663 |
+
"grad_norm": 0.19657731321379315,
|
| 1664 |
+
"learning_rate": 5.3495847041666935e-06,
|
| 1665 |
+
"loss": 1.4427,
|
| 1666 |
+
"step": 1150
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 0.53,
|
| 1670 |
+
"grad_norm": 0.19885598934336826,
|
| 1671 |
+
"learning_rate": 5.30945728314841e-06,
|
| 1672 |
+
"loss": 1.3526,
|
| 1673 |
+
"step": 1155
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 0.53,
|
| 1677 |
+
"grad_norm": 0.19763223830130308,
|
| 1678 |
+
"learning_rate": 5.269309843533222e-06,
|
| 1679 |
+
"loss": 1.3792,
|
| 1680 |
+
"step": 1160
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 0.54,
|
| 1684 |
+
"grad_norm": 0.1934600019166271,
|
| 1685 |
+
"learning_rate": 5.229144982433736e-06,
|
| 1686 |
+
"loss": 1.3827,
|
| 1687 |
+
"step": 1165
|
| 1688 |
+
},
|
| 1689 |
+
{
|
| 1690 |
+
"epoch": 0.54,
|
| 1691 |
+
"grad_norm": 0.19215817298202406,
|
| 1692 |
+
"learning_rate": 5.188965298089538e-06,
|
| 1693 |
+
"loss": 1.3609,
|
| 1694 |
+
"step": 1170
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 0.54,
|
| 1698 |
+
"grad_norm": 0.1950665854099098,
|
| 1699 |
+
"learning_rate": 5.148773389699123e-06,
|
| 1700 |
+
"loss": 1.3728,
|
| 1701 |
+
"step": 1175
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 0.54,
|
| 1705 |
+
"grad_norm": 0.20163181813335146,
|
| 1706 |
+
"learning_rate": 5.108571857251754e-06,
|
| 1707 |
+
"loss": 1.3937,
|
| 1708 |
+
"step": 1180
|
| 1709 |
+
},
|
| 1710 |
+
{
|
| 1711 |
+
"epoch": 0.55,
|
| 1712 |
+
"grad_norm": 0.19492701026725848,
|
| 1713 |
+
"learning_rate": 5.068363301359263e-06,
|
| 1714 |
+
"loss": 1.3976,
|
| 1715 |
+
"step": 1185
|
| 1716 |
+
},
|
| 1717 |
+
{
|
| 1718 |
+
"epoch": 0.55,
|
| 1719 |
+
"grad_norm": 0.1915934216230785,
|
| 1720 |
+
"learning_rate": 5.0281503230878304e-06,
|
| 1721 |
+
"loss": 1.3778,
|
| 1722 |
+
"step": 1190
|
| 1723 |
+
},
|
| 1724 |
+
{
|
| 1725 |
+
"epoch": 0.55,
|
| 1726 |
+
"grad_norm": 0.19100537033272963,
|
| 1727 |
+
"learning_rate": 4.98793552378971e-06,
|
| 1728 |
+
"loss": 1.4221,
|
| 1729 |
+
"step": 1195
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 0.55,
|
| 1733 |
+
"grad_norm": 0.19909784027087774,
|
| 1734 |
+
"learning_rate": 4.947721504934966e-06,
|
| 1735 |
+
"loss": 1.3685,
|
| 1736 |
+
"step": 1200
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 0.55,
|
| 1740 |
+
"eval_loss": 1.3122756481170654,
|
| 1741 |
+
"eval_runtime": 1747.9099,
|
| 1742 |
+
"eval_samples_per_second": 2.168,
|
| 1743 |
+
"eval_steps_per_second": 0.271,
|
| 1744 |
+
"step": 1200
|
| 1745 |
+
},
|
| 1746 |
+
{
|
| 1747 |
+
"epoch": 0.56,
|
| 1748 |
+
"grad_norm": 0.19577442673853007,
|
| 1749 |
+
"learning_rate": 4.907510867943167e-06,
|
| 1750 |
+
"loss": 1.3595,
|
| 1751 |
+
"step": 1205
|
| 1752 |
+
},
|
| 1753 |
+
{
|
| 1754 |
+
"epoch": 0.56,
|
| 1755 |
+
"grad_norm": 0.2063936713267001,
|
| 1756 |
+
"learning_rate": 4.867306214015117e-06,
|
| 1757 |
+
"loss": 1.4202,
|
| 1758 |
+
"step": 1210
|
| 1759 |
+
},
|
| 1760 |
+
{
|
| 1761 |
+
"epoch": 0.56,
|
| 1762 |
+
"grad_norm": 0.19879562103497236,
|
| 1763 |
+
"learning_rate": 4.8271101439645765e-06,
|
| 1764 |
+
"loss": 1.3934,
|
| 1765 |
+
"step": 1215
|
| 1766 |
+
},
|
| 1767 |
+
{
|
| 1768 |
+
"epoch": 0.56,
|
| 1769 |
+
"grad_norm": 0.19945548173818886,
|
| 1770 |
+
"learning_rate": 4.786925258050024e-06,
|
| 1771 |
+
"loss": 1.3395,
|
| 1772 |
+
"step": 1220
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 0.56,
|
| 1776 |
+
"grad_norm": 0.209259697791073,
|
| 1777 |
+
"learning_rate": 4.746754155806437e-06,
|
| 1778 |
+
"loss": 1.4072,
|
| 1779 |
+
"step": 1225
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 0.57,
|
| 1783 |
+
"grad_norm": 0.19280116611929857,
|
| 1784 |
+
"learning_rate": 4.706599435877143e-06,
|
| 1785 |
+
"loss": 1.3976,
|
| 1786 |
+
"step": 1230
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 0.57,
|
| 1790 |
+
"grad_norm": 0.1990941406891665,
|
| 1791 |
+
"learning_rate": 4.666463695845701e-06,
|
| 1792 |
+
"loss": 1.3912,
|
| 1793 |
+
"step": 1235
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 0.57,
|
| 1797 |
+
"grad_norm": 0.19455600992105357,
|
| 1798 |
+
"learning_rate": 4.626349532067879e-06,
|
| 1799 |
+
"loss": 1.4003,
|
| 1800 |
+
"step": 1240
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"epoch": 0.57,
|
| 1804 |
+
"grad_norm": 0.20315382252326522,
|
| 1805 |
+
"learning_rate": 4.586259539503687e-06,
|
| 1806 |
+
"loss": 1.3876,
|
| 1807 |
+
"step": 1245
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 0.58,
|
| 1811 |
+
"grad_norm": 0.19085048019709233,
|
| 1812 |
+
"learning_rate": 4.546196311549515e-06,
|
| 1813 |
+
"loss": 1.415,
|
| 1814 |
+
"step": 1250
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"epoch": 0.58,
|
| 1818 |
+
"grad_norm": 0.19155602915410036,
|
| 1819 |
+
"learning_rate": 4.506162439870366e-06,
|
| 1820 |
+
"loss": 1.388,
|
| 1821 |
+
"step": 1255
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 0.58,
|
| 1825 |
+
"grad_norm": 0.1962993457750995,
|
| 1826 |
+
"learning_rate": 4.466160514232206e-06,
|
| 1827 |
+
"loss": 1.4069,
|
| 1828 |
+
"step": 1260
|
| 1829 |
+
},
|
| 1830 |
+
{
|
| 1831 |
+
"epoch": 0.58,
|
| 1832 |
+
"grad_norm": 0.19440064625069065,
|
| 1833 |
+
"learning_rate": 4.426193122334433e-06,
|
| 1834 |
+
"loss": 1.3625,
|
| 1835 |
+
"step": 1265
|
| 1836 |
+
},
|
| 1837 |
+
{
|
| 1838 |
+
"epoch": 0.59,
|
| 1839 |
+
"grad_norm": 0.19907155435638502,
|
| 1840 |
+
"learning_rate": 4.386262849642474e-06,
|
| 1841 |
+
"loss": 1.3621,
|
| 1842 |
+
"step": 1270
|
| 1843 |
+
},
|
| 1844 |
+
{
|
| 1845 |
+
"epoch": 0.59,
|
| 1846 |
+
"grad_norm": 0.19846401001306227,
|
| 1847 |
+
"learning_rate": 4.346372279220543e-06,
|
| 1848 |
+
"loss": 1.3438,
|
| 1849 |
+
"step": 1275
|
| 1850 |
+
},
|
| 1851 |
+
{
|
| 1852 |
+
"epoch": 0.59,
|
| 1853 |
+
"grad_norm": 0.19990637435356196,
|
| 1854 |
+
"learning_rate": 4.306523991564536e-06,
|
| 1855 |
+
"loss": 1.3857,
|
| 1856 |
+
"step": 1280
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 0.59,
|
| 1860 |
+
"grad_norm": 0.1983045043565906,
|
| 1861 |
+
"learning_rate": 4.266720564435105e-06,
|
| 1862 |
+
"loss": 1.3477,
|
| 1863 |
+
"step": 1285
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 0.59,
|
| 1867 |
+
"grad_norm": 0.2008086079053878,
|
| 1868 |
+
"learning_rate": 4.226964572690905e-06,
|
| 1869 |
+
"loss": 1.4032,
|
| 1870 |
+
"step": 1290
|
| 1871 |
+
},
|
| 1872 |
+
{
|
| 1873 |
+
"epoch": 0.6,
|
| 1874 |
+
"grad_norm": 0.2394515243143434,
|
| 1875 |
+
"learning_rate": 4.187258588122019e-06,
|
| 1876 |
+
"loss": 1.3757,
|
| 1877 |
+
"step": 1295
|
| 1878 |
+
},
|
| 1879 |
+
{
|
| 1880 |
+
"epoch": 0.6,
|
| 1881 |
+
"grad_norm": 0.1971799914885616,
|
| 1882 |
+
"learning_rate": 4.147605179283604e-06,
|
| 1883 |
+
"loss": 1.4156,
|
| 1884 |
+
"step": 1300
|
| 1885 |
+
},
|
| 1886 |
+
{
|
| 1887 |
+
"epoch": 0.6,
|
| 1888 |
+
"grad_norm": 0.2073477392149783,
|
| 1889 |
+
"learning_rate": 4.108006911329722e-06,
|
| 1890 |
+
"loss": 1.3881,
|
| 1891 |
+
"step": 1305
|
| 1892 |
+
},
|
| 1893 |
+
{
|
| 1894 |
+
"epoch": 0.6,
|
| 1895 |
+
"grad_norm": 0.2073153166108959,
|
| 1896 |
+
"learning_rate": 4.068466345847409e-06,
|
| 1897 |
+
"loss": 1.3687,
|
| 1898 |
+
"step": 1310
|
| 1899 |
+
},
|
| 1900 |
+
{
|
| 1901 |
+
"epoch": 0.61,
|
| 1902 |
+
"grad_norm": 0.20054177344121227,
|
| 1903 |
+
"learning_rate": 4.028986040690963e-06,
|
| 1904 |
+
"loss": 1.3785,
|
| 1905 |
+
"step": 1315
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 0.61,
|
| 1909 |
+
"grad_norm": 0.20604849012426923,
|
| 1910 |
+
"learning_rate": 3.989568549816479e-06,
|
| 1911 |
+
"loss": 1.4169,
|
| 1912 |
+
"step": 1320
|
| 1913 |
+
},
|
| 1914 |
+
{
|
| 1915 |
+
"epoch": 0.61,
|
| 1916 |
+
"grad_norm": 0.19467062948633831,
|
| 1917 |
+
"learning_rate": 3.9502164231166354e-06,
|
| 1918 |
+
"loss": 1.4168,
|
| 1919 |
+
"step": 1325
|
| 1920 |
+
},
|
| 1921 |
+
{
|
| 1922 |
+
"epoch": 0.61,
|
| 1923 |
+
"grad_norm": 0.21219636801396732,
|
| 1924 |
+
"learning_rate": 3.910932206255742e-06,
|
| 1925 |
+
"loss": 1.3772,
|
| 1926 |
+
"step": 1330
|
| 1927 |
+
},
|
| 1928 |
+
{
|
| 1929 |
+
"epoch": 0.61,
|
| 1930 |
+
"grad_norm": 0.20051941796299297,
|
| 1931 |
+
"learning_rate": 3.87171844050507e-06,
|
| 1932 |
+
"loss": 1.3864,
|
| 1933 |
+
"step": 1335
|
| 1934 |
+
},
|
| 1935 |
+
{
|
| 1936 |
+
"epoch": 0.62,
|
| 1937 |
+
"grad_norm": 0.20033592892185176,
|
| 1938 |
+
"learning_rate": 3.8325776625784464e-06,
|
| 1939 |
+
"loss": 1.3984,
|
| 1940 |
+
"step": 1340
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"epoch": 0.62,
|
| 1944 |
+
"grad_norm": 0.19559628194598214,
|
| 1945 |
+
"learning_rate": 3.793512404468162e-06,
|
| 1946 |
+
"loss": 1.3954,
|
| 1947 |
+
"step": 1345
|
| 1948 |
+
},
|
| 1949 |
+
{
|
| 1950 |
+
"epoch": 0.62,
|
| 1951 |
+
"grad_norm": 0.21009377333677687,
|
| 1952 |
+
"learning_rate": 3.7545251932811824e-06,
|
| 1953 |
+
"loss": 1.3799,
|
| 1954 |
+
"step": 1350
|
| 1955 |
+
},
|
| 1956 |
+
{
|
| 1957 |
+
"epoch": 0.62,
|
| 1958 |
+
"grad_norm": 0.2058943301550432,
|
| 1959 |
+
"learning_rate": 3.7156185510756613e-06,
|
| 1960 |
+
"loss": 1.3763,
|
| 1961 |
+
"step": 1355
|
| 1962 |
+
},
|
| 1963 |
+
{
|
| 1964 |
+
"epoch": 0.63,
|
| 1965 |
+
"grad_norm": 0.20090178955938068,
|
| 1966 |
+
"learning_rate": 3.6767949946978026e-06,
|
| 1967 |
+
"loss": 1.4162,
|
| 1968 |
+
"step": 1360
|
| 1969 |
+
},
|
| 1970 |
+
{
|
| 1971 |
+
"epoch": 0.63,
|
| 1972 |
+
"grad_norm": 0.2034374577879598,
|
| 1973 |
+
"learning_rate": 3.6380570356190346e-06,
|
| 1974 |
+
"loss": 1.402,
|
| 1975 |
+
"step": 1365
|
| 1976 |
+
},
|
| 1977 |
+
{
|
| 1978 |
+
"epoch": 0.63,
|
| 1979 |
+
"grad_norm": 0.19652020002950302,
|
| 1980 |
+
"learning_rate": 3.5994071797735513e-06,
|
| 1981 |
+
"loss": 1.3667,
|
| 1982 |
+
"step": 1370
|
| 1983 |
+
},
|
| 1984 |
+
{
|
| 1985 |
+
"epoch": 0.63,
|
| 1986 |
+
"grad_norm": 0.20049219114904884,
|
| 1987 |
+
"learning_rate": 3.560847927396206e-06,
|
| 1988 |
+
"loss": 1.419,
|
| 1989 |
+
"step": 1375
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 0.64,
|
| 1993 |
+
"grad_norm": 0.20857502981558484,
|
| 1994 |
+
"learning_rate": 3.5223817728607675e-06,
|
| 1995 |
+
"loss": 1.4082,
|
| 1996 |
+
"step": 1380
|
| 1997 |
+
},
|
| 1998 |
+
{
|
| 1999 |
+
"epoch": 0.64,
|
| 2000 |
+
"grad_norm": 0.19767809519926405,
|
| 2001 |
+
"learning_rate": 3.484011204518568e-06,
|
| 2002 |
+
"loss": 1.3947,
|
| 2003 |
+
"step": 1385
|
| 2004 |
+
},
|
| 2005 |
+
{
|
| 2006 |
+
"epoch": 0.64,
|
| 2007 |
+
"grad_norm": 0.1948689279113259,
|
| 2008 |
+
"learning_rate": 3.4457387045375255e-06,
|
| 2009 |
+
"loss": 1.3625,
|
| 2010 |
+
"step": 1390
|
| 2011 |
+
},
|
| 2012 |
+
{
|
| 2013 |
+
"epoch": 0.64,
|
| 2014 |
+
"grad_norm": 0.20429495021474384,
|
| 2015 |
+
"learning_rate": 3.4075667487415785e-06,
|
| 2016 |
+
"loss": 1.3978,
|
| 2017 |
+
"step": 1395
|
| 2018 |
+
},
|
| 2019 |
+
{
|
| 2020 |
+
"epoch": 0.64,
|
| 2021 |
+
"grad_norm": 0.2022436664727946,
|
| 2022 |
+
"learning_rate": 3.3694978064505258e-06,
|
| 2023 |
+
"loss": 1.3487,
|
| 2024 |
+
"step": 1400
|
| 2025 |
+
},
|
| 2026 |
+
{
|
| 2027 |
+
"epoch": 0.64,
|
| 2028 |
+
"eval_loss": 1.3093819618225098,
|
| 2029 |
+
"eval_runtime": 1769.0297,
|
| 2030 |
+
"eval_samples_per_second": 2.142,
|
| 2031 |
+
"eval_steps_per_second": 0.268,
|
| 2032 |
+
"step": 1400
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 0.65,
|
| 2036 |
+
"grad_norm": 0.2010813579540422,
|
| 2037 |
+
"learning_rate": 3.331534340320287e-06,
|
| 2038 |
+
"loss": 1.3582,
|
| 2039 |
+
"step": 1405
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 0.65,
|
| 2043 |
+
"grad_norm": 0.19489960246084403,
|
| 2044 |
+
"learning_rate": 3.293678806183596e-06,
|
| 2045 |
+
"loss": 1.42,
|
| 2046 |
+
"step": 1410
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 0.65,
|
| 2050 |
+
"grad_norm": 0.20100567658267351,
|
| 2051 |
+
"learning_rate": 3.255933652891133e-06,
|
| 2052 |
+
"loss": 1.3887,
|
| 2053 |
+
"step": 1415
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.65,
|
| 2057 |
+
"grad_norm": 0.198604846014806,
|
| 2058 |
+
"learning_rate": 3.218301322153111e-06,
|
| 2059 |
+
"loss": 1.3543,
|
| 2060 |
+
"step": 1420
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 0.66,
|
| 2064 |
+
"grad_norm": 0.20073641523853392,
|
| 2065 |
+
"learning_rate": 3.180784248381322e-06,
|
| 2066 |
+
"loss": 1.3513,
|
| 2067 |
+
"step": 1425
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.66,
|
| 2071 |
+
"grad_norm": 0.19424293274594104,
|
| 2072 |
+
"learning_rate": 3.1433848585316607e-06,
|
| 2073 |
+
"loss": 1.3885,
|
| 2074 |
+
"step": 1430
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 0.66,
|
| 2078 |
+
"grad_norm": 0.2028571716247717,
|
| 2079 |
+
"learning_rate": 3.10610557194712e-06,
|
| 2080 |
+
"loss": 1.3824,
|
| 2081 |
+
"step": 1435
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 0.66,
|
| 2085 |
+
"grad_norm": 0.1973272586923241,
|
| 2086 |
+
"learning_rate": 3.068948800201289e-06,
|
| 2087 |
+
"loss": 1.3332,
|
| 2088 |
+
"step": 1440
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 0.67,
|
| 2092 |
+
"grad_norm": 0.20459650028827572,
|
| 2093 |
+
"learning_rate": 3.0319169469423487e-06,
|
| 2094 |
+
"loss": 1.3715,
|
| 2095 |
+
"step": 1445
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 0.67,
|
| 2099 |
+
"grad_norm": 0.1966290880736998,
|
| 2100 |
+
"learning_rate": 2.995012407737581e-06,
|
| 2101 |
+
"loss": 1.3985,
|
| 2102 |
+
"step": 1450
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 0.67,
|
| 2106 |
+
"grad_norm": 0.20394208158347749,
|
| 2107 |
+
"learning_rate": 2.958237569918404e-06,
|
| 2108 |
+
"loss": 1.3867,
|
| 2109 |
+
"step": 1455
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.67,
|
| 2113 |
+
"grad_norm": 0.1971397504636877,
|
| 2114 |
+
"learning_rate": 2.9215948124259343e-06,
|
| 2115 |
+
"loss": 1.3739,
|
| 2116 |
+
"step": 1460
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 0.67,
|
| 2120 |
+
"grad_norm": 0.1984132646647921,
|
| 2121 |
+
"learning_rate": 2.885086505657094e-06,
|
| 2122 |
+
"loss": 1.4459,
|
| 2123 |
+
"step": 1465
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.68,
|
| 2127 |
+
"grad_norm": 0.20375542452519896,
|
| 2128 |
+
"learning_rate": 2.848715011311271e-06,
|
| 2129 |
+
"loss": 1.3606,
|
| 2130 |
+
"step": 1470
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 0.68,
|
| 2134 |
+
"grad_norm": 0.19875885515941272,
|
| 2135 |
+
"learning_rate": 2.8124826822375473e-06,
|
| 2136 |
+
"loss": 1.4034,
|
| 2137 |
+
"step": 1475
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.68,
|
| 2141 |
+
"grad_norm": 0.20571233168262154,
|
| 2142 |
+
"learning_rate": 2.7763918622824903e-06,
|
| 2143 |
+
"loss": 1.4358,
|
| 2144 |
+
"step": 1480
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 0.68,
|
| 2148 |
+
"grad_norm": 0.20325983672817444,
|
| 2149 |
+
"learning_rate": 2.7404448861385293e-06,
|
| 2150 |
+
"loss": 1.3271,
|
| 2151 |
+
"step": 1485
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.69,
|
| 2155 |
+
"grad_norm": 0.204674596724046,
|
| 2156 |
+
"learning_rate": 2.7046440791929306e-06,
|
| 2157 |
+
"loss": 1.3656,
|
| 2158 |
+
"step": 1490
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 0.69,
|
| 2162 |
+
"grad_norm": 0.19864331126229412,
|
| 2163 |
+
"learning_rate": 2.6689917573773615e-06,
|
| 2164 |
+
"loss": 1.3712,
|
| 2165 |
+
"step": 1495
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.69,
|
| 2169 |
+
"grad_norm": 0.19759957217116436,
|
| 2170 |
+
"learning_rate": 2.633490227018092e-06,
|
| 2171 |
+
"loss": 1.4061,
|
| 2172 |
+
"step": 1500
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 0.69,
|
| 2176 |
+
"grad_norm": 0.1963001810018751,
|
| 2177 |
+
"learning_rate": 2.5981417846867753e-06,
|
| 2178 |
+
"loss": 1.3753,
|
| 2179 |
+
"step": 1505
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.7,
|
| 2183 |
+
"grad_norm": 0.2037326390652298,
|
| 2184 |
+
"learning_rate": 2.5629487170518974e-06,
|
| 2185 |
+
"loss": 1.3468,
|
| 2186 |
+
"step": 1510
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 0.7,
|
| 2190 |
+
"grad_norm": 0.20092378895163732,
|
| 2191 |
+
"learning_rate": 2.527913300730863e-06,
|
| 2192 |
+
"loss": 1.3831,
|
| 2193 |
+
"step": 1515
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 0.7,
|
| 2197 |
+
"grad_norm": 0.2075661167474541,
|
| 2198 |
+
"learning_rate": 2.4930378021426977e-06,
|
| 2199 |
+
"loss": 1.3786,
|
| 2200 |
+
"step": 1520
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 0.7,
|
| 2204 |
+
"grad_norm": 0.2002833079588797,
|
| 2205 |
+
"learning_rate": 2.4583244773614675e-06,
|
| 2206 |
+
"loss": 1.4058,
|
| 2207 |
+
"step": 1525
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 0.7,
|
| 2211 |
+
"grad_norm": 0.20306778592495606,
|
| 2212 |
+
"learning_rate": 2.423775571970301e-06,
|
| 2213 |
+
"loss": 1.3704,
|
| 2214 |
+
"step": 1530
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 0.71,
|
| 2218 |
+
"grad_norm": 0.22057110661612167,
|
| 2219 |
+
"learning_rate": 2.3893933209161465e-06,
|
| 2220 |
+
"loss": 1.3965,
|
| 2221 |
+
"step": 1535
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 0.71,
|
| 2225 |
+
"grad_norm": 0.20413023154970353,
|
| 2226 |
+
"learning_rate": 2.3551799483651894e-06,
|
| 2227 |
+
"loss": 1.3935,
|
| 2228 |
+
"step": 1540
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 0.71,
|
| 2232 |
+
"grad_norm": 0.2013070052195424,
|
| 2233 |
+
"learning_rate": 2.321137667558965e-06,
|
| 2234 |
+
"loss": 1.3757,
|
| 2235 |
+
"step": 1545
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 0.71,
|
| 2239 |
+
"grad_norm": 0.20133662802149876,
|
| 2240 |
+
"learning_rate": 2.2872686806712037e-06,
|
| 2241 |
+
"loss": 1.3533,
|
| 2242 |
+
"step": 1550
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 0.72,
|
| 2246 |
+
"grad_norm": 0.19816355686283976,
|
| 2247 |
+
"learning_rate": 2.2535751786653476e-06,
|
| 2248 |
+
"loss": 1.4014,
|
| 2249 |
+
"step": 1555
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 0.72,
|
| 2253 |
+
"grad_norm": 0.20020195119951492,
|
| 2254 |
+
"learning_rate": 2.220059341152837e-06,
|
| 2255 |
+
"loss": 1.3721,
|
| 2256 |
+
"step": 1560
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 0.72,
|
| 2260 |
+
"grad_norm": 0.20298393289470038,
|
| 2261 |
+
"learning_rate": 2.1867233362521127e-06,
|
| 2262 |
+
"loss": 1.3255,
|
| 2263 |
+
"step": 1565
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 0.72,
|
| 2267 |
+
"grad_norm": 0.20399564011279728,
|
| 2268 |
+
"learning_rate": 2.153569320448348e-06,
|
| 2269 |
+
"loss": 1.3928,
|
| 2270 |
+
"step": 1570
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 0.73,
|
| 2274 |
+
"grad_norm": 0.20016486527706043,
|
| 2275 |
+
"learning_rate": 2.120599438453968e-06,
|
| 2276 |
+
"loss": 1.3769,
|
| 2277 |
+
"step": 1575
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 0.73,
|
| 2281 |
+
"grad_norm": 0.20169522873545517,
|
| 2282 |
+
"learning_rate": 2.087815823069886e-06,
|
| 2283 |
+
"loss": 1.3745,
|
| 2284 |
+
"step": 1580
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 0.73,
|
| 2288 |
+
"grad_norm": 0.1991770376256046,
|
| 2289 |
+
"learning_rate": 2.055220595047551e-06,
|
| 2290 |
+
"loss": 1.3542,
|
| 2291 |
+
"step": 1585
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 0.73,
|
| 2295 |
+
"grad_norm": 0.2083925008192503,
|
| 2296 |
+
"learning_rate": 2.022815862951751e-06,
|
| 2297 |
+
"loss": 1.4182,
|
| 2298 |
+
"step": 1590
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 0.73,
|
| 2302 |
+
"grad_norm": 0.20086735172689546,
|
| 2303 |
+
"learning_rate": 1.990603723024213e-06,
|
| 2304 |
+
"loss": 1.3524,
|
| 2305 |
+
"step": 1595
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 0.74,
|
| 2309 |
+
"grad_norm": 0.20621921540546848,
|
| 2310 |
+
"learning_rate": 1.9585862590480005e-06,
|
| 2311 |
+
"loss": 1.3891,
|
| 2312 |
+
"step": 1600
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 0.74,
|
| 2316 |
+
"eval_loss": 1.3076461553573608,
|
| 2317 |
+
"eval_runtime": 1777.0113,
|
| 2318 |
+
"eval_samples_per_second": 2.133,
|
| 2319 |
+
"eval_steps_per_second": 0.267,
|
| 2320 |
+
"step": 1600
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 0.74,
|
| 2324 |
+
"grad_norm": 0.20007769280547363,
|
| 2325 |
+
"learning_rate": 1.926765542212707e-06,
|
| 2326 |
+
"loss": 1.3856,
|
| 2327 |
+
"step": 1605
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 0.74,
|
| 2331 |
+
"grad_norm": 0.1980821730251063,
|
| 2332 |
+
"learning_rate": 1.8951436309804766e-06,
|
| 2333 |
+
"loss": 1.383,
|
| 2334 |
+
"step": 1610
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 0.74,
|
| 2338 |
+
"grad_norm": 0.20314121257047116,
|
| 2339 |
+
"learning_rate": 1.8637225709528506e-06,
|
| 2340 |
+
"loss": 1.3752,
|
| 2341 |
+
"step": 1615
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 0.75,
|
| 2345 |
+
"grad_norm": 0.2000738503413009,
|
| 2346 |
+
"learning_rate": 1.832504394738428e-06,
|
| 2347 |
+
"loss": 1.3501,
|
| 2348 |
+
"step": 1620
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 0.75,
|
| 2352 |
+
"grad_norm": 0.19626992677384789,
|
| 2353 |
+
"learning_rate": 1.8014911218213832e-06,
|
| 2354 |
+
"loss": 1.3776,
|
| 2355 |
+
"step": 1625
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 0.75,
|
| 2359 |
+
"grad_norm": 0.2132143728962325,
|
| 2360 |
+
"learning_rate": 1.770684758430824e-06,
|
| 2361 |
+
"loss": 1.3641,
|
| 2362 |
+
"step": 1630
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 0.75,
|
| 2366 |
+
"grad_norm": 0.20230145941791186,
|
| 2367 |
+
"learning_rate": 1.7400872974110088e-06,
|
| 2368 |
+
"loss": 1.3714,
|
| 2369 |
+
"step": 1635
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 0.76,
|
| 2373 |
+
"grad_norm": 0.20322390315184813,
|
| 2374 |
+
"learning_rate": 1.7097007180924375e-06,
|
| 2375 |
+
"loss": 1.3559,
|
| 2376 |
+
"step": 1640
|
| 2377 |
+
},
|
| 2378 |
+
{
|
| 2379 |
+
"epoch": 0.76,
|
| 2380 |
+
"grad_norm": 0.2097270533204938,
|
| 2381 |
+
"learning_rate": 1.6795269861638041e-06,
|
| 2382 |
+
"loss": 1.3555,
|
| 2383 |
+
"step": 1645
|
| 2384 |
+
},
|
| 2385 |
+
{
|
| 2386 |
+
"epoch": 0.76,
|
| 2387 |
+
"grad_norm": 0.20409576963271045,
|
| 2388 |
+
"learning_rate": 1.6495680535448405e-06,
|
| 2389 |
+
"loss": 1.3376,
|
| 2390 |
+
"step": 1650
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 0.76,
|
| 2394 |
+
"grad_norm": 0.209992582333707,
|
| 2395 |
+
"learning_rate": 1.6198258582600418e-06,
|
| 2396 |
+
"loss": 1.3393,
|
| 2397 |
+
"step": 1655
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 0.76,
|
| 2401 |
+
"grad_norm": 0.20186485511811675,
|
| 2402 |
+
"learning_rate": 1.590302324313303e-06,
|
| 2403 |
+
"loss": 1.3476,
|
| 2404 |
+
"step": 1660
|
| 2405 |
+
},
|
| 2406 |
+
{
|
| 2407 |
+
"epoch": 0.77,
|
| 2408 |
+
"grad_norm": 0.2039959334961091,
|
| 2409 |
+
"learning_rate": 1.5609993615634578e-06,
|
| 2410 |
+
"loss": 1.4172,
|
| 2411 |
+
"step": 1665
|
| 2412 |
+
},
|
| 2413 |
+
{
|
| 2414 |
+
"epoch": 0.77,
|
| 2415 |
+
"grad_norm": 0.2032115658244104,
|
| 2416 |
+
"learning_rate": 1.531918865600725e-06,
|
| 2417 |
+
"loss": 1.3866,
|
| 2418 |
+
"step": 1670
|
| 2419 |
+
},
|
| 2420 |
+
{
|
| 2421 |
+
"epoch": 0.77,
|
| 2422 |
+
"grad_norm": 0.20663125873556282,
|
| 2423 |
+
"learning_rate": 1.5030627176240903e-06,
|
| 2424 |
+
"loss": 1.3413,
|
| 2425 |
+
"step": 1675
|
| 2426 |
+
},
|
| 2427 |
+
{
|
| 2428 |
+
"epoch": 0.77,
|
| 2429 |
+
"grad_norm": 0.21419285282068773,
|
| 2430 |
+
"learning_rate": 1.4744327843196043e-06,
|
| 2431 |
+
"loss": 1.3685,
|
| 2432 |
+
"step": 1680
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 0.78,
|
| 2436 |
+
"grad_norm": 0.20427116148089472,
|
| 2437 |
+
"learning_rate": 1.446030917739633e-06,
|
| 2438 |
+
"loss": 1.3864,
|
| 2439 |
+
"step": 1685
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 0.78,
|
| 2443 |
+
"grad_norm": 0.21267201464638189,
|
| 2444 |
+
"learning_rate": 1.4178589551830585e-06,
|
| 2445 |
+
"loss": 1.3578,
|
| 2446 |
+
"step": 1690
|
| 2447 |
+
},
|
| 2448 |
+
{
|
| 2449 |
+
"epoch": 0.78,
|
| 2450 |
+
"grad_norm": 0.2021417320485247,
|
| 2451 |
+
"learning_rate": 1.3899187190764062e-06,
|
| 2452 |
+
"loss": 1.4034,
|
| 2453 |
+
"step": 1695
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 0.78,
|
| 2457 |
+
"grad_norm": 0.19953428976865786,
|
| 2458 |
+
"learning_rate": 1.3622120168559656e-06,
|
| 2459 |
+
"loss": 1.3378,
|
| 2460 |
+
"step": 1700
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 0.79,
|
| 2464 |
+
"grad_norm": 0.20322168013048264,
|
| 2465 |
+
"learning_rate": 1.3347406408508695e-06,
|
| 2466 |
+
"loss": 1.4032,
|
| 2467 |
+
"step": 1705
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 0.79,
|
| 2471 |
+
"grad_norm": 0.19617963419360818,
|
| 2472 |
+
"learning_rate": 1.3075063681671408e-06,
|
| 2473 |
+
"loss": 1.3815,
|
| 2474 |
+
"step": 1710
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 0.79,
|
| 2478 |
+
"grad_norm": 0.20338294719666272,
|
| 2479 |
+
"learning_rate": 1.280510960572745e-06,
|
| 2480 |
+
"loss": 1.376,
|
| 2481 |
+
"step": 1715
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 0.79,
|
| 2485 |
+
"grad_norm": 0.20462364560864363,
|
| 2486 |
+
"learning_rate": 1.2537561643836087e-06,
|
| 2487 |
+
"loss": 1.3866,
|
| 2488 |
+
"step": 1720
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 0.79,
|
| 2492 |
+
"grad_norm": 0.1963149280229846,
|
| 2493 |
+
"learning_rate": 1.2272437103506596e-06,
|
| 2494 |
+
"loss": 1.372,
|
| 2495 |
+
"step": 1725
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 0.8,
|
| 2499 |
+
"grad_norm": 0.19716113021249304,
|
| 2500 |
+
"learning_rate": 1.200975313547867e-06,
|
| 2501 |
+
"loss": 1.3599,
|
| 2502 |
+
"step": 1730
|
| 2503 |
+
},
|
| 2504 |
+
{
|
| 2505 |
+
"epoch": 0.8,
|
| 2506 |
+
"grad_norm": 0.20573469916350295,
|
| 2507 |
+
"learning_rate": 1.1749526732612842e-06,
|
| 2508 |
+
"loss": 1.3562,
|
| 2509 |
+
"step": 1735
|
| 2510 |
+
},
|
| 2511 |
+
{
|
| 2512 |
+
"epoch": 0.8,
|
| 2513 |
+
"grad_norm": 0.20684676012413714,
|
| 2514 |
+
"learning_rate": 1.1491774728791416e-06,
|
| 2515 |
+
"loss": 1.3296,
|
| 2516 |
+
"step": 1740
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 0.8,
|
| 2520 |
+
"grad_norm": 0.2090768120512491,
|
| 2521 |
+
"learning_rate": 1.1236513797829285e-06,
|
| 2522 |
+
"loss": 1.4248,
|
| 2523 |
+
"step": 1745
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 0.81,
|
| 2527 |
+
"grad_norm": 0.20571837930886522,
|
| 2528 |
+
"learning_rate": 1.0983760452395415e-06,
|
| 2529 |
+
"loss": 1.3609,
|
| 2530 |
+
"step": 1750
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 0.81,
|
| 2534 |
+
"grad_norm": 0.20867562597707268,
|
| 2535 |
+
"learning_rate": 1.07335310429447e-06,
|
| 2536 |
+
"loss": 1.3848,
|
| 2537 |
+
"step": 1755
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 0.81,
|
| 2541 |
+
"grad_norm": 0.1988423228103918,
|
| 2542 |
+
"learning_rate": 1.048584175666012e-06,
|
| 2543 |
+
"loss": 1.3712,
|
| 2544 |
+
"step": 1760
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 0.81,
|
| 2548 |
+
"grad_norm": 0.21063039041467455,
|
| 2549 |
+
"learning_rate": 1.0240708616405788e-06,
|
| 2550 |
+
"loss": 1.3611,
|
| 2551 |
+
"step": 1765
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 0.82,
|
| 2555 |
+
"grad_norm": 0.20306439311302277,
|
| 2556 |
+
"learning_rate": 9.998147479690251e-07,
|
| 2557 |
+
"loss": 1.3478,
|
| 2558 |
+
"step": 1770
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 0.82,
|
| 2562 |
+
"grad_norm": 0.2020964557722793,
|
| 2563 |
+
"learning_rate": 9.75817403764079e-07,
|
| 2564 |
+
"loss": 1.3433,
|
| 2565 |
+
"step": 1775
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 0.82,
|
| 2569 |
+
"grad_norm": 0.20597190432737983,
|
| 2570 |
+
"learning_rate": 9.520803813988366e-07,
|
| 2571 |
+
"loss": 1.4058,
|
| 2572 |
+
"step": 1780
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 0.82,
|
| 2576 |
+
"grad_norm": 0.20380209329114748,
|
| 2577 |
+
"learning_rate": 9.286052164063369e-07,
|
| 2578 |
+
"loss": 1.4028,
|
| 2579 |
+
"step": 1785
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 0.82,
|
| 2583 |
+
"grad_norm": 0.2041857004062742,
|
| 2584 |
+
"learning_rate": 9.053934273802312e-07,
|
| 2585 |
+
"loss": 1.383,
|
| 2586 |
+
"step": 1790
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 0.83,
|
| 2590 |
+
"grad_norm": 0.20684812528414637,
|
| 2591 |
+
"learning_rate": 8.824465158765433e-07,
|
| 2592 |
+
"loss": 1.3512,
|
| 2593 |
+
"step": 1795
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 0.83,
|
| 2597 |
+
"grad_norm": 0.20386591712113425,
|
| 2598 |
+
"learning_rate": 8.597659663165364e-07,
|
| 2599 |
+
"loss": 1.3858,
|
| 2600 |
+
"step": 1800
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 0.83,
|
| 2604 |
+
"eval_loss": 1.306676983833313,
|
| 2605 |
+
"eval_runtime": 1760.6924,
|
| 2606 |
+
"eval_samples_per_second": 2.153,
|
| 2607 |
+
"eval_steps_per_second": 0.269,
|
| 2608 |
+
"step": 1800
|
| 2609 |
+
},
|
| 2610 |
+
{
|
| 2611 |
+
"epoch": 0.83,
|
| 2612 |
+
"grad_norm": 0.19511280510666812,
|
| 2613 |
+
"learning_rate": 8.373532458906897e-07,
|
| 2614 |
+
"loss": 1.3261,
|
| 2615 |
+
"step": 1805
|
| 2616 |
+
},
|
| 2617 |
+
{
|
| 2618 |
+
"epoch": 0.83,
|
| 2619 |
+
"grad_norm": 0.20356348959673148,
|
| 2620 |
+
"learning_rate": 8.15209804463783e-07,
|
| 2621 |
+
"loss": 1.3288,
|
| 2622 |
+
"step": 1810
|
| 2623 |
+
},
|
| 2624 |
+
{
|
| 2625 |
+
"epoch": 0.84,
|
| 2626 |
+
"grad_norm": 0.2103018153717413,
|
| 2627 |
+
"learning_rate": 7.93337074481108e-07,
|
| 2628 |
+
"loss": 1.4425,
|
| 2629 |
+
"step": 1815
|
| 2630 |
+
},
|
| 2631 |
+
{
|
| 2632 |
+
"epoch": 0.84,
|
| 2633 |
+
"grad_norm": 0.20468220080909677,
|
| 2634 |
+
"learning_rate": 7.717364708758024e-07,
|
| 2635 |
+
"loss": 1.406,
|
| 2636 |
+
"step": 1820
|
| 2637 |
+
},
|
| 2638 |
+
{
|
| 2639 |
+
"epoch": 0.84,
|
| 2640 |
+
"grad_norm": 0.2040164153992187,
|
| 2641 |
+
"learning_rate": 7.504093909773174e-07,
|
| 2642 |
+
"loss": 1.3601,
|
| 2643 |
+
"step": 1825
|
| 2644 |
+
},
|
| 2645 |
+
{
|
| 2646 |
+
"epoch": 0.84,
|
| 2647 |
+
"grad_norm": 0.19961500414001193,
|
| 2648 |
+
"learning_rate": 7.293572144210332e-07,
|
| 2649 |
+
"loss": 1.3777,
|
| 2650 |
+
"step": 1830
|
| 2651 |
+
},
|
| 2652 |
+
{
|
| 2653 |
+
"epoch": 0.85,
|
| 2654 |
+
"grad_norm": 0.20035042813237278,
|
| 2655 |
+
"learning_rate": 7.085813030590022e-07,
|
| 2656 |
+
"loss": 1.3944,
|
| 2657 |
+
"step": 1835
|
| 2658 |
+
},
|
| 2659 |
+
{
|
| 2660 |
+
"epoch": 0.85,
|
| 2661 |
+
"grad_norm": 0.20685428154054034,
|
| 2662 |
+
"learning_rate": 6.880830008718564e-07,
|
| 2663 |
+
"loss": 1.3778,
|
| 2664 |
+
"step": 1840
|
| 2665 |
+
},
|
| 2666 |
+
{
|
| 2667 |
+
"epoch": 0.85,
|
| 2668 |
+
"grad_norm": 0.19642667708352796,
|
| 2669 |
+
"learning_rate": 6.678636338818645e-07,
|
| 2670 |
+
"loss": 1.3458,
|
| 2671 |
+
"step": 1845
|
| 2672 |
+
},
|
| 2673 |
+
{
|
| 2674 |
+
"epoch": 0.85,
|
| 2675 |
+
"grad_norm": 0.20222774080494071,
|
| 2676 |
+
"learning_rate": 6.47924510067151e-07,
|
| 2677 |
+
"loss": 1.3655,
|
| 2678 |
+
"step": 1850
|
| 2679 |
+
},
|
| 2680 |
+
{
|
| 2681 |
+
"epoch": 0.85,
|
| 2682 |
+
"grad_norm": 0.20419539962584285,
|
| 2683 |
+
"learning_rate": 6.282669192770896e-07,
|
| 2684 |
+
"loss": 1.424,
|
| 2685 |
+
"step": 1855
|
| 2686 |
+
},
|
| 2687 |
+
{
|
| 2688 |
+
"epoch": 0.86,
|
| 2689 |
+
"grad_norm": 0.1975487856167091,
|
| 2690 |
+
"learning_rate": 6.088921331488568e-07,
|
| 2691 |
+
"loss": 1.3424,
|
| 2692 |
+
"step": 1860
|
| 2693 |
+
},
|
| 2694 |
+
{
|
| 2695 |
+
"epoch": 0.86,
|
| 2696 |
+
"grad_norm": 0.2094178118159778,
|
| 2697 |
+
"learning_rate": 5.898014050251765e-07,
|
| 2698 |
+
"loss": 1.3611,
|
| 2699 |
+
"step": 1865
|
| 2700 |
+
},
|
| 2701 |
+
{
|
| 2702 |
+
"epoch": 0.86,
|
| 2703 |
+
"grad_norm": 0.20636955576818874,
|
| 2704 |
+
"learning_rate": 5.709959698732359e-07,
|
| 2705 |
+
"loss": 1.3779,
|
| 2706 |
+
"step": 1870
|
| 2707 |
+
},
|
| 2708 |
+
{
|
| 2709 |
+
"epoch": 0.86,
|
| 2710 |
+
"grad_norm": 0.21747927560303068,
|
| 2711 |
+
"learning_rate": 5.524770442047978e-07,
|
| 2712 |
+
"loss": 1.3308,
|
| 2713 |
+
"step": 1875
|
| 2714 |
+
},
|
| 2715 |
+
{
|
| 2716 |
+
"epoch": 0.87,
|
| 2717 |
+
"grad_norm": 0.20050302654738292,
|
| 2718 |
+
"learning_rate": 5.342458259975147e-07,
|
| 2719 |
+
"loss": 1.3865,
|
| 2720 |
+
"step": 1880
|
| 2721 |
+
},
|
| 2722 |
+
{
|
| 2723 |
+
"epoch": 0.87,
|
| 2724 |
+
"grad_norm": 0.2392412132808601,
|
| 2725 |
+
"learning_rate": 5.163034946174161e-07,
|
| 2726 |
+
"loss": 1.3792,
|
| 2727 |
+
"step": 1885
|
| 2728 |
+
},
|
| 2729 |
+
{
|
| 2730 |
+
"epoch": 0.87,
|
| 2731 |
+
"grad_norm": 0.20914070749895322,
|
| 2732 |
+
"learning_rate": 4.986512107426283e-07,
|
| 2733 |
+
"loss": 1.3812,
|
| 2734 |
+
"step": 1890
|
| 2735 |
+
},
|
| 2736 |
+
{
|
| 2737 |
+
"epoch": 0.87,
|
| 2738 |
+
"grad_norm": 0.21320420478322508,
|
| 2739 |
+
"learning_rate": 4.812901162882871e-07,
|
| 2740 |
+
"loss": 1.443,
|
| 2741 |
+
"step": 1895
|
| 2742 |
+
},
|
| 2743 |
+
{
|
| 2744 |
+
"epoch": 0.88,
|
| 2745 |
+
"grad_norm": 0.20606583697965636,
|
| 2746 |
+
"learning_rate": 4.6422133433266513e-07,
|
| 2747 |
+
"loss": 1.3546,
|
| 2748 |
+
"step": 1900
|
| 2749 |
+
},
|
| 2750 |
+
{
|
| 2751 |
+
"epoch": 0.88,
|
| 2752 |
+
"grad_norm": 0.20597370559054526,
|
| 2753 |
+
"learning_rate": 4.474459690445293e-07,
|
| 2754 |
+
"loss": 1.3803,
|
| 2755 |
+
"step": 1905
|
| 2756 |
+
},
|
| 2757 |
+
{
|
| 2758 |
+
"epoch": 0.88,
|
| 2759 |
+
"grad_norm": 0.20609624124174958,
|
| 2760 |
+
"learning_rate": 4.309651056117009e-07,
|
| 2761 |
+
"loss": 1.3806,
|
| 2762 |
+
"step": 1910
|
| 2763 |
+
},
|
| 2764 |
+
{
|
| 2765 |
+
"epoch": 0.88,
|
| 2766 |
+
"grad_norm": 0.21011536963816732,
|
| 2767 |
+
"learning_rate": 4.1477981017086387e-07,
|
| 2768 |
+
"loss": 1.3857,
|
| 2769 |
+
"step": 1915
|
| 2770 |
+
},
|
| 2771 |
+
{
|
| 2772 |
+
"epoch": 0.88,
|
| 2773 |
+
"grad_norm": 0.20861991251552262,
|
| 2774 |
+
"learning_rate": 3.9889112973859554e-07,
|
| 2775 |
+
"loss": 1.4178,
|
| 2776 |
+
"step": 1920
|
| 2777 |
+
},
|
| 2778 |
+
{
|
| 2779 |
+
"epoch": 0.89,
|
| 2780 |
+
"grad_norm": 0.20565429912809985,
|
| 2781 |
+
"learning_rate": 3.8330009214363197e-07,
|
| 2782 |
+
"loss": 1.3485,
|
| 2783 |
+
"step": 1925
|
| 2784 |
+
},
|
| 2785 |
+
{
|
| 2786 |
+
"epoch": 0.89,
|
| 2787 |
+
"grad_norm": 0.213262370271027,
|
| 2788 |
+
"learning_rate": 3.680077059603876e-07,
|
| 2789 |
+
"loss": 1.3857,
|
| 2790 |
+
"step": 1930
|
| 2791 |
+
},
|
| 2792 |
+
{
|
| 2793 |
+
"epoch": 0.89,
|
| 2794 |
+
"grad_norm": 0.21006993775062202,
|
| 2795 |
+
"learning_rate": 3.530149604436983e-07,
|
| 2796 |
+
"loss": 1.3718,
|
| 2797 |
+
"step": 1935
|
| 2798 |
+
},
|
| 2799 |
+
{
|
| 2800 |
+
"epoch": 0.89,
|
| 2801 |
+
"grad_norm": 0.20971631358735854,
|
| 2802 |
+
"learning_rate": 3.3832282546483686e-07,
|
| 2803 |
+
"loss": 1.3401,
|
| 2804 |
+
"step": 1940
|
| 2805 |
+
},
|
| 2806 |
+
{
|
| 2807 |
+
"epoch": 0.9,
|
| 2808 |
+
"grad_norm": 0.20675053040706537,
|
| 2809 |
+
"learning_rate": 3.239322514487686e-07,
|
| 2810 |
+
"loss": 1.3976,
|
| 2811 |
+
"step": 1945
|
| 2812 |
+
},
|
| 2813 |
+
{
|
| 2814 |
+
"epoch": 0.9,
|
| 2815 |
+
"grad_norm": 0.2070605402743848,
|
| 2816 |
+
"learning_rate": 3.098441693126719e-07,
|
| 2817 |
+
"loss": 1.3801,
|
| 2818 |
+
"step": 1950
|
| 2819 |
+
},
|
| 2820 |
+
{
|
| 2821 |
+
"epoch": 0.9,
|
| 2822 |
+
"grad_norm": 0.2036473853339382,
|
| 2823 |
+
"learning_rate": 2.9605949040571456e-07,
|
| 2824 |
+
"loss": 1.3975,
|
| 2825 |
+
"step": 1955
|
| 2826 |
+
},
|
| 2827 |
+
{
|
| 2828 |
+
"epoch": 0.9,
|
| 2829 |
+
"grad_norm": 0.20446499651024982,
|
| 2830 |
+
"learning_rate": 2.8257910645009935e-07,
|
| 2831 |
+
"loss": 1.3932,
|
| 2832 |
+
"step": 1960
|
| 2833 |
+
},
|
| 2834 |
+
{
|
| 2835 |
+
"epoch": 0.91,
|
| 2836 |
+
"grad_norm": 0.20745728206982056,
|
| 2837 |
+
"learning_rate": 2.6940388948338057e-07,
|
| 2838 |
+
"loss": 1.4214,
|
| 2839 |
+
"step": 1965
|
| 2840 |
+
},
|
| 2841 |
+
{
|
| 2842 |
+
"epoch": 0.91,
|
| 2843 |
+
"grad_norm": 0.20628378675298625,
|
| 2844 |
+
"learning_rate": 2.565346918020534e-07,
|
| 2845 |
+
"loss": 1.3234,
|
| 2846 |
+
"step": 1970
|
| 2847 |
+
},
|
| 2848 |
+
{
|
| 2849 |
+
"epoch": 0.91,
|
| 2850 |
+
"grad_norm": 0.19884308459081187,
|
| 2851 |
+
"learning_rate": 2.4397234590641696e-07,
|
| 2852 |
+
"loss": 1.4086,
|
| 2853 |
+
"step": 1975
|
| 2854 |
+
},
|
| 2855 |
+
{
|
| 2856 |
+
"epoch": 0.91,
|
| 2857 |
+
"grad_norm": 0.196985413218799,
|
| 2858 |
+
"learning_rate": 2.3171766444672227e-07,
|
| 2859 |
+
"loss": 1.4203,
|
| 2860 |
+
"step": 1980
|
| 2861 |
+
},
|
| 2862 |
+
{
|
| 2863 |
+
"epoch": 0.91,
|
| 2864 |
+
"grad_norm": 0.20225024562843938,
|
| 2865 |
+
"learning_rate": 2.1977144017060027e-07,
|
| 2866 |
+
"loss": 1.3859,
|
| 2867 |
+
"step": 1985
|
| 2868 |
+
},
|
| 2869 |
+
{
|
| 2870 |
+
"epoch": 0.92,
|
| 2871 |
+
"grad_norm": 0.20030763530819898,
|
| 2872 |
+
"learning_rate": 2.0813444587178156e-07,
|
| 2873 |
+
"loss": 1.3889,
|
| 2874 |
+
"step": 1990
|
| 2875 |
+
},
|
| 2876 |
+
{
|
| 2877 |
+
"epoch": 0.92,
|
| 2878 |
+
"grad_norm": 0.20327002619311596,
|
| 2879 |
+
"learning_rate": 1.9680743434010385e-07,
|
| 2880 |
+
"loss": 1.3745,
|
| 2881 |
+
"step": 1995
|
| 2882 |
+
},
|
| 2883 |
+
{
|
| 2884 |
+
"epoch": 0.92,
|
| 2885 |
+
"grad_norm": 0.20095518840823687,
|
| 2886 |
+
"learning_rate": 1.8579113831281525e-07,
|
| 2887 |
+
"loss": 1.3635,
|
| 2888 |
+
"step": 2000
|
| 2889 |
+
},
|
| 2890 |
+
{
|
| 2891 |
+
"epoch": 0.92,
|
| 2892 |
+
"eval_loss": 1.3063520193099976,
|
| 2893 |
+
"eval_runtime": 2013.9504,
|
| 2894 |
+
"eval_samples_per_second": 1.882,
|
| 2895 |
+
"eval_steps_per_second": 0.235,
|
| 2896 |
+
"step": 2000
|
| 2897 |
+
},
|
| 2898 |
+
{
|
| 2899 |
+
"epoch": 0.92,
|
| 2900 |
+
"grad_norm": 0.20459938594623875,
|
| 2901 |
+
"learning_rate": 1.7508627042717387e-07,
|
| 2902 |
+
"loss": 1.4269,
|
| 2903 |
+
"step": 2005
|
| 2904 |
+
},
|
| 2905 |
+
{
|
| 2906 |
+
"epoch": 0.93,
|
| 2907 |
+
"grad_norm": 0.2004705031433909,
|
| 2908 |
+
"learning_rate": 1.6469352317434627e-07,
|
| 2909 |
+
"loss": 1.3789,
|
| 2910 |
+
"step": 2010
|
| 2911 |
+
},
|
| 2912 |
+
{
|
| 2913 |
+
"epoch": 0.93,
|
| 2914 |
+
"grad_norm": 0.19922047944368607,
|
| 2915 |
+
"learning_rate": 1.5461356885461077e-07,
|
| 2916 |
+
"loss": 1.3811,
|
| 2917 |
+
"step": 2015
|
| 2918 |
+
},
|
| 2919 |
+
{
|
| 2920 |
+
"epoch": 0.93,
|
| 2921 |
+
"grad_norm": 0.20506581374899654,
|
| 2922 |
+
"learning_rate": 1.4484705953386968e-07,
|
| 2923 |
+
"loss": 1.3677,
|
| 2924 |
+
"step": 2020
|
| 2925 |
+
},
|
| 2926 |
+
{
|
| 2927 |
+
"epoch": 0.93,
|
| 2928 |
+
"grad_norm": 0.20196871274072786,
|
| 2929 |
+
"learning_rate": 1.35394627001465e-07,
|
| 2930 |
+
"loss": 1.3871,
|
| 2931 |
+
"step": 2025
|
| 2932 |
+
},
|
| 2933 |
+
{
|
| 2934 |
+
"epoch": 0.94,
|
| 2935 |
+
"grad_norm": 0.21302376799020897,
|
| 2936 |
+
"learning_rate": 1.2625688272930925e-07,
|
| 2937 |
+
"loss": 1.3673,
|
| 2938 |
+
"step": 2030
|
| 2939 |
+
},
|
| 2940 |
+
{
|
| 2941 |
+
"epoch": 0.94,
|
| 2942 |
+
"grad_norm": 0.20437076323448575,
|
| 2943 |
+
"learning_rate": 1.174344178323289e-07,
|
| 2944 |
+
"loss": 1.3701,
|
| 2945 |
+
"step": 2035
|
| 2946 |
+
},
|
| 2947 |
+
{
|
| 2948 |
+
"epoch": 0.94,
|
| 2949 |
+
"grad_norm": 0.20259273082335125,
|
| 2950 |
+
"learning_rate": 1.0892780303022377e-07,
|
| 2951 |
+
"loss": 1.4004,
|
| 2952 |
+
"step": 2040
|
| 2953 |
+
},
|
| 2954 |
+
{
|
| 2955 |
+
"epoch": 0.94,
|
| 2956 |
+
"grad_norm": 0.19927961571470354,
|
| 2957 |
+
"learning_rate": 1.007375886105555e-07,
|
| 2958 |
+
"loss": 1.3781,
|
| 2959 |
+
"step": 2045
|
| 2960 |
+
},
|
| 2961 |
+
{
|
| 2962 |
+
"epoch": 0.94,
|
| 2963 |
+
"grad_norm": 0.19648191268958623,
|
| 2964 |
+
"learning_rate": 9.286430439313876e-08,
|
| 2965 |
+
"loss": 1.3719,
|
| 2966 |
+
"step": 2050
|
| 2967 |
+
},
|
| 2968 |
+
{
|
| 2969 |
+
"epoch": 0.95,
|
| 2970 |
+
"grad_norm": 0.2081842753213948,
|
| 2971 |
+
"learning_rate": 8.530845969577594e-08,
|
| 2972 |
+
"loss": 1.3347,
|
| 2973 |
+
"step": 2055
|
| 2974 |
+
},
|
| 2975 |
+
{
|
| 2976 |
+
"epoch": 0.95,
|
| 2977 |
+
"grad_norm": 0.19777453793305202,
|
| 2978 |
+
"learning_rate": 7.80705433013046e-08,
|
| 2979 |
+
"loss": 1.3645,
|
| 2980 |
+
"step": 2060
|
| 2981 |
+
},
|
| 2982 |
+
{
|
| 2983 |
+
"epoch": 0.95,
|
| 2984 |
+
"grad_norm": 0.2001901456526902,
|
| 2985 |
+
"learning_rate": 7.115102342598101e-08,
|
| 2986 |
+
"loss": 1.3549,
|
| 2987 |
+
"step": 2065
|
| 2988 |
+
},
|
| 2989 |
+
{
|
| 2990 |
+
"epoch": 0.95,
|
| 2991 |
+
"grad_norm": 0.2085779076020987,
|
| 2992 |
+
"learning_rate": 6.455034768919288e-08,
|
| 2993 |
+
"loss": 1.395,
|
| 2994 |
+
"step": 2070
|
| 2995 |
+
},
|
| 2996 |
+
{
|
| 2997 |
+
"epoch": 0.96,
|
| 2998 |
+
"grad_norm": 0.2007001569199437,
|
| 2999 |
+
"learning_rate": 5.826894308449904e-08,
|
| 3000 |
+
"loss": 1.3418,
|
| 3001 |
+
"step": 2075
|
| 3002 |
+
},
|
| 3003 |
+
{
|
| 3004 |
+
"epoch": 0.96,
|
| 3005 |
+
"grad_norm": 0.20019336918988379,
|
| 3006 |
+
"learning_rate": 5.230721595201049e-08,
|
| 3007 |
+
"loss": 1.3808,
|
| 3008 |
+
"step": 2080
|
| 3009 |
+
},
|
| 3010 |
+
{
|
| 3011 |
+
"epoch": 0.96,
|
| 3012 |
+
"grad_norm": 0.20532075618369505,
|
| 3013 |
+
"learning_rate": 4.666555195210365e-08,
|
| 3014 |
+
"loss": 1.3624,
|
| 3015 |
+
"step": 2085
|
| 3016 |
+
},
|
| 3017 |
+
{
|
| 3018 |
+
"epoch": 0.96,
|
| 3019 |
+
"grad_norm": 0.19955856360806487,
|
| 3020 |
+
"learning_rate": 4.134431604047195e-08,
|
| 3021 |
+
"loss": 1.3851,
|
| 3022 |
+
"step": 2090
|
| 3023 |
+
},
|
| 3024 |
+
{
|
| 3025 |
+
"epoch": 0.97,
|
| 3026 |
+
"grad_norm": 0.19995218707394016,
|
| 3027 |
+
"learning_rate": 3.63438524445181e-08,
|
| 3028 |
+
"loss": 1.404,
|
| 3029 |
+
"step": 2095
|
| 3030 |
+
},
|
| 3031 |
+
{
|
| 3032 |
+
"epoch": 0.97,
|
| 3033 |
+
"grad_norm": 0.2027473195079258,
|
| 3034 |
+
"learning_rate": 3.166448464108629e-08,
|
| 3035 |
+
"loss": 1.3654,
|
| 3036 |
+
"step": 2100
|
| 3037 |
+
},
|
| 3038 |
+
{
|
| 3039 |
+
"epoch": 0.97,
|
| 3040 |
+
"grad_norm": 0.21316411475600813,
|
| 3041 |
+
"learning_rate": 2.7306515335532857e-08,
|
| 3042 |
+
"loss": 1.4004,
|
| 3043 |
+
"step": 2105
|
| 3044 |
+
},
|
| 3045 |
+
{
|
| 3046 |
+
"epoch": 0.97,
|
| 3047 |
+
"grad_norm": 0.19985677477921807,
|
| 3048 |
+
"learning_rate": 2.327022644215193e-08,
|
| 3049 |
+
"loss": 1.3813,
|
| 3050 |
+
"step": 2110
|
| 3051 |
+
},
|
| 3052 |
+
{
|
| 3053 |
+
"epoch": 0.97,
|
| 3054 |
+
"grad_norm": 0.20946530787894166,
|
| 3055 |
+
"learning_rate": 1.9555879065930038e-08,
|
| 3056 |
+
"loss": 1.4226,
|
| 3057 |
+
"step": 2115
|
| 3058 |
+
},
|
| 3059 |
+
{
|
| 3060 |
+
"epoch": 0.98,
|
| 3061 |
+
"grad_norm": 0.1975351975591122,
|
| 3062 |
+
"learning_rate": 1.6163713485662923e-08,
|
| 3063 |
+
"loss": 1.3792,
|
| 3064 |
+
"step": 2120
|
| 3065 |
+
},
|
| 3066 |
+
{
|
| 3067 |
+
"epoch": 0.98,
|
| 3068 |
+
"grad_norm": 0.20571768755825784,
|
| 3069 |
+
"learning_rate": 1.3093949138406892e-08,
|
| 3070 |
+
"loss": 1.3918,
|
| 3071 |
+
"step": 2125
|
| 3072 |
+
},
|
| 3073 |
+
{
|
| 3074 |
+
"epoch": 0.98,
|
| 3075 |
+
"grad_norm": 0.44915439425778153,
|
| 3076 |
+
"learning_rate": 1.03467846052846e-08,
|
| 3077 |
+
"loss": 1.3642,
|
| 3078 |
+
"step": 2130
|
| 3079 |
+
},
|
| 3080 |
+
{
|
| 3081 |
+
"epoch": 0.98,
|
| 3082 |
+
"grad_norm": 0.20214902180431968,
|
| 3083 |
+
"learning_rate": 7.922397598642551e-09,
|
| 3084 |
+
"loss": 1.3599,
|
| 3085 |
+
"step": 2135
|
| 3086 |
+
},
|
| 3087 |
+
{
|
| 3088 |
+
"epoch": 0.99,
|
| 3089 |
+
"grad_norm": 0.19767842515824202,
|
| 3090 |
+
"learning_rate": 5.820944950549745e-09,
|
| 3091 |
+
"loss": 1.3599,
|
| 3092 |
+
"step": 2140
|
| 3093 |
+
},
|
| 3094 |
+
{
|
| 3095 |
+
"epoch": 0.99,
|
| 3096 |
+
"grad_norm": 0.1991438801798082,
|
| 3097 |
+
"learning_rate": 4.042562602655231e-09,
|
| 3098 |
+
"loss": 1.3446,
|
| 3099 |
+
"step": 2145
|
| 3100 |
+
},
|
| 3101 |
+
{
|
| 3102 |
+
"epoch": 0.99,
|
| 3103 |
+
"grad_norm": 0.20173015884228035,
|
| 3104 |
+
"learning_rate": 2.5873655973945864e-09,
|
| 3105 |
+
"loss": 1.3461,
|
| 3106 |
+
"step": 2150
|
| 3107 |
+
},
|
| 3108 |
+
{
|
| 3109 |
+
"epoch": 0.99,
|
| 3110 |
+
"grad_norm": 0.20119946240562925,
|
| 3111 |
+
"learning_rate": 1.4554480705458729e-09,
|
| 3112 |
+
"loss": 1.3474,
|
| 3113 |
+
"step": 2155
|
| 3114 |
+
},
|
| 3115 |
+
{
|
| 3116 |
+
"epoch": 1.0,
|
| 3117 |
+
"grad_norm": 0.20468648298029762,
|
| 3118 |
+
"learning_rate": 6.468832451417273e-10,
|
| 3119 |
+
"loss": 1.3649,
|
| 3120 |
+
"step": 2160
|
| 3121 |
+
},
|
| 3122 |
+
{
|
| 3123 |
+
"epoch": 1.0,
|
| 3124 |
+
"grad_norm": 0.19998165788056904,
|
| 3125 |
+
"learning_rate": 1.617234267320411e-10,
|
| 3126 |
+
"loss": 1.3677,
|
| 3127 |
+
"step": 2165
|
| 3128 |
+
},
|
| 3129 |
+
{
|
| 3130 |
+
"epoch": 1.0,
|
| 3131 |
+
"grad_norm": 0.21026892718522863,
|
| 3132 |
+
"learning_rate": 0.0,
|
| 3133 |
+
"loss": 1.3748,
|
| 3134 |
+
"step": 2170
|
| 3135 |
+
},
|
| 3136 |
+
{
|
| 3137 |
+
"epoch": 1.0,
|
| 3138 |
+
"step": 2170,
|
| 3139 |
+
"total_flos": 7055767844683776.0,
|
| 3140 |
+
"train_loss": 1.4133363889659056,
|
| 3141 |
+
"train_runtime": 112943.9974,
|
| 3142 |
+
"train_samples_per_second": 0.615,
|
| 3143 |
+
"train_steps_per_second": 0.019
|
| 3144 |
+
}
|
| 3145 |
+
],
|
| 3146 |
+
"logging_steps": 5,
|
| 3147 |
+
"max_steps": 2170,
|
| 3148 |
+
"num_input_tokens_seen": 0,
|
| 3149 |
+
"num_train_epochs": 1,
|
| 3150 |
+
"save_steps": 200,
|
| 3151 |
+
"total_flos": 7055767844683776.0,
|
| 3152 |
+
"train_batch_size": 2,
|
| 3153 |
+
"trial_name": null,
|
| 3154 |
+
"trial_params": null
|
| 3155 |
+
}
|