Model save
Browse files- README.md +61 -0
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +1274 -0
README.md
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: mit
|
| 4 |
+
base_model: deepseek-ai/Deepseek-R1-Distill-Qwen-32B
|
| 5 |
+
tags:
|
| 6 |
+
- trl
|
| 7 |
+
- sft
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: sft_base_masked
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# sft_base_masked
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [deepseek-ai/Deepseek-R1-Distill-Qwen-32B](https://huggingface.co/deepseek-ai/Deepseek-R1-Distill-Qwen-32B) on the None dataset.
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 5e-05
|
| 39 |
+
- train_batch_size: 4
|
| 40 |
+
- eval_batch_size: 1
|
| 41 |
+
- seed: 42
|
| 42 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- num_devices: 8
|
| 44 |
+
- total_train_batch_size: 32
|
| 45 |
+
- total_eval_batch_size: 8
|
| 46 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 47 |
+
- lr_scheduler_type: cosine
|
| 48 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 49 |
+
- num_epochs: 2
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
### Framework versions
|
| 56 |
+
|
| 57 |
+
- PEFT 0.13.2
|
| 58 |
+
- Transformers 4.47.0.dev0
|
| 59 |
+
- Pytorch 2.4.0+cu121
|
| 60 |
+
- Datasets 3.1.0
|
| 61 |
+
- Tokenizers 0.20.3
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"total_flos": 3054747482324992.0,
|
| 4 |
+
"train_loss": 0.7215218588032506,
|
| 5 |
+
"train_runtime": 3666.1508,
|
| 6 |
+
"train_samples": 2805,
|
| 7 |
+
"train_samples_per_second": 1.53,
|
| 8 |
+
"train_steps_per_second": 0.048
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"total_flos": 3054747482324992.0,
|
| 4 |
+
"train_loss": 0.7215218588032506,
|
| 5 |
+
"train_runtime": 3666.1508,
|
| 6 |
+
"train_samples": 2805,
|
| 7 |
+
"train_samples_per_second": 1.53,
|
| 8 |
+
"train_steps_per_second": 0.048
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1274 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 176,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.011363636363636364,
|
| 13 |
+
"grad_norm": 0.04888428873089485,
|
| 14 |
+
"learning_rate": 2.777777777777778e-06,
|
| 15 |
+
"loss": 0.9533,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.022727272727272728,
|
| 20 |
+
"grad_norm": 0.04118674609403888,
|
| 21 |
+
"learning_rate": 5.555555555555556e-06,
|
| 22 |
+
"loss": 0.8187,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03409090909090909,
|
| 27 |
+
"grad_norm": 0.036867673437168666,
|
| 28 |
+
"learning_rate": 8.333333333333334e-06,
|
| 29 |
+
"loss": 0.7078,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.045454545454545456,
|
| 34 |
+
"grad_norm": 0.04847692066919062,
|
| 35 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 36 |
+
"loss": 0.987,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.056818181818181816,
|
| 41 |
+
"grad_norm": 0.05003862080856868,
|
| 42 |
+
"learning_rate": 1.388888888888889e-05,
|
| 43 |
+
"loss": 0.9577,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.06818181818181818,
|
| 48 |
+
"grad_norm": 0.04493399553279938,
|
| 49 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 50 |
+
"loss": 0.9205,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.07954545454545454,
|
| 55 |
+
"grad_norm": 0.044174232851205655,
|
| 56 |
+
"learning_rate": 1.9444444444444445e-05,
|
| 57 |
+
"loss": 0.7971,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.09090909090909091,
|
| 62 |
+
"grad_norm": 0.0537270325545959,
|
| 63 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 64 |
+
"loss": 0.875,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.10227272727272728,
|
| 69 |
+
"grad_norm": 0.047274651714941,
|
| 70 |
+
"learning_rate": 2.5e-05,
|
| 71 |
+
"loss": 0.7865,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.11363636363636363,
|
| 76 |
+
"grad_norm": 0.047438139846740904,
|
| 77 |
+
"learning_rate": 2.777777777777778e-05,
|
| 78 |
+
"loss": 0.7949,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.125,
|
| 83 |
+
"grad_norm": 0.0486064821581454,
|
| 84 |
+
"learning_rate": 3.055555555555556e-05,
|
| 85 |
+
"loss": 0.9187,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.13636363636363635,
|
| 90 |
+
"grad_norm": 0.049768338512046005,
|
| 91 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 92 |
+
"loss": 0.927,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.14772727272727273,
|
| 97 |
+
"grad_norm": 0.050752786859426545,
|
| 98 |
+
"learning_rate": 3.611111111111111e-05,
|
| 99 |
+
"loss": 0.882,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.1590909090909091,
|
| 104 |
+
"grad_norm": 0.04238163918748248,
|
| 105 |
+
"learning_rate": 3.888888888888889e-05,
|
| 106 |
+
"loss": 0.8273,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.17045454545454544,
|
| 111 |
+
"grad_norm": 0.03389553366668896,
|
| 112 |
+
"learning_rate": 4.166666666666667e-05,
|
| 113 |
+
"loss": 0.801,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.18181818181818182,
|
| 118 |
+
"grad_norm": 0.03219935695711762,
|
| 119 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 120 |
+
"loss": 0.8313,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.19318181818181818,
|
| 125 |
+
"grad_norm": 0.027821411081551388,
|
| 126 |
+
"learning_rate": 4.722222222222222e-05,
|
| 127 |
+
"loss": 0.6832,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.20454545454545456,
|
| 132 |
+
"grad_norm": 0.028125631584449494,
|
| 133 |
+
"learning_rate": 5e-05,
|
| 134 |
+
"loss": 0.724,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.2159090909090909,
|
| 139 |
+
"grad_norm": 0.03372930491801512,
|
| 140 |
+
"learning_rate": 4.9995058244251644e-05,
|
| 141 |
+
"loss": 0.765,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.22727272727272727,
|
| 146 |
+
"grad_norm": 0.03207593160425088,
|
| 147 |
+
"learning_rate": 4.9980234930682546e-05,
|
| 148 |
+
"loss": 0.8319,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.23863636363636365,
|
| 153 |
+
"grad_norm": 0.04392253595539216,
|
| 154 |
+
"learning_rate": 4.995553591954832e-05,
|
| 155 |
+
"loss": 0.8572,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.25,
|
| 160 |
+
"grad_norm": 0.043837015398686424,
|
| 161 |
+
"learning_rate": 4.99209709753674e-05,
|
| 162 |
+
"loss": 0.7994,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.26136363636363635,
|
| 167 |
+
"grad_norm": 0.038660838245880964,
|
| 168 |
+
"learning_rate": 4.9876553763060684e-05,
|
| 169 |
+
"loss": 0.7595,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.2727272727272727,
|
| 174 |
+
"grad_norm": 0.03958181928823714,
|
| 175 |
+
"learning_rate": 4.982230184254933e-05,
|
| 176 |
+
"loss": 0.7524,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.2840909090909091,
|
| 181 |
+
"grad_norm": 0.04692096023674341,
|
| 182 |
+
"learning_rate": 4.975823666181255e-05,
|
| 183 |
+
"loss": 0.7565,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.29545454545454547,
|
| 188 |
+
"grad_norm": 0.039034963022689224,
|
| 189 |
+
"learning_rate": 4.968438354840834e-05,
|
| 190 |
+
"loss": 0.8968,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.3068181818181818,
|
| 195 |
+
"grad_norm": 0.03472677387974209,
|
| 196 |
+
"learning_rate": 4.960077169946052e-05,
|
| 197 |
+
"loss": 0.7522,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.3181818181818182,
|
| 202 |
+
"grad_norm": 0.031244118470989204,
|
| 203 |
+
"learning_rate": 4.950743417011591e-05,
|
| 204 |
+
"loss": 0.7937,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.32954545454545453,
|
| 209 |
+
"grad_norm": 0.029092500515729473,
|
| 210 |
+
"learning_rate": 4.940440786047628e-05,
|
| 211 |
+
"loss": 0.667,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.3409090909090909,
|
| 216 |
+
"grad_norm": 0.028474671621308404,
|
| 217 |
+
"learning_rate": 4.929173350101025e-05,
|
| 218 |
+
"loss": 0.7255,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.3522727272727273,
|
| 223 |
+
"grad_norm": 0.021514453472108053,
|
| 224 |
+
"learning_rate": 4.9169455636450935e-05,
|
| 225 |
+
"loss": 0.7683,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.36363636363636365,
|
| 230 |
+
"grad_norm": 0.01979063211912252,
|
| 231 |
+
"learning_rate": 4.903762260818551e-05,
|
| 232 |
+
"loss": 0.7236,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.375,
|
| 237 |
+
"grad_norm": 0.019373274784309575,
|
| 238 |
+
"learning_rate": 4.889628653514402e-05,
|
| 239 |
+
"loss": 0.6894,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.38636363636363635,
|
| 244 |
+
"grad_norm": 0.01807357066294673,
|
| 245 |
+
"learning_rate": 4.874550329319457e-05,
|
| 246 |
+
"loss": 0.7558,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.3977272727272727,
|
| 251 |
+
"grad_norm": 0.01770418827474799,
|
| 252 |
+
"learning_rate": 4.8585332493053364e-05,
|
| 253 |
+
"loss": 0.6813,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.4090909090909091,
|
| 258 |
+
"grad_norm": 0.01675836399147525,
|
| 259 |
+
"learning_rate": 4.84158374567182e-05,
|
| 260 |
+
"loss": 0.7559,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.42045454545454547,
|
| 265 |
+
"grad_norm": 0.021175097986321438,
|
| 266 |
+
"learning_rate": 4.8237085192434676e-05,
|
| 267 |
+
"loss": 0.8176,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.4318181818181818,
|
| 272 |
+
"grad_norm": 0.017100608642967,
|
| 273 |
+
"learning_rate": 4.804914636820517e-05,
|
| 274 |
+
"loss": 0.7112,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.4431818181818182,
|
| 279 |
+
"grad_norm": 0.01683117973292665,
|
| 280 |
+
"learning_rate": 4.7852095283850866e-05,
|
| 281 |
+
"loss": 0.7345,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.45454545454545453,
|
| 286 |
+
"grad_norm": 0.019570606734413423,
|
| 287 |
+
"learning_rate": 4.764600984163808e-05,
|
| 288 |
+
"loss": 0.8125,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.4659090909090909,
|
| 293 |
+
"grad_norm": 0.015675238814520476,
|
| 294 |
+
"learning_rate": 4.743097151548031e-05,
|
| 295 |
+
"loss": 0.6994,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.4772727272727273,
|
| 300 |
+
"grad_norm": 0.019792988850059114,
|
| 301 |
+
"learning_rate": 4.72070653187283e-05,
|
| 302 |
+
"loss": 0.7837,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.48863636363636365,
|
| 307 |
+
"grad_norm": 0.015785852432543244,
|
| 308 |
+
"learning_rate": 4.6974379770560846e-05,
|
| 309 |
+
"loss": 0.6608,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.5,
|
| 314 |
+
"grad_norm": 0.015533678745760247,
|
| 315 |
+
"learning_rate": 4.673300686098957e-05,
|
| 316 |
+
"loss": 0.7031,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.5113636363636364,
|
| 321 |
+
"grad_norm": 0.01921291960352695,
|
| 322 |
+
"learning_rate": 4.648304201449153e-05,
|
| 323 |
+
"loss": 0.8267,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.5227272727272727,
|
| 328 |
+
"grad_norm": 0.01614254754588724,
|
| 329 |
+
"learning_rate": 4.6224584052284106e-05,
|
| 330 |
+
"loss": 0.7058,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.5340909090909091,
|
| 335 |
+
"grad_norm": 0.019677063872610357,
|
| 336 |
+
"learning_rate": 4.5957735153256915e-05,
|
| 337 |
+
"loss": 0.6621,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.5454545454545454,
|
| 342 |
+
"grad_norm": 0.013519303189431392,
|
| 343 |
+
"learning_rate": 4.5682600813576435e-05,
|
| 344 |
+
"loss": 0.7478,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.5568181818181818,
|
| 349 |
+
"grad_norm": 0.013215293773761478,
|
| 350 |
+
"learning_rate": 4.539928980497903e-05,
|
| 351 |
+
"loss": 0.7034,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.5681818181818182,
|
| 356 |
+
"grad_norm": 0.013694552146445563,
|
| 357 |
+
"learning_rate": 4.510791413176912e-05,
|
| 358 |
+
"loss": 0.7448,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.5795454545454546,
|
| 363 |
+
"grad_norm": 0.016162877179262552,
|
| 364 |
+
"learning_rate": 4.480858898653936e-05,
|
| 365 |
+
"loss": 0.6728,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.5909090909090909,
|
| 370 |
+
"grad_norm": 0.017056245721837348,
|
| 371 |
+
"learning_rate": 4.4501432704630305e-05,
|
| 372 |
+
"loss": 0.6714,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.6022727272727273,
|
| 377 |
+
"grad_norm": 0.01602874080265432,
|
| 378 |
+
"learning_rate": 4.41865667173477e-05,
|
| 379 |
+
"loss": 0.7667,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.6136363636363636,
|
| 384 |
+
"grad_norm": 0.01556595840862479,
|
| 385 |
+
"learning_rate": 4.386411550395576e-05,
|
| 386 |
+
"loss": 0.6934,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.625,
|
| 391 |
+
"grad_norm": 0.014885950964239066,
|
| 392 |
+
"learning_rate": 4.353420654246546e-05,
|
| 393 |
+
"loss": 0.6909,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.6363636363636364,
|
| 398 |
+
"grad_norm": 0.01399086114921709,
|
| 399 |
+
"learning_rate": 4.319697025923736e-05,
|
| 400 |
+
"loss": 0.6817,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.6477272727272727,
|
| 405 |
+
"grad_norm": 0.016980372482516305,
|
| 406 |
+
"learning_rate": 4.285253997741875e-05,
|
| 407 |
+
"loss": 0.7485,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.6590909090909091,
|
| 412 |
+
"grad_norm": 0.01370669813419946,
|
| 413 |
+
"learning_rate": 4.2501051864235636e-05,
|
| 414 |
+
"loss": 0.5524,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.6704545454545454,
|
| 419 |
+
"grad_norm": 0.0161962614922305,
|
| 420 |
+
"learning_rate": 4.214264487716033e-05,
|
| 421 |
+
"loss": 0.7145,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.6818181818181818,
|
| 426 |
+
"grad_norm": 0.01432616251653496,
|
| 427 |
+
"learning_rate": 4.177746070897592e-05,
|
| 428 |
+
"loss": 0.7263,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.6931818181818182,
|
| 433 |
+
"grad_norm": 0.01515485647301396,
|
| 434 |
+
"learning_rate": 4.140564373175939e-05,
|
| 435 |
+
"loss": 0.6531,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.7045454545454546,
|
| 440 |
+
"grad_norm": 0.014400704458474281,
|
| 441 |
+
"learning_rate": 4.10273409398055e-05,
|
| 442 |
+
"loss": 0.7696,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.7159090909090909,
|
| 447 |
+
"grad_norm": 0.015458672360864132,
|
| 448 |
+
"learning_rate": 4.0642701891514e-05,
|
| 449 |
+
"loss": 0.7081,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.7272727272727273,
|
| 454 |
+
"grad_norm": 0.015263330526513203,
|
| 455 |
+
"learning_rate": 4.025187865026311e-05,
|
| 456 |
+
"loss": 0.725,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.7386363636363636,
|
| 461 |
+
"grad_norm": 0.015125337784791405,
|
| 462 |
+
"learning_rate": 3.985502572429276e-05,
|
| 463 |
+
"loss": 0.7111,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.75,
|
| 468 |
+
"grad_norm": 0.013985325014602094,
|
| 469 |
+
"learning_rate": 3.945230000562121e-05,
|
| 470 |
+
"loss": 0.7249,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.7613636363636364,
|
| 475 |
+
"grad_norm": 0.0155589237978013,
|
| 476 |
+
"learning_rate": 3.9043860708019273e-05,
|
| 477 |
+
"loss": 0.6881,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.7727272727272727,
|
| 482 |
+
"grad_norm": 0.01882918883166355,
|
| 483 |
+
"learning_rate": 3.862986930406669e-05,
|
| 484 |
+
"loss": 0.8102,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.7840909090909091,
|
| 489 |
+
"grad_norm": 0.015308078133970605,
|
| 490 |
+
"learning_rate": 3.821048946131549e-05,
|
| 491 |
+
"loss": 0.6919,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.7954545454545454,
|
| 496 |
+
"grad_norm": 0.01630125314346408,
|
| 497 |
+
"learning_rate": 3.778588697758556e-05,
|
| 498 |
+
"loss": 0.6464,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.8068181818181818,
|
| 503 |
+
"grad_norm": 0.015050157672318546,
|
| 504 |
+
"learning_rate": 3.7356229715418074e-05,
|
| 505 |
+
"loss": 0.7114,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.8181818181818182,
|
| 510 |
+
"grad_norm": 0.015186905856860966,
|
| 511 |
+
"learning_rate": 3.6921687535712656e-05,
|
| 512 |
+
"loss": 0.719,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.8295454545454546,
|
| 517 |
+
"grad_norm": 0.01935797435359767,
|
| 518 |
+
"learning_rate": 3.6482432230574446e-05,
|
| 519 |
+
"loss": 0.7255,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.8409090909090909,
|
| 524 |
+
"grad_norm": 0.016661093988049422,
|
| 525 |
+
"learning_rate": 3.60386374553978e-05,
|
| 526 |
+
"loss": 0.6642,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.8522727272727273,
|
| 531 |
+
"grad_norm": 0.017167771916012636,
|
| 532 |
+
"learning_rate": 3.5590478660213214e-05,
|
| 533 |
+
"loss": 0.677,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.8636363636363636,
|
| 538 |
+
"grad_norm": 0.015022481447368145,
|
| 539 |
+
"learning_rate": 3.5138133020324845e-05,
|
| 540 |
+
"loss": 0.7307,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.875,
|
| 545 |
+
"grad_norm": 0.01785502395194187,
|
| 546 |
+
"learning_rate": 3.468177936626603e-05,
|
| 547 |
+
"loss": 0.789,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.8863636363636364,
|
| 552 |
+
"grad_norm": 0.01864810858161923,
|
| 553 |
+
"learning_rate": 3.4221598113100195e-05,
|
| 554 |
+
"loss": 0.7059,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.8977272727272727,
|
| 559 |
+
"grad_norm": 0.016575657529251383,
|
| 560 |
+
"learning_rate": 3.375777118909561e-05,
|
| 561 |
+
"loss": 0.7456,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.9090909090909091,
|
| 566 |
+
"grad_norm": 0.016188984904551812,
|
| 567 |
+
"learning_rate": 3.32904819638017e-05,
|
| 568 |
+
"loss": 0.683,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.9204545454545454,
|
| 573 |
+
"grad_norm": 0.016436588560373562,
|
| 574 |
+
"learning_rate": 3.2819915175555684e-05,
|
| 575 |
+
"loss": 0.6475,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.9318181818181818,
|
| 580 |
+
"grad_norm": 0.017564054129248746,
|
| 581 |
+
"learning_rate": 3.234625685844803e-05,
|
| 582 |
+
"loss": 0.622,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.9431818181818182,
|
| 587 |
+
"grad_norm": 0.019239130214828547,
|
| 588 |
+
"learning_rate": 3.186969426877563e-05,
|
| 589 |
+
"loss": 0.638,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.9545454545454546,
|
| 594 |
+
"grad_norm": 0.01778558528784305,
|
| 595 |
+
"learning_rate": 3.139041581101187e-05,
|
| 596 |
+
"loss": 0.5941,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.9659090909090909,
|
| 601 |
+
"grad_norm": 0.03326719961885704,
|
| 602 |
+
"learning_rate": 3.090861096332263e-05,
|
| 603 |
+
"loss": 0.6721,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.9772727272727273,
|
| 608 |
+
"grad_norm": 0.017697778364759945,
|
| 609 |
+
"learning_rate": 3.042447020265795e-05,
|
| 610 |
+
"loss": 0.663,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.9886363636363636,
|
| 615 |
+
"grad_norm": 0.015032572277755535,
|
| 616 |
+
"learning_rate": 2.993818492944882e-05,
|
| 617 |
+
"loss": 0.6462,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.0,
|
| 622 |
+
"grad_norm": 0.01697573905444168,
|
| 623 |
+
"learning_rate": 2.9449947391938766e-05,
|
| 624 |
+
"loss": 0.6957,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.0113636363636365,
|
| 629 |
+
"grad_norm": 0.01629821245832795,
|
| 630 |
+
"learning_rate": 2.8959950610180374e-05,
|
| 631 |
+
"loss": 0.6629,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.0227272727272727,
|
| 636 |
+
"grad_norm": 0.015172985524910379,
|
| 637 |
+
"learning_rate": 2.8468388299726712e-05,
|
| 638 |
+
"loss": 0.6602,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.0340909090909092,
|
| 643 |
+
"grad_norm": 0.015577909780648352,
|
| 644 |
+
"learning_rate": 2.7975454795047622e-05,
|
| 645 |
+
"loss": 0.796,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.0454545454545454,
|
| 650 |
+
"grad_norm": 0.017309986409190056,
|
| 651 |
+
"learning_rate": 2.7481344972701545e-05,
|
| 652 |
+
"loss": 0.6618,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.0568181818181819,
|
| 657 |
+
"grad_norm": 0.01661621611638882,
|
| 658 |
+
"learning_rate": 2.6986254174292862e-05,
|
| 659 |
+
"loss": 0.7065,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.0681818181818181,
|
| 664 |
+
"grad_norm": 0.016737287474769654,
|
| 665 |
+
"learning_rate": 2.6490378129245498e-05,
|
| 666 |
+
"loss": 0.6457,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.0795454545454546,
|
| 671 |
+
"grad_norm": 0.016921442525318752,
|
| 672 |
+
"learning_rate": 2.599391287742315e-05,
|
| 673 |
+
"loss": 0.7422,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.0909090909090908,
|
| 678 |
+
"grad_norm": 0.01644141496345415,
|
| 679 |
+
"learning_rate": 2.5497054691626753e-05,
|
| 680 |
+
"loss": 0.7125,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.1022727272727273,
|
| 685 |
+
"grad_norm": 0.01566715623525306,
|
| 686 |
+
"learning_rate": 2.5e-05,
|
| 687 |
+
"loss": 0.7015,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.1136363636363635,
|
| 692 |
+
"grad_norm": 0.016042962886209804,
|
| 693 |
+
"learning_rate": 2.4502945308373246e-05,
|
| 694 |
+
"loss": 0.6911,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 1.125,
|
| 699 |
+
"grad_norm": 0.014451142623462782,
|
| 700 |
+
"learning_rate": 2.4006087122576863e-05,
|
| 701 |
+
"loss": 0.6499,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.1363636363636362,
|
| 706 |
+
"grad_norm": 0.016365537745248963,
|
| 707 |
+
"learning_rate": 2.3509621870754505e-05,
|
| 708 |
+
"loss": 0.6564,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.1477272727272727,
|
| 713 |
+
"grad_norm": 0.015223080653847816,
|
| 714 |
+
"learning_rate": 2.301374582570714e-05,
|
| 715 |
+
"loss": 0.6767,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 1.1590909090909092,
|
| 720 |
+
"grad_norm": 0.017013122218294784,
|
| 721 |
+
"learning_rate": 2.2518655027298464e-05,
|
| 722 |
+
"loss": 0.6712,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.1704545454545454,
|
| 727 |
+
"grad_norm": 0.017431829042961085,
|
| 728 |
+
"learning_rate": 2.2024545204952383e-05,
|
| 729 |
+
"loss": 0.6363,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.1818181818181819,
|
| 734 |
+
"grad_norm": 0.01638659813387577,
|
| 735 |
+
"learning_rate": 2.1531611700273297e-05,
|
| 736 |
+
"loss": 0.7341,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.1931818181818181,
|
| 741 |
+
"grad_norm": 0.015883920910595706,
|
| 742 |
+
"learning_rate": 2.104004938981963e-05,
|
| 743 |
+
"loss": 0.7503,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.2045454545454546,
|
| 748 |
+
"grad_norm": 0.016308759795444855,
|
| 749 |
+
"learning_rate": 2.055005260806125e-05,
|
| 750 |
+
"loss": 0.7494,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.2159090909090908,
|
| 755 |
+
"grad_norm": 0.01653825796554113,
|
| 756 |
+
"learning_rate": 2.0061815070551186e-05,
|
| 757 |
+
"loss": 0.584,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.2272727272727273,
|
| 762 |
+
"grad_norm": 0.015995947052341933,
|
| 763 |
+
"learning_rate": 1.957552979734205e-05,
|
| 764 |
+
"loss": 0.7943,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.2386363636363638,
|
| 769 |
+
"grad_norm": 0.018158719978620477,
|
| 770 |
+
"learning_rate": 1.9091389036677382e-05,
|
| 771 |
+
"loss": 0.7001,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 1.25,
|
| 776 |
+
"grad_norm": 0.015286756025554763,
|
| 777 |
+
"learning_rate": 1.8609584188988136e-05,
|
| 778 |
+
"loss": 0.6132,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.2613636363636362,
|
| 783 |
+
"grad_norm": 0.014766283231039113,
|
| 784 |
+
"learning_rate": 1.813030573122437e-05,
|
| 785 |
+
"loss": 0.6789,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.2727272727272727,
|
| 790 |
+
"grad_norm": 0.018163850190524557,
|
| 791 |
+
"learning_rate": 1.7653743141551983e-05,
|
| 792 |
+
"loss": 0.6641,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.2840909090909092,
|
| 797 |
+
"grad_norm": 0.015499094565043982,
|
| 798 |
+
"learning_rate": 1.7180084824444325e-05,
|
| 799 |
+
"loss": 0.7034,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 1.2954545454545454,
|
| 804 |
+
"grad_norm": 0.01666315009242263,
|
| 805 |
+
"learning_rate": 1.6709518036198308e-05,
|
| 806 |
+
"loss": 0.6644,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.3068181818181819,
|
| 811 |
+
"grad_norm": 0.018550049211631166,
|
| 812 |
+
"learning_rate": 1.6242228810904392e-05,
|
| 813 |
+
"loss": 0.6314,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 1.3181818181818181,
|
| 818 |
+
"grad_norm": 0.016414228273475284,
|
| 819 |
+
"learning_rate": 1.5778401886899807e-05,
|
| 820 |
+
"loss": 0.7085,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 1.3295454545454546,
|
| 825 |
+
"grad_norm": 0.016629484072509887,
|
| 826 |
+
"learning_rate": 1.5318220633733978e-05,
|
| 827 |
+
"loss": 0.6328,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 1.3409090909090908,
|
| 832 |
+
"grad_norm": 0.01735441033712776,
|
| 833 |
+
"learning_rate": 1.4861866979675154e-05,
|
| 834 |
+
"loss": 0.6987,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 1.3522727272727273,
|
| 839 |
+
"grad_norm": 0.01653379311481811,
|
| 840 |
+
"learning_rate": 1.4409521339786808e-05,
|
| 841 |
+
"loss": 0.7689,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 1.3636363636363638,
|
| 846 |
+
"grad_norm": 0.017109513908993915,
|
| 847 |
+
"learning_rate": 1.3961362544602213e-05,
|
| 848 |
+
"loss": 0.852,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.375,
|
| 853 |
+
"grad_norm": 0.015606168185551323,
|
| 854 |
+
"learning_rate": 1.3517567769425548e-05,
|
| 855 |
+
"loss": 0.6131,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 1.3863636363636362,
|
| 860 |
+
"grad_norm": 0.016954213866876906,
|
| 861 |
+
"learning_rate": 1.3078312464287353e-05,
|
| 862 |
+
"loss": 0.7262,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 1.3977272727272727,
|
| 867 |
+
"grad_norm": 0.019722191608232728,
|
| 868 |
+
"learning_rate": 1.2643770284581929e-05,
|
| 869 |
+
"loss": 0.6411,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 1.4090909090909092,
|
| 874 |
+
"grad_norm": 0.016754592315893345,
|
| 875 |
+
"learning_rate": 1.2214113022414448e-05,
|
| 876 |
+
"loss": 0.7406,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 1.4204545454545454,
|
| 881 |
+
"grad_norm": 0.01811366422363491,
|
| 882 |
+
"learning_rate": 1.1789510538684523e-05,
|
| 883 |
+
"loss": 0.6915,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 1.4318181818181819,
|
| 888 |
+
"grad_norm": 0.015117191146405742,
|
| 889 |
+
"learning_rate": 1.1370130695933318e-05,
|
| 890 |
+
"loss": 0.7914,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 1.4431818181818181,
|
| 895 |
+
"grad_norm": 0.019162871723577116,
|
| 896 |
+
"learning_rate": 1.0956139291980727e-05,
|
| 897 |
+
"loss": 0.7924,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 1.4545454545454546,
|
| 902 |
+
"grad_norm": 0.017257641671438298,
|
| 903 |
+
"learning_rate": 1.0547699994378787e-05,
|
| 904 |
+
"loss": 0.6671,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 1.4659090909090908,
|
| 909 |
+
"grad_norm": 0.018952048140386035,
|
| 910 |
+
"learning_rate": 1.0144974275707241e-05,
|
| 911 |
+
"loss": 0.7046,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 1.4772727272727273,
|
| 916 |
+
"grad_norm": 0.02016982804986924,
|
| 917 |
+
"learning_rate": 9.748121349736892e-06,
|
| 918 |
+
"loss": 0.7542,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 1.4886363636363638,
|
| 923 |
+
"grad_norm": 0.015861465051683968,
|
| 924 |
+
"learning_rate": 9.357298108486003e-06,
|
| 925 |
+
"loss": 0.6563,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 1.5,
|
| 930 |
+
"grad_norm": 0.016677424892624696,
|
| 931 |
+
"learning_rate": 8.972659060194506e-06,
|
| 932 |
+
"loss": 0.6743,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.5113636363636362,
|
| 937 |
+
"grad_norm": 0.017220590202846452,
|
| 938 |
+
"learning_rate": 8.594356268240616e-06,
|
| 939 |
+
"loss": 0.5913,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.5227272727272727,
|
| 944 |
+
"grad_norm": 0.017476835977041916,
|
| 945 |
+
"learning_rate": 8.222539291024078e-06,
|
| 946 |
+
"loss": 0.6184,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.5340909090909092,
|
| 951 |
+
"grad_norm": 0.01852744989540818,
|
| 952 |
+
"learning_rate": 7.857355122839675e-06,
|
| 953 |
+
"loss": 0.8003,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 1.5454545454545454,
|
| 958 |
+
"grad_norm": 0.017724119693348375,
|
| 959 |
+
"learning_rate": 7.4989481357643694e-06,
|
| 960 |
+
"loss": 0.7319,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 1.5568181818181817,
|
| 965 |
+
"grad_norm": 0.01827897532047109,
|
| 966 |
+
"learning_rate": 7.147460022581257e-06,
|
| 967 |
+
"loss": 0.7496,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 1.5681818181818183,
|
| 972 |
+
"grad_norm": 0.017356487062778,
|
| 973 |
+
"learning_rate": 6.803029740762648e-06,
|
| 974 |
+
"loss": 0.6998,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 1.5795454545454546,
|
| 979 |
+
"grad_norm": 0.01850857557468877,
|
| 980 |
+
"learning_rate": 6.465793457534553e-06,
|
| 981 |
+
"loss": 0.6103,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 1.5909090909090908,
|
| 986 |
+
"grad_norm": 0.018299658199403747,
|
| 987 |
+
"learning_rate": 6.135884496044244e-06,
|
| 988 |
+
"loss": 0.6448,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 1.6022727272727273,
|
| 993 |
+
"grad_norm": 0.018388053763702464,
|
| 994 |
+
"learning_rate": 5.813433282652298e-06,
|
| 995 |
+
"loss": 0.6399,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 1.6136363636363638,
|
| 1000 |
+
"grad_norm": 0.02080237717937431,
|
| 1001 |
+
"learning_rate": 5.4985672953697e-06,
|
| 1002 |
+
"loss": 0.6313,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 1.625,
|
| 1007 |
+
"grad_norm": 0.01796260664782129,
|
| 1008 |
+
"learning_rate": 5.191411013460645e-06,
|
| 1009 |
+
"loss": 0.6843,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 1.6363636363636362,
|
| 1014 |
+
"grad_norm": 0.02056859413635753,
|
| 1015 |
+
"learning_rate": 4.892085868230881e-06,
|
| 1016 |
+
"loss": 0.7157,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 1.6477272727272727,
|
| 1021 |
+
"grad_norm": 0.016274442923538548,
|
| 1022 |
+
"learning_rate": 4.600710195020982e-06,
|
| 1023 |
+
"loss": 0.7276,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 1.6590909090909092,
|
| 1028 |
+
"grad_norm": 0.01815637927898507,
|
| 1029 |
+
"learning_rate": 4.317399186423574e-06,
|
| 1030 |
+
"loss": 0.6305,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 1.6704545454545454,
|
| 1035 |
+
"grad_norm": 0.01897651128017473,
|
| 1036 |
+
"learning_rate": 4.042264846743085e-06,
|
| 1037 |
+
"loss": 0.675,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 1.6818181818181817,
|
| 1042 |
+
"grad_norm": 0.018136754953765325,
|
| 1043 |
+
"learning_rate": 3.775415947715899e-06,
|
| 1044 |
+
"loss": 0.7152,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 1.6931818181818183,
|
| 1049 |
+
"grad_norm": 0.018312167884684892,
|
| 1050 |
+
"learning_rate": 3.516957985508476e-06,
|
| 1051 |
+
"loss": 0.6128,
|
| 1052 |
+
"step": 149
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 1.7045454545454546,
|
| 1056 |
+
"grad_norm": 0.01872198284953679,
|
| 1057 |
+
"learning_rate": 3.266993139010438e-06,
|
| 1058 |
+
"loss": 0.7636,
|
| 1059 |
+
"step": 150
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 1.7159090909090908,
|
| 1063 |
+
"grad_norm": 0.019247219050936033,
|
| 1064 |
+
"learning_rate": 3.0256202294391577e-06,
|
| 1065 |
+
"loss": 0.7763,
|
| 1066 |
+
"step": 151
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 1.7272727272727273,
|
| 1070 |
+
"grad_norm": 0.01747541840805843,
|
| 1071 |
+
"learning_rate": 2.792934681271708e-06,
|
| 1072 |
+
"loss": 0.718,
|
| 1073 |
+
"step": 152
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 1.7386363636363638,
|
| 1077 |
+
"grad_norm": 0.016543357188300384,
|
| 1078 |
+
"learning_rate": 2.5690284845196923e-06,
|
| 1079 |
+
"loss": 0.7503,
|
| 1080 |
+
"step": 153
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 1.75,
|
| 1084 |
+
"grad_norm": 0.017777133602865168,
|
| 1085 |
+
"learning_rate": 2.3539901583619185e-06,
|
| 1086 |
+
"loss": 0.6796,
|
| 1087 |
+
"step": 154
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 1.7613636363636362,
|
| 1091 |
+
"grad_norm": 0.017730228650558268,
|
| 1092 |
+
"learning_rate": 2.147904716149135e-06,
|
| 1093 |
+
"loss": 0.7887,
|
| 1094 |
+
"step": 155
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 1.7727272727272727,
|
| 1098 |
+
"grad_norm": 0.016904387380041325,
|
| 1099 |
+
"learning_rate": 1.9508536317948357e-06,
|
| 1100 |
+
"loss": 0.7028,
|
| 1101 |
+
"step": 156
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 1.7840909090909092,
|
| 1105 |
+
"grad_norm": 0.017048389518616498,
|
| 1106 |
+
"learning_rate": 1.7629148075653245e-06,
|
| 1107 |
+
"loss": 0.6987,
|
| 1108 |
+
"step": 157
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 1.7954545454545454,
|
| 1112 |
+
"grad_norm": 0.019231086359691812,
|
| 1113 |
+
"learning_rate": 1.5841625432818057e-06,
|
| 1114 |
+
"loss": 0.7262,
|
| 1115 |
+
"step": 158
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 1.8068181818181817,
|
| 1119 |
+
"grad_norm": 0.018406406662889105,
|
| 1120 |
+
"learning_rate": 1.4146675069466403e-06,
|
| 1121 |
+
"loss": 0.6232,
|
| 1122 |
+
"step": 159
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 1.8181818181818183,
|
| 1126 |
+
"grad_norm": 0.01859904836356649,
|
| 1127 |
+
"learning_rate": 1.2544967068054332e-06,
|
| 1128 |
+
"loss": 0.7216,
|
| 1129 |
+
"step": 160
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.8295454545454546,
|
| 1133 |
+
"grad_norm": 0.017748264732114775,
|
| 1134 |
+
"learning_rate": 1.1037134648559794e-06,
|
| 1135 |
+
"loss": 0.66,
|
| 1136 |
+
"step": 161
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 1.8409090909090908,
|
| 1140 |
+
"grad_norm": 0.019172670841775385,
|
| 1141 |
+
"learning_rate": 9.623773918144897e-07,
|
| 1142 |
+
"loss": 0.6719,
|
| 1143 |
+
"step": 162
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 1.8522727272727273,
|
| 1147 |
+
"grad_norm": 0.017201032284762996,
|
| 1148 |
+
"learning_rate": 8.305443635490711e-07,
|
| 1149 |
+
"loss": 0.6841,
|
| 1150 |
+
"step": 163
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 1.8636363636363638,
|
| 1154 |
+
"grad_norm": 0.017602592399586683,
|
| 1155 |
+
"learning_rate": 7.082664989897487e-07,
|
| 1156 |
+
"loss": 0.759,
|
| 1157 |
+
"step": 164
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.875,
|
| 1161 |
+
"grad_norm": 0.01737274402951971,
|
| 1162 |
+
"learning_rate": 5.955921395237318e-07,
|
| 1163 |
+
"loss": 0.6251,
|
| 1164 |
+
"step": 165
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 1.8863636363636362,
|
| 1168 |
+
"grad_norm": 0.018381873767541995,
|
| 1169 |
+
"learning_rate": 4.925658298840979e-07,
|
| 1170 |
+
"loss": 0.7006,
|
| 1171 |
+
"step": 166
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 1.8977272727272727,
|
| 1175 |
+
"grad_norm": 0.017002639935913035,
|
| 1176 |
+
"learning_rate": 3.992283005394837e-07,
|
| 1177 |
+
"loss": 0.5917,
|
| 1178 |
+
"step": 167
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 1.9090909090909092,
|
| 1182 |
+
"grad_norm": 0.017463979654969486,
|
| 1183 |
+
"learning_rate": 3.1561645159166597e-07,
|
| 1184 |
+
"loss": 0.6757,
|
| 1185 |
+
"step": 168
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.9204545454545454,
|
| 1189 |
+
"grad_norm": 0.018406237369712176,
|
| 1190 |
+
"learning_rate": 2.417633381874534e-07,
|
| 1191 |
+
"loss": 0.7824,
|
| 1192 |
+
"step": 169
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 1.9318181818181817,
|
| 1196 |
+
"grad_norm": 0.017967868873337563,
|
| 1197 |
+
"learning_rate": 1.7769815745066475e-07,
|
| 1198 |
+
"loss": 0.7394,
|
| 1199 |
+
"step": 170
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 1.9431818181818183,
|
| 1203 |
+
"grad_norm": 0.01623825702144127,
|
| 1204 |
+
"learning_rate": 1.234462369393147e-07,
|
| 1205 |
+
"loss": 0.7684,
|
| 1206 |
+
"step": 171
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 1.9545454545454546,
|
| 1210 |
+
"grad_norm": 0.017608033119901965,
|
| 1211 |
+
"learning_rate": 7.90290246326042e-08,
|
| 1212 |
+
"loss": 0.7831,
|
| 1213 |
+
"step": 172
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 1.9659090909090908,
|
| 1217 |
+
"grad_norm": 0.017319359934865306,
|
| 1218 |
+
"learning_rate": 4.4464080451675494e-08,
|
| 1219 |
+
"loss": 0.6974,
|
| 1220 |
+
"step": 173
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 1.9772727272727273,
|
| 1224 |
+
"grad_norm": 0.017475580158119938,
|
| 1225 |
+
"learning_rate": 1.976506931745392e-08,
|
| 1226 |
+
"loss": 0.7574,
|
| 1227 |
+
"step": 174
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 1.9886363636363638,
|
| 1231 |
+
"grad_norm": 0.017048411256850495,
|
| 1232 |
+
"learning_rate": 4.941755748361088e-09,
|
| 1233 |
+
"loss": 0.6594,
|
| 1234 |
+
"step": 175
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 2.0,
|
| 1238 |
+
"grad_norm": 0.018638627651477082,
|
| 1239 |
+
"learning_rate": 0.0,
|
| 1240 |
+
"loss": 0.7388,
|
| 1241 |
+
"step": 176
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 2.0,
|
| 1245 |
+
"step": 176,
|
| 1246 |
+
"total_flos": 3054747482324992.0,
|
| 1247 |
+
"train_loss": 0.7215218588032506,
|
| 1248 |
+
"train_runtime": 3666.1508,
|
| 1249 |
+
"train_samples_per_second": 1.53,
|
| 1250 |
+
"train_steps_per_second": 0.048
|
| 1251 |
+
}
|
| 1252 |
+
],
|
| 1253 |
+
"logging_steps": 1,
|
| 1254 |
+
"max_steps": 176,
|
| 1255 |
+
"num_input_tokens_seen": 0,
|
| 1256 |
+
"num_train_epochs": 2,
|
| 1257 |
+
"save_steps": 500,
|
| 1258 |
+
"stateful_callbacks": {
|
| 1259 |
+
"TrainerControl": {
|
| 1260 |
+
"args": {
|
| 1261 |
+
"should_epoch_stop": false,
|
| 1262 |
+
"should_evaluate": false,
|
| 1263 |
+
"should_log": false,
|
| 1264 |
+
"should_save": true,
|
| 1265 |
+
"should_training_stop": true
|
| 1266 |
+
},
|
| 1267 |
+
"attributes": {}
|
| 1268 |
+
}
|
| 1269 |
+
},
|
| 1270 |
+
"total_flos": 3054747482324992.0,
|
| 1271 |
+
"train_batch_size": 4,
|
| 1272 |
+
"trial_name": null,
|
| 1273 |
+
"trial_params": null
|
| 1274 |
+
}
|