Model save
Browse files- README.md +66 -0
- all_results.json +13 -0
- eval_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +1088 -0
README.md
ADDED
|
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: mistralai/Mistral-7B-v0.1
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: mistral-convsearch-7b
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# mistral-convsearch-7b
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.6596
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 2e-05
|
| 38 |
+
- train_batch_size: 8
|
| 39 |
+
- eval_batch_size: 8
|
| 40 |
+
- seed: 42
|
| 41 |
+
- distributed_type: multi-GPU
|
| 42 |
+
- num_devices: 2
|
| 43 |
+
- gradient_accumulation_steps: 32
|
| 44 |
+
- total_train_batch_size: 512
|
| 45 |
+
- total_eval_batch_size: 16
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: cosine
|
| 48 |
+
- num_epochs: 5
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 54 |
+
| 0.9605 | 0.62 | 34 | 0.9471 |
|
| 55 |
+
| 0.7935 | 1.62 | 68 | 0.7886 |
|
| 56 |
+
| 0.7104 | 2.62 | 102 | 0.7083 |
|
| 57 |
+
| 0.6798 | 3.62 | 136 | 0.6753 |
|
| 58 |
+
| 0.6571 | 4.62 | 170 | 0.6582 |
|
| 59 |
+
|
| 60 |
+
|
| 61 |
+
### Framework versions
|
| 62 |
+
|
| 63 |
+
- Transformers 4.35.0
|
| 64 |
+
- Pytorch 2.1.1+cu118
|
| 65 |
+
- Datasets 2.14.6
|
| 66 |
+
- Tokenizers 0.14.1
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.62,
|
| 3 |
+
"eval_loss": 0.6595966815948486,
|
| 4 |
+
"eval_runtime": 22.784,
|
| 5 |
+
"eval_samples": 200,
|
| 6 |
+
"eval_samples_per_second": 8.778,
|
| 7 |
+
"eval_steps_per_second": 0.571,
|
| 8 |
+
"train_loss": 0.8249162855393747,
|
| 9 |
+
"train_runtime": 52349.2428,
|
| 10 |
+
"train_samples": 27870,
|
| 11 |
+
"train_samples_per_second": 2.662,
|
| 12 |
+
"train_steps_per_second": 0.005
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.62,
|
| 3 |
+
"eval_loss": 0.6595966815948486,
|
| 4 |
+
"eval_runtime": 22.784,
|
| 5 |
+
"eval_samples": 200,
|
| 6 |
+
"eval_samples_per_second": 8.778,
|
| 7 |
+
"eval_steps_per_second": 0.571
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.62,
|
| 3 |
+
"train_loss": 0.8249162855393747,
|
| 4 |
+
"train_runtime": 52349.2428,
|
| 5 |
+
"train_samples": 27870,
|
| 6 |
+
"train_samples_per_second": 2.662,
|
| 7 |
+
"train_steps_per_second": 0.005
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1088 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.622273249138921,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 170,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02,
|
| 13 |
+
"learning_rate": 1.9999323080037623e-05,
|
| 14 |
+
"loss": 1.399,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.04,
|
| 19 |
+
"learning_rate": 1.999729241179462e-05,
|
| 20 |
+
"loss": 1.4014,
|
| 21 |
+
"step": 2
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.06,
|
| 25 |
+
"learning_rate": 1.999390827019096e-05,
|
| 26 |
+
"loss": 1.3897,
|
| 27 |
+
"step": 3
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.07,
|
| 31 |
+
"learning_rate": 1.998917111338525e-05,
|
| 32 |
+
"loss": 1.3771,
|
| 33 |
+
"step": 4
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.09,
|
| 37 |
+
"learning_rate": 1.9983081582712684e-05,
|
| 38 |
+
"loss": 1.3699,
|
| 39 |
+
"step": 5
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.11,
|
| 43 |
+
"learning_rate": 1.9975640502598243e-05,
|
| 44 |
+
"loss": 1.3372,
|
| 45 |
+
"step": 6
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.13,
|
| 49 |
+
"learning_rate": 1.996684888044506e-05,
|
| 50 |
+
"loss": 1.3135,
|
| 51 |
+
"step": 7
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.15,
|
| 55 |
+
"learning_rate": 1.9956707906498046e-05,
|
| 56 |
+
"loss": 1.2847,
|
| 57 |
+
"step": 8
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.17,
|
| 61 |
+
"learning_rate": 1.9945218953682736e-05,
|
| 62 |
+
"loss": 1.2688,
|
| 63 |
+
"step": 9
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.18,
|
| 67 |
+
"learning_rate": 1.9932383577419432e-05,
|
| 68 |
+
"loss": 1.256,
|
| 69 |
+
"step": 10
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.2,
|
| 73 |
+
"learning_rate": 1.9918203515412616e-05,
|
| 74 |
+
"loss": 1.238,
|
| 75 |
+
"step": 11
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.22,
|
| 79 |
+
"learning_rate": 1.9902680687415704e-05,
|
| 80 |
+
"loss": 1.2066,
|
| 81 |
+
"step": 12
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.24,
|
| 85 |
+
"learning_rate": 1.9885817194971116e-05,
|
| 86 |
+
"loss": 1.1979,
|
| 87 |
+
"step": 13
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.26,
|
| 91 |
+
"learning_rate": 1.9867615321125796e-05,
|
| 92 |
+
"loss": 1.1685,
|
| 93 |
+
"step": 14
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.28,
|
| 97 |
+
"learning_rate": 1.9848077530122083e-05,
|
| 98 |
+
"loss": 1.1574,
|
| 99 |
+
"step": 15
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.29,
|
| 103 |
+
"learning_rate": 1.9827206467064133e-05,
|
| 104 |
+
"loss": 1.1427,
|
| 105 |
+
"step": 16
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.31,
|
| 109 |
+
"learning_rate": 1.9805004957559795e-05,
|
| 110 |
+
"loss": 1.122,
|
| 111 |
+
"step": 17
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.33,
|
| 115 |
+
"learning_rate": 1.9781476007338058e-05,
|
| 116 |
+
"loss": 1.1201,
|
| 117 |
+
"step": 18
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.35,
|
| 121 |
+
"learning_rate": 1.9756622801842144e-05,
|
| 122 |
+
"loss": 1.0971,
|
| 123 |
+
"step": 19
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.37,
|
| 127 |
+
"learning_rate": 1.973044870579824e-05,
|
| 128 |
+
"loss": 1.086,
|
| 129 |
+
"step": 20
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.39,
|
| 133 |
+
"learning_rate": 1.9702957262759964e-05,
|
| 134 |
+
"loss": 1.0764,
|
| 135 |
+
"step": 21
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.4,
|
| 139 |
+
"learning_rate": 1.967415219462864e-05,
|
| 140 |
+
"loss": 1.0692,
|
| 141 |
+
"step": 22
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.42,
|
| 145 |
+
"learning_rate": 1.964403740114939e-05,
|
| 146 |
+
"loss": 1.0525,
|
| 147 |
+
"step": 23
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.44,
|
| 151 |
+
"learning_rate": 1.961261695938319e-05,
|
| 152 |
+
"loss": 1.0412,
|
| 153 |
+
"step": 24
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.46,
|
| 157 |
+
"learning_rate": 1.957989512315489e-05,
|
| 158 |
+
"loss": 1.0329,
|
| 159 |
+
"step": 25
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.48,
|
| 163 |
+
"learning_rate": 1.954587632247732e-05,
|
| 164 |
+
"loss": 1.023,
|
| 165 |
+
"step": 26
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.5,
|
| 169 |
+
"learning_rate": 1.9510565162951538e-05,
|
| 170 |
+
"loss": 1.019,
|
| 171 |
+
"step": 27
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.51,
|
| 175 |
+
"learning_rate": 1.9473966425143292e-05,
|
| 176 |
+
"loss": 1.0028,
|
| 177 |
+
"step": 28
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.53,
|
| 181 |
+
"learning_rate": 1.9436085063935837e-05,
|
| 182 |
+
"loss": 0.9944,
|
| 183 |
+
"step": 29
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.55,
|
| 187 |
+
"learning_rate": 1.9396926207859085e-05,
|
| 188 |
+
"loss": 0.9901,
|
| 189 |
+
"step": 30
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.57,
|
| 193 |
+
"learning_rate": 1.9356495158395317e-05,
|
| 194 |
+
"loss": 0.9879,
|
| 195 |
+
"step": 31
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.59,
|
| 199 |
+
"learning_rate": 1.9314797389261426e-05,
|
| 200 |
+
"loss": 0.9729,
|
| 201 |
+
"step": 32
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.61,
|
| 205 |
+
"learning_rate": 1.9271838545667876e-05,
|
| 206 |
+
"loss": 0.9611,
|
| 207 |
+
"step": 33
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.62,
|
| 211 |
+
"learning_rate": 1.9227624443554425e-05,
|
| 212 |
+
"loss": 0.9605,
|
| 213 |
+
"step": 34
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.62,
|
| 217 |
+
"eval_loss": 0.9471226930618286,
|
| 218 |
+
"eval_runtime": 24.0918,
|
| 219 |
+
"eval_samples_per_second": 8.302,
|
| 220 |
+
"eval_steps_per_second": 0.54,
|
| 221 |
+
"step": 34
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.02,
|
| 225 |
+
"learning_rate": 1.9182161068802742e-05,
|
| 226 |
+
"loss": 0.9495,
|
| 227 |
+
"step": 35
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.04,
|
| 231 |
+
"learning_rate": 1.913545457642601e-05,
|
| 232 |
+
"loss": 0.948,
|
| 233 |
+
"step": 36
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.05,
|
| 237 |
+
"learning_rate": 1.9087511289735646e-05,
|
| 238 |
+
"loss": 0.9363,
|
| 239 |
+
"step": 37
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.07,
|
| 243 |
+
"learning_rate": 1.9038337699485207e-05,
|
| 244 |
+
"loss": 0.9356,
|
| 245 |
+
"step": 38
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.09,
|
| 249 |
+
"learning_rate": 1.8987940462991673e-05,
|
| 250 |
+
"loss": 0.9322,
|
| 251 |
+
"step": 39
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 1.11,
|
| 255 |
+
"learning_rate": 1.8936326403234125e-05,
|
| 256 |
+
"loss": 0.919,
|
| 257 |
+
"step": 40
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.13,
|
| 261 |
+
"learning_rate": 1.8883502507930044e-05,
|
| 262 |
+
"loss": 0.9141,
|
| 263 |
+
"step": 41
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 1.15,
|
| 267 |
+
"learning_rate": 1.8829475928589272e-05,
|
| 268 |
+
"loss": 0.9057,
|
| 269 |
+
"step": 42
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.16,
|
| 273 |
+
"learning_rate": 1.877425397954582e-05,
|
| 274 |
+
"loss": 0.8991,
|
| 275 |
+
"step": 43
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.18,
|
| 279 |
+
"learning_rate": 1.8717844136967626e-05,
|
| 280 |
+
"loss": 0.8994,
|
| 281 |
+
"step": 44
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.2,
|
| 285 |
+
"learning_rate": 1.866025403784439e-05,
|
| 286 |
+
"loss": 0.8916,
|
| 287 |
+
"step": 45
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 1.22,
|
| 291 |
+
"learning_rate": 1.860149147895366e-05,
|
| 292 |
+
"loss": 0.8881,
|
| 293 |
+
"step": 46
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 1.24,
|
| 297 |
+
"learning_rate": 1.854156441580526e-05,
|
| 298 |
+
"loss": 0.8798,
|
| 299 |
+
"step": 47
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.26,
|
| 303 |
+
"learning_rate": 1.848048096156426e-05,
|
| 304 |
+
"loss": 0.8753,
|
| 305 |
+
"step": 48
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 1.27,
|
| 309 |
+
"learning_rate": 1.8418249385952575e-05,
|
| 310 |
+
"loss": 0.8738,
|
| 311 |
+
"step": 49
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.29,
|
| 315 |
+
"learning_rate": 1.8354878114129368e-05,
|
| 316 |
+
"loss": 0.871,
|
| 317 |
+
"step": 50
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.31,
|
| 321 |
+
"learning_rate": 1.8290375725550417e-05,
|
| 322 |
+
"loss": 0.8617,
|
| 323 |
+
"step": 51
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 1.33,
|
| 327 |
+
"learning_rate": 1.8224750952806626e-05,
|
| 328 |
+
"loss": 0.8646,
|
| 329 |
+
"step": 52
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 1.35,
|
| 333 |
+
"learning_rate": 1.8158012680441723e-05,
|
| 334 |
+
"loss": 0.8547,
|
| 335 |
+
"step": 53
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 1.37,
|
| 339 |
+
"learning_rate": 1.8090169943749477e-05,
|
| 340 |
+
"loss": 0.8523,
|
| 341 |
+
"step": 54
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 1.39,
|
| 345 |
+
"learning_rate": 1.802123192755044e-05,
|
| 346 |
+
"loss": 0.8425,
|
| 347 |
+
"step": 55
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 1.4,
|
| 351 |
+
"learning_rate": 1.795120796494848e-05,
|
| 352 |
+
"loss": 0.8455,
|
| 353 |
+
"step": 56
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.42,
|
| 357 |
+
"learning_rate": 1.788010753606722e-05,
|
| 358 |
+
"loss": 0.8367,
|
| 359 |
+
"step": 57
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.44,
|
| 363 |
+
"learning_rate": 1.7807940266766595e-05,
|
| 364 |
+
"loss": 0.832,
|
| 365 |
+
"step": 58
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 1.46,
|
| 369 |
+
"learning_rate": 1.7734715927339642e-05,
|
| 370 |
+
"loss": 0.828,
|
| 371 |
+
"step": 59
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 1.48,
|
| 375 |
+
"learning_rate": 1.766044443118978e-05,
|
| 376 |
+
"loss": 0.8302,
|
| 377 |
+
"step": 60
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.5,
|
| 381 |
+
"learning_rate": 1.7585135833488692e-05,
|
| 382 |
+
"loss": 0.8194,
|
| 383 |
+
"step": 61
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 1.51,
|
| 387 |
+
"learning_rate": 1.7508800329814993e-05,
|
| 388 |
+
"loss": 0.8123,
|
| 389 |
+
"step": 62
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 1.53,
|
| 393 |
+
"learning_rate": 1.7431448254773943e-05,
|
| 394 |
+
"loss": 0.8113,
|
| 395 |
+
"step": 63
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.55,
|
| 399 |
+
"learning_rate": 1.735309008059829e-05,
|
| 400 |
+
"loss": 0.813,
|
| 401 |
+
"step": 64
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 1.57,
|
| 405 |
+
"learning_rate": 1.7273736415730488e-05,
|
| 406 |
+
"loss": 0.8104,
|
| 407 |
+
"step": 65
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 1.59,
|
| 411 |
+
"learning_rate": 1.7193398003386514e-05,
|
| 412 |
+
"loss": 0.8008,
|
| 413 |
+
"step": 66
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 1.61,
|
| 417 |
+
"learning_rate": 1.711208572010137e-05,
|
| 418 |
+
"loss": 0.7963,
|
| 419 |
+
"step": 67
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 1.62,
|
| 423 |
+
"learning_rate": 1.702981057425662e-05,
|
| 424 |
+
"loss": 0.7935,
|
| 425 |
+
"step": 68
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 1.62,
|
| 429 |
+
"eval_loss": 0.7886030077934265,
|
| 430 |
+
"eval_runtime": 23.1527,
|
| 431 |
+
"eval_samples_per_second": 8.638,
|
| 432 |
+
"eval_steps_per_second": 0.561,
|
| 433 |
+
"step": 68
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 2.02,
|
| 437 |
+
"learning_rate": 1.6946583704589973e-05,
|
| 438 |
+
"loss": 0.7855,
|
| 439 |
+
"step": 69
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 2.04,
|
| 443 |
+
"learning_rate": 1.686241637868734e-05,
|
| 444 |
+
"loss": 0.7851,
|
| 445 |
+
"step": 70
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 2.05,
|
| 449 |
+
"learning_rate": 1.6777319991457325e-05,
|
| 450 |
+
"loss": 0.7832,
|
| 451 |
+
"step": 71
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 2.07,
|
| 455 |
+
"learning_rate": 1.6691306063588583e-05,
|
| 456 |
+
"loss": 0.7768,
|
| 457 |
+
"step": 72
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 2.09,
|
| 461 |
+
"learning_rate": 1.6604386239990077e-05,
|
| 462 |
+
"loss": 0.7786,
|
| 463 |
+
"step": 73
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 2.11,
|
| 467 |
+
"learning_rate": 1.6516572288214555e-05,
|
| 468 |
+
"loss": 0.772,
|
| 469 |
+
"step": 74
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 2.13,
|
| 473 |
+
"learning_rate": 1.6427876096865394e-05,
|
| 474 |
+
"loss": 0.7644,
|
| 475 |
+
"step": 75
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 2.15,
|
| 479 |
+
"learning_rate": 1.63383096739871e-05,
|
| 480 |
+
"loss": 0.7616,
|
| 481 |
+
"step": 76
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 2.16,
|
| 485 |
+
"learning_rate": 1.6247885145439602e-05,
|
| 486 |
+
"loss": 0.761,
|
| 487 |
+
"step": 77
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 2.18,
|
| 491 |
+
"learning_rate": 1.6156614753256583e-05,
|
| 492 |
+
"loss": 0.7587,
|
| 493 |
+
"step": 78
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 2.2,
|
| 497 |
+
"learning_rate": 1.6064510853988137e-05,
|
| 498 |
+
"loss": 0.7573,
|
| 499 |
+
"step": 79
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 2.22,
|
| 503 |
+
"learning_rate": 1.5971585917027864e-05,
|
| 504 |
+
"loss": 0.7558,
|
| 505 |
+
"step": 80
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 2.24,
|
| 509 |
+
"learning_rate": 1.5877852522924733e-05,
|
| 510 |
+
"loss": 0.7519,
|
| 511 |
+
"step": 81
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 2.26,
|
| 515 |
+
"learning_rate": 1.5783323361679865e-05,
|
| 516 |
+
"loss": 0.7427,
|
| 517 |
+
"step": 82
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 2.27,
|
| 521 |
+
"learning_rate": 1.568801123102852e-05,
|
| 522 |
+
"loss": 0.7504,
|
| 523 |
+
"step": 83
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 2.29,
|
| 527 |
+
"learning_rate": 1.5591929034707468e-05,
|
| 528 |
+
"loss": 0.7435,
|
| 529 |
+
"step": 84
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 2.31,
|
| 533 |
+
"learning_rate": 1.5495089780708062e-05,
|
| 534 |
+
"loss": 0.7417,
|
| 535 |
+
"step": 85
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 2.33,
|
| 539 |
+
"learning_rate": 1.539750657951513e-05,
|
| 540 |
+
"loss": 0.7445,
|
| 541 |
+
"step": 86
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 2.35,
|
| 545 |
+
"learning_rate": 1.529919264233205e-05,
|
| 546 |
+
"loss": 0.7416,
|
| 547 |
+
"step": 87
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 2.37,
|
| 551 |
+
"learning_rate": 1.5200161279292154e-05,
|
| 552 |
+
"loss": 0.7392,
|
| 553 |
+
"step": 88
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 2.38,
|
| 557 |
+
"learning_rate": 1.5100425897656754e-05,
|
| 558 |
+
"loss": 0.7369,
|
| 559 |
+
"step": 89
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 2.4,
|
| 563 |
+
"learning_rate": 1.5000000000000002e-05,
|
| 564 |
+
"loss": 0.7346,
|
| 565 |
+
"step": 90
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 2.42,
|
| 569 |
+
"learning_rate": 1.4898897182380872e-05,
|
| 570 |
+
"loss": 0.7293,
|
| 571 |
+
"step": 91
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 2.44,
|
| 575 |
+
"learning_rate": 1.4797131132502464e-05,
|
| 576 |
+
"loss": 0.726,
|
| 577 |
+
"step": 92
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 2.46,
|
| 581 |
+
"learning_rate": 1.469471562785891e-05,
|
| 582 |
+
"loss": 0.729,
|
| 583 |
+
"step": 93
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 2.48,
|
| 587 |
+
"learning_rate": 1.4591664533870118e-05,
|
| 588 |
+
"loss": 0.7262,
|
| 589 |
+
"step": 94
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 2.49,
|
| 593 |
+
"learning_rate": 1.4487991802004625e-05,
|
| 594 |
+
"loss": 0.7296,
|
| 595 |
+
"step": 95
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 2.51,
|
| 599 |
+
"learning_rate": 1.4383711467890776e-05,
|
| 600 |
+
"loss": 0.7249,
|
| 601 |
+
"step": 96
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 2.53,
|
| 605 |
+
"learning_rate": 1.4278837649416543e-05,
|
| 606 |
+
"loss": 0.7173,
|
| 607 |
+
"step": 97
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 2.55,
|
| 611 |
+
"learning_rate": 1.417338454481818e-05,
|
| 612 |
+
"loss": 0.7206,
|
| 613 |
+
"step": 98
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 2.57,
|
| 617 |
+
"learning_rate": 1.4067366430758004e-05,
|
| 618 |
+
"loss": 0.7233,
|
| 619 |
+
"step": 99
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 2.59,
|
| 623 |
+
"learning_rate": 1.396079766039157e-05,
|
| 624 |
+
"loss": 0.72,
|
| 625 |
+
"step": 100
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 2.61,
|
| 629 |
+
"learning_rate": 1.3853692661424485e-05,
|
| 630 |
+
"loss": 0.7152,
|
| 631 |
+
"step": 101
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 2.62,
|
| 635 |
+
"learning_rate": 1.3746065934159123e-05,
|
| 636 |
+
"loss": 0.7104,
|
| 637 |
+
"step": 102
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 2.62,
|
| 641 |
+
"eval_loss": 0.7083348631858826,
|
| 642 |
+
"eval_runtime": 23.1348,
|
| 643 |
+
"eval_samples_per_second": 8.645,
|
| 644 |
+
"eval_steps_per_second": 0.562,
|
| 645 |
+
"step": 102
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 3.02,
|
| 649 |
+
"learning_rate": 1.3637932049531517e-05,
|
| 650 |
+
"loss": 0.7093,
|
| 651 |
+
"step": 103
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 3.04,
|
| 655 |
+
"learning_rate": 1.3529305647138689e-05,
|
| 656 |
+
"loss": 0.7102,
|
| 657 |
+
"step": 104
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 3.05,
|
| 661 |
+
"learning_rate": 1.342020143325669e-05,
|
| 662 |
+
"loss": 0.7093,
|
| 663 |
+
"step": 105
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 3.07,
|
| 667 |
+
"learning_rate": 1.3310634178849583e-05,
|
| 668 |
+
"loss": 0.7063,
|
| 669 |
+
"step": 106
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 3.09,
|
| 673 |
+
"learning_rate": 1.3200618717569716e-05,
|
| 674 |
+
"loss": 0.7098,
|
| 675 |
+
"step": 107
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 3.11,
|
| 679 |
+
"learning_rate": 1.3090169943749475e-05,
|
| 680 |
+
"loss": 0.7039,
|
| 681 |
+
"step": 108
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 3.13,
|
| 685 |
+
"learning_rate": 1.297930281038482e-05,
|
| 686 |
+
"loss": 0.702,
|
| 687 |
+
"step": 109
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 3.15,
|
| 691 |
+
"learning_rate": 1.2868032327110904e-05,
|
| 692 |
+
"loss": 0.6992,
|
| 693 |
+
"step": 110
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 3.16,
|
| 697 |
+
"learning_rate": 1.2756373558169992e-05,
|
| 698 |
+
"loss": 0.6958,
|
| 699 |
+
"step": 111
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 3.18,
|
| 703 |
+
"learning_rate": 1.2644341620372025e-05,
|
| 704 |
+
"loss": 0.6987,
|
| 705 |
+
"step": 112
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 3.2,
|
| 709 |
+
"learning_rate": 1.253195168104802e-05,
|
| 710 |
+
"loss": 0.6971,
|
| 711 |
+
"step": 113
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 3.22,
|
| 715 |
+
"learning_rate": 1.2419218955996677e-05,
|
| 716 |
+
"loss": 0.7017,
|
| 717 |
+
"step": 114
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 3.24,
|
| 721 |
+
"learning_rate": 1.2306158707424402e-05,
|
| 722 |
+
"loss": 0.6922,
|
| 723 |
+
"step": 115
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 3.26,
|
| 727 |
+
"learning_rate": 1.2192786241879033e-05,
|
| 728 |
+
"loss": 0.6908,
|
| 729 |
+
"step": 116
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 3.27,
|
| 733 |
+
"learning_rate": 1.2079116908177592e-05,
|
| 734 |
+
"loss": 0.6964,
|
| 735 |
+
"step": 117
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 3.29,
|
| 739 |
+
"learning_rate": 1.1965166095328302e-05,
|
| 740 |
+
"loss": 0.6948,
|
| 741 |
+
"step": 118
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 3.31,
|
| 745 |
+
"learning_rate": 1.1850949230447146e-05,
|
| 746 |
+
"loss": 0.6899,
|
| 747 |
+
"step": 119
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 3.33,
|
| 751 |
+
"learning_rate": 1.1736481776669307e-05,
|
| 752 |
+
"loss": 0.6951,
|
| 753 |
+
"step": 120
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 3.35,
|
| 757 |
+
"learning_rate": 1.1621779231055677e-05,
|
| 758 |
+
"loss": 0.6913,
|
| 759 |
+
"step": 121
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 3.37,
|
| 763 |
+
"learning_rate": 1.1506857122494832e-05,
|
| 764 |
+
"loss": 0.69,
|
| 765 |
+
"step": 122
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 3.38,
|
| 769 |
+
"learning_rate": 1.1391731009600655e-05,
|
| 770 |
+
"loss": 0.6901,
|
| 771 |
+
"step": 123
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 3.4,
|
| 775 |
+
"learning_rate": 1.127641647860595e-05,
|
| 776 |
+
"loss": 0.6898,
|
| 777 |
+
"step": 124
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 3.42,
|
| 781 |
+
"learning_rate": 1.1160929141252303e-05,
|
| 782 |
+
"loss": 0.6859,
|
| 783 |
+
"step": 125
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 3.44,
|
| 787 |
+
"learning_rate": 1.1045284632676535e-05,
|
| 788 |
+
"loss": 0.686,
|
| 789 |
+
"step": 126
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 3.46,
|
| 793 |
+
"learning_rate": 1.0929498609293925e-05,
|
| 794 |
+
"loss": 0.682,
|
| 795 |
+
"step": 127
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 3.48,
|
| 799 |
+
"learning_rate": 1.0813586746678584e-05,
|
| 800 |
+
"loss": 0.6862,
|
| 801 |
+
"step": 128
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 3.49,
|
| 805 |
+
"learning_rate": 1.0697564737441254e-05,
|
| 806 |
+
"loss": 0.687,
|
| 807 |
+
"step": 129
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 3.51,
|
| 811 |
+
"learning_rate": 1.0581448289104759e-05,
|
| 812 |
+
"loss": 0.6805,
|
| 813 |
+
"step": 130
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 3.53,
|
| 817 |
+
"learning_rate": 1.046525312197747e-05,
|
| 818 |
+
"loss": 0.679,
|
| 819 |
+
"step": 131
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 3.55,
|
| 823 |
+
"learning_rate": 1.0348994967025012e-05,
|
| 824 |
+
"loss": 0.6851,
|
| 825 |
+
"step": 132
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 3.57,
|
| 829 |
+
"learning_rate": 1.0232689563740563e-05,
|
| 830 |
+
"loss": 0.6884,
|
| 831 |
+
"step": 133
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 3.59,
|
| 835 |
+
"learning_rate": 1.0116352658013973e-05,
|
| 836 |
+
"loss": 0.6786,
|
| 837 |
+
"step": 134
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 3.6,
|
| 841 |
+
"learning_rate": 1e-05,
|
| 842 |
+
"loss": 0.6755,
|
| 843 |
+
"step": 135
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 3.62,
|
| 847 |
+
"learning_rate": 9.883647341986032e-06,
|
| 848 |
+
"loss": 0.6798,
|
| 849 |
+
"step": 136
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 3.62,
|
| 853 |
+
"eval_loss": 0.6752661466598511,
|
| 854 |
+
"eval_runtime": 23.1352,
|
| 855 |
+
"eval_samples_per_second": 8.645,
|
| 856 |
+
"eval_steps_per_second": 0.562,
|
| 857 |
+
"step": 136
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 4.02,
|
| 861 |
+
"learning_rate": 9.767310436259438e-06,
|
| 862 |
+
"loss": 0.6762,
|
| 863 |
+
"step": 137
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 4.03,
|
| 867 |
+
"learning_rate": 9.651005032974994e-06,
|
| 868 |
+
"loss": 0.6758,
|
| 869 |
+
"step": 138
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 4.05,
|
| 873 |
+
"learning_rate": 9.534746878022533e-06,
|
| 874 |
+
"loss": 0.6737,
|
| 875 |
+
"step": 139
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 4.07,
|
| 879 |
+
"learning_rate": 9.418551710895243e-06,
|
| 880 |
+
"loss": 0.6783,
|
| 881 |
+
"step": 140
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 4.09,
|
| 885 |
+
"learning_rate": 9.302435262558748e-06,
|
| 886 |
+
"loss": 0.6744,
|
| 887 |
+
"step": 141
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 4.11,
|
| 891 |
+
"learning_rate": 9.18641325332142e-06,
|
| 892 |
+
"loss": 0.6722,
|
| 893 |
+
"step": 142
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 4.13,
|
| 897 |
+
"learning_rate": 9.07050139070608e-06,
|
| 898 |
+
"loss": 0.6715,
|
| 899 |
+
"step": 143
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 4.14,
|
| 903 |
+
"learning_rate": 8.954715367323468e-06,
|
| 904 |
+
"loss": 0.6696,
|
| 905 |
+
"step": 144
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 4.16,
|
| 909 |
+
"learning_rate": 8.839070858747697e-06,
|
| 910 |
+
"loss": 0.666,
|
| 911 |
+
"step": 145
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 4.18,
|
| 915 |
+
"learning_rate": 8.723583521394054e-06,
|
| 916 |
+
"loss": 0.6709,
|
| 917 |
+
"step": 146
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 4.2,
|
| 921 |
+
"learning_rate": 8.60826899039935e-06,
|
| 922 |
+
"loss": 0.6739,
|
| 923 |
+
"step": 147
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 4.22,
|
| 927 |
+
"learning_rate": 8.49314287750517e-06,
|
| 928 |
+
"loss": 0.6678,
|
| 929 |
+
"step": 148
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 4.24,
|
| 933 |
+
"learning_rate": 8.378220768944328e-06,
|
| 934 |
+
"loss": 0.6628,
|
| 935 |
+
"step": 149
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 4.25,
|
| 939 |
+
"learning_rate": 8.263518223330698e-06,
|
| 940 |
+
"loss": 0.6722,
|
| 941 |
+
"step": 150
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 4.27,
|
| 945 |
+
"learning_rate": 8.149050769552856e-06,
|
| 946 |
+
"loss": 0.6669,
|
| 947 |
+
"step": 151
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 4.29,
|
| 951 |
+
"learning_rate": 8.034833904671698e-06,
|
| 952 |
+
"loss": 0.6685,
|
| 953 |
+
"step": 152
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 4.31,
|
| 957 |
+
"learning_rate": 7.92088309182241e-06,
|
| 958 |
+
"loss": 0.6648,
|
| 959 |
+
"step": 153
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 4.33,
|
| 963 |
+
"learning_rate": 7.807213758120965e-06,
|
| 964 |
+
"loss": 0.6693,
|
| 965 |
+
"step": 154
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 4.35,
|
| 969 |
+
"learning_rate": 7.6938412925756e-06,
|
| 970 |
+
"loss": 0.669,
|
| 971 |
+
"step": 155
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 4.37,
|
| 975 |
+
"learning_rate": 7.580781044003324e-06,
|
| 976 |
+
"loss": 0.6664,
|
| 977 |
+
"step": 156
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 4.38,
|
| 981 |
+
"learning_rate": 7.468048318951983e-06,
|
| 982 |
+
"loss": 0.6661,
|
| 983 |
+
"step": 157
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 4.4,
|
| 987 |
+
"learning_rate": 7.355658379627981e-06,
|
| 988 |
+
"loss": 0.6661,
|
| 989 |
+
"step": 158
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 4.42,
|
| 993 |
+
"learning_rate": 7.243626441830009e-06,
|
| 994 |
+
"loss": 0.6642,
|
| 995 |
+
"step": 159
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 4.44,
|
| 999 |
+
"learning_rate": 7.131967672889101e-06,
|
| 1000 |
+
"loss": 0.6648,
|
| 1001 |
+
"step": 160
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 4.46,
|
| 1005 |
+
"learning_rate": 7.02069718961518e-06,
|
| 1006 |
+
"loss": 0.6606,
|
| 1007 |
+
"step": 161
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 4.48,
|
| 1011 |
+
"learning_rate": 6.909830056250527e-06,
|
| 1012 |
+
"loss": 0.6613,
|
| 1013 |
+
"step": 162
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 4.49,
|
| 1017 |
+
"learning_rate": 6.799381282430284e-06,
|
| 1018 |
+
"loss": 0.668,
|
| 1019 |
+
"step": 163
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 4.51,
|
| 1023 |
+
"learning_rate": 6.689365821150421e-06,
|
| 1024 |
+
"loss": 0.6605,
|
| 1025 |
+
"step": 164
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 4.53,
|
| 1029 |
+
"learning_rate": 6.579798566743314e-06,
|
| 1030 |
+
"loss": 0.6632,
|
| 1031 |
+
"step": 165
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 4.55,
|
| 1035 |
+
"learning_rate": 6.4706943528613135e-06,
|
| 1036 |
+
"loss": 0.6587,
|
| 1037 |
+
"step": 166
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 4.57,
|
| 1041 |
+
"learning_rate": 6.362067950468489e-06,
|
| 1042 |
+
"loss": 0.666,
|
| 1043 |
+
"step": 167
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 4.59,
|
| 1047 |
+
"learning_rate": 6.25393406584088e-06,
|
| 1048 |
+
"loss": 0.6672,
|
| 1049 |
+
"step": 168
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 4.6,
|
| 1053 |
+
"learning_rate": 6.146307338575519e-06,
|
| 1054 |
+
"loss": 0.663,
|
| 1055 |
+
"step": 169
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 4.62,
|
| 1059 |
+
"learning_rate": 6.039202339608432e-06,
|
| 1060 |
+
"loss": 0.6571,
|
| 1061 |
+
"step": 170
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 4.62,
|
| 1065 |
+
"eval_loss": 0.6581608653068542,
|
| 1066 |
+
"eval_runtime": 23.2031,
|
| 1067 |
+
"eval_samples_per_second": 8.62,
|
| 1068 |
+
"eval_steps_per_second": 0.56,
|
| 1069 |
+
"step": 170
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 4.62,
|
| 1073 |
+
"step": 170,
|
| 1074 |
+
"total_flos": 3.168954324143309e+16,
|
| 1075 |
+
"train_loss": 0.8249162855393747,
|
| 1076 |
+
"train_runtime": 52349.2428,
|
| 1077 |
+
"train_samples_per_second": 2.662,
|
| 1078 |
+
"train_steps_per_second": 0.005
|
| 1079 |
+
}
|
| 1080 |
+
],
|
| 1081 |
+
"logging_steps": 1,
|
| 1082 |
+
"max_steps": 270,
|
| 1083 |
+
"num_train_epochs": 5,
|
| 1084 |
+
"save_steps": 500,
|
| 1085 |
+
"total_flos": 3.168954324143309e+16,
|
| 1086 |
+
"trial_name": null,
|
| 1087 |
+
"trial_params": null
|
| 1088 |
+
}
|