Model save
Browse files- README.md +64 -0
- adapter_model.safetensors +1 -1
- all_results.json +13 -0
- eval_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +1028 -0
README.md
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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: 01-ai/Yi-6B
|
| 11 |
+
model-index:
|
| 12 |
+
- name: Yi-6B-zhihu3
|
| 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 |
+
# Yi-6B-zhihu3
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [01-ai/Yi-6B](https://huggingface.co/01-ai/Yi-6B) on the generator dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 2.3217
|
| 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: 0.0002
|
| 43 |
+
- train_batch_size: 1
|
| 44 |
+
- eval_batch_size: 1
|
| 45 |
+
- seed: 42
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: cosine
|
| 48 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 49 |
+
- num_epochs: 1
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 55 |
+
| 2.303 | 1.0 | 820 | 2.3217 |
|
| 56 |
+
|
| 57 |
+
|
| 58 |
+
### Framework versions
|
| 59 |
+
|
| 60 |
+
- PEFT 0.7.1
|
| 61 |
+
- Transformers 4.36.2
|
| 62 |
+
- Pytorch 2.2.2+cu118
|
| 63 |
+
- Datasets 2.14.6
|
| 64 |
+
- Tokenizers 0.15.2
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 72673912
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:90339a8cec1ad9e41932eb681ceaa230df1f38f31c97f2b2195877ed2b254d6d
|
| 3 |
size 72673912
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 2.321652412414551,
|
| 4 |
+
"eval_runtime": 249.2875,
|
| 5 |
+
"eval_samples": 2561,
|
| 6 |
+
"eval_samples_per_second": 3.289,
|
| 7 |
+
"eval_steps_per_second": 3.289,
|
| 8 |
+
"train_loss": 0.9362016701116794,
|
| 9 |
+
"train_runtime": 598.217,
|
| 10 |
+
"train_samples": 2561,
|
| 11 |
+
"train_samples_per_second": 1.371,
|
| 12 |
+
"train_steps_per_second": 1.371
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 2.321652412414551,
|
| 4 |
+
"eval_runtime": 249.2875,
|
| 5 |
+
"eval_samples": 2561,
|
| 6 |
+
"eval_samples_per_second": 3.289,
|
| 7 |
+
"eval_steps_per_second": 3.289
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.9362016701116794,
|
| 4 |
+
"train_runtime": 598.217,
|
| 5 |
+
"train_samples": 2561,
|
| 6 |
+
"train_samples_per_second": 1.371,
|
| 7 |
+
"train_steps_per_second": 1.371
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1028 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 820,
|
| 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 |
+
"learning_rate": 2.4390243902439027e-06,
|
| 14 |
+
"loss": 2.6767,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"learning_rate": 1.2195121951219513e-05,
|
| 20 |
+
"loss": 2.7823,
|
| 21 |
+
"step": 5
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.01,
|
| 25 |
+
"learning_rate": 2.4390243902439026e-05,
|
| 26 |
+
"loss": 2.4361,
|
| 27 |
+
"step": 10
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.02,
|
| 31 |
+
"learning_rate": 3.6585365853658535e-05,
|
| 32 |
+
"loss": 2.535,
|
| 33 |
+
"step": 15
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.02,
|
| 37 |
+
"learning_rate": 4.878048780487805e-05,
|
| 38 |
+
"loss": 2.5652,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.03,
|
| 43 |
+
"learning_rate": 6.097560975609756e-05,
|
| 44 |
+
"loss": 2.6216,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.04,
|
| 49 |
+
"learning_rate": 7.317073170731707e-05,
|
| 50 |
+
"loss": 2.1459,
|
| 51 |
+
"step": 30
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.04,
|
| 55 |
+
"learning_rate": 8.53658536585366e-05,
|
| 56 |
+
"loss": 2.5116,
|
| 57 |
+
"step": 35
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.05,
|
| 61 |
+
"learning_rate": 9.75609756097561e-05,
|
| 62 |
+
"loss": 2.5704,
|
| 63 |
+
"step": 40
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.05,
|
| 67 |
+
"learning_rate": 0.00010975609756097563,
|
| 68 |
+
"loss": 2.3636,
|
| 69 |
+
"step": 45
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.06,
|
| 73 |
+
"learning_rate": 0.00012195121951219512,
|
| 74 |
+
"loss": 2.6786,
|
| 75 |
+
"step": 50
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.07,
|
| 79 |
+
"learning_rate": 0.00013414634146341464,
|
| 80 |
+
"loss": 2.4003,
|
| 81 |
+
"step": 55
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.07,
|
| 85 |
+
"learning_rate": 0.00014634146341463414,
|
| 86 |
+
"loss": 2.4267,
|
| 87 |
+
"step": 60
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.08,
|
| 91 |
+
"learning_rate": 0.00015853658536585366,
|
| 92 |
+
"loss": 2.4149,
|
| 93 |
+
"step": 65
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.09,
|
| 97 |
+
"learning_rate": 0.0001707317073170732,
|
| 98 |
+
"loss": 2.1072,
|
| 99 |
+
"step": 70
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.09,
|
| 103 |
+
"learning_rate": 0.0001829268292682927,
|
| 104 |
+
"loss": 2.3557,
|
| 105 |
+
"step": 75
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.1,
|
| 109 |
+
"learning_rate": 0.0001951219512195122,
|
| 110 |
+
"loss": 2.3392,
|
| 111 |
+
"step": 80
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.1,
|
| 115 |
+
"learning_rate": 0.00019999184556954776,
|
| 116 |
+
"loss": 2.2043,
|
| 117 |
+
"step": 85
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.11,
|
| 121 |
+
"learning_rate": 0.0001999420177550043,
|
| 122 |
+
"loss": 2.2218,
|
| 123 |
+
"step": 90
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.12,
|
| 127 |
+
"learning_rate": 0.00019984691491033906,
|
| 128 |
+
"loss": 2.4057,
|
| 129 |
+
"step": 95
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.12,
|
| 133 |
+
"learning_rate": 0.00019970658011837404,
|
| 134 |
+
"loss": 2.3682,
|
| 135 |
+
"step": 100
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.13,
|
| 139 |
+
"learning_rate": 0.00019952107695258992,
|
| 140 |
+
"loss": 2.718,
|
| 141 |
+
"step": 105
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.13,
|
| 145 |
+
"learning_rate": 0.00019929048944832638,
|
| 146 |
+
"loss": 2.4517,
|
| 147 |
+
"step": 110
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.14,
|
| 151 |
+
"learning_rate": 0.00019901492206471325,
|
| 152 |
+
"loss": 2.5616,
|
| 153 |
+
"step": 115
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.15,
|
| 157 |
+
"learning_rate": 0.00019869449963734893,
|
| 158 |
+
"loss": 2.496,
|
| 159 |
+
"step": 120
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.15,
|
| 163 |
+
"learning_rate": 0.00019832936732174834,
|
| 164 |
+
"loss": 2.1452,
|
| 165 |
+
"step": 125
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.16,
|
| 169 |
+
"learning_rate": 0.00019791969052758562,
|
| 170 |
+
"loss": 2.2789,
|
| 171 |
+
"step": 130
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.16,
|
| 175 |
+
"learning_rate": 0.00019746565484376132,
|
| 176 |
+
"loss": 2.0612,
|
| 177 |
+
"step": 135
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.17,
|
| 181 |
+
"learning_rate": 0.00019696746595432828,
|
| 182 |
+
"loss": 2.2248,
|
| 183 |
+
"step": 140
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.18,
|
| 187 |
+
"learning_rate": 0.0001964253495453141,
|
| 188 |
+
"loss": 2.6121,
|
| 189 |
+
"step": 145
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.18,
|
| 193 |
+
"learning_rate": 0.00019583955120248237,
|
| 194 |
+
"loss": 2.4211,
|
| 195 |
+
"step": 150
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.19,
|
| 199 |
+
"learning_rate": 0.00019521033630007928,
|
| 200 |
+
"loss": 2.5135,
|
| 201 |
+
"step": 155
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.2,
|
| 205 |
+
"learning_rate": 0.00019453798988061535,
|
| 206 |
+
"loss": 2.343,
|
| 207 |
+
"step": 160
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.2,
|
| 211 |
+
"learning_rate": 0.00019382281652573785,
|
| 212 |
+
"loss": 2.5214,
|
| 213 |
+
"step": 165
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.21,
|
| 217 |
+
"learning_rate": 0.00019306514021825118,
|
| 218 |
+
"loss": 2.6032,
|
| 219 |
+
"step": 170
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.21,
|
| 223 |
+
"learning_rate": 0.00019226530419534833,
|
| 224 |
+
"loss": 2.7405,
|
| 225 |
+
"step": 175
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.22,
|
| 229 |
+
"learning_rate": 0.00019142367079312021,
|
| 230 |
+
"loss": 2.2154,
|
| 231 |
+
"step": 180
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.23,
|
| 235 |
+
"learning_rate": 0.00019054062128241264,
|
| 236 |
+
"loss": 2.5134,
|
| 237 |
+
"step": 185
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.23,
|
| 241 |
+
"learning_rate": 0.00018961655569610557,
|
| 242 |
+
"loss": 2.3687,
|
| 243 |
+
"step": 190
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.24,
|
| 247 |
+
"learning_rate": 0.0001886518926478932,
|
| 248 |
+
"loss": 2.4462,
|
| 249 |
+
"step": 195
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.24,
|
| 253 |
+
"learning_rate": 0.00018764706914264635,
|
| 254 |
+
"loss": 2.0328,
|
| 255 |
+
"step": 200
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.25,
|
| 259 |
+
"learning_rate": 0.00018660254037844388,
|
| 260 |
+
"loss": 2.5844,
|
| 261 |
+
"step": 205
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.26,
|
| 265 |
+
"learning_rate": 0.00018551877954036162,
|
| 266 |
+
"loss": 2.5333,
|
| 267 |
+
"step": 210
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.26,
|
| 271 |
+
"learning_rate": 0.00018439627758611385,
|
| 272 |
+
"loss": 2.3423,
|
| 273 |
+
"step": 215
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.27,
|
| 277 |
+
"learning_rate": 0.00018323554302364272,
|
| 278 |
+
"loss": 2.5999,
|
| 279 |
+
"step": 220
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.27,
|
| 283 |
+
"learning_rate": 0.00018203710168075788,
|
| 284 |
+
"loss": 2.421,
|
| 285 |
+
"step": 225
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.28,
|
| 289 |
+
"learning_rate": 0.0001808014964669293,
|
| 290 |
+
"loss": 2.5597,
|
| 291 |
+
"step": 230
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.29,
|
| 295 |
+
"learning_rate": 0.00017952928712734268,
|
| 296 |
+
"loss": 2.48,
|
| 297 |
+
"step": 235
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.29,
|
| 301 |
+
"learning_rate": 0.00017822104998932713,
|
| 302 |
+
"loss": 2.6025,
|
| 303 |
+
"step": 240
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.3,
|
| 307 |
+
"learning_rate": 0.00017687737770127185,
|
| 308 |
+
"loss": 2.3616,
|
| 309 |
+
"step": 245
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.3,
|
| 313 |
+
"learning_rate": 0.00017549887896414851,
|
| 314 |
+
"loss": 2.4311,
|
| 315 |
+
"step": 250
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.31,
|
| 319 |
+
"learning_rate": 0.0001740861782557618,
|
| 320 |
+
"loss": 2.5858,
|
| 321 |
+
"step": 255
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.32,
|
| 325 |
+
"learning_rate": 0.0001726399155478529,
|
| 326 |
+
"loss": 2.4726,
|
| 327 |
+
"step": 260
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.32,
|
| 331 |
+
"learning_rate": 0.00017116074601618417,
|
| 332 |
+
"loss": 2.4097,
|
| 333 |
+
"step": 265
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.33,
|
| 337 |
+
"learning_rate": 0.0001696493397437357,
|
| 338 |
+
"loss": 2.4452,
|
| 339 |
+
"step": 270
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.34,
|
| 343 |
+
"learning_rate": 0.00016810638141714934,
|
| 344 |
+
"loss": 2.341,
|
| 345 |
+
"step": 275
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.34,
|
| 349 |
+
"learning_rate": 0.00016653257001655652,
|
| 350 |
+
"loss": 2.2435,
|
| 351 |
+
"step": 280
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.35,
|
| 355 |
+
"learning_rate": 0.0001649286184989315,
|
| 356 |
+
"loss": 2.3826,
|
| 357 |
+
"step": 285
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.35,
|
| 361 |
+
"learning_rate": 0.0001632952534751122,
|
| 362 |
+
"loss": 2.3505,
|
| 363 |
+
"step": 290
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.36,
|
| 367 |
+
"learning_rate": 0.00016163321488063637,
|
| 368 |
+
"loss": 2.5566,
|
| 369 |
+
"step": 295
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.37,
|
| 373 |
+
"learning_rate": 0.00015994325564054122,
|
| 374 |
+
"loss": 2.3983,
|
| 375 |
+
"step": 300
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.37,
|
| 379 |
+
"learning_rate": 0.00015822614132827837,
|
| 380 |
+
"loss": 2.0597,
|
| 381 |
+
"step": 305
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.38,
|
| 385 |
+
"learning_rate": 0.00015648264981889934,
|
| 386 |
+
"loss": 2.3717,
|
| 387 |
+
"step": 310
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.38,
|
| 391 |
+
"learning_rate": 0.00015471357093666804,
|
| 392 |
+
"loss": 2.6116,
|
| 393 |
+
"step": 315
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.39,
|
| 397 |
+
"learning_rate": 0.00015291970609726007,
|
| 398 |
+
"loss": 2.3766,
|
| 399 |
+
"step": 320
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.4,
|
| 403 |
+
"learning_rate": 0.00015110186794471103,
|
| 404 |
+
"loss": 2.2623,
|
| 405 |
+
"step": 325
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.4,
|
| 409 |
+
"learning_rate": 0.00014926087998327837,
|
| 410 |
+
"loss": 2.3868,
|
| 411 |
+
"step": 330
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.41,
|
| 415 |
+
"learning_rate": 0.00014739757620438307,
|
| 416 |
+
"loss": 2.6517,
|
| 417 |
+
"step": 335
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.41,
|
| 421 |
+
"learning_rate": 0.0001455128007088009,
|
| 422 |
+
"loss": 2.355,
|
| 423 |
+
"step": 340
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.42,
|
| 427 |
+
"learning_rate": 0.00014360740732427367,
|
| 428 |
+
"loss": 2.3603,
|
| 429 |
+
"step": 345
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.43,
|
| 433 |
+
"learning_rate": 0.00014168225921871433,
|
| 434 |
+
"loss": 2.4304,
|
| 435 |
+
"step": 350
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.43,
|
| 439 |
+
"learning_rate": 0.00013973822850918055,
|
| 440 |
+
"loss": 2.3809,
|
| 441 |
+
"step": 355
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.44,
|
| 445 |
+
"learning_rate": 0.0001377761958667946,
|
| 446 |
+
"loss": 2.6495,
|
| 447 |
+
"step": 360
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.45,
|
| 451 |
+
"learning_rate": 0.00013579705011778766,
|
| 452 |
+
"loss": 2.4582,
|
| 453 |
+
"step": 365
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.45,
|
| 457 |
+
"learning_rate": 0.00013380168784085027,
|
| 458 |
+
"loss": 2.4106,
|
| 459 |
+
"step": 370
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.46,
|
| 463 |
+
"learning_rate": 0.00013179101296097035,
|
| 464 |
+
"loss": 2.1831,
|
| 465 |
+
"step": 375
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.46,
|
| 469 |
+
"learning_rate": 0.00012976593633994346,
|
| 470 |
+
"loss": 2.5222,
|
| 471 |
+
"step": 380
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.47,
|
| 475 |
+
"learning_rate": 0.0001277273753637408,
|
| 476 |
+
"loss": 2.4411,
|
| 477 |
+
"step": 385
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.48,
|
| 481 |
+
"learning_rate": 0.00012567625352692127,
|
| 482 |
+
"loss": 2.468,
|
| 483 |
+
"step": 390
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.48,
|
| 487 |
+
"learning_rate": 0.0001236135000142765,
|
| 488 |
+
"loss": 2.5124,
|
| 489 |
+
"step": 395
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.49,
|
| 493 |
+
"learning_rate": 0.00012154004927989815,
|
| 494 |
+
"loss": 2.2386,
|
| 495 |
+
"step": 400
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.49,
|
| 499 |
+
"learning_rate": 0.00011945684062385803,
|
| 500 |
+
"loss": 2.3717,
|
| 501 |
+
"step": 405
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.5,
|
| 505 |
+
"learning_rate": 0.00011736481776669306,
|
| 506 |
+
"loss": 2.4957,
|
| 507 |
+
"step": 410
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.51,
|
| 511 |
+
"learning_rate": 0.00011526492842188745,
|
| 512 |
+
"loss": 2.5043,
|
| 513 |
+
"step": 415
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.51,
|
| 517 |
+
"learning_rate": 0.0001131581238665465,
|
| 518 |
+
"loss": 2.4179,
|
| 519 |
+
"step": 420
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.52,
|
| 523 |
+
"learning_rate": 0.00011104535851045539,
|
| 524 |
+
"loss": 2.3551,
|
| 525 |
+
"step": 425
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.52,
|
| 529 |
+
"learning_rate": 0.00010892758946371944,
|
| 530 |
+
"loss": 2.3083,
|
| 531 |
+
"step": 430
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.53,
|
| 535 |
+
"learning_rate": 0.00010680577610318072,
|
| 536 |
+
"loss": 2.5975,
|
| 537 |
+
"step": 435
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.54,
|
| 541 |
+
"learning_rate": 0.00010468087963780789,
|
| 542 |
+
"loss": 2.2378,
|
| 543 |
+
"step": 440
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.54,
|
| 547 |
+
"learning_rate": 0.00010255386267325602,
|
| 548 |
+
"loss": 2.2045,
|
| 549 |
+
"step": 445
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.55,
|
| 553 |
+
"learning_rate": 0.00010042568877579388,
|
| 554 |
+
"loss": 2.0761,
|
| 555 |
+
"step": 450
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.55,
|
| 559 |
+
"learning_rate": 9.829732203579584e-05,
|
| 560 |
+
"loss": 2.3797,
|
| 561 |
+
"step": 455
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.56,
|
| 565 |
+
"learning_rate": 9.616972663099647e-05,
|
| 566 |
+
"loss": 2.457,
|
| 567 |
+
"step": 460
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.57,
|
| 571 |
+
"learning_rate": 9.404386638970542e-05,
|
| 572 |
+
"loss": 2.4869,
|
| 573 |
+
"step": 465
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.57,
|
| 577 |
+
"learning_rate": 9.192070435418079e-05,
|
| 578 |
+
"loss": 2.3134,
|
| 579 |
+
"step": 470
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.58,
|
| 583 |
+
"learning_rate": 8.980120234435849e-05,
|
| 584 |
+
"loss": 2.6018,
|
| 585 |
+
"step": 475
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.59,
|
| 589 |
+
"learning_rate": 8.768632052213531e-05,
|
| 590 |
+
"loss": 2.3912,
|
| 591 |
+
"step": 480
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.59,
|
| 595 |
+
"learning_rate": 8.557701695640321e-05,
|
| 596 |
+
"loss": 2.273,
|
| 597 |
+
"step": 485
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.6,
|
| 601 |
+
"learning_rate": 8.347424718903151e-05,
|
| 602 |
+
"loss": 2.4595,
|
| 603 |
+
"step": 490
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.6,
|
| 607 |
+
"learning_rate": 8.13789638019942e-05,
|
| 608 |
+
"loss": 2.4639,
|
| 609 |
+
"step": 495
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.61,
|
| 613 |
+
"learning_rate": 7.929211598583794e-05,
|
| 614 |
+
"loss": 2.3833,
|
| 615 |
+
"step": 500
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.62,
|
| 619 |
+
"learning_rate": 7.721464910968627e-05,
|
| 620 |
+
"loss": 2.1531,
|
| 621 |
+
"step": 505
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.62,
|
| 625 |
+
"learning_rate": 7.514750429297528e-05,
|
| 626 |
+
"loss": 1.9377,
|
| 627 |
+
"step": 510
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.63,
|
| 631 |
+
"learning_rate": 7.309161797911441e-05,
|
| 632 |
+
"loss": 2.3244,
|
| 633 |
+
"step": 515
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.63,
|
| 637 |
+
"learning_rate": 7.104792151126515e-05,
|
| 638 |
+
"loss": 2.452,
|
| 639 |
+
"step": 520
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.64,
|
| 643 |
+
"learning_rate": 6.901734071043071e-05,
|
| 644 |
+
"loss": 2.5114,
|
| 645 |
+
"step": 525
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.65,
|
| 649 |
+
"learning_rate": 6.700079545604708e-05,
|
| 650 |
+
"loss": 2.4173,
|
| 651 |
+
"step": 530
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 0.65,
|
| 655 |
+
"learning_rate": 6.499919926926566e-05,
|
| 656 |
+
"loss": 2.3595,
|
| 657 |
+
"step": 535
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.66,
|
| 661 |
+
"learning_rate": 6.301345889911637e-05,
|
| 662 |
+
"loss": 2.5965,
|
| 663 |
+
"step": 540
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.66,
|
| 667 |
+
"learning_rate": 6.104447391173858e-05,
|
| 668 |
+
"loss": 2.4791,
|
| 669 |
+
"step": 545
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.67,
|
| 673 |
+
"learning_rate": 5.909313628286601e-05,
|
| 674 |
+
"loss": 2.3998,
|
| 675 |
+
"step": 550
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.68,
|
| 679 |
+
"learning_rate": 5.716032999375006e-05,
|
| 680 |
+
"loss": 2.5947,
|
| 681 |
+
"step": 555
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.68,
|
| 685 |
+
"learning_rate": 5.524693063070492e-05,
|
| 686 |
+
"loss": 2.5223,
|
| 687 |
+
"step": 560
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 0.69,
|
| 691 |
+
"learning_rate": 5.335380498845559e-05,
|
| 692 |
+
"loss": 2.4139,
|
| 693 |
+
"step": 565
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 0.7,
|
| 697 |
+
"learning_rate": 5.148181067746862e-05,
|
| 698 |
+
"loss": 2.4851,
|
| 699 |
+
"step": 570
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.7,
|
| 703 |
+
"learning_rate": 4.963179573544357e-05,
|
| 704 |
+
"loss": 2.3187,
|
| 705 |
+
"step": 575
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.71,
|
| 709 |
+
"learning_rate": 4.7804598243140666e-05,
|
| 710 |
+
"loss": 2.5466,
|
| 711 |
+
"step": 580
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.71,
|
| 715 |
+
"learning_rate": 4.60010459447196e-05,
|
| 716 |
+
"loss": 2.5622,
|
| 717 |
+
"step": 585
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.72,
|
| 721 |
+
"learning_rate": 4.422195587276058e-05,
|
| 722 |
+
"loss": 2.3284,
|
| 723 |
+
"step": 590
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.73,
|
| 727 |
+
"learning_rate": 4.2468133978137945e-05,
|
| 728 |
+
"loss": 2.1308,
|
| 729 |
+
"step": 595
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.73,
|
| 733 |
+
"learning_rate": 4.0740374764914136e-05,
|
| 734 |
+
"loss": 2.5981,
|
| 735 |
+
"step": 600
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 0.74,
|
| 739 |
+
"learning_rate": 3.903946093041877e-05,
|
| 740 |
+
"loss": 2.1314,
|
| 741 |
+
"step": 605
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.74,
|
| 745 |
+
"learning_rate": 3.736616301067694e-05,
|
| 746 |
+
"loss": 2.2348,
|
| 747 |
+
"step": 610
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.75,
|
| 751 |
+
"learning_rate": 3.5721239031346066e-05,
|
| 752 |
+
"loss": 2.5269,
|
| 753 |
+
"step": 615
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.76,
|
| 757 |
+
"learning_rate": 3.410543416432069e-05,
|
| 758 |
+
"loss": 2.3657,
|
| 759 |
+
"step": 620
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.76,
|
| 763 |
+
"learning_rate": 3.2519480390159806e-05,
|
| 764 |
+
"loss": 2.4194,
|
| 765 |
+
"step": 625
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.77,
|
| 769 |
+
"learning_rate": 3.096409616649023e-05,
|
| 770 |
+
"loss": 2.4472,
|
| 771 |
+
"step": 630
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 0.77,
|
| 775 |
+
"learning_rate": 2.9439986102536043e-05,
|
| 776 |
+
"loss": 2.0381,
|
| 777 |
+
"step": 635
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.78,
|
| 781 |
+
"learning_rate": 2.794784063992131e-05,
|
| 782 |
+
"loss": 1.9038,
|
| 783 |
+
"step": 640
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.79,
|
| 787 |
+
"learning_rate": 2.6488335739891178e-05,
|
| 788 |
+
"loss": 2.5467,
|
| 789 |
+
"step": 645
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.79,
|
| 793 |
+
"learning_rate": 2.50621325770927e-05,
|
| 794 |
+
"loss": 2.3751,
|
| 795 |
+
"step": 650
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.8,
|
| 799 |
+
"learning_rate": 2.366987724005404e-05,
|
| 800 |
+
"loss": 2.2535,
|
| 801 |
+
"step": 655
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.8,
|
| 805 |
+
"learning_rate": 2.2312200438498043e-05,
|
| 806 |
+
"loss": 2.5885,
|
| 807 |
+
"step": 660
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.81,
|
| 811 |
+
"learning_rate": 2.0989717217622652e-05,
|
| 812 |
+
"loss": 2.4353,
|
| 813 |
+
"step": 665
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.82,
|
| 817 |
+
"learning_rate": 1.9703026679477256e-05,
|
| 818 |
+
"loss": 2.3635,
|
| 819 |
+
"step": 670
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.82,
|
| 823 |
+
"learning_rate": 1.8452711711561842e-05,
|
| 824 |
+
"loss": 2.4849,
|
| 825 |
+
"step": 675
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.83,
|
| 829 |
+
"learning_rate": 1.7239338722771327e-05,
|
| 830 |
+
"loss": 2.3917,
|
| 831 |
+
"step": 680
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.84,
|
| 835 |
+
"learning_rate": 1.6063457386805004e-05,
|
| 836 |
+
"loss": 2.7249,
|
| 837 |
+
"step": 685
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.84,
|
| 841 |
+
"learning_rate": 1.4925600393157324e-05,
|
| 842 |
+
"loss": 2.5142,
|
| 843 |
+
"step": 690
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.85,
|
| 847 |
+
"learning_rate": 1.3826283205802427e-05,
|
| 848 |
+
"loss": 2.5111,
|
| 849 |
+
"step": 695
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.85,
|
| 853 |
+
"learning_rate": 1.2766003829682505e-05,
|
| 854 |
+
"loss": 2.1423,
|
| 855 |
+
"step": 700
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.86,
|
| 859 |
+
"learning_rate": 1.1745242585104955e-05,
|
| 860 |
+
"loss": 2.2201,
|
| 861 |
+
"step": 705
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.87,
|
| 865 |
+
"learning_rate": 1.0764461890151112e-05,
|
| 866 |
+
"loss": 2.5609,
|
| 867 |
+
"step": 710
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 0.87,
|
| 871 |
+
"learning_rate": 9.824106051194859e-06,
|
| 872 |
+
"loss": 2.339,
|
| 873 |
+
"step": 715
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.88,
|
| 877 |
+
"learning_rate": 8.924601061626048e-06,
|
| 878 |
+
"loss": 2.5648,
|
| 879 |
+
"step": 720
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.88,
|
| 883 |
+
"learning_rate": 8.066354408870048e-06,
|
| 884 |
+
"loss": 2.3712,
|
| 885 |
+
"step": 725
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.89,
|
| 889 |
+
"learning_rate": 7.249754889790539e-06,
|
| 890 |
+
"loss": 2.4474,
|
| 891 |
+
"step": 730
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.9,
|
| 895 |
+
"learning_rate": 6.475172434559573e-06,
|
| 896 |
+
"loss": 2.4237,
|
| 897 |
+
"step": 735
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.9,
|
| 901 |
+
"learning_rate": 5.742957939074412e-06,
|
| 902 |
+
"loss": 2.401,
|
| 903 |
+
"step": 740
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.91,
|
| 907 |
+
"learning_rate": 5.0534431059970685e-06,
|
| 908 |
+
"loss": 2.6402,
|
| 909 |
+
"step": 745
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 0.91,
|
| 913 |
+
"learning_rate": 4.40694029448877e-06,
|
| 914 |
+
"loss": 2.2489,
|
| 915 |
+
"step": 750
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.92,
|
| 919 |
+
"learning_rate": 3.803742378707198e-06,
|
| 920 |
+
"loss": 2.1774,
|
| 921 |
+
"step": 755
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.93,
|
| 925 |
+
"learning_rate": 3.2441226151306404e-06,
|
| 926 |
+
"loss": 2.4729,
|
| 927 |
+
"step": 760
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.93,
|
| 931 |
+
"learning_rate": 2.7283345187693264e-06,
|
| 932 |
+
"loss": 2.1403,
|
| 933 |
+
"step": 765
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.94,
|
| 937 |
+
"learning_rate": 2.256611748319792e-06,
|
| 938 |
+
"loss": 2.818,
|
| 939 |
+
"step": 770
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.95,
|
| 943 |
+
"learning_rate": 1.8291680003145073e-06,
|
| 944 |
+
"loss": 2.8155,
|
| 945 |
+
"step": 775
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 0.95,
|
| 949 |
+
"learning_rate": 1.4461969123145457e-06,
|
| 950 |
+
"loss": 2.2691,
|
| 951 |
+
"step": 780
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 0.96,
|
| 955 |
+
"learning_rate": 1.107871975189234e-06,
|
| 956 |
+
"loss": 2.3321,
|
| 957 |
+
"step": 785
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.96,
|
| 961 |
+
"learning_rate": 8.143464545226298e-07,
|
| 962 |
+
"loss": 2.3751,
|
| 963 |
+
"step": 790
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 0.97,
|
| 967 |
+
"learning_rate": 5.657533211820942e-07,
|
| 968 |
+
"loss": 2.5208,
|
| 969 |
+
"step": 795
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.98,
|
| 973 |
+
"learning_rate": 3.622051910808666e-07,
|
| 974 |
+
"loss": 1.9324,
|
| 975 |
+
"step": 800
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.98,
|
| 979 |
+
"learning_rate": 2.037942741615617e-07,
|
| 980 |
+
"loss": 2.6099,
|
| 981 |
+
"step": 805
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.99,
|
| 985 |
+
"learning_rate": 9.059233262386225e-08,
|
| 986 |
+
"loss": 2.4554,
|
| 987 |
+
"step": 810
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 0.99,
|
| 991 |
+
"learning_rate": 2.2650648415334376e-08,
|
| 992 |
+
"loss": 2.5679,
|
| 993 |
+
"step": 815
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 1.0,
|
| 997 |
+
"learning_rate": 0.0,
|
| 998 |
+
"loss": 2.303,
|
| 999 |
+
"step": 820
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 1.0,
|
| 1003 |
+
"eval_loss": 2.321652412414551,
|
| 1004 |
+
"eval_runtime": 249.3077,
|
| 1005 |
+
"eval_samples_per_second": 3.289,
|
| 1006 |
+
"eval_steps_per_second": 3.289,
|
| 1007 |
+
"step": 820
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 1.0,
|
| 1011 |
+
"step": 820,
|
| 1012 |
+
"total_flos": 5.879639335501824e+16,
|
| 1013 |
+
"train_loss": 0.9362016701116794,
|
| 1014 |
+
"train_runtime": 598.217,
|
| 1015 |
+
"train_samples_per_second": 1.371,
|
| 1016 |
+
"train_steps_per_second": 1.371
|
| 1017 |
+
}
|
| 1018 |
+
],
|
| 1019 |
+
"logging_steps": 5,
|
| 1020 |
+
"max_steps": 820,
|
| 1021 |
+
"num_input_tokens_seen": 0,
|
| 1022 |
+
"num_train_epochs": 1,
|
| 1023 |
+
"save_steps": 100,
|
| 1024 |
+
"total_flos": 5.879639335501824e+16,
|
| 1025 |
+
"train_batch_size": 1,
|
| 1026 |
+
"trial_name": null,
|
| 1027 |
+
"trial_params": null
|
| 1028 |
+
}
|