Model save
Browse files- README.md +64 -0
- adapter_config.json +4 -4
- adapter_model.safetensors +1 -1
- all_results.json +13 -0
- eval_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +992 -0
- training_args.bin +1 -1
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-zhihu2
|
| 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-zhihu2
|
| 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: 2.4003
|
| 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 |
+
| 2.3449 | 1.0 | 793 | 2.4003 |
|
| 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_config.json
CHANGED
|
@@ -19,13 +19,13 @@
|
|
| 19 |
"rank_pattern": {},
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
|
|
|
| 22 |
"k_proj",
|
| 23 |
"down_proj",
|
| 24 |
-
"gate_proj",
|
| 25 |
-
"up_proj",
|
| 26 |
"v_proj",
|
| 27 |
-
"
|
| 28 |
-
"q_proj"
|
|
|
|
| 29 |
],
|
| 30 |
"task_type": "CAUSAL_LM"
|
| 31 |
}
|
|
|
|
| 19 |
"rank_pattern": {},
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
| 22 |
+
"up_proj",
|
| 23 |
"k_proj",
|
| 24 |
"down_proj",
|
|
|
|
|
|
|
| 25 |
"v_proj",
|
| 26 |
+
"gate_proj",
|
| 27 |
+
"q_proj",
|
| 28 |
+
"o_proj"
|
| 29 |
],
|
| 30 |
"task_type": "CAUSAL_LM"
|
| 31 |
}
|
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:ba58f6abf07230a73a5dd88a21a98be79ddfaee0786e56ac817c81e7a379935b
|
| 3 |
size 72673912
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 2.400331974029541,
|
| 4 |
+
"eval_runtime": 240.7429,
|
| 5 |
+
"eval_samples": 2561,
|
| 6 |
+
"eval_samples_per_second": 3.294,
|
| 7 |
+
"eval_steps_per_second": 3.294,
|
| 8 |
+
"train_loss": 0.28998795253181214,
|
| 9 |
+
"train_runtime": 345.0365,
|
| 10 |
+
"train_samples": 2561,
|
| 11 |
+
"train_samples_per_second": 2.298,
|
| 12 |
+
"train_steps_per_second": 2.298
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 2.400331974029541,
|
| 4 |
+
"eval_runtime": 240.7429,
|
| 5 |
+
"eval_samples": 2561,
|
| 6 |
+
"eval_samples_per_second": 3.294,
|
| 7 |
+
"eval_steps_per_second": 3.294
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.28998795253181214,
|
| 4 |
+
"train_runtime": 345.0365,
|
| 5 |
+
"train_samples": 2561,
|
| 6 |
+
"train_samples_per_second": 2.298,
|
| 7 |
+
"train_steps_per_second": 2.298
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,992 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 793,
|
| 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": 2.5e-06,
|
| 14 |
+
"loss": 2.731,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"learning_rate": 1.25e-05,
|
| 20 |
+
"loss": 2.4673,
|
| 21 |
+
"step": 5
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.01,
|
| 25 |
+
"learning_rate": 2.5e-05,
|
| 26 |
+
"loss": 2.6706,
|
| 27 |
+
"step": 10
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.02,
|
| 31 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 32 |
+
"loss": 2.6655,
|
| 33 |
+
"step": 15
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.03,
|
| 37 |
+
"learning_rate": 5e-05,
|
| 38 |
+
"loss": 2.6413,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.03,
|
| 43 |
+
"learning_rate": 6.25e-05,
|
| 44 |
+
"loss": 2.5822,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.04,
|
| 49 |
+
"learning_rate": 7.500000000000001e-05,
|
| 50 |
+
"loss": 2.5791,
|
| 51 |
+
"step": 30
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.04,
|
| 55 |
+
"learning_rate": 8.75e-05,
|
| 56 |
+
"loss": 2.4541,
|
| 57 |
+
"step": 35
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.05,
|
| 61 |
+
"learning_rate": 0.0001,
|
| 62 |
+
"loss": 2.2348,
|
| 63 |
+
"step": 40
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.06,
|
| 67 |
+
"learning_rate": 0.00011250000000000001,
|
| 68 |
+
"loss": 2.4262,
|
| 69 |
+
"step": 45
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.06,
|
| 73 |
+
"learning_rate": 0.000125,
|
| 74 |
+
"loss": 2.5609,
|
| 75 |
+
"step": 50
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.07,
|
| 79 |
+
"learning_rate": 0.0001375,
|
| 80 |
+
"loss": 2.3085,
|
| 81 |
+
"step": 55
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.08,
|
| 85 |
+
"learning_rate": 0.00015000000000000001,
|
| 86 |
+
"loss": 2.4856,
|
| 87 |
+
"step": 60
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.08,
|
| 91 |
+
"learning_rate": 0.00016250000000000002,
|
| 92 |
+
"loss": 2.5578,
|
| 93 |
+
"step": 65
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.09,
|
| 97 |
+
"learning_rate": 0.000175,
|
| 98 |
+
"loss": 2.5337,
|
| 99 |
+
"step": 70
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.09,
|
| 103 |
+
"learning_rate": 0.0001875,
|
| 104 |
+
"loss": 2.6725,
|
| 105 |
+
"step": 75
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.1,
|
| 109 |
+
"learning_rate": 0.0002,
|
| 110 |
+
"loss": 2.0052,
|
| 111 |
+
"step": 80
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.11,
|
| 115 |
+
"learning_rate": 0.0001999757331652354,
|
| 116 |
+
"loss": 2.8976,
|
| 117 |
+
"step": 85
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.11,
|
| 121 |
+
"learning_rate": 0.00019990294443852685,
|
| 122 |
+
"loss": 2.7538,
|
| 123 |
+
"step": 90
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.12,
|
| 127 |
+
"learning_rate": 0.00019978166914691453,
|
| 128 |
+
"loss": 2.11,
|
| 129 |
+
"step": 95
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.13,
|
| 133 |
+
"learning_rate": 0.00019961196614974767,
|
| 134 |
+
"loss": 2.4711,
|
| 135 |
+
"step": 100
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.13,
|
| 139 |
+
"learning_rate": 0.00019939391781011807,
|
| 140 |
+
"loss": 2.1637,
|
| 141 |
+
"step": 105
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.14,
|
| 145 |
+
"learning_rate": 0.00019912762995488633,
|
| 146 |
+
"loss": 2.6475,
|
| 147 |
+
"step": 110
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.15,
|
| 151 |
+
"learning_rate": 0.00019881323182332006,
|
| 152 |
+
"loss": 2.3961,
|
| 153 |
+
"step": 115
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.15,
|
| 157 |
+
"learning_rate": 0.00019845087600436947,
|
| 158 |
+
"loss": 2.6875,
|
| 159 |
+
"step": 120
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.16,
|
| 163 |
+
"learning_rate": 0.00019804073836261025,
|
| 164 |
+
"loss": 2.6841,
|
| 165 |
+
"step": 125
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.16,
|
| 169 |
+
"learning_rate": 0.0001975830179528901,
|
| 170 |
+
"loss": 2.6747,
|
| 171 |
+
"step": 130
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.17,
|
| 175 |
+
"learning_rate": 0.00019707793692372,
|
| 176 |
+
"loss": 2.6586,
|
| 177 |
+
"step": 135
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.18,
|
| 181 |
+
"learning_rate": 0.00019652574040945745,
|
| 182 |
+
"loss": 2.4275,
|
| 183 |
+
"step": 140
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.18,
|
| 187 |
+
"learning_rate": 0.00019592669641133395,
|
| 188 |
+
"loss": 2.4158,
|
| 189 |
+
"step": 145
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.19,
|
| 193 |
+
"learning_rate": 0.00019528109566738382,
|
| 194 |
+
"loss": 2.2207,
|
| 195 |
+
"step": 150
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.2,
|
| 199 |
+
"learning_rate": 0.0001945892515113386,
|
| 200 |
+
"loss": 2.3564,
|
| 201 |
+
"step": 155
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.2,
|
| 205 |
+
"learning_rate": 0.00019385149972055466,
|
| 206 |
+
"loss": 2.9308,
|
| 207 |
+
"step": 160
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.21,
|
| 211 |
+
"learning_rate": 0.0001930681983530481,
|
| 212 |
+
"loss": 2.7843,
|
| 213 |
+
"step": 165
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.21,
|
| 217 |
+
"learning_rate": 0.000192239727573716,
|
| 218 |
+
"loss": 2.5293,
|
| 219 |
+
"step": 170
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.22,
|
| 223 |
+
"learning_rate": 0.0001913664894698286,
|
| 224 |
+
"loss": 2.374,
|
| 225 |
+
"step": 175
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.23,
|
| 229 |
+
"learning_rate": 0.0001904489078558814,
|
| 230 |
+
"loss": 2.6003,
|
| 231 |
+
"step": 180
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.23,
|
| 235 |
+
"learning_rate": 0.0001894874280679026,
|
| 236 |
+
"loss": 2.3425,
|
| 237 |
+
"step": 185
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.24,
|
| 241 |
+
"learning_rate": 0.00018848251674731507,
|
| 242 |
+
"loss": 2.5159,
|
| 243 |
+
"step": 190
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.25,
|
| 247 |
+
"learning_rate": 0.00018743466161445823,
|
| 248 |
+
"loss": 2.6329,
|
| 249 |
+
"step": 195
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.25,
|
| 253 |
+
"learning_rate": 0.00018634437123187937,
|
| 254 |
+
"loss": 2.3351,
|
| 255 |
+
"step": 200
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.26,
|
| 259 |
+
"learning_rate": 0.00018521217475750973,
|
| 260 |
+
"loss": 2.5704,
|
| 261 |
+
"step": 205
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.26,
|
| 265 |
+
"learning_rate": 0.00018403862168784457,
|
| 266 |
+
"loss": 2.4092,
|
| 267 |
+
"step": 210
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.27,
|
| 271 |
+
"learning_rate": 0.00018282428159125248,
|
| 272 |
+
"loss": 2.4303,
|
| 273 |
+
"step": 215
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.28,
|
| 277 |
+
"learning_rate": 0.0001815697438315429,
|
| 278 |
+
"loss": 2.4577,
|
| 279 |
+
"step": 220
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.28,
|
| 283 |
+
"learning_rate": 0.00018027561728192626,
|
| 284 |
+
"loss": 2.46,
|
| 285 |
+
"step": 225
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.29,
|
| 289 |
+
"learning_rate": 0.00017894253002950542,
|
| 290 |
+
"loss": 2.5202,
|
| 291 |
+
"step": 230
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.3,
|
| 295 |
+
"learning_rate": 0.000177571129070442,
|
| 296 |
+
"loss": 2.6827,
|
| 297 |
+
"step": 235
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.3,
|
| 301 |
+
"learning_rate": 0.0001761620799959454,
|
| 302 |
+
"loss": 2.989,
|
| 303 |
+
"step": 240
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.31,
|
| 307 |
+
"learning_rate": 0.000174716066669237,
|
| 308 |
+
"loss": 2.7209,
|
| 309 |
+
"step": 245
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.32,
|
| 313 |
+
"learning_rate": 0.00017323379089364602,
|
| 314 |
+
"loss": 2.6086,
|
| 315 |
+
"step": 250
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.32,
|
| 319 |
+
"learning_rate": 0.000171715972071999,
|
| 320 |
+
"loss": 2.6182,
|
| 321 |
+
"step": 255
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.33,
|
| 325 |
+
"learning_rate": 0.00017016334685746685,
|
| 326 |
+
"loss": 2.5666,
|
| 327 |
+
"step": 260
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.33,
|
| 331 |
+
"learning_rate": 0.0001685766687960402,
|
| 332 |
+
"loss": 2.4663,
|
| 333 |
+
"step": 265
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.34,
|
| 337 |
+
"learning_rate": 0.00016695670796080592,
|
| 338 |
+
"loss": 2.3282,
|
| 339 |
+
"step": 270
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.35,
|
| 343 |
+
"learning_rate": 0.00016530425057820227,
|
| 344 |
+
"loss": 2.4567,
|
| 345 |
+
"step": 275
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.35,
|
| 349 |
+
"learning_rate": 0.00016362009864643443,
|
| 350 |
+
"loss": 2.2274,
|
| 351 |
+
"step": 280
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.36,
|
| 355 |
+
"learning_rate": 0.0001619050695462353,
|
| 356 |
+
"loss": 2.2665,
|
| 357 |
+
"step": 285
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.37,
|
| 361 |
+
"learning_rate": 0.00016015999564416078,
|
| 362 |
+
"loss": 2.046,
|
| 363 |
+
"step": 290
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.37,
|
| 367 |
+
"learning_rate": 0.00015838572388861147,
|
| 368 |
+
"loss": 2.2182,
|
| 369 |
+
"step": 295
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.38,
|
| 373 |
+
"learning_rate": 0.0001565831153987778,
|
| 374 |
+
"loss": 2.4857,
|
| 375 |
+
"step": 300
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.38,
|
| 379 |
+
"learning_rate": 0.0001547530450467071,
|
| 380 |
+
"loss": 2.3942,
|
| 381 |
+
"step": 305
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.39,
|
| 385 |
+
"learning_rate": 0.00015289640103269625,
|
| 386 |
+
"loss": 2.635,
|
| 387 |
+
"step": 310
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.4,
|
| 391 |
+
"learning_rate": 0.0001510140844542153,
|
| 392 |
+
"loss": 2.4103,
|
| 393 |
+
"step": 315
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.4,
|
| 397 |
+
"learning_rate": 0.00014910700886857197,
|
| 398 |
+
"loss": 2.5356,
|
| 399 |
+
"step": 320
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.41,
|
| 403 |
+
"learning_rate": 0.00014717609984952866,
|
| 404 |
+
"loss": 2.6382,
|
| 405 |
+
"step": 325
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.42,
|
| 409 |
+
"learning_rate": 0.00014522229453808758,
|
| 410 |
+
"loss": 2.1514,
|
| 411 |
+
"step": 330
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.42,
|
| 415 |
+
"learning_rate": 0.0001432465411876618,
|
| 416 |
+
"loss": 2.5063,
|
| 417 |
+
"step": 335
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.43,
|
| 421 |
+
"learning_rate": 0.0001412497987038532,
|
| 422 |
+
"loss": 2.4789,
|
| 423 |
+
"step": 340
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.44,
|
| 427 |
+
"learning_rate": 0.00013923303617906015,
|
| 428 |
+
"loss": 2.3494,
|
| 429 |
+
"step": 345
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.44,
|
| 433 |
+
"learning_rate": 0.00013719723242214168,
|
| 434 |
+
"loss": 2.443,
|
| 435 |
+
"step": 350
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.45,
|
| 439 |
+
"learning_rate": 0.0001351433754833654,
|
| 440 |
+
"loss": 2.382,
|
| 441 |
+
"step": 355
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.45,
|
| 445 |
+
"learning_rate": 0.0001330724621748706,
|
| 446 |
+
"loss": 2.5961,
|
| 447 |
+
"step": 360
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.46,
|
| 451 |
+
"learning_rate": 0.00013098549758687865,
|
| 452 |
+
"loss": 2.8336,
|
| 453 |
+
"step": 365
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.47,
|
| 457 |
+
"learning_rate": 0.0001288834945998859,
|
| 458 |
+
"loss": 2.5518,
|
| 459 |
+
"step": 370
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.47,
|
| 463 |
+
"learning_rate": 0.00012676747339307554,
|
| 464 |
+
"loss": 2.1127,
|
| 465 |
+
"step": 375
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.48,
|
| 469 |
+
"learning_rate": 0.00012463846094918723,
|
| 470 |
+
"loss": 2.6908,
|
| 471 |
+
"step": 380
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.49,
|
| 475 |
+
"learning_rate": 0.00012249749055608474,
|
| 476 |
+
"loss": 2.6419,
|
| 477 |
+
"step": 385
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.49,
|
| 481 |
+
"learning_rate": 0.0001203456013052634,
|
| 482 |
+
"loss": 2.4063,
|
| 483 |
+
"step": 390
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.5,
|
| 487 |
+
"learning_rate": 0.00011818383758754082,
|
| 488 |
+
"loss": 2.2766,
|
| 489 |
+
"step": 395
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.5,
|
| 493 |
+
"learning_rate": 0.00011601324858617572,
|
| 494 |
+
"loss": 2.5315,
|
| 495 |
+
"step": 400
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.51,
|
| 499 |
+
"learning_rate": 0.00011383488776766093,
|
| 500 |
+
"loss": 2.8151,
|
| 501 |
+
"step": 405
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.52,
|
| 505 |
+
"learning_rate": 0.00011164981237043728,
|
| 506 |
+
"loss": 2.6057,
|
| 507 |
+
"step": 410
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.52,
|
| 511 |
+
"learning_rate": 0.00010945908289177694,
|
| 512 |
+
"loss": 2.4863,
|
| 513 |
+
"step": 415
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.53,
|
| 517 |
+
"learning_rate": 0.00010726376257308544,
|
| 518 |
+
"loss": 2.2287,
|
| 519 |
+
"step": 420
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.54,
|
| 523 |
+
"learning_rate": 0.00010506491688387127,
|
| 524 |
+
"loss": 2.3064,
|
| 525 |
+
"step": 425
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.54,
|
| 529 |
+
"learning_rate": 0.00010286361300463481,
|
| 530 |
+
"loss": 2.4449,
|
| 531 |
+
"step": 430
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.55,
|
| 535 |
+
"learning_rate": 0.00010066091930892605,
|
| 536 |
+
"loss": 2.7777,
|
| 537 |
+
"step": 435
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.55,
|
| 541 |
+
"learning_rate": 9.845790484482404e-05,
|
| 542 |
+
"loss": 2.5837,
|
| 543 |
+
"step": 440
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.56,
|
| 547 |
+
"learning_rate": 9.625563881608847e-05,
|
| 548 |
+
"loss": 2.4259,
|
| 549 |
+
"step": 445
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.57,
|
| 553 |
+
"learning_rate": 9.405519006323588e-05,
|
| 554 |
+
"loss": 2.7834,
|
| 555 |
+
"step": 450
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.57,
|
| 559 |
+
"learning_rate": 9.185762654479219e-05,
|
| 560 |
+
"loss": 2.6675,
|
| 561 |
+
"step": 455
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.58,
|
| 565 |
+
"learning_rate": 8.966401481897304e-05,
|
| 566 |
+
"loss": 2.5957,
|
| 567 |
+
"step": 460
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.59,
|
| 571 |
+
"learning_rate": 8.747541952604423e-05,
|
| 572 |
+
"loss": 2.3405,
|
| 573 |
+
"step": 465
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.59,
|
| 577 |
+
"learning_rate": 8.52929028716126e-05,
|
| 578 |
+
"loss": 2.4473,
|
| 579 |
+
"step": 470
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.6,
|
| 583 |
+
"learning_rate": 8.311752411109863e-05,
|
| 584 |
+
"loss": 2.2817,
|
| 585 |
+
"step": 475
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.61,
|
| 589 |
+
"learning_rate": 8.095033903564091e-05,
|
| 590 |
+
"loss": 2.7025,
|
| 591 |
+
"step": 480
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.61,
|
| 595 |
+
"learning_rate": 7.879239945968209e-05,
|
| 596 |
+
"loss": 2.3289,
|
| 597 |
+
"step": 485
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.62,
|
| 601 |
+
"learning_rate": 7.664475271048458e-05,
|
| 602 |
+
"loss": 2.6471,
|
| 603 |
+
"step": 490
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.62,
|
| 607 |
+
"learning_rate": 7.450844111982436e-05,
|
| 608 |
+
"loss": 2.5394,
|
| 609 |
+
"step": 495
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.63,
|
| 613 |
+
"learning_rate": 7.238450151810885e-05,
|
| 614 |
+
"loss": 2.422,
|
| 615 |
+
"step": 500
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.64,
|
| 619 |
+
"learning_rate": 7.02739647311654e-05,
|
| 620 |
+
"loss": 2.4525,
|
| 621 |
+
"step": 505
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.64,
|
| 625 |
+
"learning_rate": 6.817785507994349e-05,
|
| 626 |
+
"loss": 2.5048,
|
| 627 |
+
"step": 510
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.65,
|
| 631 |
+
"learning_rate": 6.609718988337423e-05,
|
| 632 |
+
"loss": 2.5573,
|
| 633 |
+
"step": 515
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.66,
|
| 637 |
+
"learning_rate": 6.403297896462807e-05,
|
| 638 |
+
"loss": 2.6636,
|
| 639 |
+
"step": 520
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.66,
|
| 643 |
+
"learning_rate": 6.198622416101077e-05,
|
| 644 |
+
"loss": 2.4896,
|
| 645 |
+
"step": 525
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.67,
|
| 649 |
+
"learning_rate": 5.995791883773474e-05,
|
| 650 |
+
"loss": 2.5308,
|
| 651 |
+
"step": 530
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 0.67,
|
| 655 |
+
"learning_rate": 5.794904740580269e-05,
|
| 656 |
+
"loss": 2.4272,
|
| 657 |
+
"step": 535
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.68,
|
| 661 |
+
"learning_rate": 5.596058484423656e-05,
|
| 662 |
+
"loss": 2.4119,
|
| 663 |
+
"step": 540
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.69,
|
| 667 |
+
"learning_rate": 5.399349622688479e-05,
|
| 668 |
+
"loss": 2.7247,
|
| 669 |
+
"step": 545
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.69,
|
| 673 |
+
"learning_rate": 5.20487362540362e-05,
|
| 674 |
+
"loss": 2.4899,
|
| 675 |
+
"step": 550
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.7,
|
| 679 |
+
"learning_rate": 5.012724878906926e-05,
|
| 680 |
+
"loss": 2.4428,
|
| 681 |
+
"step": 555
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.71,
|
| 685 |
+
"learning_rate": 4.82299664003601e-05,
|
| 686 |
+
"loss": 2.613,
|
| 687 |
+
"step": 560
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 0.71,
|
| 691 |
+
"learning_rate": 4.6357809908673435e-05,
|
| 692 |
+
"loss": 2.5947,
|
| 693 |
+
"step": 565
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 0.72,
|
| 697 |
+
"learning_rate": 4.451168794025391e-05,
|
| 698 |
+
"loss": 2.3137,
|
| 699 |
+
"step": 570
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.73,
|
| 703 |
+
"learning_rate": 4.269249648583692e-05,
|
| 704 |
+
"loss": 2.3568,
|
| 705 |
+
"step": 575
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.73,
|
| 709 |
+
"learning_rate": 4.0901118465790875e-05,
|
| 710 |
+
"loss": 1.9487,
|
| 711 |
+
"step": 580
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.74,
|
| 715 |
+
"learning_rate": 3.9138423301604154e-05,
|
| 716 |
+
"loss": 2.3949,
|
| 717 |
+
"step": 585
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.74,
|
| 721 |
+
"learning_rate": 3.740526649392256e-05,
|
| 722 |
+
"loss": 2.6208,
|
| 723 |
+
"step": 590
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.75,
|
| 727 |
+
"learning_rate": 3.570248920734354e-05,
|
| 728 |
+
"loss": 2.3749,
|
| 729 |
+
"step": 595
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.76,
|
| 733 |
+
"learning_rate": 3.4030917862168165e-05,
|
| 734 |
+
"loss": 2.5309,
|
| 735 |
+
"step": 600
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 0.76,
|
| 739 |
+
"learning_rate": 3.239136373330903e-05,
|
| 740 |
+
"loss": 2.6263,
|
| 741 |
+
"step": 605
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.77,
|
| 745 |
+
"learning_rate": 3.0784622556548856e-05,
|
| 746 |
+
"loss": 2.5203,
|
| 747 |
+
"step": 610
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.78,
|
| 751 |
+
"learning_rate": 2.921147414234051e-05,
|
| 752 |
+
"loss": 2.3685,
|
| 753 |
+
"step": 615
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.78,
|
| 757 |
+
"learning_rate": 2.767268199733657e-05,
|
| 758 |
+
"loss": 2.7285,
|
| 759 |
+
"step": 620
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.79,
|
| 763 |
+
"learning_rate": 2.6168992953831396e-05,
|
| 764 |
+
"loss": 2.3638,
|
| 765 |
+
"step": 625
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.79,
|
| 769 |
+
"learning_rate": 2.4701136807296177e-05,
|
| 770 |
+
"loss": 2.1867,
|
| 771 |
+
"step": 630
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 0.8,
|
| 775 |
+
"learning_rate": 2.326982596218219e-05,
|
| 776 |
+
"loss": 2.6267,
|
| 777 |
+
"step": 635
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.81,
|
| 781 |
+
"learning_rate": 2.187575508616493e-05,
|
| 782 |
+
"loss": 2.6749,
|
| 783 |
+
"step": 640
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.81,
|
| 787 |
+
"learning_rate": 2.0519600772996405e-05,
|
| 788 |
+
"loss": 2.4208,
|
| 789 |
+
"step": 645
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.82,
|
| 793 |
+
"learning_rate": 1.920202121412924e-05,
|
| 794 |
+
"loss": 2.6287,
|
| 795 |
+
"step": 650
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.83,
|
| 799 |
+
"learning_rate": 1.7923655879272393e-05,
|
| 800 |
+
"loss": 2.6315,
|
| 801 |
+
"step": 655
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.83,
|
| 805 |
+
"learning_rate": 1.668512520603276e-05,
|
| 806 |
+
"loss": 2.5708,
|
| 807 |
+
"step": 660
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.84,
|
| 811 |
+
"learning_rate": 1.548703029879437e-05,
|
| 812 |
+
"loss": 2.3316,
|
| 813 |
+
"step": 665
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.84,
|
| 817 |
+
"learning_rate": 1.4329952636980115e-05,
|
| 818 |
+
"loss": 2.1933,
|
| 819 |
+
"step": 670
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.85,
|
| 823 |
+
"learning_rate": 1.321445379283861e-05,
|
| 824 |
+
"loss": 2.1816,
|
| 825 |
+
"step": 675
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.86,
|
| 829 |
+
"learning_rate": 1.214107515889248e-05,
|
| 830 |
+
"loss": 2.474,
|
| 831 |
+
"step": 680
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.86,
|
| 835 |
+
"learning_rate": 1.111033768518066e-05,
|
| 836 |
+
"loss": 2.5638,
|
| 837 |
+
"step": 685
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.87,
|
| 841 |
+
"learning_rate": 1.0122741626422438e-05,
|
| 842 |
+
"loss": 2.5808,
|
| 843 |
+
"step": 690
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.88,
|
| 847 |
+
"learning_rate": 9.178766299225205e-06,
|
| 848 |
+
"loss": 2.1113,
|
| 849 |
+
"step": 695
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.88,
|
| 853 |
+
"learning_rate": 8.278869849454718e-06,
|
| 854 |
+
"loss": 2.6343,
|
| 855 |
+
"step": 700
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.89,
|
| 859 |
+
"learning_rate": 7.423489029879982e-06,
|
| 860 |
+
"loss": 2.3117,
|
| 861 |
+
"step": 705
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.9,
|
| 865 |
+
"learning_rate": 6.613038988201237e-06,
|
| 866 |
+
"loss": 2.7684,
|
| 867 |
+
"step": 710
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 0.9,
|
| 871 |
+
"learning_rate": 5.847913065563382e-06,
|
| 872 |
+
"loss": 2.5271,
|
| 873 |
+
"step": 715
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.91,
|
| 877 |
+
"learning_rate": 5.128482605653173e-06,
|
| 878 |
+
"loss": 2.2342,
|
| 879 |
+
"step": 720
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.91,
|
| 883 |
+
"learning_rate": 4.455096774472567e-06,
|
| 884 |
+
"loss": 2.2851,
|
| 885 |
+
"step": 725
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.92,
|
| 889 |
+
"learning_rate": 3.828082390875487e-06,
|
| 890 |
+
"loss": 2.4365,
|
| 891 |
+
"step": 730
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.93,
|
| 895 |
+
"learning_rate": 3.247743767950795e-06,
|
| 896 |
+
"loss": 2.6543,
|
| 897 |
+
"step": 735
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.93,
|
| 901 |
+
"learning_rate": 2.714362565327866e-06,
|
| 902 |
+
"loss": 2.6314,
|
| 903 |
+
"step": 740
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.94,
|
| 907 |
+
"learning_rate": 2.2281976524769266e-06,
|
| 908 |
+
"loss": 2.1431,
|
| 909 |
+
"step": 745
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 0.95,
|
| 913 |
+
"learning_rate": 1.7894849830701443e-06,
|
| 914 |
+
"loss": 2.4283,
|
| 915 |
+
"step": 750
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.95,
|
| 919 |
+
"learning_rate": 1.398437480464676e-06,
|
| 920 |
+
"loss": 2.5455,
|
| 921 |
+
"step": 755
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.96,
|
| 925 |
+
"learning_rate": 1.055244934363131e-06,
|
| 926 |
+
"loss": 2.4203,
|
| 927 |
+
"step": 760
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.96,
|
| 931 |
+
"learning_rate": 7.600739087016862e-07,
|
| 932 |
+
"loss": 2.5425,
|
| 933 |
+
"step": 765
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.97,
|
| 937 |
+
"learning_rate": 5.130676608104845e-07,
|
| 938 |
+
"loss": 2.623,
|
| 939 |
+
"step": 770
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.98,
|
| 943 |
+
"learning_rate": 3.143460718855962e-07,
|
| 944 |
+
"loss": 2.5706,
|
| 945 |
+
"step": 775
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 0.98,
|
| 949 |
+
"learning_rate": 1.6400558880627082e-07,
|
| 950 |
+
"loss": 2.4692,
|
| 951 |
+
"step": 780
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 0.99,
|
| 955 |
+
"learning_rate": 6.21191773257368e-08,
|
| 956 |
+
"loss": 2.684,
|
| 957 |
+
"step": 785
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 1.0,
|
| 961 |
+
"learning_rate": 8.736286658228565e-09,
|
| 962 |
+
"loss": 2.3449,
|
| 963 |
+
"step": 790
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 1.0,
|
| 967 |
+
"eval_loss": 2.400331974029541,
|
| 968 |
+
"eval_runtime": 240.8241,
|
| 969 |
+
"eval_samples_per_second": 3.293,
|
| 970 |
+
"eval_steps_per_second": 3.293,
|
| 971 |
+
"step": 793
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 1.0,
|
| 975 |
+
"step": 793,
|
| 976 |
+
"total_flos": 5.686041454942618e+16,
|
| 977 |
+
"train_loss": 0.28998795253181214,
|
| 978 |
+
"train_runtime": 345.0365,
|
| 979 |
+
"train_samples_per_second": 2.298,
|
| 980 |
+
"train_steps_per_second": 2.298
|
| 981 |
+
}
|
| 982 |
+
],
|
| 983 |
+
"logging_steps": 5,
|
| 984 |
+
"max_steps": 793,
|
| 985 |
+
"num_input_tokens_seen": 0,
|
| 986 |
+
"num_train_epochs": 1,
|
| 987 |
+
"save_steps": 100,
|
| 988 |
+
"total_flos": 5.686041454942618e+16,
|
| 989 |
+
"train_batch_size": 1,
|
| 990 |
+
"trial_name": null,
|
| 991 |
+
"trial_params": null
|
| 992 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4728
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72a327e8bae144d9e9964d6521d481f48688a6203407522e8d479e192b2f4f7e
|
| 3 |
size 4728
|