Model save
Browse files- README.md +67 -0
- all_results.json +9 -0
- generation_config.json +6 -0
- runs/Sep11_06-41-53_COE-CS-sv003/events.out.tfevents.1726036938.COE-CS-sv003.915569.0 +2 -2
- train_results.json +9 -0
- trainer_state.json +1744 -0
README.md
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: mistralai/Mistral-7B-Instruct-v0.2
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- sft
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
datasets:
|
| 9 |
+
- generator
|
| 10 |
+
model-index:
|
| 11 |
+
- name: preference_p0.1_seed42_level2_syntaxmix
|
| 12 |
+
results: []
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
+
|
| 18 |
+
# preference_p0.1_seed42_level2_syntaxmix
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.3199
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 1e-05
|
| 42 |
+
- train_batch_size: 4
|
| 43 |
+
- eval_batch_size: 1
|
| 44 |
+
- seed: 42
|
| 45 |
+
- distributed_type: multi-GPU
|
| 46 |
+
- num_devices: 4
|
| 47 |
+
- gradient_accumulation_steps: 2
|
| 48 |
+
- total_train_batch_size: 32
|
| 49 |
+
- total_eval_batch_size: 4
|
| 50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
+
- lr_scheduler_type: cosine
|
| 52 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 53 |
+
- num_epochs: 1
|
| 54 |
+
|
| 55 |
+
### Training results
|
| 56 |
+
|
| 57 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 58 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 59 |
+
| 0.3623 | 1.0 | 1205 | 0.3199 |
|
| 60 |
+
|
| 61 |
+
|
| 62 |
+
### Framework versions
|
| 63 |
+
|
| 64 |
+
- Transformers 4.43.4
|
| 65 |
+
- Pytorch 2.3.1+cu121
|
| 66 |
+
- Datasets 2.19.1
|
| 67 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 252197795266560.0,
|
| 4 |
+
"train_loss": 0.5424416576678327,
|
| 5 |
+
"train_runtime": 23511.1257,
|
| 6 |
+
"train_samples": 98873,
|
| 7 |
+
"train_samples_per_second": 1.639,
|
| 8 |
+
"train_steps_per_second": 0.051
|
| 9 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.43.4"
|
| 6 |
+
}
|
runs/Sep11_06-41-53_COE-CS-sv003/events.out.tfevents.1726036938.COE-CS-sv003.915569.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e5dcbf0aa9db2887da515c72119cc9c4529cc299498d3e542b7a6bae64a687c
|
| 3 |
+
size 56831
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 252197795266560.0,
|
| 4 |
+
"train_loss": 0.5424416576678327,
|
| 5 |
+
"train_runtime": 23511.1257,
|
| 6 |
+
"train_samples": 98873,
|
| 7 |
+
"train_samples_per_second": 1.639,
|
| 8 |
+
"train_steps_per_second": 0.051
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1744 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1205,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0008298755186721991,
|
| 13 |
+
"grad_norm": 23.66355396613384,
|
| 14 |
+
"learning_rate": 8.264462809917357e-08,
|
| 15 |
+
"loss": 1.4427,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.004149377593360996,
|
| 20 |
+
"grad_norm": 23.666427649458576,
|
| 21 |
+
"learning_rate": 4.132231404958678e-07,
|
| 22 |
+
"loss": 1.4251,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.008298755186721992,
|
| 27 |
+
"grad_norm": 8.13472184690251,
|
| 28 |
+
"learning_rate": 8.264462809917356e-07,
|
| 29 |
+
"loss": 1.3136,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.012448132780082987,
|
| 34 |
+
"grad_norm": 10.227426110416495,
|
| 35 |
+
"learning_rate": 1.2396694214876035e-06,
|
| 36 |
+
"loss": 1.1782,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.016597510373443983,
|
| 41 |
+
"grad_norm": 2.9983433935088764,
|
| 42 |
+
"learning_rate": 1.6528925619834712e-06,
|
| 43 |
+
"loss": 1.0153,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.02074688796680498,
|
| 48 |
+
"grad_norm": 2.7990610124740405,
|
| 49 |
+
"learning_rate": 2.066115702479339e-06,
|
| 50 |
+
"loss": 0.9803,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.024896265560165973,
|
| 55 |
+
"grad_norm": 2.4757391776519464,
|
| 56 |
+
"learning_rate": 2.479338842975207e-06,
|
| 57 |
+
"loss": 0.9414,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.029045643153526972,
|
| 62 |
+
"grad_norm": 2.369524052256136,
|
| 63 |
+
"learning_rate": 2.8925619834710743e-06,
|
| 64 |
+
"loss": 0.9136,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.03319502074688797,
|
| 69 |
+
"grad_norm": 2.2685836127457777,
|
| 70 |
+
"learning_rate": 3.3057851239669424e-06,
|
| 71 |
+
"loss": 0.9046,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.03734439834024896,
|
| 76 |
+
"grad_norm": 2.280617723317066,
|
| 77 |
+
"learning_rate": 3.71900826446281e-06,
|
| 78 |
+
"loss": 0.8837,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.04149377593360996,
|
| 83 |
+
"grad_norm": 2.5321104543831545,
|
| 84 |
+
"learning_rate": 4.132231404958678e-06,
|
| 85 |
+
"loss": 0.8832,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.04564315352697095,
|
| 90 |
+
"grad_norm": 2.431703080743525,
|
| 91 |
+
"learning_rate": 4.5454545454545455e-06,
|
| 92 |
+
"loss": 0.8805,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.04979253112033195,
|
| 97 |
+
"grad_norm": 2.3196841399300054,
|
| 98 |
+
"learning_rate": 4.958677685950414e-06,
|
| 99 |
+
"loss": 0.8701,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.05394190871369295,
|
| 104 |
+
"grad_norm": 2.3618202415732195,
|
| 105 |
+
"learning_rate": 5.371900826446281e-06,
|
| 106 |
+
"loss": 0.8579,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.058091286307053944,
|
| 111 |
+
"grad_norm": 2.3717003204055405,
|
| 112 |
+
"learning_rate": 5.785123966942149e-06,
|
| 113 |
+
"loss": 0.8505,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.06224066390041494,
|
| 118 |
+
"grad_norm": 2.524204535368378,
|
| 119 |
+
"learning_rate": 6.198347107438017e-06,
|
| 120 |
+
"loss": 0.8402,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.06639004149377593,
|
| 125 |
+
"grad_norm": 2.4015926775695804,
|
| 126 |
+
"learning_rate": 6.611570247933885e-06,
|
| 127 |
+
"loss": 0.8402,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.07053941908713693,
|
| 132 |
+
"grad_norm": 2.388794422413219,
|
| 133 |
+
"learning_rate": 7.0247933884297525e-06,
|
| 134 |
+
"loss": 0.8355,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.07468879668049792,
|
| 139 |
+
"grad_norm": 2.4148605854925704,
|
| 140 |
+
"learning_rate": 7.43801652892562e-06,
|
| 141 |
+
"loss": 0.8256,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.07883817427385892,
|
| 146 |
+
"grad_norm": 2.4479657967512414,
|
| 147 |
+
"learning_rate": 7.851239669421489e-06,
|
| 148 |
+
"loss": 0.8126,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.08298755186721991,
|
| 153 |
+
"grad_norm": 2.4560082465511863,
|
| 154 |
+
"learning_rate": 8.264462809917356e-06,
|
| 155 |
+
"loss": 0.8226,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.08713692946058091,
|
| 160 |
+
"grad_norm": 2.3573417388565976,
|
| 161 |
+
"learning_rate": 8.677685950413224e-06,
|
| 162 |
+
"loss": 0.8175,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.0912863070539419,
|
| 167 |
+
"grad_norm": 2.468662387879913,
|
| 168 |
+
"learning_rate": 9.090909090909091e-06,
|
| 169 |
+
"loss": 0.8158,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.0954356846473029,
|
| 174 |
+
"grad_norm": 2.5046573038316837,
|
| 175 |
+
"learning_rate": 9.50413223140496e-06,
|
| 176 |
+
"loss": 0.8116,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.0995850622406639,
|
| 181 |
+
"grad_norm": 2.539643690091556,
|
| 182 |
+
"learning_rate": 9.917355371900828e-06,
|
| 183 |
+
"loss": 0.8005,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.1037344398340249,
|
| 188 |
+
"grad_norm": 2.911760533276573,
|
| 189 |
+
"learning_rate": 9.999664033241933e-06,
|
| 190 |
+
"loss": 0.7939,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.1078838174273859,
|
| 195 |
+
"grad_norm": 2.582851539753205,
|
| 196 |
+
"learning_rate": 9.9982992456671e-06,
|
| 197 |
+
"loss": 0.8055,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.11203319502074689,
|
| 202 |
+
"grad_norm": 2.4256847202133356,
|
| 203 |
+
"learning_rate": 9.99588492570789e-06,
|
| 204 |
+
"loss": 0.7868,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.11618257261410789,
|
| 209 |
+
"grad_norm": 2.363704333423417,
|
| 210 |
+
"learning_rate": 9.992421580318146e-06,
|
| 211 |
+
"loss": 0.7931,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.12033195020746888,
|
| 216 |
+
"grad_norm": 2.5814735842129646,
|
| 217 |
+
"learning_rate": 9.98790993672386e-06,
|
| 218 |
+
"loss": 0.792,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.12448132780082988,
|
| 223 |
+
"grad_norm": 2.3697758205953496,
|
| 224 |
+
"learning_rate": 9.982350942270482e-06,
|
| 225 |
+
"loss": 0.7803,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.12863070539419086,
|
| 230 |
+
"grad_norm": 2.715505233595166,
|
| 231 |
+
"learning_rate": 9.975745764224003e-06,
|
| 232 |
+
"loss": 0.7801,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.13278008298755187,
|
| 237 |
+
"grad_norm": 2.408139672943199,
|
| 238 |
+
"learning_rate": 9.968095789525844e-06,
|
| 239 |
+
"loss": 0.7752,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.13692946058091288,
|
| 244 |
+
"grad_norm": 2.6010481805450576,
|
| 245 |
+
"learning_rate": 9.959402624501636e-06,
|
| 246 |
+
"loss": 0.7643,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.14107883817427386,
|
| 251 |
+
"grad_norm": 2.296000230707304,
|
| 252 |
+
"learning_rate": 9.949668094523923e-06,
|
| 253 |
+
"loss": 0.7693,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.14522821576763487,
|
| 258 |
+
"grad_norm": 2.3353134794630943,
|
| 259 |
+
"learning_rate": 9.938894243628876e-06,
|
| 260 |
+
"loss": 0.76,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.14937759336099585,
|
| 265 |
+
"grad_norm": 2.4548337376467226,
|
| 266 |
+
"learning_rate": 9.927083334087095e-06,
|
| 267 |
+
"loss": 0.7553,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.15352697095435686,
|
| 272 |
+
"grad_norm": 2.4799784321191325,
|
| 273 |
+
"learning_rate": 9.914237845928574e-06,
|
| 274 |
+
"loss": 0.7466,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.15767634854771784,
|
| 279 |
+
"grad_norm": 2.3334152911020754,
|
| 280 |
+
"learning_rate": 9.900360476421953e-06,
|
| 281 |
+
"loss": 0.7469,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.16182572614107885,
|
| 286 |
+
"grad_norm": 2.8513960305920065,
|
| 287 |
+
"learning_rate": 9.885454139508156e-06,
|
| 288 |
+
"loss": 0.7478,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.16597510373443983,
|
| 293 |
+
"grad_norm": 2.3540844011309288,
|
| 294 |
+
"learning_rate": 9.869521965188516e-06,
|
| 295 |
+
"loss": 0.7419,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.17012448132780084,
|
| 300 |
+
"grad_norm": 2.4949727451490458,
|
| 301 |
+
"learning_rate": 9.852567298867557e-06,
|
| 302 |
+
"loss": 0.7443,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.17427385892116182,
|
| 307 |
+
"grad_norm": 2.4359748708393196,
|
| 308 |
+
"learning_rate": 9.83459370065053e-06,
|
| 309 |
+
"loss": 0.715,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.17842323651452283,
|
| 314 |
+
"grad_norm": 2.194244707564717,
|
| 315 |
+
"learning_rate": 9.815604944595856e-06,
|
| 316 |
+
"loss": 0.732,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.1825726141078838,
|
| 321 |
+
"grad_norm": 2.3813196851718668,
|
| 322 |
+
"learning_rate": 9.79560501792268e-06,
|
| 323 |
+
"loss": 0.7133,
|
| 324 |
+
"step": 220
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.18672199170124482,
|
| 328 |
+
"grad_norm": 2.323752421674217,
|
| 329 |
+
"learning_rate": 9.774598120173625e-06,
|
| 330 |
+
"loss": 0.7241,
|
| 331 |
+
"step": 225
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.1908713692946058,
|
| 335 |
+
"grad_norm": 2.3526306711964797,
|
| 336 |
+
"learning_rate": 9.752588662332986e-06,
|
| 337 |
+
"loss": 0.7043,
|
| 338 |
+
"step": 230
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.1950207468879668,
|
| 342 |
+
"grad_norm": 2.2642342063534096,
|
| 343 |
+
"learning_rate": 9.729581265900524e-06,
|
| 344 |
+
"loss": 0.7103,
|
| 345 |
+
"step": 235
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.1991701244813278,
|
| 349 |
+
"grad_norm": 2.516182372123314,
|
| 350 |
+
"learning_rate": 9.70558076192105e-06,
|
| 351 |
+
"loss": 0.7267,
|
| 352 |
+
"step": 240
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.2033195020746888,
|
| 356 |
+
"grad_norm": 2.370762773316826,
|
| 357 |
+
"learning_rate": 9.680592189970015e-06,
|
| 358 |
+
"loss": 0.7123,
|
| 359 |
+
"step": 245
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.2074688796680498,
|
| 363 |
+
"grad_norm": 2.207456321652819,
|
| 364 |
+
"learning_rate": 9.654620797095307e-06,
|
| 365 |
+
"loss": 0.6962,
|
| 366 |
+
"step": 250
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.21161825726141079,
|
| 370 |
+
"grad_norm": 2.2364777487963643,
|
| 371 |
+
"learning_rate": 9.627672036715484e-06,
|
| 372 |
+
"loss": 0.6898,
|
| 373 |
+
"step": 255
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.2157676348547718,
|
| 377 |
+
"grad_norm": 2.3651072953613754,
|
| 378 |
+
"learning_rate": 9.599751567474695e-06,
|
| 379 |
+
"loss": 0.6759,
|
| 380 |
+
"step": 260
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.21991701244813278,
|
| 384 |
+
"grad_norm": 2.450633099288444,
|
| 385 |
+
"learning_rate": 9.570865252054462e-06,
|
| 386 |
+
"loss": 0.7034,
|
| 387 |
+
"step": 265
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.22406639004149378,
|
| 391 |
+
"grad_norm": 2.3473986013625963,
|
| 392 |
+
"learning_rate": 9.541019155942663e-06,
|
| 393 |
+
"loss": 0.6822,
|
| 394 |
+
"step": 270
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.22821576763485477,
|
| 398 |
+
"grad_norm": 2.548163258213224,
|
| 399 |
+
"learning_rate": 9.51021954615992e-06,
|
| 400 |
+
"loss": 0.6789,
|
| 401 |
+
"step": 275
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.23236514522821577,
|
| 405 |
+
"grad_norm": 2.5379693961647303,
|
| 406 |
+
"learning_rate": 9.478472889943644e-06,
|
| 407 |
+
"loss": 0.6625,
|
| 408 |
+
"step": 280
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.23651452282157676,
|
| 412 |
+
"grad_norm": 2.327924483215091,
|
| 413 |
+
"learning_rate": 9.445785853390074e-06,
|
| 414 |
+
"loss": 0.6721,
|
| 415 |
+
"step": 285
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.24066390041493776,
|
| 419 |
+
"grad_norm": 2.262881099755119,
|
| 420 |
+
"learning_rate": 9.412165300054536e-06,
|
| 421 |
+
"loss": 0.6566,
|
| 422 |
+
"step": 290
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.24481327800829875,
|
| 426 |
+
"grad_norm": 2.265488203072667,
|
| 427 |
+
"learning_rate": 9.377618289510251e-06,
|
| 428 |
+
"loss": 0.6608,
|
| 429 |
+
"step": 295
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.24896265560165975,
|
| 433 |
+
"grad_norm": 2.5878567494362175,
|
| 434 |
+
"learning_rate": 9.34215207586598e-06,
|
| 435 |
+
"loss": 0.6499,
|
| 436 |
+
"step": 300
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.25311203319502074,
|
| 440 |
+
"grad_norm": 2.3658001383539733,
|
| 441 |
+
"learning_rate": 9.305774106242825e-06,
|
| 442 |
+
"loss": 0.6484,
|
| 443 |
+
"step": 305
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.2572614107883817,
|
| 447 |
+
"grad_norm": 2.243961082145765,
|
| 448 |
+
"learning_rate": 9.268492019210486e-06,
|
| 449 |
+
"loss": 0.6564,
|
| 450 |
+
"step": 310
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.26141078838174275,
|
| 454 |
+
"grad_norm": 2.380897449863462,
|
| 455 |
+
"learning_rate": 9.23031364318335e-06,
|
| 456 |
+
"loss": 0.6348,
|
| 457 |
+
"step": 315
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.26556016597510373,
|
| 461 |
+
"grad_norm": 2.5103759793912817,
|
| 462 |
+
"learning_rate": 9.191246994776676e-06,
|
| 463 |
+
"loss": 0.6363,
|
| 464 |
+
"step": 320
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.2697095435684647,
|
| 468 |
+
"grad_norm": 2.249912565836941,
|
| 469 |
+
"learning_rate": 9.1513002771233e-06,
|
| 470 |
+
"loss": 0.6419,
|
| 471 |
+
"step": 325
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.27385892116182575,
|
| 475 |
+
"grad_norm": 2.163581249856587,
|
| 476 |
+
"learning_rate": 9.110481878151147e-06,
|
| 477 |
+
"loss": 0.6301,
|
| 478 |
+
"step": 330
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.27800829875518673,
|
| 482 |
+
"grad_norm": 2.190865179892157,
|
| 483 |
+
"learning_rate": 9.068800368821957e-06,
|
| 484 |
+
"loss": 0.6325,
|
| 485 |
+
"step": 335
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.2821576763485477,
|
| 489 |
+
"grad_norm": 2.265573915661597,
|
| 490 |
+
"learning_rate": 9.026264501331571e-06,
|
| 491 |
+
"loss": 0.6322,
|
| 492 |
+
"step": 340
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.2863070539419087,
|
| 496 |
+
"grad_norm": 2.2910874776204286,
|
| 497 |
+
"learning_rate": 8.982883207272164e-06,
|
| 498 |
+
"loss": 0.623,
|
| 499 |
+
"step": 345
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.29045643153526973,
|
| 503 |
+
"grad_norm": 2.384654294302928,
|
| 504 |
+
"learning_rate": 8.938665595756807e-06,
|
| 505 |
+
"loss": 0.6246,
|
| 506 |
+
"step": 350
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.2946058091286307,
|
| 510 |
+
"grad_norm": 2.4124577641889537,
|
| 511 |
+
"learning_rate": 8.893620951506755e-06,
|
| 512 |
+
"loss": 0.6136,
|
| 513 |
+
"step": 355
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.2987551867219917,
|
| 517 |
+
"grad_norm": 2.6221754387144562,
|
| 518 |
+
"learning_rate": 8.84775873290186e-06,
|
| 519 |
+
"loss": 0.6187,
|
| 520 |
+
"step": 360
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.3029045643153527,
|
| 524 |
+
"grad_norm": 2.2955995327624277,
|
| 525 |
+
"learning_rate": 8.801088569994523e-06,
|
| 526 |
+
"loss": 0.6048,
|
| 527 |
+
"step": 365
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.3070539419087137,
|
| 531 |
+
"grad_norm": 2.138665428419567,
|
| 532 |
+
"learning_rate": 8.75362026248759e-06,
|
| 533 |
+
"loss": 0.6031,
|
| 534 |
+
"step": 370
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.3112033195020747,
|
| 538 |
+
"grad_norm": 2.1328698825170593,
|
| 539 |
+
"learning_rate": 8.705363777676641e-06,
|
| 540 |
+
"loss": 0.6063,
|
| 541 |
+
"step": 375
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.3153526970954357,
|
| 545 |
+
"grad_norm": 2.1479776795024783,
|
| 546 |
+
"learning_rate": 8.656329248357065e-06,
|
| 547 |
+
"loss": 0.5942,
|
| 548 |
+
"step": 380
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.31950207468879666,
|
| 552 |
+
"grad_norm": 2.134654863907731,
|
| 553 |
+
"learning_rate": 8.60652697069641e-06,
|
| 554 |
+
"loss": 0.5904,
|
| 555 |
+
"step": 385
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.3236514522821577,
|
| 559 |
+
"grad_norm": 2.374467014031146,
|
| 560 |
+
"learning_rate": 8.555967402072402e-06,
|
| 561 |
+
"loss": 0.5995,
|
| 562 |
+
"step": 390
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.3278008298755187,
|
| 566 |
+
"grad_norm": 2.40926239385975,
|
| 567 |
+
"learning_rate": 8.50466115887714e-06,
|
| 568 |
+
"loss": 0.5927,
|
| 569 |
+
"step": 395
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.33195020746887965,
|
| 573 |
+
"grad_norm": 2.3502075362637767,
|
| 574 |
+
"learning_rate": 8.452619014287882e-06,
|
| 575 |
+
"loss": 0.5847,
|
| 576 |
+
"step": 400
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.3360995850622407,
|
| 580 |
+
"grad_norm": 2.4126500802319097,
|
| 581 |
+
"learning_rate": 8.399851896004914e-06,
|
| 582 |
+
"loss": 0.5862,
|
| 583 |
+
"step": 405
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.34024896265560167,
|
| 587 |
+
"grad_norm": 2.2950749664456227,
|
| 588 |
+
"learning_rate": 8.346370883956975e-06,
|
| 589 |
+
"loss": 0.5855,
|
| 590 |
+
"step": 410
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.34439834024896265,
|
| 594 |
+
"grad_norm": 2.161036752273593,
|
| 595 |
+
"learning_rate": 8.292187207974723e-06,
|
| 596 |
+
"loss": 0.5746,
|
| 597 |
+
"step": 415
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.34854771784232363,
|
| 601 |
+
"grad_norm": 2.4188236778063352,
|
| 602 |
+
"learning_rate": 8.237312245432709e-06,
|
| 603 |
+
"loss": 0.5879,
|
| 604 |
+
"step": 420
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.35269709543568467,
|
| 608 |
+
"grad_norm": 2.2090916593497636,
|
| 609 |
+
"learning_rate": 8.181757518860387e-06,
|
| 610 |
+
"loss": 0.5773,
|
| 611 |
+
"step": 425
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.35684647302904565,
|
| 615 |
+
"grad_norm": 2.3146906711334734,
|
| 616 |
+
"learning_rate": 8.125534693522639e-06,
|
| 617 |
+
"loss": 0.5735,
|
| 618 |
+
"step": 430
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.36099585062240663,
|
| 622 |
+
"grad_norm": 2.239996996129289,
|
| 623 |
+
"learning_rate": 8.068655574970316e-06,
|
| 624 |
+
"loss": 0.554,
|
| 625 |
+
"step": 435
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.3651452282157676,
|
| 629 |
+
"grad_norm": 2.363097757813145,
|
| 630 |
+
"learning_rate": 8.011132106561347e-06,
|
| 631 |
+
"loss": 0.5545,
|
| 632 |
+
"step": 440
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.36929460580912865,
|
| 636 |
+
"grad_norm": 2.27029308132692,
|
| 637 |
+
"learning_rate": 7.952976366952888e-06,
|
| 638 |
+
"loss": 0.5683,
|
| 639 |
+
"step": 445
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.37344398340248963,
|
| 643 |
+
"grad_norm": 2.1074572809534375,
|
| 644 |
+
"learning_rate": 7.894200567565075e-06,
|
| 645 |
+
"loss": 0.5648,
|
| 646 |
+
"step": 450
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.3775933609958506,
|
| 650 |
+
"grad_norm": 2.273342227929578,
|
| 651 |
+
"learning_rate": 7.834817050016899e-06,
|
| 652 |
+
"loss": 0.5679,
|
| 653 |
+
"step": 455
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.3817427385892116,
|
| 657 |
+
"grad_norm": 2.2797216207901383,
|
| 658 |
+
"learning_rate": 7.774838283534724e-06,
|
| 659 |
+
"loss": 0.5559,
|
| 660 |
+
"step": 460
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.38589211618257263,
|
| 664 |
+
"grad_norm": 2.104532263164514,
|
| 665 |
+
"learning_rate": 7.714276862334051e-06,
|
| 666 |
+
"loss": 0.54,
|
| 667 |
+
"step": 465
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.3900414937759336,
|
| 671 |
+
"grad_norm": 2.1184787555923212,
|
| 672 |
+
"learning_rate": 7.653145502974982e-06,
|
| 673 |
+
"loss": 0.555,
|
| 674 |
+
"step": 470
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.3941908713692946,
|
| 678 |
+
"grad_norm": 2.1723348338228328,
|
| 679 |
+
"learning_rate": 7.591457041692045e-06,
|
| 680 |
+
"loss": 0.546,
|
| 681 |
+
"step": 475
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.3983402489626556,
|
| 685 |
+
"grad_norm": 2.1840500746464295,
|
| 686 |
+
"learning_rate": 7.529224431698858e-06,
|
| 687 |
+
"loss": 0.547,
|
| 688 |
+
"step": 480
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.4024896265560166,
|
| 692 |
+
"grad_norm": 2.318164164245411,
|
| 693 |
+
"learning_rate": 7.466460740468246e-06,
|
| 694 |
+
"loss": 0.542,
|
| 695 |
+
"step": 485
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.4066390041493776,
|
| 699 |
+
"grad_norm": 2.3138151208917126,
|
| 700 |
+
"learning_rate": 7.40317914698835e-06,
|
| 701 |
+
"loss": 0.5445,
|
| 702 |
+
"step": 490
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.4107883817427386,
|
| 706 |
+
"grad_norm": 2.1331277286671186,
|
| 707 |
+
"learning_rate": 7.339392938995349e-06,
|
| 708 |
+
"loss": 0.5319,
|
| 709 |
+
"step": 495
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.4149377593360996,
|
| 713 |
+
"grad_norm": 2.2351009447186803,
|
| 714 |
+
"learning_rate": 7.2751155101833095e-06,
|
| 715 |
+
"loss": 0.5273,
|
| 716 |
+
"step": 500
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.4190871369294606,
|
| 720 |
+
"grad_norm": 2.135991611803002,
|
| 721 |
+
"learning_rate": 7.210360357391818e-06,
|
| 722 |
+
"loss": 0.5376,
|
| 723 |
+
"step": 505
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.42323651452282157,
|
| 727 |
+
"grad_norm": 2.5539346756615906,
|
| 728 |
+
"learning_rate": 7.145141077771938e-06,
|
| 729 |
+
"loss": 0.5273,
|
| 730 |
+
"step": 510
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.42738589211618255,
|
| 734 |
+
"grad_norm": 2.047264916869935,
|
| 735 |
+
"learning_rate": 7.0794713659311145e-06,
|
| 736 |
+
"loss": 0.5277,
|
| 737 |
+
"step": 515
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.4315352697095436,
|
| 741 |
+
"grad_norm": 2.2988994571475994,
|
| 742 |
+
"learning_rate": 7.0133650110576e-06,
|
| 743 |
+
"loss": 0.5124,
|
| 744 |
+
"step": 520
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.43568464730290457,
|
| 748 |
+
"grad_norm": 2.185194372325859,
|
| 749 |
+
"learning_rate": 6.946835894025037e-06,
|
| 750 |
+
"loss": 0.526,
|
| 751 |
+
"step": 525
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.43983402489626555,
|
| 755 |
+
"grad_norm": 2.1924305119120095,
|
| 756 |
+
"learning_rate": 6.879897984477778e-06,
|
| 757 |
+
"loss": 0.5297,
|
| 758 |
+
"step": 530
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.44398340248962653,
|
| 762 |
+
"grad_norm": 2.2531761041789458,
|
| 763 |
+
"learning_rate": 6.8125653378975675e-06,
|
| 764 |
+
"loss": 0.5135,
|
| 765 |
+
"step": 535
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.44813278008298757,
|
| 769 |
+
"grad_norm": 2.1140660080628217,
|
| 770 |
+
"learning_rate": 6.7448520926522084e-06,
|
| 771 |
+
"loss": 0.5209,
|
| 772 |
+
"step": 540
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.45228215767634855,
|
| 776 |
+
"grad_norm": 2.2942813216608995,
|
| 777 |
+
"learning_rate": 6.676772467026809e-06,
|
| 778 |
+
"loss": 0.5153,
|
| 779 |
+
"step": 545
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.45643153526970953,
|
| 783 |
+
"grad_norm": 2.1380478037125026,
|
| 784 |
+
"learning_rate": 6.608340756238261e-06,
|
| 785 |
+
"loss": 0.5205,
|
| 786 |
+
"step": 550
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.4605809128630705,
|
| 790 |
+
"grad_norm": 2.2305987813784665,
|
| 791 |
+
"learning_rate": 6.539571329433562e-06,
|
| 792 |
+
"loss": 0.5042,
|
| 793 |
+
"step": 555
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.46473029045643155,
|
| 797 |
+
"grad_norm": 2.0259829999672583,
|
| 798 |
+
"learning_rate": 6.470478626672607e-06,
|
| 799 |
+
"loss": 0.5063,
|
| 800 |
+
"step": 560
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.46887966804979253,
|
| 804 |
+
"grad_norm": 2.1482954433368966,
|
| 805 |
+
"learning_rate": 6.401077155896098e-06,
|
| 806 |
+
"loss": 0.5037,
|
| 807 |
+
"step": 565
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.4730290456431535,
|
| 811 |
+
"grad_norm": 2.0722196480572967,
|
| 812 |
+
"learning_rate": 6.3313814898792e-06,
|
| 813 |
+
"loss": 0.5119,
|
| 814 |
+
"step": 570
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.47717842323651455,
|
| 818 |
+
"grad_norm": 2.0766008318122116,
|
| 819 |
+
"learning_rate": 6.261406263171574e-06,
|
| 820 |
+
"loss": 0.4936,
|
| 821 |
+
"step": 575
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.48132780082987553,
|
| 825 |
+
"grad_norm": 2.170054524337145,
|
| 826 |
+
"learning_rate": 6.191166169024449e-06,
|
| 827 |
+
"loss": 0.5115,
|
| 828 |
+
"step": 580
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.4854771784232365,
|
| 832 |
+
"grad_norm": 2.165392386687399,
|
| 833 |
+
"learning_rate": 6.120675956305363e-06,
|
| 834 |
+
"loss": 0.506,
|
| 835 |
+
"step": 585
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.4896265560165975,
|
| 839 |
+
"grad_norm": 2.1917064615978865,
|
| 840 |
+
"learning_rate": 6.049950426401224e-06,
|
| 841 |
+
"loss": 0.4922,
|
| 842 |
+
"step": 590
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.49377593360995853,
|
| 846 |
+
"grad_norm": 2.1320846413675754,
|
| 847 |
+
"learning_rate": 5.979004430110356e-06,
|
| 848 |
+
"loss": 0.4962,
|
| 849 |
+
"step": 595
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.4979253112033195,
|
| 853 |
+
"grad_norm": 2.2214982569308943,
|
| 854 |
+
"learning_rate": 5.907852864524141e-06,
|
| 855 |
+
"loss": 0.4798,
|
| 856 |
+
"step": 600
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.5020746887966805,
|
| 860 |
+
"grad_norm": 2.1478446403131017,
|
| 861 |
+
"learning_rate": 5.836510669898984e-06,
|
| 862 |
+
"loss": 0.488,
|
| 863 |
+
"step": 605
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.5062240663900415,
|
| 867 |
+
"grad_norm": 2.0711442564532683,
|
| 868 |
+
"learning_rate": 5.7649928265191625e-06,
|
| 869 |
+
"loss": 0.4809,
|
| 870 |
+
"step": 610
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.5103734439834025,
|
| 874 |
+
"grad_norm": 2.0362299353680875,
|
| 875 |
+
"learning_rate": 5.693314351551317e-06,
|
| 876 |
+
"loss": 0.4779,
|
| 877 |
+
"step": 615
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.5145228215767634,
|
| 881 |
+
"grad_norm": 2.223869208837942,
|
| 882 |
+
"learning_rate": 5.621490295891172e-06,
|
| 883 |
+
"loss": 0.4816,
|
| 884 |
+
"step": 620
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.5186721991701245,
|
| 888 |
+
"grad_norm": 2.184093648016579,
|
| 889 |
+
"learning_rate": 5.5495357410031805e-06,
|
| 890 |
+
"loss": 0.4767,
|
| 891 |
+
"step": 625
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.5228215767634855,
|
| 895 |
+
"grad_norm": 2.0615628269463455,
|
| 896 |
+
"learning_rate": 5.477465795753744e-06,
|
| 897 |
+
"loss": 0.4721,
|
| 898 |
+
"step": 630
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.5269709543568465,
|
| 902 |
+
"grad_norm": 2.139010346072537,
|
| 903 |
+
"learning_rate": 5.405295593238701e-06,
|
| 904 |
+
"loss": 0.4695,
|
| 905 |
+
"step": 635
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.5311203319502075,
|
| 909 |
+
"grad_norm": 2.123946607015628,
|
| 910 |
+
"learning_rate": 5.333040287605687e-06,
|
| 911 |
+
"loss": 0.4723,
|
| 912 |
+
"step": 640
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.5352697095435685,
|
| 916 |
+
"grad_norm": 2.3651276982269964,
|
| 917 |
+
"learning_rate": 5.260715050872119e-06,
|
| 918 |
+
"loss": 0.4624,
|
| 919 |
+
"step": 645
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.5394190871369294,
|
| 923 |
+
"grad_norm": 2.287295610466921,
|
| 924 |
+
"learning_rate": 5.1883350697394e-06,
|
| 925 |
+
"loss": 0.4644,
|
| 926 |
+
"step": 650
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.5435684647302904,
|
| 930 |
+
"grad_norm": 2.105320559946653,
|
| 931 |
+
"learning_rate": 5.115915542404045e-06,
|
| 932 |
+
"loss": 0.4584,
|
| 933 |
+
"step": 655
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.5477178423236515,
|
| 937 |
+
"grad_norm": 2.170432310241974,
|
| 938 |
+
"learning_rate": 5.0434716753663984e-06,
|
| 939 |
+
"loss": 0.4612,
|
| 940 |
+
"step": 660
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.5518672199170125,
|
| 944 |
+
"grad_norm": 2.194690777716423,
|
| 945 |
+
"learning_rate": 4.971018680237602e-06,
|
| 946 |
+
"loss": 0.4607,
|
| 947 |
+
"step": 665
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.5560165975103735,
|
| 951 |
+
"grad_norm": 1.9776501173869443,
|
| 952 |
+
"learning_rate": 4.8985717705455e-06,
|
| 953 |
+
"loss": 0.4611,
|
| 954 |
+
"step": 670
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.5601659751037344,
|
| 958 |
+
"grad_norm": 2.108677954477835,
|
| 959 |
+
"learning_rate": 4.826146158540125e-06,
|
| 960 |
+
"loss": 0.464,
|
| 961 |
+
"step": 675
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.5643153526970954,
|
| 965 |
+
"grad_norm": 2.2306541731963265,
|
| 966 |
+
"learning_rate": 4.753757051999468e-06,
|
| 967 |
+
"loss": 0.4575,
|
| 968 |
+
"step": 680
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.5684647302904564,
|
| 972 |
+
"grad_norm": 2.177699396676135,
|
| 973 |
+
"learning_rate": 4.681419651036177e-06,
|
| 974 |
+
"loss": 0.4515,
|
| 975 |
+
"step": 685
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.5726141078838174,
|
| 979 |
+
"grad_norm": 2.1123134999189603,
|
| 980 |
+
"learning_rate": 4.609149144905874e-06,
|
| 981 |
+
"loss": 0.4609,
|
| 982 |
+
"step": 690
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.5767634854771784,
|
| 986 |
+
"grad_norm": 2.2267780701787343,
|
| 987 |
+
"learning_rate": 4.536960708817743e-06,
|
| 988 |
+
"loss": 0.4517,
|
| 989 |
+
"step": 695
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.5809128630705395,
|
| 993 |
+
"grad_norm": 2.0878112877178725,
|
| 994 |
+
"learning_rate": 4.464869500748075e-06,
|
| 995 |
+
"loss": 0.4532,
|
| 996 |
+
"step": 700
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.5850622406639004,
|
| 1000 |
+
"grad_norm": 2.064093943237562,
|
| 1001 |
+
"learning_rate": 4.392890658257421e-06,
|
| 1002 |
+
"loss": 0.4545,
|
| 1003 |
+
"step": 705
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.5892116182572614,
|
| 1007 |
+
"grad_norm": 2.091722197853374,
|
| 1008 |
+
"learning_rate": 4.321039295312048e-06,
|
| 1009 |
+
"loss": 0.4346,
|
| 1010 |
+
"step": 710
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.5933609958506224,
|
| 1014 |
+
"grad_norm": 1.9233248459765655,
|
| 1015 |
+
"learning_rate": 4.249330499110334e-06,
|
| 1016 |
+
"loss": 0.436,
|
| 1017 |
+
"step": 715
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.5975103734439834,
|
| 1021 |
+
"grad_norm": 1.9972967400785588,
|
| 1022 |
+
"learning_rate": 4.177779326914793e-06,
|
| 1023 |
+
"loss": 0.435,
|
| 1024 |
+
"step": 720
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.6016597510373444,
|
| 1028 |
+
"grad_norm": 2.0247163429595743,
|
| 1029 |
+
"learning_rate": 4.106400802890377e-06,
|
| 1030 |
+
"loss": 0.438,
|
| 1031 |
+
"step": 725
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.6058091286307054,
|
| 1035 |
+
"grad_norm": 2.082262528377969,
|
| 1036 |
+
"learning_rate": 4.03520991494974e-06,
|
| 1037 |
+
"loss": 0.4419,
|
| 1038 |
+
"step": 730
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.6099585062240664,
|
| 1042 |
+
"grad_norm": 2.1097886512141386,
|
| 1043 |
+
"learning_rate": 3.964221611606108e-06,
|
| 1044 |
+
"loss": 0.4355,
|
| 1045 |
+
"step": 735
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.6141078838174274,
|
| 1049 |
+
"grad_norm": 2.055338754378088,
|
| 1050 |
+
"learning_rate": 3.893450798834412e-06,
|
| 1051 |
+
"loss": 0.4365,
|
| 1052 |
+
"step": 740
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.6182572614107884,
|
| 1056 |
+
"grad_norm": 2.0758265457246154,
|
| 1057 |
+
"learning_rate": 3.822912336941375e-06,
|
| 1058 |
+
"loss": 0.4316,
|
| 1059 |
+
"step": 745
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.6224066390041494,
|
| 1063 |
+
"grad_norm": 2.0060803377407788,
|
| 1064 |
+
"learning_rate": 3.7526210374451665e-06,
|
| 1065 |
+
"loss": 0.4336,
|
| 1066 |
+
"step": 750
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.6265560165975104,
|
| 1070 |
+
"grad_norm": 2.1438017129720324,
|
| 1071 |
+
"learning_rate": 3.6825916599653177e-06,
|
| 1072 |
+
"loss": 0.432,
|
| 1073 |
+
"step": 755
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.6307053941908713,
|
| 1077 |
+
"grad_norm": 2.066973580119617,
|
| 1078 |
+
"learning_rate": 3.6128389091235207e-06,
|
| 1079 |
+
"loss": 0.439,
|
| 1080 |
+
"step": 760
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.6348547717842323,
|
| 1084 |
+
"grad_norm": 2.0587913853717947,
|
| 1085 |
+
"learning_rate": 3.543377431455991e-06,
|
| 1086 |
+
"loss": 0.4278,
|
| 1087 |
+
"step": 765
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.6390041493775933,
|
| 1091 |
+
"grad_norm": 2.0295102232187894,
|
| 1092 |
+
"learning_rate": 3.4742218123380085e-06,
|
| 1093 |
+
"loss": 0.4141,
|
| 1094 |
+
"step": 770
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.6431535269709544,
|
| 1098 |
+
"grad_norm": 2.1211936908053803,
|
| 1099 |
+
"learning_rate": 3.4053865729213267e-06,
|
| 1100 |
+
"loss": 0.4269,
|
| 1101 |
+
"step": 775
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.6473029045643154,
|
| 1105 |
+
"grad_norm": 2.073558611545013,
|
| 1106 |
+
"learning_rate": 3.3368861670850316e-06,
|
| 1107 |
+
"loss": 0.4242,
|
| 1108 |
+
"step": 780
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.6514522821576764,
|
| 1112 |
+
"grad_norm": 2.1028200278850906,
|
| 1113 |
+
"learning_rate": 3.268734978400564e-06,
|
| 1114 |
+
"loss": 0.4255,
|
| 1115 |
+
"step": 785
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.6556016597510373,
|
| 1119 |
+
"grad_norm": 2.074338043700759,
|
| 1120 |
+
"learning_rate": 3.2009473171114748e-06,
|
| 1121 |
+
"loss": 0.4127,
|
| 1122 |
+
"step": 790
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.6597510373443983,
|
| 1126 |
+
"grad_norm": 2.0169788933206965,
|
| 1127 |
+
"learning_rate": 3.1335374171285993e-06,
|
| 1128 |
+
"loss": 0.4273,
|
| 1129 |
+
"step": 795
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.6639004149377593,
|
| 1133 |
+
"grad_norm": 2.132031529237029,
|
| 1134 |
+
"learning_rate": 3.0665194330412453e-06,
|
| 1135 |
+
"loss": 0.4199,
|
| 1136 |
+
"step": 800
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.6680497925311203,
|
| 1140 |
+
"grad_norm": 1.974289618100589,
|
| 1141 |
+
"learning_rate": 2.999907437145042e-06,
|
| 1142 |
+
"loss": 0.4141,
|
| 1143 |
+
"step": 805
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.6721991701244814,
|
| 1147 |
+
"grad_norm": 1.9950951128394907,
|
| 1148 |
+
"learning_rate": 2.9337154164870723e-06,
|
| 1149 |
+
"loss": 0.4141,
|
| 1150 |
+
"step": 810
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.6763485477178424,
|
| 1154 |
+
"grad_norm": 2.0422579243315298,
|
| 1155 |
+
"learning_rate": 2.8679572699288993e-06,
|
| 1156 |
+
"loss": 0.4117,
|
| 1157 |
+
"step": 815
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.6804979253112033,
|
| 1161 |
+
"grad_norm": 2.049127089823568,
|
| 1162 |
+
"learning_rate": 2.802646805228115e-06,
|
| 1163 |
+
"loss": 0.4055,
|
| 1164 |
+
"step": 820
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.6846473029045643,
|
| 1168 |
+
"grad_norm": 2.0129580531205686,
|
| 1169 |
+
"learning_rate": 2.7377977361390118e-06,
|
| 1170 |
+
"loss": 0.4032,
|
| 1171 |
+
"step": 825
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.6887966804979253,
|
| 1175 |
+
"grad_norm": 2.1533361617257496,
|
| 1176 |
+
"learning_rate": 2.673423679533003e-06,
|
| 1177 |
+
"loss": 0.4049,
|
| 1178 |
+
"step": 830
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.6929460580912863,
|
| 1182 |
+
"grad_norm": 2.012532576052599,
|
| 1183 |
+
"learning_rate": 2.609538152539375e-06,
|
| 1184 |
+
"loss": 0.4112,
|
| 1185 |
+
"step": 835
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.6970954356846473,
|
| 1189 |
+
"grad_norm": 2.0005545981205013,
|
| 1190 |
+
"learning_rate": 2.546154569706991e-06,
|
| 1191 |
+
"loss": 0.4062,
|
| 1192 |
+
"step": 840
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.7012448132780082,
|
| 1196 |
+
"grad_norm": 1.9763702850969325,
|
| 1197 |
+
"learning_rate": 2.483286240187538e-06,
|
| 1198 |
+
"loss": 0.4076,
|
| 1199 |
+
"step": 845
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.7053941908713693,
|
| 1203 |
+
"grad_norm": 1.9363754039901064,
|
| 1204 |
+
"learning_rate": 2.420946364940885e-06,
|
| 1205 |
+
"loss": 0.3983,
|
| 1206 |
+
"step": 850
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.7095435684647303,
|
| 1210 |
+
"grad_norm": 1.9964976216880392,
|
| 1211 |
+
"learning_rate": 2.359148033963195e-06,
|
| 1212 |
+
"loss": 0.4012,
|
| 1213 |
+
"step": 855
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.7136929460580913,
|
| 1217 |
+
"grad_norm": 1.9539357011094127,
|
| 1218 |
+
"learning_rate": 2.297904223538289e-06,
|
| 1219 |
+
"loss": 0.4014,
|
| 1220 |
+
"step": 860
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.7178423236514523,
|
| 1224 |
+
"grad_norm": 2.003285264891127,
|
| 1225 |
+
"learning_rate": 2.237227793512935e-06,
|
| 1226 |
+
"loss": 0.4005,
|
| 1227 |
+
"step": 865
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.7219917012448133,
|
| 1231 |
+
"grad_norm": 2.0469841226757826,
|
| 1232 |
+
"learning_rate": 2.1771314845965485e-06,
|
| 1233 |
+
"loss": 0.3919,
|
| 1234 |
+
"step": 870
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.7261410788381742,
|
| 1238 |
+
"grad_norm": 2.0771139142501482,
|
| 1239 |
+
"learning_rate": 2.1176279156859396e-06,
|
| 1240 |
+
"loss": 0.3967,
|
| 1241 |
+
"step": 875
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.7302904564315352,
|
| 1245 |
+
"grad_norm": 2.0143075674387734,
|
| 1246 |
+
"learning_rate": 2.0587295812156117e-06,
|
| 1247 |
+
"loss": 0.4042,
|
| 1248 |
+
"step": 880
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.7344398340248963,
|
| 1252 |
+
"grad_norm": 2.033797194926859,
|
| 1253 |
+
"learning_rate": 2.000448848534209e-06,
|
| 1254 |
+
"loss": 0.3889,
|
| 1255 |
+
"step": 885
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.7385892116182573,
|
| 1259 |
+
"grad_norm": 2.123163913068704,
|
| 1260 |
+
"learning_rate": 1.942797955307655e-06,
|
| 1261 |
+
"loss": 0.3927,
|
| 1262 |
+
"step": 890
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.7427385892116183,
|
| 1266 |
+
"grad_norm": 2.1029028753084855,
|
| 1267 |
+
"learning_rate": 1.8857890069494983e-06,
|
| 1268 |
+
"loss": 0.3862,
|
| 1269 |
+
"step": 895
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.7468879668049793,
|
| 1273 |
+
"grad_norm": 1.9596988626179463,
|
| 1274 |
+
"learning_rate": 1.8294339740790595e-06,
|
| 1275 |
+
"loss": 0.3926,
|
| 1276 |
+
"step": 900
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.7510373443983402,
|
| 1280 |
+
"grad_norm": 2.045654702642933,
|
| 1281 |
+
"learning_rate": 1.7737446900078503e-06,
|
| 1282 |
+
"loss": 0.3902,
|
| 1283 |
+
"step": 905
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.7551867219917012,
|
| 1287 |
+
"grad_norm": 1.8714455878320024,
|
| 1288 |
+
"learning_rate": 1.7187328482548543e-06,
|
| 1289 |
+
"loss": 0.3858,
|
| 1290 |
+
"step": 910
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.7593360995850622,
|
| 1294 |
+
"grad_norm": 1.9719509461323035,
|
| 1295 |
+
"learning_rate": 1.6644100000911312e-06,
|
| 1296 |
+
"loss": 0.3858,
|
| 1297 |
+
"step": 915
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.7634854771784232,
|
| 1301 |
+
"grad_norm": 2.0199806220076995,
|
| 1302 |
+
"learning_rate": 1.61078755211432e-06,
|
| 1303 |
+
"loss": 0.3901,
|
| 1304 |
+
"step": 920
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.7676348547717843,
|
| 1308 |
+
"grad_norm": 1.8860408333074137,
|
| 1309 |
+
"learning_rate": 1.557876763853493e-06,
|
| 1310 |
+
"loss": 0.3789,
|
| 1311 |
+
"step": 925
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.7717842323651453,
|
| 1315 |
+
"grad_norm": 2.0409354742092725,
|
| 1316 |
+
"learning_rate": 1.5056887454049129e-06,
|
| 1317 |
+
"loss": 0.3977,
|
| 1318 |
+
"step": 930
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.7759336099585062,
|
| 1322 |
+
"grad_norm": 1.986307727470136,
|
| 1323 |
+
"learning_rate": 1.4542344550991538e-06,
|
| 1324 |
+
"loss": 0.3908,
|
| 1325 |
+
"step": 935
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.7800829875518672,
|
| 1329 |
+
"grad_norm": 1.8832678493109687,
|
| 1330 |
+
"learning_rate": 1.4035246972000922e-06,
|
| 1331 |
+
"loss": 0.3935,
|
| 1332 |
+
"step": 940
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.7842323651452282,
|
| 1336 |
+
"grad_norm": 2.020212496636967,
|
| 1337 |
+
"learning_rate": 1.353570119636255e-06,
|
| 1338 |
+
"loss": 0.379,
|
| 1339 |
+
"step": 945
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.7883817427385892,
|
| 1343 |
+
"grad_norm": 2.0199477511715638,
|
| 1344 |
+
"learning_rate": 1.3043812117649846e-06,
|
| 1345 |
+
"loss": 0.3931,
|
| 1346 |
+
"step": 950
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.7925311203319502,
|
| 1350 |
+
"grad_norm": 2.015693992608451,
|
| 1351 |
+
"learning_rate": 1.2559683021699132e-06,
|
| 1352 |
+
"loss": 0.3774,
|
| 1353 |
+
"step": 955
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.7966804979253111,
|
| 1357 |
+
"grad_norm": 2.0495350044403113,
|
| 1358 |
+
"learning_rate": 1.2083415564921775e-06,
|
| 1359 |
+
"loss": 0.3845,
|
| 1360 |
+
"step": 960
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.8008298755186722,
|
| 1364 |
+
"grad_norm": 2.1357993118322,
|
| 1365 |
+
"learning_rate": 1.1615109752958715e-06,
|
| 1366 |
+
"loss": 0.3781,
|
| 1367 |
+
"step": 965
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.8049792531120332,
|
| 1371 |
+
"grad_norm": 2.0787734920639553,
|
| 1372 |
+
"learning_rate": 1.1154863919681358e-06,
|
| 1373 |
+
"loss": 0.3786,
|
| 1374 |
+
"step": 970
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.8091286307053942,
|
| 1378 |
+
"grad_norm": 2.0147166599927817,
|
| 1379 |
+
"learning_rate": 1.0702774706543772e-06,
|
| 1380 |
+
"loss": 0.3801,
|
| 1381 |
+
"step": 975
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.8132780082987552,
|
| 1385 |
+
"grad_norm": 2.1274229351405682,
|
| 1386 |
+
"learning_rate": 1.0258937042289986e-06,
|
| 1387 |
+
"loss": 0.3758,
|
| 1388 |
+
"step": 980
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.8174273858921162,
|
| 1392 |
+
"grad_norm": 2.020236024053247,
|
| 1393 |
+
"learning_rate": 9.82344412302117e-07,
|
| 1394 |
+
"loss": 0.3745,
|
| 1395 |
+
"step": 985
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.8215767634854771,
|
| 1399 |
+
"grad_norm": 2.0310388332900224,
|
| 1400 |
+
"learning_rate": 9.396387392626399e-07,
|
| 1401 |
+
"loss": 0.3716,
|
| 1402 |
+
"step": 990
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.8257261410788381,
|
| 1406 |
+
"grad_norm": 2.1668749663108717,
|
| 1407 |
+
"learning_rate": 8.97785652358158e-07,
|
| 1408 |
+
"loss": 0.3697,
|
| 1409 |
+
"step": 995
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.8298755186721992,
|
| 1413 |
+
"grad_norm": 2.0045742016058914,
|
| 1414 |
+
"learning_rate": 8.567939398120095e-07,
|
| 1415 |
+
"loss": 0.376,
|
| 1416 |
+
"step": 1000
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.8340248962655602,
|
| 1420 |
+
"grad_norm": 1.9913802328205135,
|
| 1421 |
+
"learning_rate": 8.166722089779539e-07,
|
| 1422 |
+
"loss": 0.3662,
|
| 1423 |
+
"step": 1005
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.8381742738589212,
|
| 1427 |
+
"grad_norm": 2.054785546661835,
|
| 1428 |
+
"learning_rate": 7.774288845328193e-07,
|
| 1429 |
+
"loss": 0.3797,
|
| 1430 |
+
"step": 1010
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.8423236514522822,
|
| 1434 |
+
"grad_norm": 2.066321355843617,
|
| 1435 |
+
"learning_rate": 7.390722067075024e-07,
|
| 1436 |
+
"loss": 0.3836,
|
| 1437 |
+
"step": 1015
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.8464730290456431,
|
| 1441 |
+
"grad_norm": 1.9972704924078868,
|
| 1442 |
+
"learning_rate": 7.016102295567046e-07,
|
| 1443 |
+
"loss": 0.3654,
|
| 1444 |
+
"step": 1020
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.8506224066390041,
|
| 1448 |
+
"grad_norm": 1.9358010759861928,
|
| 1449 |
+
"learning_rate": 6.650508192677546e-07,
|
| 1450 |
+
"loss": 0.3649,
|
| 1451 |
+
"step": 1025
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.8547717842323651,
|
| 1455 |
+
"grad_norm": 2.0175675008368645,
|
| 1456 |
+
"learning_rate": 6.294016525088914e-07,
|
| 1457 |
+
"loss": 0.3682,
|
| 1458 |
+
"step": 1030
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.8589211618257261,
|
| 1462 |
+
"grad_norm": 2.046261015462815,
|
| 1463 |
+
"learning_rate": 5.946702148173211e-07,
|
| 1464 |
+
"loss": 0.3601,
|
| 1465 |
+
"step": 1035
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.8630705394190872,
|
| 1469 |
+
"grad_norm": 2.08234471232173,
|
| 1470 |
+
"learning_rate": 5.608637990274335e-07,
|
| 1471 |
+
"loss": 0.3675,
|
| 1472 |
+
"step": 1040
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.8672199170124482,
|
| 1476 |
+
"grad_norm": 2.061640652779725,
|
| 1477 |
+
"learning_rate": 5.279895037394567e-07,
|
| 1478 |
+
"loss": 0.3675,
|
| 1479 |
+
"step": 1045
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.8713692946058091,
|
| 1483 |
+
"grad_norm": 2.050116976236056,
|
| 1484 |
+
"learning_rate": 4.960542318289118e-07,
|
| 1485 |
+
"loss": 0.3663,
|
| 1486 |
+
"step": 1050
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.8755186721991701,
|
| 1490 |
+
"grad_norm": 2.072309354512263,
|
| 1491 |
+
"learning_rate": 4.6506468899716607e-07,
|
| 1492 |
+
"loss": 0.372,
|
| 1493 |
+
"step": 1055
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.8796680497925311,
|
| 1497 |
+
"grad_norm": 2.152457552234192,
|
| 1498 |
+
"learning_rate": 4.3502738236337605e-07,
|
| 1499 |
+
"loss": 0.3593,
|
| 1500 |
+
"step": 1060
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 0.8838174273858921,
|
| 1504 |
+
"grad_norm": 1.996868735465177,
|
| 1505 |
+
"learning_rate": 4.0594861909814266e-07,
|
| 1506 |
+
"loss": 0.3604,
|
| 1507 |
+
"step": 1065
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.8879668049792531,
|
| 1511 |
+
"grad_norm": 1.9994915003373548,
|
| 1512 |
+
"learning_rate": 3.7783450509914e-07,
|
| 1513 |
+
"loss": 0.3656,
|
| 1514 |
+
"step": 1070
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.8921161825726142,
|
| 1518 |
+
"grad_norm": 1.9740173742965879,
|
| 1519 |
+
"learning_rate": 3.5069094370901613e-07,
|
| 1520 |
+
"loss": 0.3633,
|
| 1521 |
+
"step": 1075
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.8962655601659751,
|
| 1525 |
+
"grad_norm": 1.961688927842617,
|
| 1526 |
+
"learning_rate": 3.245236344758179e-07,
|
| 1527 |
+
"loss": 0.3634,
|
| 1528 |
+
"step": 1080
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 0.9004149377593361,
|
| 1532 |
+
"grad_norm": 2.0299031717626463,
|
| 1533 |
+
"learning_rate": 2.9933807195621446e-07,
|
| 1534 |
+
"loss": 0.3643,
|
| 1535 |
+
"step": 1085
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.9045643153526971,
|
| 1539 |
+
"grad_norm": 1.9933810295199255,
|
| 1540 |
+
"learning_rate": 2.751395445617594e-07,
|
| 1541 |
+
"loss": 0.3611,
|
| 1542 |
+
"step": 1090
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 0.9087136929460581,
|
| 1546 |
+
"grad_norm": 1.9428008804611876,
|
| 1547 |
+
"learning_rate": 2.5193313344844427e-07,
|
| 1548 |
+
"loss": 0.3647,
|
| 1549 |
+
"step": 1095
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.9128630705394191,
|
| 1553 |
+
"grad_norm": 2.070451744064332,
|
| 1554 |
+
"learning_rate": 2.2972371144976524e-07,
|
| 1555 |
+
"loss": 0.3578,
|
| 1556 |
+
"step": 1100
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 0.91701244813278,
|
| 1560 |
+
"grad_norm": 2.004094672792972,
|
| 1561 |
+
"learning_rate": 2.0851594205353543e-07,
|
| 1562 |
+
"loss": 0.3682,
|
| 1563 |
+
"step": 1105
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.921161825726141,
|
| 1567 |
+
"grad_norm": 1.99685429733088,
|
| 1568 |
+
"learning_rate": 1.8831427842266047e-07,
|
| 1569 |
+
"loss": 0.3629,
|
| 1570 |
+
"step": 1110
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.9253112033195021,
|
| 1574 |
+
"grad_norm": 2.0362204051502495,
|
| 1575 |
+
"learning_rate": 1.6912296246006544e-07,
|
| 1576 |
+
"loss": 0.3619,
|
| 1577 |
+
"step": 1115
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.9294605809128631,
|
| 1581 |
+
"grad_norm": 1.9954463784544125,
|
| 1582 |
+
"learning_rate": 1.5094602391799606e-07,
|
| 1583 |
+
"loss": 0.359,
|
| 1584 |
+
"step": 1120
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.9336099585062241,
|
| 1588 |
+
"grad_norm": 2.101222001014506,
|
| 1589 |
+
"learning_rate": 1.3378727955185243e-07,
|
| 1590 |
+
"loss": 0.3643,
|
| 1591 |
+
"step": 1125
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.9377593360995851,
|
| 1595 |
+
"grad_norm": 2.0097408515894477,
|
| 1596 |
+
"learning_rate": 1.1765033231876332e-07,
|
| 1597 |
+
"loss": 0.365,
|
| 1598 |
+
"step": 1130
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.941908713692946,
|
| 1602 |
+
"grad_norm": 2.083152089600553,
|
| 1603 |
+
"learning_rate": 1.0253857062103579e-07,
|
| 1604 |
+
"loss": 0.356,
|
| 1605 |
+
"step": 1135
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.946058091286307,
|
| 1609 |
+
"grad_norm": 2.1343299677958565,
|
| 1610 |
+
"learning_rate": 8.845516759467432e-08,
|
| 1611 |
+
"loss": 0.3637,
|
| 1612 |
+
"step": 1140
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 0.950207468879668,
|
| 1616 |
+
"grad_norm": 2.0339392745318854,
|
| 1617 |
+
"learning_rate": 7.540308044308442e-08,
|
| 1618 |
+
"loss": 0.3654,
|
| 1619 |
+
"step": 1145
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.9543568464730291,
|
| 1623 |
+
"grad_norm": 2.0235713792250674,
|
| 1624 |
+
"learning_rate": 6.338504981613037e-08,
|
| 1625 |
+
"loss": 0.3601,
|
| 1626 |
+
"step": 1150
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.9585062240663901,
|
| 1630 |
+
"grad_norm": 2.109608243011711,
|
| 1631 |
+
"learning_rate": 5.2403599234658876e-08,
|
| 1632 |
+
"loss": 0.356,
|
| 1633 |
+
"step": 1155
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.9626556016597511,
|
| 1637 |
+
"grad_norm": 2.0760547345374603,
|
| 1638 |
+
"learning_rate": 4.246103456061246e-08,
|
| 1639 |
+
"loss": 0.3595,
|
| 1640 |
+
"step": 1160
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.966804979253112,
|
| 1644 |
+
"grad_norm": 2.052680320906187,
|
| 1645 |
+
"learning_rate": 3.355944351285278e-08,
|
| 1646 |
+
"loss": 0.3664,
|
| 1647 |
+
"step": 1165
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.970954356846473,
|
| 1651 |
+
"grad_norm": 2.0133846012871484,
|
| 1652 |
+
"learning_rate": 2.5700695228783045e-08,
|
| 1653 |
+
"loss": 0.3602,
|
| 1654 |
+
"step": 1170
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 0.975103734439834,
|
| 1658 |
+
"grad_norm": 2.0460051222086517,
|
| 1659 |
+
"learning_rate": 1.8886439871874662e-08,
|
| 1660 |
+
"loss": 0.3614,
|
| 1661 |
+
"step": 1175
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.979253112033195,
|
| 1665 |
+
"grad_norm": 1.9713443728652713,
|
| 1666 |
+
"learning_rate": 1.31181082851628e-08,
|
| 1667 |
+
"loss": 0.3634,
|
| 1668 |
+
"step": 1180
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 0.983402489626556,
|
| 1672 |
+
"grad_norm": 1.9598526108360579,
|
| 1673 |
+
"learning_rate": 8.396911690807253e-09,
|
| 1674 |
+
"loss": 0.3633,
|
| 1675 |
+
"step": 1185
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.9875518672199171,
|
| 1679 |
+
"grad_norm": 2.018358583132368,
|
| 1680 |
+
"learning_rate": 4.723841435759769e-09,
|
| 1681 |
+
"loss": 0.3678,
|
| 1682 |
+
"step": 1190
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.991701244813278,
|
| 1686 |
+
"grad_norm": 2.0932112430813317,
|
| 1687 |
+
"learning_rate": 2.0996687836016825e-09,
|
| 1688 |
+
"loss": 0.364,
|
| 1689 |
+
"step": 1195
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.995850622406639,
|
| 1693 |
+
"grad_norm": 2.064858475016426,
|
| 1694 |
+
"learning_rate": 5.249447525995654e-10,
|
| 1695 |
+
"loss": 0.3573,
|
| 1696 |
+
"step": 1200
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 1.0,
|
| 1700 |
+
"grad_norm": 2.020766577175708,
|
| 1701 |
+
"learning_rate": 0.0,
|
| 1702 |
+
"loss": 0.3623,
|
| 1703 |
+
"step": 1205
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 1.0,
|
| 1707 |
+
"eval_loss": 0.3198564946651459,
|
| 1708 |
+
"eval_runtime": 1.1889,
|
| 1709 |
+
"eval_samples_per_second": 2.523,
|
| 1710 |
+
"eval_steps_per_second": 0.841,
|
| 1711 |
+
"step": 1205
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 1.0,
|
| 1715 |
+
"step": 1205,
|
| 1716 |
+
"total_flos": 252197795266560.0,
|
| 1717 |
+
"train_loss": 0.5424416576678327,
|
| 1718 |
+
"train_runtime": 23511.1257,
|
| 1719 |
+
"train_samples_per_second": 1.639,
|
| 1720 |
+
"train_steps_per_second": 0.051
|
| 1721 |
+
}
|
| 1722 |
+
],
|
| 1723 |
+
"logging_steps": 5,
|
| 1724 |
+
"max_steps": 1205,
|
| 1725 |
+
"num_input_tokens_seen": 0,
|
| 1726 |
+
"num_train_epochs": 1,
|
| 1727 |
+
"save_steps": 100,
|
| 1728 |
+
"stateful_callbacks": {
|
| 1729 |
+
"TrainerControl": {
|
| 1730 |
+
"args": {
|
| 1731 |
+
"should_epoch_stop": false,
|
| 1732 |
+
"should_evaluate": false,
|
| 1733 |
+
"should_log": false,
|
| 1734 |
+
"should_save": true,
|
| 1735 |
+
"should_training_stop": true
|
| 1736 |
+
},
|
| 1737 |
+
"attributes": {}
|
| 1738 |
+
}
|
| 1739 |
+
},
|
| 1740 |
+
"total_flos": 252197795266560.0,
|
| 1741 |
+
"train_batch_size": 4,
|
| 1742 |
+
"trial_name": null,
|
| 1743 |
+
"trial_params": null
|
| 1744 |
+
}
|