End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +1449 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: apache-2.0
|
|
| 4 |
base_model: Qwen/Qwen2.5-7B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: qwen2-5_multiple_samples_gpt_verification_seed_code
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# qwen2-5_multiple_samples_gpt_verification_seed_code
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 4 |
base_model: Qwen/Qwen2.5-7B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: qwen2-5_multiple_samples_gpt_verification_seed_code
|
|
|
|
| 16 |
|
| 17 |
# qwen2-5_multiple_samples_gpt_verification_seed_code
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/multiple_samples_gpt_verification_seed_code dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.985148514851485,
|
| 3 |
+
"total_flos": 138721009057792.0,
|
| 4 |
+
"train_loss": 0.7744821606583856,
|
| 5 |
+
"train_runtime": 2765.7022,
|
| 6 |
+
"train_samples_per_second": 6.994,
|
| 7 |
+
"train_steps_per_second": 0.073
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.985148514851485,
|
| 3 |
+
"total_flos": 138721009057792.0,
|
| 4 |
+
"train_loss": 0.7744821606583856,
|
| 5 |
+
"train_runtime": 2765.7022,
|
| 6 |
+
"train_samples_per_second": 6.994,
|
| 7 |
+
"train_steps_per_second": 0.073
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1449 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.985148514851485,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 201,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01485148514851485,
|
| 13 |
+
"grad_norm": 6.48456557234758,
|
| 14 |
+
"learning_rate": 4.7619047619047623e-07,
|
| 15 |
+
"loss": 1.1703,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0297029702970297,
|
| 20 |
+
"grad_norm": 6.594689369570434,
|
| 21 |
+
"learning_rate": 9.523809523809525e-07,
|
| 22 |
+
"loss": 1.1918,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.04455445544554455,
|
| 27 |
+
"grad_norm": 6.23293374565609,
|
| 28 |
+
"learning_rate": 1.4285714285714286e-06,
|
| 29 |
+
"loss": 1.1576,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0594059405940594,
|
| 34 |
+
"grad_norm": 6.401466218218343,
|
| 35 |
+
"learning_rate": 1.904761904761905e-06,
|
| 36 |
+
"loss": 1.2099,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.07425742574257425,
|
| 41 |
+
"grad_norm": 5.7694144179716,
|
| 42 |
+
"learning_rate": 2.380952380952381e-06,
|
| 43 |
+
"loss": 1.1447,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.0891089108910891,
|
| 48 |
+
"grad_norm": 4.584773158856208,
|
| 49 |
+
"learning_rate": 2.8571428571428573e-06,
|
| 50 |
+
"loss": 1.1128,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.10396039603960396,
|
| 55 |
+
"grad_norm": 4.408264566567633,
|
| 56 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 57 |
+
"loss": 1.1444,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.1188118811881188,
|
| 62 |
+
"grad_norm": 2.6961190293519213,
|
| 63 |
+
"learning_rate": 3.80952380952381e-06,
|
| 64 |
+
"loss": 1.0333,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.13366336633663367,
|
| 69 |
+
"grad_norm": 2.366910263126932,
|
| 70 |
+
"learning_rate": 4.2857142857142855e-06,
|
| 71 |
+
"loss": 1.039,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.1485148514851485,
|
| 76 |
+
"grad_norm": 3.6999770055634555,
|
| 77 |
+
"learning_rate": 4.761904761904762e-06,
|
| 78 |
+
"loss": 1.0171,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.16336633663366337,
|
| 83 |
+
"grad_norm": 3.894316339063172,
|
| 84 |
+
"learning_rate": 5.2380952380952384e-06,
|
| 85 |
+
"loss": 1.0232,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.1782178217821782,
|
| 90 |
+
"grad_norm": 3.8249399482892703,
|
| 91 |
+
"learning_rate": 5.7142857142857145e-06,
|
| 92 |
+
"loss": 1.0875,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.19306930693069307,
|
| 97 |
+
"grad_norm": 3.0670108504304334,
|
| 98 |
+
"learning_rate": 6.1904761904761914e-06,
|
| 99 |
+
"loss": 1.0108,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.2079207920792079,
|
| 104 |
+
"grad_norm": 2.6030053112293676,
|
| 105 |
+
"learning_rate": 6.666666666666667e-06,
|
| 106 |
+
"loss": 0.9857,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.22277227722772278,
|
| 111 |
+
"grad_norm": 2.370576635506437,
|
| 112 |
+
"learning_rate": 7.1428571428571436e-06,
|
| 113 |
+
"loss": 0.9728,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.2376237623762376,
|
| 118 |
+
"grad_norm": 2.3399338429829615,
|
| 119 |
+
"learning_rate": 7.61904761904762e-06,
|
| 120 |
+
"loss": 0.9694,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.2524752475247525,
|
| 125 |
+
"grad_norm": 1.8311702968068935,
|
| 126 |
+
"learning_rate": 8.095238095238097e-06,
|
| 127 |
+
"loss": 0.934,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.26732673267326734,
|
| 132 |
+
"grad_norm": 1.4308728197686567,
|
| 133 |
+
"learning_rate": 8.571428571428571e-06,
|
| 134 |
+
"loss": 0.9175,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.28217821782178215,
|
| 139 |
+
"grad_norm": 1.5620018816986423,
|
| 140 |
+
"learning_rate": 9.047619047619049e-06,
|
| 141 |
+
"loss": 0.9595,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.297029702970297,
|
| 146 |
+
"grad_norm": 1.4122378912732825,
|
| 147 |
+
"learning_rate": 9.523809523809525e-06,
|
| 148 |
+
"loss": 0.9082,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.3118811881188119,
|
| 153 |
+
"grad_norm": 1.2544223318659375,
|
| 154 |
+
"learning_rate": 1e-05,
|
| 155 |
+
"loss": 0.8293,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.32673267326732675,
|
| 160 |
+
"grad_norm": 1.0621864931131515,
|
| 161 |
+
"learning_rate": 9.999238475781957e-06,
|
| 162 |
+
"loss": 0.8615,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.3415841584158416,
|
| 167 |
+
"grad_norm": 1.067756678297183,
|
| 168 |
+
"learning_rate": 9.99695413509548e-06,
|
| 169 |
+
"loss": 0.8963,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.3564356435643564,
|
| 174 |
+
"grad_norm": 1.1625635155258327,
|
| 175 |
+
"learning_rate": 9.993147673772869e-06,
|
| 176 |
+
"loss": 0.875,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.3712871287128713,
|
| 181 |
+
"grad_norm": 0.9411109178322155,
|
| 182 |
+
"learning_rate": 9.987820251299121e-06,
|
| 183 |
+
"loss": 0.8488,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.38613861386138615,
|
| 188 |
+
"grad_norm": 0.8920662981646181,
|
| 189 |
+
"learning_rate": 9.980973490458728e-06,
|
| 190 |
+
"loss": 0.8838,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.400990099009901,
|
| 195 |
+
"grad_norm": 0.9110888685882579,
|
| 196 |
+
"learning_rate": 9.972609476841368e-06,
|
| 197 |
+
"loss": 0.8299,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.4158415841584158,
|
| 202 |
+
"grad_norm": 0.8423480290666405,
|
| 203 |
+
"learning_rate": 9.962730758206612e-06,
|
| 204 |
+
"loss": 0.866,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.4306930693069307,
|
| 209 |
+
"grad_norm": 0.8825677961798845,
|
| 210 |
+
"learning_rate": 9.951340343707852e-06,
|
| 211 |
+
"loss": 0.8509,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.44554455445544555,
|
| 216 |
+
"grad_norm": 0.7581834656729458,
|
| 217 |
+
"learning_rate": 9.938441702975689e-06,
|
| 218 |
+
"loss": 0.8288,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.4603960396039604,
|
| 223 |
+
"grad_norm": 1.055473120057636,
|
| 224 |
+
"learning_rate": 9.924038765061042e-06,
|
| 225 |
+
"loss": 0.838,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.4752475247524752,
|
| 230 |
+
"grad_norm": 0.7922082592771019,
|
| 231 |
+
"learning_rate": 9.908135917238321e-06,
|
| 232 |
+
"loss": 0.8609,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.4900990099009901,
|
| 237 |
+
"grad_norm": 0.754302150819188,
|
| 238 |
+
"learning_rate": 9.890738003669029e-06,
|
| 239 |
+
"loss": 0.8583,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.504950495049505,
|
| 244 |
+
"grad_norm": 1.0626447047968044,
|
| 245 |
+
"learning_rate": 9.871850323926178e-06,
|
| 246 |
+
"loss": 0.7944,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.5198019801980198,
|
| 251 |
+
"grad_norm": 0.8923345386621004,
|
| 252 |
+
"learning_rate": 9.851478631379982e-06,
|
| 253 |
+
"loss": 0.8975,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.5346534653465347,
|
| 258 |
+
"grad_norm": 0.7366372348142536,
|
| 259 |
+
"learning_rate": 9.829629131445342e-06,
|
| 260 |
+
"loss": 0.8676,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.5495049504950495,
|
| 265 |
+
"grad_norm": 1.2738146882781316,
|
| 266 |
+
"learning_rate": 9.806308479691595e-06,
|
| 267 |
+
"loss": 0.8975,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.5643564356435643,
|
| 272 |
+
"grad_norm": 0.8592154350621992,
|
| 273 |
+
"learning_rate": 9.781523779815178e-06,
|
| 274 |
+
"loss": 0.8207,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.5792079207920792,
|
| 279 |
+
"grad_norm": 0.7049611640819059,
|
| 280 |
+
"learning_rate": 9.755282581475769e-06,
|
| 281 |
+
"loss": 0.8416,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.594059405940594,
|
| 286 |
+
"grad_norm": 0.8172609258295951,
|
| 287 |
+
"learning_rate": 9.727592877996585e-06,
|
| 288 |
+
"loss": 0.9003,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.6089108910891089,
|
| 293 |
+
"grad_norm": 0.943383839148404,
|
| 294 |
+
"learning_rate": 9.698463103929542e-06,
|
| 295 |
+
"loss": 0.8279,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.6237623762376238,
|
| 300 |
+
"grad_norm": 0.8200827897891733,
|
| 301 |
+
"learning_rate": 9.667902132486009e-06,
|
| 302 |
+
"loss": 0.8252,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.6386138613861386,
|
| 307 |
+
"grad_norm": 0.750459606762128,
|
| 308 |
+
"learning_rate": 9.635919272833938e-06,
|
| 309 |
+
"loss": 0.8417,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.6534653465346535,
|
| 314 |
+
"grad_norm": 0.8256180076390092,
|
| 315 |
+
"learning_rate": 9.602524267262202e-06,
|
| 316 |
+
"loss": 0.8068,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.6683168316831684,
|
| 321 |
+
"grad_norm": 0.7362971479000804,
|
| 322 |
+
"learning_rate": 9.567727288213005e-06,
|
| 323 |
+
"loss": 0.8116,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.6831683168316832,
|
| 328 |
+
"grad_norm": 0.6611484879378139,
|
| 329 |
+
"learning_rate": 9.531538935183252e-06,
|
| 330 |
+
"loss": 0.8049,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.698019801980198,
|
| 335 |
+
"grad_norm": 0.6483590920807921,
|
| 336 |
+
"learning_rate": 9.493970231495836e-06,
|
| 337 |
+
"loss": 0.8158,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.7128712871287128,
|
| 342 |
+
"grad_norm": 0.6499715006108466,
|
| 343 |
+
"learning_rate": 9.45503262094184e-06,
|
| 344 |
+
"loss": 0.7963,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.7277227722772277,
|
| 349 |
+
"grad_norm": 0.6445318374705665,
|
| 350 |
+
"learning_rate": 9.414737964294636e-06,
|
| 351 |
+
"loss": 0.8372,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.7425742574257426,
|
| 356 |
+
"grad_norm": 0.6749851299246947,
|
| 357 |
+
"learning_rate": 9.37309853569698e-06,
|
| 358 |
+
"loss": 0.7974,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.7574257425742574,
|
| 363 |
+
"grad_norm": 0.6430920805349686,
|
| 364 |
+
"learning_rate": 9.330127018922195e-06,
|
| 365 |
+
"loss": 0.797,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.7722772277227723,
|
| 370 |
+
"grad_norm": 0.7122774157069339,
|
| 371 |
+
"learning_rate": 9.285836503510562e-06,
|
| 372 |
+
"loss": 0.8178,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.7871287128712872,
|
| 377 |
+
"grad_norm": 0.6222782441453497,
|
| 378 |
+
"learning_rate": 9.24024048078213e-06,
|
| 379 |
+
"loss": 0.8286,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.801980198019802,
|
| 384 |
+
"grad_norm": 0.6774898848973883,
|
| 385 |
+
"learning_rate": 9.193352839727122e-06,
|
| 386 |
+
"loss": 0.8199,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.8168316831683168,
|
| 391 |
+
"grad_norm": 0.6685577033399003,
|
| 392 |
+
"learning_rate": 9.145187862775208e-06,
|
| 393 |
+
"loss": 0.8325,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.8316831683168316,
|
| 398 |
+
"grad_norm": 0.6954610466193606,
|
| 399 |
+
"learning_rate": 9.09576022144496e-06,
|
| 400 |
+
"loss": 0.7876,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.8465346534653465,
|
| 405 |
+
"grad_norm": 0.6717917465533401,
|
| 406 |
+
"learning_rate": 9.045084971874738e-06,
|
| 407 |
+
"loss": 0.7889,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.8613861386138614,
|
| 412 |
+
"grad_norm": 0.6710948817812145,
|
| 413 |
+
"learning_rate": 8.993177550236464e-06,
|
| 414 |
+
"loss": 0.819,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.8762376237623762,
|
| 419 |
+
"grad_norm": 0.6677437938362905,
|
| 420 |
+
"learning_rate": 8.94005376803361e-06,
|
| 421 |
+
"loss": 0.815,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.8910891089108911,
|
| 426 |
+
"grad_norm": 0.6333145369648289,
|
| 427 |
+
"learning_rate": 8.885729807284855e-06,
|
| 428 |
+
"loss": 0.8033,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.905940594059406,
|
| 433 |
+
"grad_norm": 0.810414558269581,
|
| 434 |
+
"learning_rate": 8.83022221559489e-06,
|
| 435 |
+
"loss": 0.8495,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.9207920792079208,
|
| 440 |
+
"grad_norm": 0.8092632573192287,
|
| 441 |
+
"learning_rate": 8.773547901113862e-06,
|
| 442 |
+
"loss": 0.7934,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.9356435643564357,
|
| 447 |
+
"grad_norm": 0.6595329129270622,
|
| 448 |
+
"learning_rate": 8.715724127386971e-06,
|
| 449 |
+
"loss": 0.8037,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.9504950495049505,
|
| 454 |
+
"grad_norm": 0.8763924940559503,
|
| 455 |
+
"learning_rate": 8.656768508095853e-06,
|
| 456 |
+
"loss": 0.8148,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.9653465346534653,
|
| 461 |
+
"grad_norm": 0.7170557641262976,
|
| 462 |
+
"learning_rate": 8.596699001693257e-06,
|
| 463 |
+
"loss": 0.8634,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.9801980198019802,
|
| 468 |
+
"grad_norm": 0.7120219047413958,
|
| 469 |
+
"learning_rate": 8.535533905932739e-06,
|
| 470 |
+
"loss": 0.8066,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.995049504950495,
|
| 475 |
+
"grad_norm": 0.7743156368261691,
|
| 476 |
+
"learning_rate": 8.473291852294986e-06,
|
| 477 |
+
"loss": 0.7911,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 1.00990099009901,
|
| 482 |
+
"grad_norm": 1.3350443160879135,
|
| 483 |
+
"learning_rate": 8.409991800312493e-06,
|
| 484 |
+
"loss": 1.252,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 1.0247524752475248,
|
| 489 |
+
"grad_norm": 0.7990302178349659,
|
| 490 |
+
"learning_rate": 8.345653031794292e-06,
|
| 491 |
+
"loss": 0.8425,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 1.0396039603960396,
|
| 496 |
+
"grad_norm": 0.6239804634649714,
|
| 497 |
+
"learning_rate": 8.280295144952537e-06,
|
| 498 |
+
"loss": 0.6491,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 1.0544554455445545,
|
| 503 |
+
"grad_norm": 0.6694927788559727,
|
| 504 |
+
"learning_rate": 8.213938048432697e-06,
|
| 505 |
+
"loss": 0.7202,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.0693069306930694,
|
| 510 |
+
"grad_norm": 0.7432686527943043,
|
| 511 |
+
"learning_rate": 8.146601955249187e-06,
|
| 512 |
+
"loss": 0.741,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.0841584158415842,
|
| 517 |
+
"grad_norm": 0.6416160685114952,
|
| 518 |
+
"learning_rate": 8.078307376628292e-06,
|
| 519 |
+
"loss": 0.8075,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.099009900990099,
|
| 524 |
+
"grad_norm": 0.698781285729984,
|
| 525 |
+
"learning_rate": 8.009075115760243e-06,
|
| 526 |
+
"loss": 0.6919,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.113861386138614,
|
| 531 |
+
"grad_norm": 0.6958006649391136,
|
| 532 |
+
"learning_rate": 7.938926261462366e-06,
|
| 533 |
+
"loss": 0.6921,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.1287128712871288,
|
| 538 |
+
"grad_norm": 0.6237956171364151,
|
| 539 |
+
"learning_rate": 7.86788218175523e-06,
|
| 540 |
+
"loss": 0.7287,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.1435643564356435,
|
| 545 |
+
"grad_norm": 0.7252061300181446,
|
| 546 |
+
"learning_rate": 7.795964517353734e-06,
|
| 547 |
+
"loss": 0.8264,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.1584158415841583,
|
| 552 |
+
"grad_norm": 0.674352802334064,
|
| 553 |
+
"learning_rate": 7.723195175075136e-06,
|
| 554 |
+
"loss": 0.6763,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.1732673267326732,
|
| 559 |
+
"grad_norm": 0.6546358450685043,
|
| 560 |
+
"learning_rate": 7.649596321166024e-06,
|
| 561 |
+
"loss": 0.7588,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.188118811881188,
|
| 566 |
+
"grad_norm": 0.6479565965693698,
|
| 567 |
+
"learning_rate": 7.575190374550272e-06,
|
| 568 |
+
"loss": 0.7277,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.202970297029703,
|
| 573 |
+
"grad_norm": 0.6626458405633724,
|
| 574 |
+
"learning_rate": 7.500000000000001e-06,
|
| 575 |
+
"loss": 0.7174,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.2178217821782178,
|
| 580 |
+
"grad_norm": 0.6756782160293404,
|
| 581 |
+
"learning_rate": 7.424048101231687e-06,
|
| 582 |
+
"loss": 0.7548,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 1.2326732673267327,
|
| 587 |
+
"grad_norm": 0.808652221633845,
|
| 588 |
+
"learning_rate": 7.347357813929455e-06,
|
| 589 |
+
"loss": 0.7933,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.2475247524752475,
|
| 594 |
+
"grad_norm": 0.573811498550998,
|
| 595 |
+
"learning_rate": 7.269952498697734e-06,
|
| 596 |
+
"loss": 0.6931,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.2623762376237624,
|
| 601 |
+
"grad_norm": 0.646918318906572,
|
| 602 |
+
"learning_rate": 7.191855733945388e-06,
|
| 603 |
+
"loss": 0.7785,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.2772277227722773,
|
| 608 |
+
"grad_norm": 0.5958671013573899,
|
| 609 |
+
"learning_rate": 7.113091308703498e-06,
|
| 610 |
+
"loss": 0.709,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.2920792079207921,
|
| 615 |
+
"grad_norm": 0.7165583961725527,
|
| 616 |
+
"learning_rate": 7.033683215379002e-06,
|
| 617 |
+
"loss": 0.6866,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.306930693069307,
|
| 622 |
+
"grad_norm": 0.8848970604430635,
|
| 623 |
+
"learning_rate": 6.953655642446368e-06,
|
| 624 |
+
"loss": 0.7576,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.3217821782178218,
|
| 629 |
+
"grad_norm": 0.6315927520470037,
|
| 630 |
+
"learning_rate": 6.873032967079562e-06,
|
| 631 |
+
"loss": 0.7615,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.3366336633663367,
|
| 636 |
+
"grad_norm": 0.6472208368826241,
|
| 637 |
+
"learning_rate": 6.7918397477265e-06,
|
| 638 |
+
"loss": 0.7158,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.3514851485148514,
|
| 643 |
+
"grad_norm": 0.8136088626747461,
|
| 644 |
+
"learning_rate": 6.710100716628345e-06,
|
| 645 |
+
"loss": 0.8109,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.3663366336633662,
|
| 650 |
+
"grad_norm": 0.6789106969356933,
|
| 651 |
+
"learning_rate": 6.627840772285784e-06,
|
| 652 |
+
"loss": 0.6553,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.381188118811881,
|
| 657 |
+
"grad_norm": 0.6684192399196682,
|
| 658 |
+
"learning_rate": 6.545084971874738e-06,
|
| 659 |
+
"loss": 0.7604,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.396039603960396,
|
| 664 |
+
"grad_norm": 0.6470872320361255,
|
| 665 |
+
"learning_rate": 6.461858523613684e-06,
|
| 666 |
+
"loss": 0.7548,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.4108910891089108,
|
| 671 |
+
"grad_norm": 0.6486567165728302,
|
| 672 |
+
"learning_rate": 6.378186779084996e-06,
|
| 673 |
+
"loss": 0.7484,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.4257425742574257,
|
| 678 |
+
"grad_norm": 0.8461471561359525,
|
| 679 |
+
"learning_rate": 6.294095225512604e-06,
|
| 680 |
+
"loss": 0.7523,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.4405940594059405,
|
| 685 |
+
"grad_norm": 0.6814439448544345,
|
| 686 |
+
"learning_rate": 6.209609477998339e-06,
|
| 687 |
+
"loss": 0.7334,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.4554455445544554,
|
| 692 |
+
"grad_norm": 0.5328496145736351,
|
| 693 |
+
"learning_rate": 6.124755271719326e-06,
|
| 694 |
+
"loss": 0.6584,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 1.4702970297029703,
|
| 699 |
+
"grad_norm": 0.680813767822209,
|
| 700 |
+
"learning_rate": 6.039558454088796e-06,
|
| 701 |
+
"loss": 0.8677,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.4851485148514851,
|
| 706 |
+
"grad_norm": 0.7359886080900357,
|
| 707 |
+
"learning_rate": 5.954044976882725e-06,
|
| 708 |
+
"loss": 0.7591,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.5,
|
| 713 |
+
"grad_norm": 0.6483808901598864,
|
| 714 |
+
"learning_rate": 5.8682408883346535e-06,
|
| 715 |
+
"loss": 0.7024,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 1.5148514851485149,
|
| 720 |
+
"grad_norm": 0.573259352808237,
|
| 721 |
+
"learning_rate": 5.782172325201155e-06,
|
| 722 |
+
"loss": 0.7647,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.5297029702970297,
|
| 727 |
+
"grad_norm": 0.620232903115091,
|
| 728 |
+
"learning_rate": 5.695865504800328e-06,
|
| 729 |
+
"loss": 0.746,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.5445544554455446,
|
| 734 |
+
"grad_norm": 0.6008704350145148,
|
| 735 |
+
"learning_rate": 5.609346717025738e-06,
|
| 736 |
+
"loss": 0.7653,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.5594059405940595,
|
| 741 |
+
"grad_norm": 0.6651231967169247,
|
| 742 |
+
"learning_rate": 5.522642316338268e-06,
|
| 743 |
+
"loss": 0.7284,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.5742574257425743,
|
| 748 |
+
"grad_norm": 0.6508987525775917,
|
| 749 |
+
"learning_rate": 5.435778713738292e-06,
|
| 750 |
+
"loss": 0.7081,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.5891089108910892,
|
| 755 |
+
"grad_norm": 0.6668715575162661,
|
| 756 |
+
"learning_rate": 5.348782368720627e-06,
|
| 757 |
+
"loss": 0.7653,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.603960396039604,
|
| 762 |
+
"grad_norm": 0.5993279825702773,
|
| 763 |
+
"learning_rate": 5.2616797812147205e-06,
|
| 764 |
+
"loss": 0.6936,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.618811881188119,
|
| 769 |
+
"grad_norm": 0.6642916869660335,
|
| 770 |
+
"learning_rate": 5.174497483512506e-06,
|
| 771 |
+
"loss": 0.6781,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 1.6336633663366338,
|
| 776 |
+
"grad_norm": 0.666238358663729,
|
| 777 |
+
"learning_rate": 5.087262032186418e-06,
|
| 778 |
+
"loss": 0.7442,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.6485148514851486,
|
| 783 |
+
"grad_norm": 0.5597421651434128,
|
| 784 |
+
"learning_rate": 5e-06,
|
| 785 |
+
"loss": 0.781,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.6633663366336635,
|
| 790 |
+
"grad_norm": 0.5707641758576157,
|
| 791 |
+
"learning_rate": 4.9127379678135825e-06,
|
| 792 |
+
"loss": 0.6567,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.6782178217821784,
|
| 797 |
+
"grad_norm": 0.7209030283118137,
|
| 798 |
+
"learning_rate": 4.825502516487497e-06,
|
| 799 |
+
"loss": 0.8752,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 1.693069306930693,
|
| 804 |
+
"grad_norm": 0.6674679363110967,
|
| 805 |
+
"learning_rate": 4.738320218785281e-06,
|
| 806 |
+
"loss": 0.6735,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.7079207920792079,
|
| 811 |
+
"grad_norm": 0.5604986801350424,
|
| 812 |
+
"learning_rate": 4.651217631279374e-06,
|
| 813 |
+
"loss": 0.6056,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 1.7227722772277227,
|
| 818 |
+
"grad_norm": 0.6669131750643947,
|
| 819 |
+
"learning_rate": 4.564221286261709e-06,
|
| 820 |
+
"loss": 0.7485,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 1.7376237623762376,
|
| 825 |
+
"grad_norm": 0.64731110152955,
|
| 826 |
+
"learning_rate": 4.477357683661734e-06,
|
| 827 |
+
"loss": 0.7505,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 1.7524752475247525,
|
| 832 |
+
"grad_norm": 0.6087298446862004,
|
| 833 |
+
"learning_rate": 4.390653282974264e-06,
|
| 834 |
+
"loss": 0.7236,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 1.7673267326732673,
|
| 839 |
+
"grad_norm": 0.605354758035472,
|
| 840 |
+
"learning_rate": 4.304134495199675e-06,
|
| 841 |
+
"loss": 0.7576,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 1.7821782178217822,
|
| 846 |
+
"grad_norm": 0.592121550404726,
|
| 847 |
+
"learning_rate": 4.217827674798845e-06,
|
| 848 |
+
"loss": 0.6612,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.797029702970297,
|
| 853 |
+
"grad_norm": 0.583998747608208,
|
| 854 |
+
"learning_rate": 4.131759111665349e-06,
|
| 855 |
+
"loss": 0.8031,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 1.811881188118812,
|
| 860 |
+
"grad_norm": 0.5401381825177095,
|
| 861 |
+
"learning_rate": 4.045955023117276e-06,
|
| 862 |
+
"loss": 0.7083,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 1.8267326732673266,
|
| 867 |
+
"grad_norm": 0.5505024887448378,
|
| 868 |
+
"learning_rate": 3.960441545911205e-06,
|
| 869 |
+
"loss": 0.6603,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 1.8415841584158414,
|
| 874 |
+
"grad_norm": 0.5807490002016577,
|
| 875 |
+
"learning_rate": 3.875244728280676e-06,
|
| 876 |
+
"loss": 0.7428,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 1.8564356435643563,
|
| 881 |
+
"grad_norm": 0.5775296918472558,
|
| 882 |
+
"learning_rate": 3.790390522001662e-06,
|
| 883 |
+
"loss": 0.7071,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 1.8712871287128712,
|
| 888 |
+
"grad_norm": 0.5618797996455542,
|
| 889 |
+
"learning_rate": 3.705904774487396e-06,
|
| 890 |
+
"loss": 0.7738,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 1.886138613861386,
|
| 895 |
+
"grad_norm": 0.5612544221604727,
|
| 896 |
+
"learning_rate": 3.6218132209150047e-06,
|
| 897 |
+
"loss": 0.7353,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 1.900990099009901,
|
| 902 |
+
"grad_norm": 0.5269006078917019,
|
| 903 |
+
"learning_rate": 3.538141476386317e-06,
|
| 904 |
+
"loss": 0.7185,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 1.9158415841584158,
|
| 909 |
+
"grad_norm": 0.5442468804329766,
|
| 910 |
+
"learning_rate": 3.4549150281252635e-06,
|
| 911 |
+
"loss": 0.696,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 1.9306930693069306,
|
| 916 |
+
"grad_norm": 0.5960660751056697,
|
| 917 |
+
"learning_rate": 3.372159227714218e-06,
|
| 918 |
+
"loss": 0.7649,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 1.9455445544554455,
|
| 923 |
+
"grad_norm": 0.4969333687228696,
|
| 924 |
+
"learning_rate": 3.289899283371657e-06,
|
| 925 |
+
"loss": 0.7024,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 1.9603960396039604,
|
| 930 |
+
"grad_norm": 0.5553043936209708,
|
| 931 |
+
"learning_rate": 3.2081602522734987e-06,
|
| 932 |
+
"loss": 0.823,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.9752475247524752,
|
| 937 |
+
"grad_norm": 0.5681040781939833,
|
| 938 |
+
"learning_rate": 3.12696703292044e-06,
|
| 939 |
+
"loss": 0.7705,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.99009900990099,
|
| 944 |
+
"grad_norm": 0.6009985220517085,
|
| 945 |
+
"learning_rate": 3.0463443575536324e-06,
|
| 946 |
+
"loss": 0.7319,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 2.004950495049505,
|
| 951 |
+
"grad_norm": 1.2209353424526557,
|
| 952 |
+
"learning_rate": 2.966316784621e-06,
|
| 953 |
+
"loss": 0.9991,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 2.01980198019802,
|
| 958 |
+
"grad_norm": 0.6663865953806991,
|
| 959 |
+
"learning_rate": 2.886908691296504e-06,
|
| 960 |
+
"loss": 0.7344,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 2.0346534653465347,
|
| 965 |
+
"grad_norm": 0.6515234599013568,
|
| 966 |
+
"learning_rate": 2.8081442660546126e-06,
|
| 967 |
+
"loss": 0.6747,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 2.0495049504950495,
|
| 972 |
+
"grad_norm": 0.5730091194025813,
|
| 973 |
+
"learning_rate": 2.7300475013022666e-06,
|
| 974 |
+
"loss": 0.603,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 2.0643564356435644,
|
| 979 |
+
"grad_norm": 0.5406638850651563,
|
| 980 |
+
"learning_rate": 2.6526421860705474e-06,
|
| 981 |
+
"loss": 0.7451,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 2.0792079207920793,
|
| 986 |
+
"grad_norm": 0.5841557122529807,
|
| 987 |
+
"learning_rate": 2.5759518987683154e-06,
|
| 988 |
+
"loss": 0.7037,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 2.094059405940594,
|
| 993 |
+
"grad_norm": 0.5894024920902818,
|
| 994 |
+
"learning_rate": 2.5000000000000015e-06,
|
| 995 |
+
"loss": 0.6763,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 2.108910891089109,
|
| 1000 |
+
"grad_norm": 0.6174804381821258,
|
| 1001 |
+
"learning_rate": 2.424809625449729e-06,
|
| 1002 |
+
"loss": 0.6384,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 2.123762376237624,
|
| 1007 |
+
"grad_norm": 0.6119987306390974,
|
| 1008 |
+
"learning_rate": 2.3504036788339763e-06,
|
| 1009 |
+
"loss": 0.7545,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 2.1386138613861387,
|
| 1014 |
+
"grad_norm": 0.5006999182134887,
|
| 1015 |
+
"learning_rate": 2.2768048249248648e-06,
|
| 1016 |
+
"loss": 0.5474,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 2.1534653465346536,
|
| 1021 |
+
"grad_norm": 0.5375559180884052,
|
| 1022 |
+
"learning_rate": 2.204035482646267e-06,
|
| 1023 |
+
"loss": 0.6522,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 2.1683168316831685,
|
| 1028 |
+
"grad_norm": 0.5708691567653545,
|
| 1029 |
+
"learning_rate": 2.132117818244771e-06,
|
| 1030 |
+
"loss": 0.6746,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 2.1831683168316833,
|
| 1035 |
+
"grad_norm": 0.5360011345721072,
|
| 1036 |
+
"learning_rate": 2.061073738537635e-06,
|
| 1037 |
+
"loss": 0.6705,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 2.198019801980198,
|
| 1042 |
+
"grad_norm": 0.6053709432824774,
|
| 1043 |
+
"learning_rate": 1.990924884239758e-06,
|
| 1044 |
+
"loss": 0.7101,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 2.212871287128713,
|
| 1049 |
+
"grad_norm": 0.5531801803062121,
|
| 1050 |
+
"learning_rate": 1.9216926233717087e-06,
|
| 1051 |
+
"loss": 0.6503,
|
| 1052 |
+
"step": 149
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 2.227722772277228,
|
| 1056 |
+
"grad_norm": 0.5761743172160733,
|
| 1057 |
+
"learning_rate": 1.8533980447508138e-06,
|
| 1058 |
+
"loss": 0.6597,
|
| 1059 |
+
"step": 150
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 2.2425742574257423,
|
| 1063 |
+
"grad_norm": 0.5920189276988723,
|
| 1064 |
+
"learning_rate": 1.7860619515673034e-06,
|
| 1065 |
+
"loss": 0.7937,
|
| 1066 |
+
"step": 151
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 2.2574257425742577,
|
| 1070 |
+
"grad_norm": 0.4711557273037673,
|
| 1071 |
+
"learning_rate": 1.7197048550474643e-06,
|
| 1072 |
+
"loss": 0.574,
|
| 1073 |
+
"step": 152
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 2.272277227722772,
|
| 1077 |
+
"grad_norm": 0.5323981360953441,
|
| 1078 |
+
"learning_rate": 1.6543469682057105e-06,
|
| 1079 |
+
"loss": 0.6766,
|
| 1080 |
+
"step": 153
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 2.287128712871287,
|
| 1084 |
+
"grad_norm": 0.5677075588486846,
|
| 1085 |
+
"learning_rate": 1.5900081996875083e-06,
|
| 1086 |
+
"loss": 0.7836,
|
| 1087 |
+
"step": 154
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 2.301980198019802,
|
| 1091 |
+
"grad_norm": 0.495711192365763,
|
| 1092 |
+
"learning_rate": 1.5267081477050132e-06,
|
| 1093 |
+
"loss": 0.5805,
|
| 1094 |
+
"step": 155
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 2.3168316831683167,
|
| 1098 |
+
"grad_norm": 0.5019129834363211,
|
| 1099 |
+
"learning_rate": 1.4644660940672628e-06,
|
| 1100 |
+
"loss": 0.6805,
|
| 1101 |
+
"step": 156
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 2.3316831683168315,
|
| 1105 |
+
"grad_norm": 0.5924600811693187,
|
| 1106 |
+
"learning_rate": 1.4033009983067454e-06,
|
| 1107 |
+
"loss": 0.6958,
|
| 1108 |
+
"step": 157
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 2.3465346534653464,
|
| 1112 |
+
"grad_norm": 0.5679498872247285,
|
| 1113 |
+
"learning_rate": 1.3432314919041478e-06,
|
| 1114 |
+
"loss": 0.7157,
|
| 1115 |
+
"step": 158
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 2.3613861386138613,
|
| 1119 |
+
"grad_norm": 0.5378653771399984,
|
| 1120 |
+
"learning_rate": 1.2842758726130283e-06,
|
| 1121 |
+
"loss": 0.6421,
|
| 1122 |
+
"step": 159
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 2.376237623762376,
|
| 1126 |
+
"grad_norm": 0.5716411245552344,
|
| 1127 |
+
"learning_rate": 1.22645209888614e-06,
|
| 1128 |
+
"loss": 0.7546,
|
| 1129 |
+
"step": 160
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 2.391089108910891,
|
| 1133 |
+
"grad_norm": 0.5031816053120705,
|
| 1134 |
+
"learning_rate": 1.1697777844051105e-06,
|
| 1135 |
+
"loss": 0.7018,
|
| 1136 |
+
"step": 161
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 2.405940594059406,
|
| 1140 |
+
"grad_norm": 0.46660397121098096,
|
| 1141 |
+
"learning_rate": 1.1142701927151456e-06,
|
| 1142 |
+
"loss": 0.639,
|
| 1143 |
+
"step": 162
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 2.4207920792079207,
|
| 1147 |
+
"grad_norm": 0.5135926843254873,
|
| 1148 |
+
"learning_rate": 1.0599462319663906e-06,
|
| 1149 |
+
"loss": 0.7345,
|
| 1150 |
+
"step": 163
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 2.4356435643564356,
|
| 1154 |
+
"grad_norm": 0.5145225601719905,
|
| 1155 |
+
"learning_rate": 1.006822449763537e-06,
|
| 1156 |
+
"loss": 0.6413,
|
| 1157 |
+
"step": 164
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 2.4504950495049505,
|
| 1161 |
+
"grad_norm": 0.4781710026536871,
|
| 1162 |
+
"learning_rate": 9.549150281252633e-07,
|
| 1163 |
+
"loss": 0.6647,
|
| 1164 |
+
"step": 165
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 2.4653465346534653,
|
| 1168 |
+
"grad_norm": 0.48799619696609925,
|
| 1169 |
+
"learning_rate": 9.042397785550405e-07,
|
| 1170 |
+
"loss": 0.7179,
|
| 1171 |
+
"step": 166
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 2.48019801980198,
|
| 1175 |
+
"grad_norm": 0.488756423169197,
|
| 1176 |
+
"learning_rate": 8.54812137224792e-07,
|
| 1177 |
+
"loss": 0.6727,
|
| 1178 |
+
"step": 167
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 2.495049504950495,
|
| 1182 |
+
"grad_norm": 0.47225504186982886,
|
| 1183 |
+
"learning_rate": 8.066471602728804e-07,
|
| 1184 |
+
"loss": 0.7016,
|
| 1185 |
+
"step": 168
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 2.50990099009901,
|
| 1189 |
+
"grad_norm": 0.4884739098762309,
|
| 1190 |
+
"learning_rate": 7.597595192178702e-07,
|
| 1191 |
+
"loss": 0.7249,
|
| 1192 |
+
"step": 169
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 2.5247524752475248,
|
| 1196 |
+
"grad_norm": 0.470588495873427,
|
| 1197 |
+
"learning_rate": 7.141634964894389e-07,
|
| 1198 |
+
"loss": 0.6672,
|
| 1199 |
+
"step": 170
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 2.5396039603960396,
|
| 1203 |
+
"grad_norm": 0.4673487289438152,
|
| 1204 |
+
"learning_rate": 6.698729810778065e-07,
|
| 1205 |
+
"loss": 0.6774,
|
| 1206 |
+
"step": 171
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 2.5544554455445545,
|
| 1210 |
+
"grad_norm": 0.4635764685120432,
|
| 1211 |
+
"learning_rate": 6.269014643030214e-07,
|
| 1212 |
+
"loss": 0.679,
|
| 1213 |
+
"step": 172
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 2.5693069306930694,
|
| 1217 |
+
"grad_norm": 0.4956166674866954,
|
| 1218 |
+
"learning_rate": 5.852620357053651e-07,
|
| 1219 |
+
"loss": 0.6947,
|
| 1220 |
+
"step": 173
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 2.5841584158415842,
|
| 1224 |
+
"grad_norm": 0.4817833751685946,
|
| 1225 |
+
"learning_rate": 5.449673790581611e-07,
|
| 1226 |
+
"loss": 0.6292,
|
| 1227 |
+
"step": 174
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 2.599009900990099,
|
| 1231 |
+
"grad_norm": 0.5033414960012568,
|
| 1232 |
+
"learning_rate": 5.06029768504166e-07,
|
| 1233 |
+
"loss": 0.6521,
|
| 1234 |
+
"step": 175
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 2.613861386138614,
|
| 1238 |
+
"grad_norm": 0.4826152038387741,
|
| 1239 |
+
"learning_rate": 4.6846106481675035e-07,
|
| 1240 |
+
"loss": 0.6345,
|
| 1241 |
+
"step": 176
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 2.628712871287129,
|
| 1245 |
+
"grad_norm": 0.5148110561313826,
|
| 1246 |
+
"learning_rate": 4.322727117869951e-07,
|
| 1247 |
+
"loss": 0.7187,
|
| 1248 |
+
"step": 177
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 2.6435643564356437,
|
| 1252 |
+
"grad_norm": 0.520468554829645,
|
| 1253 |
+
"learning_rate": 3.9747573273779816e-07,
|
| 1254 |
+
"loss": 0.6922,
|
| 1255 |
+
"step": 178
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 2.6584158415841586,
|
| 1259 |
+
"grad_norm": 0.48040006877742775,
|
| 1260 |
+
"learning_rate": 3.6408072716606346e-07,
|
| 1261 |
+
"loss": 0.6394,
|
| 1262 |
+
"step": 179
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 2.6732673267326734,
|
| 1266 |
+
"grad_norm": 0.49771916703934643,
|
| 1267 |
+
"learning_rate": 3.320978675139919e-07,
|
| 1268 |
+
"loss": 0.6555,
|
| 1269 |
+
"step": 180
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 2.6881188118811883,
|
| 1273 |
+
"grad_norm": 0.4985224870159162,
|
| 1274 |
+
"learning_rate": 3.015368960704584e-07,
|
| 1275 |
+
"loss": 0.6621,
|
| 1276 |
+
"step": 181
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 2.7029702970297027,
|
| 1280 |
+
"grad_norm": 0.5032558199370275,
|
| 1281 |
+
"learning_rate": 2.724071220034158e-07,
|
| 1282 |
+
"loss": 0.7285,
|
| 1283 |
+
"step": 182
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 2.717821782178218,
|
| 1287 |
+
"grad_norm": 0.4881972665265835,
|
| 1288 |
+
"learning_rate": 2.447174185242324e-07,
|
| 1289 |
+
"loss": 0.6426,
|
| 1290 |
+
"step": 183
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 2.7326732673267324,
|
| 1294 |
+
"grad_norm": 0.4828031422366926,
|
| 1295 |
+
"learning_rate": 2.1847622018482283e-07,
|
| 1296 |
+
"loss": 0.6782,
|
| 1297 |
+
"step": 184
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 2.7475247524752477,
|
| 1301 |
+
"grad_norm": 0.47484851901453023,
|
| 1302 |
+
"learning_rate": 1.9369152030840553e-07,
|
| 1303 |
+
"loss": 0.6326,
|
| 1304 |
+
"step": 185
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 2.762376237623762,
|
| 1308 |
+
"grad_norm": 0.5311388807144789,
|
| 1309 |
+
"learning_rate": 1.7037086855465902e-07,
|
| 1310 |
+
"loss": 0.7419,
|
| 1311 |
+
"step": 186
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 2.7772277227722775,
|
| 1315 |
+
"grad_norm": 0.4614470612824122,
|
| 1316 |
+
"learning_rate": 1.4852136862001766e-07,
|
| 1317 |
+
"loss": 0.6123,
|
| 1318 |
+
"step": 187
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 2.792079207920792,
|
| 1322 |
+
"grad_norm": 0.48962299396889825,
|
| 1323 |
+
"learning_rate": 1.2814967607382433e-07,
|
| 1324 |
+
"loss": 0.7775,
|
| 1325 |
+
"step": 188
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 2.806930693069307,
|
| 1329 |
+
"grad_norm": 0.5121698180749854,
|
| 1330 |
+
"learning_rate": 1.0926199633097156e-07,
|
| 1331 |
+
"loss": 0.6253,
|
| 1332 |
+
"step": 189
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 2.8217821782178216,
|
| 1336 |
+
"grad_norm": 0.5454806153588347,
|
| 1337 |
+
"learning_rate": 9.186408276168012e-08,
|
| 1338 |
+
"loss": 0.6817,
|
| 1339 |
+
"step": 190
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 2.8366336633663365,
|
| 1343 |
+
"grad_norm": 0.47926294627215255,
|
| 1344 |
+
"learning_rate": 7.59612349389599e-08,
|
| 1345 |
+
"loss": 0.6702,
|
| 1346 |
+
"step": 191
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 2.8514851485148514,
|
| 1350 |
+
"grad_norm": 0.488962969794833,
|
| 1351 |
+
"learning_rate": 6.15582970243117e-08,
|
| 1352 |
+
"loss": 0.6687,
|
| 1353 |
+
"step": 192
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 2.866336633663366,
|
| 1357 |
+
"grad_norm": 0.5042360939591695,
|
| 1358 |
+
"learning_rate": 4.865965629214819e-08,
|
| 1359 |
+
"loss": 0.6828,
|
| 1360 |
+
"step": 193
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 2.881188118811881,
|
| 1364 |
+
"grad_norm": 0.4737639717650882,
|
| 1365 |
+
"learning_rate": 3.726924179339009e-08,
|
| 1366 |
+
"loss": 0.6109,
|
| 1367 |
+
"step": 194
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 2.896039603960396,
|
| 1371 |
+
"grad_norm": 0.5367048842660397,
|
| 1372 |
+
"learning_rate": 2.7390523158633552e-08,
|
| 1373 |
+
"loss": 0.6467,
|
| 1374 |
+
"step": 195
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 2.910891089108911,
|
| 1378 |
+
"grad_norm": 0.5043896642226987,
|
| 1379 |
+
"learning_rate": 1.9026509541272276e-08,
|
| 1380 |
+
"loss": 0.7169,
|
| 1381 |
+
"step": 196
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 2.9257425742574257,
|
| 1385 |
+
"grad_norm": 0.4791625292476249,
|
| 1386 |
+
"learning_rate": 1.2179748700879013e-08,
|
| 1387 |
+
"loss": 0.7351,
|
| 1388 |
+
"step": 197
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 2.9405940594059405,
|
| 1392 |
+
"grad_norm": 0.5102082840215327,
|
| 1393 |
+
"learning_rate": 6.852326227130835e-09,
|
| 1394 |
+
"loss": 0.6391,
|
| 1395 |
+
"step": 198
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 2.9554455445544554,
|
| 1399 |
+
"grad_norm": 0.4865097004583583,
|
| 1400 |
+
"learning_rate": 3.0458649045211897e-09,
|
| 1401 |
+
"loss": 0.6674,
|
| 1402 |
+
"step": 199
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 2.9702970297029703,
|
| 1406 |
+
"grad_norm": 0.5133741423875121,
|
| 1407 |
+
"learning_rate": 7.615242180436521e-10,
|
| 1408 |
+
"loss": 0.7427,
|
| 1409 |
+
"step": 200
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 2.985148514851485,
|
| 1413 |
+
"grad_norm": 0.4923182359179608,
|
| 1414 |
+
"learning_rate": 0.0,
|
| 1415 |
+
"loss": 0.595,
|
| 1416 |
+
"step": 201
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 2.985148514851485,
|
| 1420 |
+
"step": 201,
|
| 1421 |
+
"total_flos": 138721009057792.0,
|
| 1422 |
+
"train_loss": 0.7744821606583856,
|
| 1423 |
+
"train_runtime": 2765.7022,
|
| 1424 |
+
"train_samples_per_second": 6.994,
|
| 1425 |
+
"train_steps_per_second": 0.073
|
| 1426 |
+
}
|
| 1427 |
+
],
|
| 1428 |
+
"logging_steps": 1,
|
| 1429 |
+
"max_steps": 201,
|
| 1430 |
+
"num_input_tokens_seen": 0,
|
| 1431 |
+
"num_train_epochs": 3,
|
| 1432 |
+
"save_steps": 500,
|
| 1433 |
+
"stateful_callbacks": {
|
| 1434 |
+
"TrainerControl": {
|
| 1435 |
+
"args": {
|
| 1436 |
+
"should_epoch_stop": false,
|
| 1437 |
+
"should_evaluate": false,
|
| 1438 |
+
"should_log": false,
|
| 1439 |
+
"should_save": true,
|
| 1440 |
+
"should_training_stop": true
|
| 1441 |
+
},
|
| 1442 |
+
"attributes": {}
|
| 1443 |
+
}
|
| 1444 |
+
},
|
| 1445 |
+
"total_flos": 138721009057792.0,
|
| 1446 |
+
"train_batch_size": 1,
|
| 1447 |
+
"trial_name": null,
|
| 1448 |
+
"trial_params": null
|
| 1449 |
+
}
|
training_loss.png
ADDED
|