End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +1260 -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: llama3-1_8b_multiple_samples_majority_consensus_numina_aime
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# llama3-1_8b_multiple_samples_majority_consensus_numina_aime
|
| 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: llama3-1_8b_multiple_samples_majority_consensus_numina_aime
|
|
|
|
| 16 |
|
| 17 |
# llama3-1_8b_multiple_samples_majority_consensus_numina_aime
|
| 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_majority_consensus_numina_aime dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.965909090909091,
|
| 3 |
+
"total_flos": 156886855483392.0,
|
| 4 |
+
"train_loss": 0.7380151625337272,
|
| 5 |
+
"train_runtime": 2697.8392,
|
| 6 |
+
"train_samples_per_second": 6.228,
|
| 7 |
+
"train_steps_per_second": 0.064
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.965909090909091,
|
| 3 |
+
"total_flos": 156886855483392.0,
|
| 4 |
+
"train_loss": 0.7380151625337272,
|
| 5 |
+
"train_runtime": 2697.8392,
|
| 6 |
+
"train_samples_per_second": 6.228,
|
| 7 |
+
"train_steps_per_second": 0.064
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1260 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.965909090909091,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 174,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.017045454545454544,
|
| 13 |
+
"grad_norm": 7.22884205408755,
|
| 14 |
+
"learning_rate": 5.555555555555555e-07,
|
| 15 |
+
"loss": 1.1159,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.03409090909090909,
|
| 20 |
+
"grad_norm": 6.86377349527473,
|
| 21 |
+
"learning_rate": 1.111111111111111e-06,
|
| 22 |
+
"loss": 1.0455,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.05113636363636364,
|
| 27 |
+
"grad_norm": 7.199961151138557,
|
| 28 |
+
"learning_rate": 1.6666666666666667e-06,
|
| 29 |
+
"loss": 1.1275,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.06818181818181818,
|
| 34 |
+
"grad_norm": 7.268274547750973,
|
| 35 |
+
"learning_rate": 2.222222222222222e-06,
|
| 36 |
+
"loss": 1.1096,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.08522727272727272,
|
| 41 |
+
"grad_norm": 6.311407588180345,
|
| 42 |
+
"learning_rate": 2.7777777777777783e-06,
|
| 43 |
+
"loss": 1.0481,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.10227272727272728,
|
| 48 |
+
"grad_norm": 5.325136507507456,
|
| 49 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 50 |
+
"loss": 1.0745,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.11931818181818182,
|
| 55 |
+
"grad_norm": 3.204819984360326,
|
| 56 |
+
"learning_rate": 3.88888888888889e-06,
|
| 57 |
+
"loss": 0.9787,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.13636363636363635,
|
| 62 |
+
"grad_norm": 2.6398476108217075,
|
| 63 |
+
"learning_rate": 4.444444444444444e-06,
|
| 64 |
+
"loss": 0.9367,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.1534090909090909,
|
| 69 |
+
"grad_norm": 2.5518759893438645,
|
| 70 |
+
"learning_rate": 5e-06,
|
| 71 |
+
"loss": 0.9116,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.17045454545454544,
|
| 76 |
+
"grad_norm": 5.223827384885404,
|
| 77 |
+
"learning_rate": 5.555555555555557e-06,
|
| 78 |
+
"loss": 0.9835,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.1875,
|
| 83 |
+
"grad_norm": 4.47133774615716,
|
| 84 |
+
"learning_rate": 6.111111111111112e-06,
|
| 85 |
+
"loss": 0.9244,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.20454545454545456,
|
| 90 |
+
"grad_norm": 4.277259377499211,
|
| 91 |
+
"learning_rate": 6.666666666666667e-06,
|
| 92 |
+
"loss": 0.9496,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.2215909090909091,
|
| 97 |
+
"grad_norm": 3.526152904409924,
|
| 98 |
+
"learning_rate": 7.222222222222223e-06,
|
| 99 |
+
"loss": 0.8649,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.23863636363636365,
|
| 104 |
+
"grad_norm": 3.259182755810135,
|
| 105 |
+
"learning_rate": 7.77777777777778e-06,
|
| 106 |
+
"loss": 0.882,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.2556818181818182,
|
| 111 |
+
"grad_norm": 2.657169823270014,
|
| 112 |
+
"learning_rate": 8.333333333333334e-06,
|
| 113 |
+
"loss": 0.9532,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.2727272727272727,
|
| 118 |
+
"grad_norm": 2.2469055281791768,
|
| 119 |
+
"learning_rate": 8.888888888888888e-06,
|
| 120 |
+
"loss": 0.8686,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.2897727272727273,
|
| 125 |
+
"grad_norm": 2.2961013306684492,
|
| 126 |
+
"learning_rate": 9.444444444444445e-06,
|
| 127 |
+
"loss": 0.9136,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.3068181818181818,
|
| 132 |
+
"grad_norm": 2.0321977080614575,
|
| 133 |
+
"learning_rate": 1e-05,
|
| 134 |
+
"loss": 0.8197,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.32386363636363635,
|
| 139 |
+
"grad_norm": 1.5442837234976816,
|
| 140 |
+
"learning_rate": 9.998986144924253e-06,
|
| 141 |
+
"loss": 0.7929,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.3409090909090909,
|
| 146 |
+
"grad_norm": 1.3959797656829187,
|
| 147 |
+
"learning_rate": 9.995944990857848e-06,
|
| 148 |
+
"loss": 0.746,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.35795454545454547,
|
| 153 |
+
"grad_norm": 1.6413702216042307,
|
| 154 |
+
"learning_rate": 9.990877771116588e-06,
|
| 155 |
+
"loss": 0.8195,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.375,
|
| 160 |
+
"grad_norm": 1.1455825686481986,
|
| 161 |
+
"learning_rate": 9.983786540671052e-06,
|
| 162 |
+
"loss": 0.7925,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.39204545454545453,
|
| 167 |
+
"grad_norm": 1.1413214191419678,
|
| 168 |
+
"learning_rate": 9.974674175313228e-06,
|
| 169 |
+
"loss": 0.8086,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.4090909090909091,
|
| 174 |
+
"grad_norm": 1.1533147121145144,
|
| 175 |
+
"learning_rate": 9.96354437049027e-06,
|
| 176 |
+
"loss": 0.8001,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.42613636363636365,
|
| 181 |
+
"grad_norm": 0.9882676326329094,
|
| 182 |
+
"learning_rate": 9.950401639805822e-06,
|
| 183 |
+
"loss": 0.868,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.4431818181818182,
|
| 188 |
+
"grad_norm": 1.028373201431852,
|
| 189 |
+
"learning_rate": 9.935251313189564e-06,
|
| 190 |
+
"loss": 0.7855,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.4602272727272727,
|
| 195 |
+
"grad_norm": 1.049228042355448,
|
| 196 |
+
"learning_rate": 9.91809953473572e-06,
|
| 197 |
+
"loss": 0.7744,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.4772727272727273,
|
| 202 |
+
"grad_norm": 0.8404995559488506,
|
| 203 |
+
"learning_rate": 9.89895326021134e-06,
|
| 204 |
+
"loss": 0.7396,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.4943181818181818,
|
| 209 |
+
"grad_norm": 0.9078468037297426,
|
| 210 |
+
"learning_rate": 9.87782025423547e-06,
|
| 211 |
+
"loss": 0.8565,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.5113636363636364,
|
| 216 |
+
"grad_norm": 0.8508053415926495,
|
| 217 |
+
"learning_rate": 9.854709087130261e-06,
|
| 218 |
+
"loss": 0.729,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.5284090909090909,
|
| 223 |
+
"grad_norm": 0.944676094285407,
|
| 224 |
+
"learning_rate": 9.829629131445342e-06,
|
| 225 |
+
"loss": 0.7635,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.5454545454545454,
|
| 230 |
+
"grad_norm": 0.7058532649010517,
|
| 231 |
+
"learning_rate": 9.802590558156863e-06,
|
| 232 |
+
"loss": 0.7878,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.5625,
|
| 237 |
+
"grad_norm": 0.8621390038765169,
|
| 238 |
+
"learning_rate": 9.77360433254273e-06,
|
| 239 |
+
"loss": 0.8099,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.5795454545454546,
|
| 244 |
+
"grad_norm": 0.8073345495598823,
|
| 245 |
+
"learning_rate": 9.742682209735727e-06,
|
| 246 |
+
"loss": 0.7863,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.5965909090909091,
|
| 251 |
+
"grad_norm": 0.6669987952697678,
|
| 252 |
+
"learning_rate": 9.709836729956326e-06,
|
| 253 |
+
"loss": 0.7973,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.6136363636363636,
|
| 258 |
+
"grad_norm": 0.8486755092214402,
|
| 259 |
+
"learning_rate": 9.675081213427076e-06,
|
| 260 |
+
"loss": 0.7459,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.6306818181818182,
|
| 265 |
+
"grad_norm": 0.7143187741160664,
|
| 266 |
+
"learning_rate": 9.638429754970715e-06,
|
| 267 |
+
"loss": 0.7543,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.6477272727272727,
|
| 272 |
+
"grad_norm": 0.6848079020913995,
|
| 273 |
+
"learning_rate": 9.599897218294122e-06,
|
| 274 |
+
"loss": 0.8018,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.6647727272727273,
|
| 279 |
+
"grad_norm": 0.853749579569145,
|
| 280 |
+
"learning_rate": 9.55949922996045e-06,
|
| 281 |
+
"loss": 0.7145,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.6818181818181818,
|
| 286 |
+
"grad_norm": 0.68372338772216,
|
| 287 |
+
"learning_rate": 9.517252173051912e-06,
|
| 288 |
+
"loss": 0.764,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.6988636363636364,
|
| 293 |
+
"grad_norm": 0.6422340925591769,
|
| 294 |
+
"learning_rate": 9.473173180525737e-06,
|
| 295 |
+
"loss": 0.7332,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.7159090909090909,
|
| 300 |
+
"grad_norm": 0.7261628443441004,
|
| 301 |
+
"learning_rate": 9.427280128266049e-06,
|
| 302 |
+
"loss": 0.7428,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.7329545454545454,
|
| 307 |
+
"grad_norm": 0.7702313145051908,
|
| 308 |
+
"learning_rate": 9.37959162783444e-06,
|
| 309 |
+
"loss": 0.7859,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.75,
|
| 314 |
+
"grad_norm": 0.6747045160311267,
|
| 315 |
+
"learning_rate": 9.330127018922195e-06,
|
| 316 |
+
"loss": 0.824,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.7670454545454546,
|
| 321 |
+
"grad_norm": 0.7223692043597745,
|
| 322 |
+
"learning_rate": 9.278906361507238e-06,
|
| 323 |
+
"loss": 0.7605,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.7840909090909091,
|
| 328 |
+
"grad_norm": 0.578610691292999,
|
| 329 |
+
"learning_rate": 9.225950427718974e-06,
|
| 330 |
+
"loss": 0.7546,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.8011363636363636,
|
| 335 |
+
"grad_norm": 0.7399134643017758,
|
| 336 |
+
"learning_rate": 9.171280693414307e-06,
|
| 337 |
+
"loss": 0.7068,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.8181818181818182,
|
| 342 |
+
"grad_norm": 0.6651749348569863,
|
| 343 |
+
"learning_rate": 9.114919329468283e-06,
|
| 344 |
+
"loss": 0.7707,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.8352272727272727,
|
| 349 |
+
"grad_norm": 0.6681727962907063,
|
| 350 |
+
"learning_rate": 9.056889192782865e-06,
|
| 351 |
+
"loss": 0.7423,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.8522727272727273,
|
| 356 |
+
"grad_norm": 0.5989175339145305,
|
| 357 |
+
"learning_rate": 8.997213817017508e-06,
|
| 358 |
+
"loss": 0.7367,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.8693181818181818,
|
| 363 |
+
"grad_norm": 0.6415631156829461,
|
| 364 |
+
"learning_rate": 8.935917403045251e-06,
|
| 365 |
+
"loss": 0.7742,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.8863636363636364,
|
| 370 |
+
"grad_norm": 0.7053287962999208,
|
| 371 |
+
"learning_rate": 8.873024809138272e-06,
|
| 372 |
+
"loss": 0.8004,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.9034090909090909,
|
| 377 |
+
"grad_norm": 0.6616877102090415,
|
| 378 |
+
"learning_rate": 8.808561540886796e-06,
|
| 379 |
+
"loss": 0.8331,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.9204545454545454,
|
| 384 |
+
"grad_norm": 0.6686807030220209,
|
| 385 |
+
"learning_rate": 8.742553740855507e-06,
|
| 386 |
+
"loss": 0.7622,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.9375,
|
| 391 |
+
"grad_norm": 0.6207828741528636,
|
| 392 |
+
"learning_rate": 8.675028177981643e-06,
|
| 393 |
+
"loss": 0.7329,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.9545454545454546,
|
| 398 |
+
"grad_norm": 0.5650546394483587,
|
| 399 |
+
"learning_rate": 8.606012236719073e-06,
|
| 400 |
+
"loss": 0.7638,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.9715909090909091,
|
| 405 |
+
"grad_norm": 0.6124784723851092,
|
| 406 |
+
"learning_rate": 8.535533905932739e-06,
|
| 407 |
+
"loss": 0.7341,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.9886363636363636,
|
| 412 |
+
"grad_norm": 0.6052340709182291,
|
| 413 |
+
"learning_rate": 8.463621767547998e-06,
|
| 414 |
+
"loss": 0.7457,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 1.0056818181818181,
|
| 419 |
+
"grad_norm": 0.8052906258453199,
|
| 420 |
+
"learning_rate": 8.390304984959455e-06,
|
| 421 |
+
"loss": 0.939,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.0227272727272727,
|
| 426 |
+
"grad_norm": 0.6376926058729759,
|
| 427 |
+
"learning_rate": 8.315613291203977e-06,
|
| 428 |
+
"loss": 0.7367,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.0397727272727273,
|
| 433 |
+
"grad_norm": 0.6369503379591582,
|
| 434 |
+
"learning_rate": 8.239576976902694e-06,
|
| 435 |
+
"loss": 0.7449,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 1.0568181818181819,
|
| 440 |
+
"grad_norm": 0.6969242917426808,
|
| 441 |
+
"learning_rate": 8.162226877976886e-06,
|
| 442 |
+
"loss": 0.7259,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.0738636363636365,
|
| 447 |
+
"grad_norm": 0.6530544217263711,
|
| 448 |
+
"learning_rate": 8.083594363142717e-06,
|
| 449 |
+
"loss": 0.646,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.0909090909090908,
|
| 454 |
+
"grad_norm": 0.5900438510967748,
|
| 455 |
+
"learning_rate": 8.003711321189895e-06,
|
| 456 |
+
"loss": 0.6842,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 1.1079545454545454,
|
| 461 |
+
"grad_norm": 0.6284392353104462,
|
| 462 |
+
"learning_rate": 7.922610148049445e-06,
|
| 463 |
+
"loss": 0.8002,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.125,
|
| 468 |
+
"grad_norm": 0.6494425439689134,
|
| 469 |
+
"learning_rate": 7.84032373365578e-06,
|
| 470 |
+
"loss": 0.638,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.1420454545454546,
|
| 475 |
+
"grad_norm": 0.5499044253465919,
|
| 476 |
+
"learning_rate": 7.75688544860846e-06,
|
| 477 |
+
"loss": 0.6289,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 1.1590909090909092,
|
| 482 |
+
"grad_norm": 0.6392668714240907,
|
| 483 |
+
"learning_rate": 7.672329130639007e-06,
|
| 484 |
+
"loss": 0.7572,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 1.1761363636363638,
|
| 489 |
+
"grad_norm": 0.673210138953056,
|
| 490 |
+
"learning_rate": 7.586689070888284e-06,
|
| 491 |
+
"loss": 0.6524,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 1.1931818181818181,
|
| 496 |
+
"grad_norm": 0.6410447658297229,
|
| 497 |
+
"learning_rate": 7.500000000000001e-06,
|
| 498 |
+
"loss": 0.7362,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 1.2102272727272727,
|
| 503 |
+
"grad_norm": 0.6785817657314511,
|
| 504 |
+
"learning_rate": 7.412297074035968e-06,
|
| 505 |
+
"loss": 0.7131,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.2272727272727273,
|
| 510 |
+
"grad_norm": 0.861453272486042,
|
| 511 |
+
"learning_rate": 7.323615860218844e-06,
|
| 512 |
+
"loss": 0.7169,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.2443181818181819,
|
| 517 |
+
"grad_norm": 0.611947189690942,
|
| 518 |
+
"learning_rate": 7.2339923225081296e-06,
|
| 519 |
+
"loss": 0.7185,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.2613636363636362,
|
| 524 |
+
"grad_norm": 0.6501253363478586,
|
| 525 |
+
"learning_rate": 7.143462807015271e-06,
|
| 526 |
+
"loss": 0.6616,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.2784090909090908,
|
| 531 |
+
"grad_norm": 0.715695504058172,
|
| 532 |
+
"learning_rate": 7.052064027263785e-06,
|
| 533 |
+
"loss": 0.7005,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.2954545454545454,
|
| 538 |
+
"grad_norm": 0.7073752700474762,
|
| 539 |
+
"learning_rate": 6.959833049300376e-06,
|
| 540 |
+
"loss": 0.7879,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.3125,
|
| 545 |
+
"grad_norm": 0.49068564720807656,
|
| 546 |
+
"learning_rate": 6.8668072766631054e-06,
|
| 547 |
+
"loss": 0.6314,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.3295454545454546,
|
| 552 |
+
"grad_norm": 0.7803765124238339,
|
| 553 |
+
"learning_rate": 6.773024435212678e-06,
|
| 554 |
+
"loss": 0.7851,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.3465909090909092,
|
| 559 |
+
"grad_norm": 0.5942335579737438,
|
| 560 |
+
"learning_rate": 6.678522557833025e-06,
|
| 561 |
+
"loss": 0.689,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.3636363636363638,
|
| 566 |
+
"grad_norm": 0.5176233208142944,
|
| 567 |
+
"learning_rate": 6.583339969007364e-06,
|
| 568 |
+
"loss": 0.6542,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.3806818181818181,
|
| 573 |
+
"grad_norm": 0.607753727654389,
|
| 574 |
+
"learning_rate": 6.487515269276015e-06,
|
| 575 |
+
"loss": 0.7534,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.3977272727272727,
|
| 580 |
+
"grad_norm": 0.5409054512847689,
|
| 581 |
+
"learning_rate": 6.391087319582264e-06,
|
| 582 |
+
"loss": 0.6305,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 1.4147727272727273,
|
| 587 |
+
"grad_norm": 0.5071385453642557,
|
| 588 |
+
"learning_rate": 6.294095225512604e-06,
|
| 589 |
+
"loss": 0.7589,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.4318181818181819,
|
| 594 |
+
"grad_norm": 0.5143547906358554,
|
| 595 |
+
"learning_rate": 6.1965783214377895e-06,
|
| 596 |
+
"loss": 0.7914,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.4488636363636362,
|
| 601 |
+
"grad_norm": 0.5071795878844763,
|
| 602 |
+
"learning_rate": 6.0985761545610865e-06,
|
| 603 |
+
"loss": 0.6643,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.4659090909090908,
|
| 608 |
+
"grad_norm": 0.5505402808974502,
|
| 609 |
+
"learning_rate": 6.000128468880223e-06,
|
| 610 |
+
"loss": 0.7187,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.4829545454545454,
|
| 615 |
+
"grad_norm": 0.5577932417601431,
|
| 616 |
+
"learning_rate": 5.90127518906953e-06,
|
| 617 |
+
"loss": 0.6295,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.5,
|
| 622 |
+
"grad_norm": 0.6475715595827016,
|
| 623 |
+
"learning_rate": 5.8020564042888015e-06,
|
| 624 |
+
"loss": 0.7056,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.5170454545454546,
|
| 629 |
+
"grad_norm": 0.5835532211565827,
|
| 630 |
+
"learning_rate": 5.7025123519254644e-06,
|
| 631 |
+
"loss": 0.7256,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.5340909090909092,
|
| 636 |
+
"grad_norm": 0.5415921745872375,
|
| 637 |
+
"learning_rate": 5.6026834012766155e-06,
|
| 638 |
+
"loss": 0.7471,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.5511363636363638,
|
| 643 |
+
"grad_norm": 0.5833270165675741,
|
| 644 |
+
"learning_rate": 5.502610037177586e-06,
|
| 645 |
+
"loss": 0.7633,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.5681818181818183,
|
| 650 |
+
"grad_norm": 0.560199988553917,
|
| 651 |
+
"learning_rate": 5.402332843583631e-06,
|
| 652 |
+
"loss": 0.6595,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.5852272727272727,
|
| 657 |
+
"grad_norm": 0.4939855321494504,
|
| 658 |
+
"learning_rate": 5.301892487111431e-06,
|
| 659 |
+
"loss": 0.6958,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.6022727272727273,
|
| 664 |
+
"grad_norm": 0.5378643220876148,
|
| 665 |
+
"learning_rate": 5.201329700547077e-06,
|
| 666 |
+
"loss": 0.6934,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.6193181818181817,
|
| 671 |
+
"grad_norm": 0.5420525607884883,
|
| 672 |
+
"learning_rate": 5.100685266327202e-06,
|
| 673 |
+
"loss": 0.6365,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.6363636363636362,
|
| 678 |
+
"grad_norm": 0.4520550820837634,
|
| 679 |
+
"learning_rate": 5e-06,
|
| 680 |
+
"loss": 0.6338,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.6534090909090908,
|
| 685 |
+
"grad_norm": 0.5117553753106799,
|
| 686 |
+
"learning_rate": 4.8993147336728e-06,
|
| 687 |
+
"loss": 0.7532,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.6704545454545454,
|
| 692 |
+
"grad_norm": 0.5106162671673076,
|
| 693 |
+
"learning_rate": 4.798670299452926e-06,
|
| 694 |
+
"loss": 0.7011,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 1.6875,
|
| 699 |
+
"grad_norm": 0.47075334035417565,
|
| 700 |
+
"learning_rate": 4.69810751288857e-06,
|
| 701 |
+
"loss": 0.6379,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.7045454545454546,
|
| 706 |
+
"grad_norm": 0.5343852849626032,
|
| 707 |
+
"learning_rate": 4.597667156416371e-06,
|
| 708 |
+
"loss": 0.7058,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.7215909090909092,
|
| 713 |
+
"grad_norm": 0.5025252513851014,
|
| 714 |
+
"learning_rate": 4.497389962822416e-06,
|
| 715 |
+
"loss": 0.7518,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 1.7386363636363638,
|
| 720 |
+
"grad_norm": 0.4973905372002931,
|
| 721 |
+
"learning_rate": 4.397316598723385e-06,
|
| 722 |
+
"loss": 0.7153,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.7556818181818183,
|
| 727 |
+
"grad_norm": 0.46247569289594587,
|
| 728 |
+
"learning_rate": 4.297487648074538e-06,
|
| 729 |
+
"loss": 0.6349,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.7727272727272727,
|
| 734 |
+
"grad_norm": 0.48340291588569545,
|
| 735 |
+
"learning_rate": 4.1979435957111984e-06,
|
| 736 |
+
"loss": 0.7174,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.7897727272727273,
|
| 741 |
+
"grad_norm": 0.45562405643253756,
|
| 742 |
+
"learning_rate": 4.098724810930472e-06,
|
| 743 |
+
"loss": 0.6847,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.8068181818181817,
|
| 748 |
+
"grad_norm": 0.47781922446221436,
|
| 749 |
+
"learning_rate": 3.999871531119779e-06,
|
| 750 |
+
"loss": 0.7162,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.8238636363636362,
|
| 755 |
+
"grad_norm": 0.4315069745006211,
|
| 756 |
+
"learning_rate": 3.901423845438916e-06,
|
| 757 |
+
"loss": 0.6691,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.8409090909090908,
|
| 762 |
+
"grad_norm": 0.47883228124204524,
|
| 763 |
+
"learning_rate": 3.803421678562213e-06,
|
| 764 |
+
"loss": 0.7257,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.8579545454545454,
|
| 769 |
+
"grad_norm": 0.5320184023237785,
|
| 770 |
+
"learning_rate": 3.705904774487396e-06,
|
| 771 |
+
"loss": 0.7532,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 1.875,
|
| 776 |
+
"grad_norm": 0.4269725257899147,
|
| 777 |
+
"learning_rate": 3.6089126804177373e-06,
|
| 778 |
+
"loss": 0.6863,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.8920454545454546,
|
| 783 |
+
"grad_norm": 0.4583005565763506,
|
| 784 |
+
"learning_rate": 3.5124847307239863e-06,
|
| 785 |
+
"loss": 0.7502,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.9090909090909092,
|
| 790 |
+
"grad_norm": 0.4486844352174395,
|
| 791 |
+
"learning_rate": 3.416660030992639e-06,
|
| 792 |
+
"loss": 0.6897,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.9261363636363638,
|
| 797 |
+
"grad_norm": 0.49053197217486366,
|
| 798 |
+
"learning_rate": 3.3214774421669777e-06,
|
| 799 |
+
"loss": 0.698,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 1.9431818181818183,
|
| 804 |
+
"grad_norm": 0.5128637973645126,
|
| 805 |
+
"learning_rate": 3.226975564787322e-06,
|
| 806 |
+
"loss": 0.6907,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.9602272727272727,
|
| 811 |
+
"grad_norm": 0.478047879056811,
|
| 812 |
+
"learning_rate": 3.1331927233368954e-06,
|
| 813 |
+
"loss": 0.7661,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 1.9772727272727273,
|
| 818 |
+
"grad_norm": 0.4387651831852447,
|
| 819 |
+
"learning_rate": 3.040166950699626e-06,
|
| 820 |
+
"loss": 0.6683,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 1.9943181818181817,
|
| 825 |
+
"grad_norm": 0.5998562328424022,
|
| 826 |
+
"learning_rate": 2.947935972736217e-06,
|
| 827 |
+
"loss": 0.8983,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 2.0113636363636362,
|
| 832 |
+
"grad_norm": 0.5630847402650452,
|
| 833 |
+
"learning_rate": 2.8565371929847286e-06,
|
| 834 |
+
"loss": 0.6758,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 2.028409090909091,
|
| 839 |
+
"grad_norm": 0.4489743674974812,
|
| 840 |
+
"learning_rate": 2.766007677491871e-06,
|
| 841 |
+
"loss": 0.6843,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 2.0454545454545454,
|
| 846 |
+
"grad_norm": 0.4457573392562645,
|
| 847 |
+
"learning_rate": 2.6763841397811576e-06,
|
| 848 |
+
"loss": 0.6327,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 2.0625,
|
| 853 |
+
"grad_norm": 0.5634916203600439,
|
| 854 |
+
"learning_rate": 2.587702925964034e-06,
|
| 855 |
+
"loss": 0.6627,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 2.0795454545454546,
|
| 860 |
+
"grad_norm": 0.4707269296382247,
|
| 861 |
+
"learning_rate": 2.5000000000000015e-06,
|
| 862 |
+
"loss": 0.7272,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 2.096590909090909,
|
| 867 |
+
"grad_norm": 0.443373403354557,
|
| 868 |
+
"learning_rate": 2.4133109291117156e-06,
|
| 869 |
+
"loss": 0.6195,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 2.1136363636363638,
|
| 874 |
+
"grad_norm": 0.46908613730040055,
|
| 875 |
+
"learning_rate": 2.3276708693609947e-06,
|
| 876 |
+
"loss": 0.5704,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 2.1306818181818183,
|
| 881 |
+
"grad_norm": 0.4105495278728908,
|
| 882 |
+
"learning_rate": 2.243114551391542e-06,
|
| 883 |
+
"loss": 0.711,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 2.147727272727273,
|
| 888 |
+
"grad_norm": 0.537311901769593,
|
| 889 |
+
"learning_rate": 2.159676266344222e-06,
|
| 890 |
+
"loss": 0.7541,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 2.164772727272727,
|
| 895 |
+
"grad_norm": 0.5468018420551715,
|
| 896 |
+
"learning_rate": 2.077389851950557e-06,
|
| 897 |
+
"loss": 0.5964,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 2.1818181818181817,
|
| 902 |
+
"grad_norm": 0.5124295355078099,
|
| 903 |
+
"learning_rate": 1.996288678810105e-06,
|
| 904 |
+
"loss": 0.6619,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 2.1988636363636362,
|
| 909 |
+
"grad_norm": 0.4715818069175043,
|
| 910 |
+
"learning_rate": 1.9164056368572847e-06,
|
| 911 |
+
"loss": 0.6833,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 2.215909090909091,
|
| 916 |
+
"grad_norm": 0.48951497017695567,
|
| 917 |
+
"learning_rate": 1.8377731220231144e-06,
|
| 918 |
+
"loss": 0.6855,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 2.2329545454545454,
|
| 923 |
+
"grad_norm": 0.42265291988632153,
|
| 924 |
+
"learning_rate": 1.7604230230973068e-06,
|
| 925 |
+
"loss": 0.6424,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 2.25,
|
| 930 |
+
"grad_norm": 0.4650605098758252,
|
| 931 |
+
"learning_rate": 1.6843867087960252e-06,
|
| 932 |
+
"loss": 0.6231,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 2.2670454545454546,
|
| 937 |
+
"grad_norm": 0.4143527777268036,
|
| 938 |
+
"learning_rate": 1.6096950150405454e-06,
|
| 939 |
+
"loss": 0.5598,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 2.284090909090909,
|
| 944 |
+
"grad_norm": 0.44107050291230937,
|
| 945 |
+
"learning_rate": 1.5363782324520033e-06,
|
| 946 |
+
"loss": 0.7221,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 2.3011363636363638,
|
| 951 |
+
"grad_norm": 0.445778553889928,
|
| 952 |
+
"learning_rate": 1.4644660940672628e-06,
|
| 953 |
+
"loss": 0.6413,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 2.3181818181818183,
|
| 958 |
+
"grad_norm": 0.4187405257211714,
|
| 959 |
+
"learning_rate": 1.3939877632809279e-06,
|
| 960 |
+
"loss": 0.6992,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 2.3352272727272725,
|
| 965 |
+
"grad_norm": 0.4350630455961759,
|
| 966 |
+
"learning_rate": 1.3249718220183583e-06,
|
| 967 |
+
"loss": 0.6878,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 2.3522727272727275,
|
| 972 |
+
"grad_norm": 0.393861708986206,
|
| 973 |
+
"learning_rate": 1.257446259144494e-06,
|
| 974 |
+
"loss": 0.6385,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 2.3693181818181817,
|
| 979 |
+
"grad_norm": 0.42310655150402887,
|
| 980 |
+
"learning_rate": 1.1914384591132045e-06,
|
| 981 |
+
"loss": 0.7421,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 2.3863636363636362,
|
| 986 |
+
"grad_norm": 0.40172644758715986,
|
| 987 |
+
"learning_rate": 1.1269751908617277e-06,
|
| 988 |
+
"loss": 0.647,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 2.403409090909091,
|
| 993 |
+
"grad_norm": 0.4418275610345151,
|
| 994 |
+
"learning_rate": 1.0640825969547498e-06,
|
| 995 |
+
"loss": 0.6702,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 2.4204545454545454,
|
| 1000 |
+
"grad_norm": 0.3802094194842585,
|
| 1001 |
+
"learning_rate": 1.0027861829824953e-06,
|
| 1002 |
+
"loss": 0.5888,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 2.4375,
|
| 1007 |
+
"grad_norm": 0.39698478453376557,
|
| 1008 |
+
"learning_rate": 9.431108072171346e-07,
|
| 1009 |
+
"loss": 0.7405,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 2.4545454545454546,
|
| 1014 |
+
"grad_norm": 0.4302235176734781,
|
| 1015 |
+
"learning_rate": 8.850806705317183e-07,
|
| 1016 |
+
"loss": 0.6819,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 2.471590909090909,
|
| 1021 |
+
"grad_norm": 0.4055826304794628,
|
| 1022 |
+
"learning_rate": 8.287193065856936e-07,
|
| 1023 |
+
"loss": 0.6332,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 2.4886363636363638,
|
| 1028 |
+
"grad_norm": 0.4307108144646676,
|
| 1029 |
+
"learning_rate": 7.740495722810271e-07,
|
| 1030 |
+
"loss": 0.676,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 2.5056818181818183,
|
| 1035 |
+
"grad_norm": 0.4295524075776934,
|
| 1036 |
+
"learning_rate": 7.210936384927631e-07,
|
| 1037 |
+
"loss": 0.7018,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 2.5227272727272725,
|
| 1042 |
+
"grad_norm": 0.3860805358590195,
|
| 1043 |
+
"learning_rate": 6.698729810778065e-07,
|
| 1044 |
+
"loss": 0.6894,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 2.5397727272727275,
|
| 1049 |
+
"grad_norm": 0.4334053053827782,
|
| 1050 |
+
"learning_rate": 6.204083721655607e-07,
|
| 1051 |
+
"loss": 0.645,
|
| 1052 |
+
"step": 149
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 2.5568181818181817,
|
| 1056 |
+
"grad_norm": 0.4287547792874842,
|
| 1057 |
+
"learning_rate": 5.727198717339511e-07,
|
| 1058 |
+
"loss": 0.7111,
|
| 1059 |
+
"step": 150
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 2.5738636363636362,
|
| 1063 |
+
"grad_norm": 0.3887625011714418,
|
| 1064 |
+
"learning_rate": 5.268268194742638e-07,
|
| 1065 |
+
"loss": 0.7216,
|
| 1066 |
+
"step": 151
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 2.590909090909091,
|
| 1070 |
+
"grad_norm": 0.3798899338475208,
|
| 1071 |
+
"learning_rate": 4.827478269480895e-07,
|
| 1072 |
+
"loss": 0.621,
|
| 1073 |
+
"step": 152
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 2.6079545454545454,
|
| 1077 |
+
"grad_norm": 0.45053111754260017,
|
| 1078 |
+
"learning_rate": 4.405007700395497e-07,
|
| 1079 |
+
"loss": 0.7521,
|
| 1080 |
+
"step": 153
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 2.625,
|
| 1084 |
+
"grad_norm": 0.377645018921979,
|
| 1085 |
+
"learning_rate": 4.001027817058789e-07,
|
| 1086 |
+
"loss": 0.6145,
|
| 1087 |
+
"step": 154
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 2.6420454545454546,
|
| 1091 |
+
"grad_norm": 0.3776664317185743,
|
| 1092 |
+
"learning_rate": 3.615702450292857e-07,
|
| 1093 |
+
"loss": 0.6278,
|
| 1094 |
+
"step": 155
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 2.659090909090909,
|
| 1098 |
+
"grad_norm": 0.4305890271008056,
|
| 1099 |
+
"learning_rate": 3.2491878657292643e-07,
|
| 1100 |
+
"loss": 0.7472,
|
| 1101 |
+
"step": 156
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 2.6761363636363638,
|
| 1105 |
+
"grad_norm": 0.40843066342237466,
|
| 1106 |
+
"learning_rate": 2.901632700436757e-07,
|
| 1107 |
+
"loss": 0.6258,
|
| 1108 |
+
"step": 157
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 2.6931818181818183,
|
| 1112 |
+
"grad_norm": 0.3956427977171968,
|
| 1113 |
+
"learning_rate": 2.573177902642726e-07,
|
| 1114 |
+
"loss": 0.6839,
|
| 1115 |
+
"step": 158
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 2.7102272727272725,
|
| 1119 |
+
"grad_norm": 0.41431945926782104,
|
| 1120 |
+
"learning_rate": 2.2639566745727203e-07,
|
| 1121 |
+
"loss": 0.6734,
|
| 1122 |
+
"step": 159
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 2.7272727272727275,
|
| 1126 |
+
"grad_norm": 0.3818344903770187,
|
| 1127 |
+
"learning_rate": 1.9740944184313882e-07,
|
| 1128 |
+
"loss": 0.6367,
|
| 1129 |
+
"step": 160
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 2.7443181818181817,
|
| 1133 |
+
"grad_norm": 0.38077075132026156,
|
| 1134 |
+
"learning_rate": 1.7037086855465902e-07,
|
| 1135 |
+
"loss": 0.632,
|
| 1136 |
+
"step": 161
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 2.7613636363636362,
|
| 1140 |
+
"grad_norm": 0.39006091928915276,
|
| 1141 |
+
"learning_rate": 1.4529091286973994e-07,
|
| 1142 |
+
"loss": 0.6924,
|
| 1143 |
+
"step": 162
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 2.778409090909091,
|
| 1147 |
+
"grad_norm": 0.38840487543638486,
|
| 1148 |
+
"learning_rate": 1.2217974576453072e-07,
|
| 1149 |
+
"loss": 0.7466,
|
| 1150 |
+
"step": 163
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 2.7954545454545454,
|
| 1154 |
+
"grad_norm": 0.45834263911645595,
|
| 1155 |
+
"learning_rate": 1.0104673978866164e-07,
|
| 1156 |
+
"loss": 0.6057,
|
| 1157 |
+
"step": 164
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 2.8125,
|
| 1161 |
+
"grad_norm": 0.38210612410412104,
|
| 1162 |
+
"learning_rate": 8.190046526428241e-08,
|
| 1163 |
+
"loss": 0.663,
|
| 1164 |
+
"step": 165
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 2.8295454545454546,
|
| 1168 |
+
"grad_norm": 0.38478210491106063,
|
| 1169 |
+
"learning_rate": 6.474868681043578e-08,
|
| 1170 |
+
"loss": 0.6762,
|
| 1171 |
+
"step": 166
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 2.846590909090909,
|
| 1175 |
+
"grad_norm": 0.3720363705810689,
|
| 1176 |
+
"learning_rate": 4.959836019417963e-08,
|
| 1177 |
+
"loss": 0.6105,
|
| 1178 |
+
"step": 167
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 2.8636363636363638,
|
| 1182 |
+
"grad_norm": 0.4440736370045247,
|
| 1183 |
+
"learning_rate": 3.645562950973014e-08,
|
| 1184 |
+
"loss": 0.7567,
|
| 1185 |
+
"step": 168
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 2.8806818181818183,
|
| 1189 |
+
"grad_norm": 0.381304638800026,
|
| 1190 |
+
"learning_rate": 2.5325824686772138e-08,
|
| 1191 |
+
"loss": 0.6174,
|
| 1192 |
+
"step": 169
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 2.8977272727272725,
|
| 1196 |
+
"grad_norm": 0.4156474533014312,
|
| 1197 |
+
"learning_rate": 1.6213459328950355e-08,
|
| 1198 |
+
"loss": 0.5918,
|
| 1199 |
+
"step": 170
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 2.9147727272727275,
|
| 1203 |
+
"grad_norm": 0.4459243063651079,
|
| 1204 |
+
"learning_rate": 9.12222888341252e-09,
|
| 1205 |
+
"loss": 0.693,
|
| 1206 |
+
"step": 171
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 2.9318181818181817,
|
| 1210 |
+
"grad_norm": 0.3705961074102094,
|
| 1211 |
+
"learning_rate": 4.055009142152066e-09,
|
| 1212 |
+
"loss": 0.6132,
|
| 1213 |
+
"step": 172
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 2.9488636363636362,
|
| 1217 |
+
"grad_norm": 0.3768879535202281,
|
| 1218 |
+
"learning_rate": 1.0138550757493592e-09,
|
| 1219 |
+
"loss": 0.6515,
|
| 1220 |
+
"step": 173
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 2.965909090909091,
|
| 1224 |
+
"grad_norm": 0.39814357318394317,
|
| 1225 |
+
"learning_rate": 0.0,
|
| 1226 |
+
"loss": 0.7362,
|
| 1227 |
+
"step": 174
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 2.965909090909091,
|
| 1231 |
+
"step": 174,
|
| 1232 |
+
"total_flos": 156886855483392.0,
|
| 1233 |
+
"train_loss": 0.7380151625337272,
|
| 1234 |
+
"train_runtime": 2697.8392,
|
| 1235 |
+
"train_samples_per_second": 6.228,
|
| 1236 |
+
"train_steps_per_second": 0.064
|
| 1237 |
+
}
|
| 1238 |
+
],
|
| 1239 |
+
"logging_steps": 1,
|
| 1240 |
+
"max_steps": 174,
|
| 1241 |
+
"num_input_tokens_seen": 0,
|
| 1242 |
+
"num_train_epochs": 3,
|
| 1243 |
+
"save_steps": 500,
|
| 1244 |
+
"stateful_callbacks": {
|
| 1245 |
+
"TrainerControl": {
|
| 1246 |
+
"args": {
|
| 1247 |
+
"should_epoch_stop": false,
|
| 1248 |
+
"should_evaluate": false,
|
| 1249 |
+
"should_log": false,
|
| 1250 |
+
"should_save": true,
|
| 1251 |
+
"should_training_stop": true
|
| 1252 |
+
},
|
| 1253 |
+
"attributes": {}
|
| 1254 |
+
}
|
| 1255 |
+
},
|
| 1256 |
+
"total_flos": 156886855483392.0,
|
| 1257 |
+
"train_batch_size": 1,
|
| 1258 |
+
"trial_name": null,
|
| 1259 |
+
"trial_params": null
|
| 1260 |
+
}
|
training_loss.png
ADDED
|