End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +1491 -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: multiple_samples_majority_consensus_numina_aime_math_verify
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# multiple_samples_majority_consensus_numina_aime_math_verify
|
| 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: multiple_samples_majority_consensus_numina_aime_math_verify
|
|
|
|
| 16 |
|
| 17 |
# multiple_samples_majority_consensus_numina_aime_math_verify
|
| 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_math_verify dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.971291866028708,
|
| 3 |
+
"total_flos": 188453441536000.0,
|
| 4 |
+
"train_loss": 0.730322139562616,
|
| 5 |
+
"train_runtime": 6590.3033,
|
| 6 |
+
"train_samples_per_second": 3.031,
|
| 7 |
+
"train_steps_per_second": 0.031
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.971291866028708,
|
| 3 |
+
"total_flos": 188453441536000.0,
|
| 4 |
+
"train_loss": 0.730322139562616,
|
| 5 |
+
"train_runtime": 6590.3033,
|
| 6 |
+
"train_samples_per_second": 3.031,
|
| 7 |
+
"train_steps_per_second": 0.031
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1491 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.971291866028708,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 207,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.014354066985645933,
|
| 13 |
+
"grad_norm": 6.606319427490234,
|
| 14 |
+
"learning_rate": 4.7619047619047623e-07,
|
| 15 |
+
"loss": 1.0115,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.028708133971291867,
|
| 20 |
+
"grad_norm": 7.199845790863037,
|
| 21 |
+
"learning_rate": 9.523809523809525e-07,
|
| 22 |
+
"loss": 1.1216,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.0430622009569378,
|
| 27 |
+
"grad_norm": 6.635139465332031,
|
| 28 |
+
"learning_rate": 1.4285714285714286e-06,
|
| 29 |
+
"loss": 1.0261,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.05741626794258373,
|
| 34 |
+
"grad_norm": 6.910861492156982,
|
| 35 |
+
"learning_rate": 1.904761904761905e-06,
|
| 36 |
+
"loss": 1.0921,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.07177033492822966,
|
| 41 |
+
"grad_norm": 6.314844131469727,
|
| 42 |
+
"learning_rate": 2.380952380952381e-06,
|
| 43 |
+
"loss": 1.0275,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.0861244019138756,
|
| 48 |
+
"grad_norm": 5.247089385986328,
|
| 49 |
+
"learning_rate": 2.8571428571428573e-06,
|
| 50 |
+
"loss": 1.0085,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.10047846889952153,
|
| 55 |
+
"grad_norm": 5.063007354736328,
|
| 56 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 57 |
+
"loss": 1.033,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.11483253588516747,
|
| 62 |
+
"grad_norm": 3.0375494956970215,
|
| 63 |
+
"learning_rate": 3.80952380952381e-06,
|
| 64 |
+
"loss": 0.9662,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.1291866028708134,
|
| 69 |
+
"grad_norm": 2.6783761978149414,
|
| 70 |
+
"learning_rate": 4.2857142857142855e-06,
|
| 71 |
+
"loss": 0.9595,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.14354066985645933,
|
| 76 |
+
"grad_norm": 4.661453723907471,
|
| 77 |
+
"learning_rate": 4.761904761904762e-06,
|
| 78 |
+
"loss": 1.0393,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.15789473684210525,
|
| 83 |
+
"grad_norm": 4.916615962982178,
|
| 84 |
+
"learning_rate": 5.2380952380952384e-06,
|
| 85 |
+
"loss": 1.0032,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.1722488038277512,
|
| 90 |
+
"grad_norm": 4.34993314743042,
|
| 91 |
+
"learning_rate": 5.7142857142857145e-06,
|
| 92 |
+
"loss": 0.8942,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.18660287081339713,
|
| 97 |
+
"grad_norm": 4.2541680335998535,
|
| 98 |
+
"learning_rate": 6.1904761904761914e-06,
|
| 99 |
+
"loss": 0.9252,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.20095693779904306,
|
| 104 |
+
"grad_norm": 3.9607222080230713,
|
| 105 |
+
"learning_rate": 6.666666666666667e-06,
|
| 106 |
+
"loss": 0.9681,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.215311004784689,
|
| 111 |
+
"grad_norm": 3.0537819862365723,
|
| 112 |
+
"learning_rate": 7.1428571428571436e-06,
|
| 113 |
+
"loss": 0.9224,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.22966507177033493,
|
| 118 |
+
"grad_norm": 2.2377824783325195,
|
| 119 |
+
"learning_rate": 7.61904761904762e-06,
|
| 120 |
+
"loss": 0.8487,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.24401913875598086,
|
| 125 |
+
"grad_norm": 2.3145549297332764,
|
| 126 |
+
"learning_rate": 8.095238095238097e-06,
|
| 127 |
+
"loss": 0.8575,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.2583732057416268,
|
| 132 |
+
"grad_norm": 2.0530638694763184,
|
| 133 |
+
"learning_rate": 8.571428571428571e-06,
|
| 134 |
+
"loss": 0.8741,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.2727272727272727,
|
| 139 |
+
"grad_norm": 2.009566307067871,
|
| 140 |
+
"learning_rate": 9.047619047619049e-06,
|
| 141 |
+
"loss": 0.831,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.28708133971291866,
|
| 146 |
+
"grad_norm": 1.5277960300445557,
|
| 147 |
+
"learning_rate": 9.523809523809525e-06,
|
| 148 |
+
"loss": 0.8632,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.3014354066985646,
|
| 153 |
+
"grad_norm": 1.7812334299087524,
|
| 154 |
+
"learning_rate": 1e-05,
|
| 155 |
+
"loss": 0.8273,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.3157894736842105,
|
| 160 |
+
"grad_norm": 1.7438181638717651,
|
| 161 |
+
"learning_rate": 9.99928681279855e-06,
|
| 162 |
+
"loss": 0.8396,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.33014354066985646,
|
| 167 |
+
"grad_norm": 1.3840367794036865,
|
| 168 |
+
"learning_rate": 9.99714745464859e-06,
|
| 169 |
+
"loss": 0.7935,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.3444976076555024,
|
| 174 |
+
"grad_norm": 1.191886067390442,
|
| 175 |
+
"learning_rate": 9.993582535855265e-06,
|
| 176 |
+
"loss": 0.7566,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.3588516746411483,
|
| 181 |
+
"grad_norm": 1.3671236038208008,
|
| 182 |
+
"learning_rate": 9.988593073400354e-06,
|
| 183 |
+
"loss": 0.7909,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.37320574162679426,
|
| 188 |
+
"grad_norm": 1.0295319557189941,
|
| 189 |
+
"learning_rate": 9.982180490652165e-06,
|
| 190 |
+
"loss": 0.8096,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.3875598086124402,
|
| 195 |
+
"grad_norm": 0.9974440932273865,
|
| 196 |
+
"learning_rate": 9.974346616959476e-06,
|
| 197 |
+
"loss": 0.7236,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.4019138755980861,
|
| 202 |
+
"grad_norm": 1.062990427017212,
|
| 203 |
+
"learning_rate": 9.965093687129669e-06,
|
| 204 |
+
"loss": 0.7804,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.41626794258373206,
|
| 209 |
+
"grad_norm": 1.1406022310256958,
|
| 210 |
+
"learning_rate": 9.954424340791195e-06,
|
| 211 |
+
"loss": 0.8745,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.430622009569378,
|
| 216 |
+
"grad_norm": 0.9804137945175171,
|
| 217 |
+
"learning_rate": 9.942341621640558e-06,
|
| 218 |
+
"loss": 0.8287,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.4449760765550239,
|
| 223 |
+
"grad_norm": 0.8890625238418579,
|
| 224 |
+
"learning_rate": 9.92884897657402e-06,
|
| 225 |
+
"loss": 0.6832,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.45933014354066987,
|
| 230 |
+
"grad_norm": 0.9111762046813965,
|
| 231 |
+
"learning_rate": 9.913950254704291e-06,
|
| 232 |
+
"loss": 0.7849,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.47368421052631576,
|
| 237 |
+
"grad_norm": 0.7645003795623779,
|
| 238 |
+
"learning_rate": 9.897649706262474e-06,
|
| 239 |
+
"loss": 0.7755,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.4880382775119617,
|
| 244 |
+
"grad_norm": 0.8128668069839478,
|
| 245 |
+
"learning_rate": 9.879951981385577e-06,
|
| 246 |
+
"loss": 0.7993,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.5023923444976076,
|
| 251 |
+
"grad_norm": 0.8182640075683594,
|
| 252 |
+
"learning_rate": 9.860862128789954e-06,
|
| 253 |
+
"loss": 0.7783,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.5167464114832536,
|
| 258 |
+
"grad_norm": 0.6668164730072021,
|
| 259 |
+
"learning_rate": 9.840385594331022e-06,
|
| 260 |
+
"loss": 0.7621,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.5311004784688995,
|
| 265 |
+
"grad_norm": 0.7160326838493347,
|
| 266 |
+
"learning_rate": 9.818528219449705e-06,
|
| 267 |
+
"loss": 0.7604,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.5454545454545454,
|
| 272 |
+
"grad_norm": 0.8054168820381165,
|
| 273 |
+
"learning_rate": 9.795296239506011e-06,
|
| 274 |
+
"loss": 0.7777,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.5598086124401914,
|
| 279 |
+
"grad_norm": 0.7040032148361206,
|
| 280 |
+
"learning_rate": 9.770696282000245e-06,
|
| 281 |
+
"loss": 0.7655,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.5741626794258373,
|
| 286 |
+
"grad_norm": 0.7737412452697754,
|
| 287 |
+
"learning_rate": 9.744735364682347e-06,
|
| 288 |
+
"loss": 0.7782,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.5885167464114832,
|
| 293 |
+
"grad_norm": 0.756745457649231,
|
| 294 |
+
"learning_rate": 9.717420893549902e-06,
|
| 295 |
+
"loss": 0.8125,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.6028708133971292,
|
| 300 |
+
"grad_norm": 0.8294979333877563,
|
| 301 |
+
"learning_rate": 9.688760660735403e-06,
|
| 302 |
+
"loss": 0.8397,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.6172248803827751,
|
| 307 |
+
"grad_norm": 0.7612116932868958,
|
| 308 |
+
"learning_rate": 9.658762842283343e-06,
|
| 309 |
+
"loss": 0.7491,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.631578947368421,
|
| 314 |
+
"grad_norm": 0.6338142156600952,
|
| 315 |
+
"learning_rate": 9.627435995817799e-06,
|
| 316 |
+
"loss": 0.7566,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.645933014354067,
|
| 321 |
+
"grad_norm": 0.7347820997238159,
|
| 322 |
+
"learning_rate": 9.594789058101154e-06,
|
| 323 |
+
"loss": 0.7458,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.6602870813397129,
|
| 328 |
+
"grad_norm": 0.8506797552108765,
|
| 329 |
+
"learning_rate": 9.560831342484668e-06,
|
| 330 |
+
"loss": 0.7787,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.6746411483253588,
|
| 335 |
+
"grad_norm": 0.6443374752998352,
|
| 336 |
+
"learning_rate": 9.525572536251608e-06,
|
| 337 |
+
"loss": 0.7706,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.6889952153110048,
|
| 342 |
+
"grad_norm": 0.8315154314041138,
|
| 343 |
+
"learning_rate": 9.48902269785371e-06,
|
| 344 |
+
"loss": 0.7446,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.7033492822966507,
|
| 349 |
+
"grad_norm": 0.6317525506019592,
|
| 350 |
+
"learning_rate": 9.451192254041759e-06,
|
| 351 |
+
"loss": 0.7717,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.7177033492822966,
|
| 356 |
+
"grad_norm": 0.7524369955062866,
|
| 357 |
+
"learning_rate": 9.412091996891097e-06,
|
| 358 |
+
"loss": 0.7462,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.7320574162679426,
|
| 363 |
+
"grad_norm": 0.8177095651626587,
|
| 364 |
+
"learning_rate": 9.371733080722911e-06,
|
| 365 |
+
"loss": 0.7728,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.7464114832535885,
|
| 370 |
+
"grad_norm": 0.6658672094345093,
|
| 371 |
+
"learning_rate": 9.330127018922195e-06,
|
| 372 |
+
"loss": 0.7859,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.7607655502392344,
|
| 377 |
+
"grad_norm": 0.6971548795700073,
|
| 378 |
+
"learning_rate": 9.287285680653254e-06,
|
| 379 |
+
"loss": 0.7333,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.7751196172248804,
|
| 384 |
+
"grad_norm": 0.6469892859458923,
|
| 385 |
+
"learning_rate": 9.243221287473755e-06,
|
| 386 |
+
"loss": 0.7714,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.7894736842105263,
|
| 391 |
+
"grad_norm": 0.6104458570480347,
|
| 392 |
+
"learning_rate": 9.197946409848196e-06,
|
| 393 |
+
"loss": 0.7166,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.8038277511961722,
|
| 398 |
+
"grad_norm": 0.5406800508499146,
|
| 399 |
+
"learning_rate": 9.151473963561884e-06,
|
| 400 |
+
"loss": 0.7421,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.8181818181818182,
|
| 405 |
+
"grad_norm": 0.5975339412689209,
|
| 406 |
+
"learning_rate": 9.103817206036383e-06,
|
| 407 |
+
"loss": 0.7147,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.8325358851674641,
|
| 412 |
+
"grad_norm": 0.7101950645446777,
|
| 413 |
+
"learning_rate": 9.054989732547507e-06,
|
| 414 |
+
"loss": 0.704,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.84688995215311,
|
| 419 |
+
"grad_norm": 0.5458029508590698,
|
| 420 |
+
"learning_rate": 9.005005472346923e-06,
|
| 421 |
+
"loss": 0.7642,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.861244019138756,
|
| 426 |
+
"grad_norm": 0.5615411400794983,
|
| 427 |
+
"learning_rate": 8.953878684688492e-06,
|
| 428 |
+
"loss": 0.7633,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.8755980861244019,
|
| 433 |
+
"grad_norm": 0.6739734411239624,
|
| 434 |
+
"learning_rate": 8.90162395476046e-06,
|
| 435 |
+
"loss": 0.8023,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.8899521531100478,
|
| 440 |
+
"grad_norm": 0.6366813778877258,
|
| 441 |
+
"learning_rate": 8.848256189524661e-06,
|
| 442 |
+
"loss": 0.686,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.9043062200956937,
|
| 447 |
+
"grad_norm": 0.5781328678131104,
|
| 448 |
+
"learning_rate": 8.793790613463956e-06,
|
| 449 |
+
"loss": 0.76,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.9186602870813397,
|
| 454 |
+
"grad_norm": 0.7186875343322754,
|
| 455 |
+
"learning_rate": 8.738242764239046e-06,
|
| 456 |
+
"loss": 0.7369,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.9330143540669856,
|
| 461 |
+
"grad_norm": 0.7098949551582336,
|
| 462 |
+
"learning_rate": 8.681628488255986e-06,
|
| 463 |
+
"loss": 0.7003,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.9473684210526315,
|
| 468 |
+
"grad_norm": 0.5867261290550232,
|
| 469 |
+
"learning_rate": 8.6239639361456e-06,
|
| 470 |
+
"loss": 0.7072,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.9617224880382775,
|
| 475 |
+
"grad_norm": 0.7924665808677673,
|
| 476 |
+
"learning_rate": 8.565265558156101e-06,
|
| 477 |
+
"loss": 0.7688,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.9760765550239234,
|
| 482 |
+
"grad_norm": 0.6175984144210815,
|
| 483 |
+
"learning_rate": 8.505550099460264e-06,
|
| 484 |
+
"loss": 0.7654,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.9904306220095693,
|
| 489 |
+
"grad_norm": 0.5630785822868347,
|
| 490 |
+
"learning_rate": 8.444834595378434e-06,
|
| 491 |
+
"loss": 0.6622,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 1.0047846889952152,
|
| 496 |
+
"grad_norm": 0.8506320714950562,
|
| 497 |
+
"learning_rate": 8.383136366518788e-06,
|
| 498 |
+
"loss": 0.8726,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 1.0191387559808613,
|
| 503 |
+
"grad_norm": 0.6059301495552063,
|
| 504 |
+
"learning_rate": 8.320473013836197e-06,
|
| 505 |
+
"loss": 0.8143,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.0334928229665072,
|
| 510 |
+
"grad_norm": 0.6086148619651794,
|
| 511 |
+
"learning_rate": 8.256862413611113e-06,
|
| 512 |
+
"loss": 0.6725,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.0478468899521531,
|
| 517 |
+
"grad_norm": 0.6276902556419373,
|
| 518 |
+
"learning_rate": 8.192322712349917e-06,
|
| 519 |
+
"loss": 0.6635,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.062200956937799,
|
| 524 |
+
"grad_norm": 0.5304465889930725,
|
| 525 |
+
"learning_rate": 8.126872321608185e-06,
|
| 526 |
+
"loss": 0.6695,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.076555023923445,
|
| 531 |
+
"grad_norm": 0.6066795587539673,
|
| 532 |
+
"learning_rate": 8.060529912738316e-06,
|
| 533 |
+
"loss": 0.7012,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.0909090909090908,
|
| 538 |
+
"grad_norm": 0.7892539501190186,
|
| 539 |
+
"learning_rate": 7.993314411563075e-06,
|
| 540 |
+
"loss": 0.7472,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.1052631578947367,
|
| 545 |
+
"grad_norm": 0.5043841600418091,
|
| 546 |
+
"learning_rate": 7.925244992976538e-06,
|
| 547 |
+
"loss": 0.7198,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.1196172248803828,
|
| 552 |
+
"grad_norm": 0.601098358631134,
|
| 553 |
+
"learning_rate": 7.856341075473963e-06,
|
| 554 |
+
"loss": 0.6603,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.1339712918660287,
|
| 559 |
+
"grad_norm": 0.7463696002960205,
|
| 560 |
+
"learning_rate": 7.786622315612182e-06,
|
| 561 |
+
"loss": 0.7573,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.1483253588516746,
|
| 566 |
+
"grad_norm": 0.6070399880409241,
|
| 567 |
+
"learning_rate": 7.716108602402094e-06,
|
| 568 |
+
"loss": 0.6886,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.1626794258373205,
|
| 573 |
+
"grad_norm": 0.6200478076934814,
|
| 574 |
+
"learning_rate": 7.644820051634813e-06,
|
| 575 |
+
"loss": 0.6959,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.1770334928229664,
|
| 580 |
+
"grad_norm": 0.6048188209533691,
|
| 581 |
+
"learning_rate": 7.572777000143145e-06,
|
| 582 |
+
"loss": 0.5509,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 1.1913875598086126,
|
| 587 |
+
"grad_norm": 0.6651050448417664,
|
| 588 |
+
"learning_rate": 7.500000000000001e-06,
|
| 589 |
+
"loss": 0.6593,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.2057416267942584,
|
| 594 |
+
"grad_norm": 0.6162533760070801,
|
| 595 |
+
"learning_rate": 7.4265098126554065e-06,
|
| 596 |
+
"loss": 0.7186,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.2200956937799043,
|
| 601 |
+
"grad_norm": 0.63652503490448,
|
| 602 |
+
"learning_rate": 7.352327403013779e-06,
|
| 603 |
+
"loss": 0.6801,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.2344497607655502,
|
| 608 |
+
"grad_norm": 0.700792670249939,
|
| 609 |
+
"learning_rate": 7.27747393345317e-06,
|
| 610 |
+
"loss": 0.7402,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.2488038277511961,
|
| 615 |
+
"grad_norm": 0.5938558578491211,
|
| 616 |
+
"learning_rate": 7.201970757788172e-06,
|
| 617 |
+
"loss": 0.685,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.263157894736842,
|
| 622 |
+
"grad_norm": 0.6236053705215454,
|
| 623 |
+
"learning_rate": 7.125839415178204e-06,
|
| 624 |
+
"loss": 0.7496,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.277511961722488,
|
| 629 |
+
"grad_norm": 0.6197056174278259,
|
| 630 |
+
"learning_rate": 7.049101623982938e-06,
|
| 631 |
+
"loss": 0.7925,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.291866028708134,
|
| 636 |
+
"grad_norm": 0.6353892683982849,
|
| 637 |
+
"learning_rate": 6.971779275566593e-06,
|
| 638 |
+
"loss": 0.6172,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.30622009569378,
|
| 643 |
+
"grad_norm": 0.6898404955863953,
|
| 644 |
+
"learning_rate": 6.893894428052881e-06,
|
| 645 |
+
"loss": 0.7854,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.3205741626794258,
|
| 650 |
+
"grad_norm": 0.6065007448196411,
|
| 651 |
+
"learning_rate": 6.815469300032374e-06,
|
| 652 |
+
"loss": 0.6519,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.3349282296650717,
|
| 657 |
+
"grad_norm": 0.7258915305137634,
|
| 658 |
+
"learning_rate": 6.736526264224101e-06,
|
| 659 |
+
"loss": 0.7472,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.3492822966507176,
|
| 664 |
+
"grad_norm": 0.5999413728713989,
|
| 665 |
+
"learning_rate": 6.657087841093179e-06,
|
| 666 |
+
"loss": 0.6688,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.3636363636363638,
|
| 671 |
+
"grad_norm": 0.7258263826370239,
|
| 672 |
+
"learning_rate": 6.5771766924262795e-06,
|
| 673 |
+
"loss": 0.7773,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.3779904306220097,
|
| 678 |
+
"grad_norm": 0.5349370241165161,
|
| 679 |
+
"learning_rate": 6.496815614866792e-06,
|
| 680 |
+
"loss": 0.6967,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.3923444976076556,
|
| 685 |
+
"grad_norm": 0.6183546781539917,
|
| 686 |
+
"learning_rate": 6.41602753341152e-06,
|
| 687 |
+
"loss": 0.7134,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.4066985645933014,
|
| 692 |
+
"grad_norm": 0.5610795617103577,
|
| 693 |
+
"learning_rate": 6.334835494870759e-06,
|
| 694 |
+
"loss": 0.6693,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 1.4210526315789473,
|
| 699 |
+
"grad_norm": 0.6121208071708679,
|
| 700 |
+
"learning_rate": 6.2532626612936035e-06,
|
| 701 |
+
"loss": 0.7383,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.4354066985645932,
|
| 706 |
+
"grad_norm": 0.4912906289100647,
|
| 707 |
+
"learning_rate": 6.171332303360411e-06,
|
| 708 |
+
"loss": 0.6147,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.4497607655502391,
|
| 713 |
+
"grad_norm": 0.5811400413513184,
|
| 714 |
+
"learning_rate": 6.089067793744258e-06,
|
| 715 |
+
"loss": 0.7924,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 1.464114832535885,
|
| 720 |
+
"grad_norm": 0.5423148274421692,
|
| 721 |
+
"learning_rate": 6.006492600443301e-06,
|
| 722 |
+
"loss": 0.7318,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.4784688995215312,
|
| 727 |
+
"grad_norm": 0.5195919275283813,
|
| 728 |
+
"learning_rate": 5.923630280085948e-06,
|
| 729 |
+
"loss": 0.6703,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.492822966507177,
|
| 734 |
+
"grad_norm": 0.5913715958595276,
|
| 735 |
+
"learning_rate": 5.840504471210742e-06,
|
| 736 |
+
"loss": 0.741,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.507177033492823,
|
| 741 |
+
"grad_norm": 0.5833776593208313,
|
| 742 |
+
"learning_rate": 5.757138887522884e-06,
|
| 743 |
+
"loss": 0.7187,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.5215311004784688,
|
| 748 |
+
"grad_norm": 0.5346126556396484,
|
| 749 |
+
"learning_rate": 5.673557311129306e-06,
|
| 750 |
+
"loss": 0.7267,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.535885167464115,
|
| 755 |
+
"grad_norm": 0.563261866569519,
|
| 756 |
+
"learning_rate": 5.5897835857542315e-06,
|
| 757 |
+
"loss": 0.7054,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.5502392344497609,
|
| 762 |
+
"grad_norm": 0.6093409061431885,
|
| 763 |
+
"learning_rate": 5.505841609937162e-06,
|
| 764 |
+
"loss": 0.6203,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.5645933014354068,
|
| 769 |
+
"grad_norm": 0.4867560565471649,
|
| 770 |
+
"learning_rate": 5.421755330215223e-06,
|
| 771 |
+
"loss": 0.7287,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 1.5789473684210527,
|
| 776 |
+
"grad_norm": 0.4358079433441162,
|
| 777 |
+
"learning_rate": 5.337548734291827e-06,
|
| 778 |
+
"loss": 0.6202,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.5933014354066986,
|
| 783 |
+
"grad_norm": 0.484427273273468,
|
| 784 |
+
"learning_rate": 5.253245844193564e-06,
|
| 785 |
+
"loss": 0.7408,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.6076555023923444,
|
| 790 |
+
"grad_norm": 0.5462157130241394,
|
| 791 |
+
"learning_rate": 5.168870709417342e-06,
|
| 792 |
+
"loss": 0.6979,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.6220095693779903,
|
| 797 |
+
"grad_norm": 0.5546799898147583,
|
| 798 |
+
"learning_rate": 5.084447400069656e-06,
|
| 799 |
+
"loss": 0.7994,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 1.6363636363636362,
|
| 804 |
+
"grad_norm": 0.4335629343986511,
|
| 805 |
+
"learning_rate": 5e-06,
|
| 806 |
+
"loss": 0.7086,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.6507177033492821,
|
| 811 |
+
"grad_norm": 0.48268577456474304,
|
| 812 |
+
"learning_rate": 4.915552599930345e-06,
|
| 813 |
+
"loss": 0.6805,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 1.6650717703349283,
|
| 818 |
+
"grad_norm": 0.5249758958816528,
|
| 819 |
+
"learning_rate": 4.83112929058266e-06,
|
| 820 |
+
"loss": 0.7796,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 1.6794258373205742,
|
| 825 |
+
"grad_norm": 0.5026386976242065,
|
| 826 |
+
"learning_rate": 4.746754155806437e-06,
|
| 827 |
+
"loss": 0.6331,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 1.69377990430622,
|
| 832 |
+
"grad_norm": 0.5191088318824768,
|
| 833 |
+
"learning_rate": 4.662451265708174e-06,
|
| 834 |
+
"loss": 0.6923,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 1.7081339712918662,
|
| 839 |
+
"grad_norm": 0.4637056291103363,
|
| 840 |
+
"learning_rate": 4.5782446697847775e-06,
|
| 841 |
+
"loss": 0.7035,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 1.722488038277512,
|
| 846 |
+
"grad_norm": 0.5935611128807068,
|
| 847 |
+
"learning_rate": 4.49415839006284e-06,
|
| 848 |
+
"loss": 0.7395,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.736842105263158,
|
| 853 |
+
"grad_norm": 0.4833378791809082,
|
| 854 |
+
"learning_rate": 4.410216414245771e-06,
|
| 855 |
+
"loss": 0.6636,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 1.7511961722488039,
|
| 860 |
+
"grad_norm": 0.5400302410125732,
|
| 861 |
+
"learning_rate": 4.326442688870697e-06,
|
| 862 |
+
"loss": 0.797,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 1.7655502392344498,
|
| 867 |
+
"grad_norm": 0.4824999272823334,
|
| 868 |
+
"learning_rate": 4.2428611124771184e-06,
|
| 869 |
+
"loss": 0.6631,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 1.7799043062200957,
|
| 874 |
+
"grad_norm": 0.4362877607345581,
|
| 875 |
+
"learning_rate": 4.15949552878926e-06,
|
| 876 |
+
"loss": 0.6653,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 1.7942583732057416,
|
| 881 |
+
"grad_norm": 0.46789178252220154,
|
| 882 |
+
"learning_rate": 4.076369719914055e-06,
|
| 883 |
+
"loss": 0.6705,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 1.8086124401913874,
|
| 888 |
+
"grad_norm": 0.5709954500198364,
|
| 889 |
+
"learning_rate": 3.993507399556699e-06,
|
| 890 |
+
"loss": 0.7049,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 1.8229665071770333,
|
| 895 |
+
"grad_norm": 0.4306061863899231,
|
| 896 |
+
"learning_rate": 3.910932206255742e-06,
|
| 897 |
+
"loss": 0.5775,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 1.8373205741626795,
|
| 902 |
+
"grad_norm": 0.5206833481788635,
|
| 903 |
+
"learning_rate": 3.8286676966395895e-06,
|
| 904 |
+
"loss": 0.7015,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 1.8516746411483254,
|
| 909 |
+
"grad_norm": 0.48339328169822693,
|
| 910 |
+
"learning_rate": 3.7467373387063973e-06,
|
| 911 |
+
"loss": 0.7644,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 1.8660287081339713,
|
| 916 |
+
"grad_norm": 0.5255927443504333,
|
| 917 |
+
"learning_rate": 3.6651645051292415e-06,
|
| 918 |
+
"loss": 0.6665,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 1.8803827751196174,
|
| 923 |
+
"grad_norm": 0.5118809342384338,
|
| 924 |
+
"learning_rate": 3.58397246658848e-06,
|
| 925 |
+
"loss": 0.7223,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 1.8947368421052633,
|
| 930 |
+
"grad_norm": 0.4518415033817291,
|
| 931 |
+
"learning_rate": 3.5031843851332105e-06,
|
| 932 |
+
"loss": 0.62,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.9090909090909092,
|
| 937 |
+
"grad_norm": 0.4885469079017639,
|
| 938 |
+
"learning_rate": 3.4228233075737225e-06,
|
| 939 |
+
"loss": 0.743,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.923444976076555,
|
| 944 |
+
"grad_norm": 0.45925790071487427,
|
| 945 |
+
"learning_rate": 3.3429121589068213e-06,
|
| 946 |
+
"loss": 0.6161,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.937799043062201,
|
| 951 |
+
"grad_norm": 0.5271123051643372,
|
| 952 |
+
"learning_rate": 3.2634737357758994e-06,
|
| 953 |
+
"loss": 0.7556,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 1.9521531100478469,
|
| 958 |
+
"grad_norm": 0.47831523418426514,
|
| 959 |
+
"learning_rate": 3.1845306999676274e-06,
|
| 960 |
+
"loss": 0.6835,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 1.9665071770334928,
|
| 965 |
+
"grad_norm": 0.47705405950546265,
|
| 966 |
+
"learning_rate": 3.10610557194712e-06,
|
| 967 |
+
"loss": 0.6996,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 1.9808612440191387,
|
| 972 |
+
"grad_norm": 0.4368450939655304,
|
| 973 |
+
"learning_rate": 3.0282207244334084e-06,
|
| 974 |
+
"loss": 0.6532,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 1.9952153110047846,
|
| 979 |
+
"grad_norm": 0.5632436275482178,
|
| 980 |
+
"learning_rate": 2.950898376017064e-06,
|
| 981 |
+
"loss": 0.822,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 2.0095693779904304,
|
| 986 |
+
"grad_norm": 0.6237561702728271,
|
| 987 |
+
"learning_rate": 2.874160584821798e-06,
|
| 988 |
+
"loss": 0.7384,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 2.0239234449760763,
|
| 993 |
+
"grad_norm": 0.5388489961624146,
|
| 994 |
+
"learning_rate": 2.7980292422118282e-06,
|
| 995 |
+
"loss": 0.6775,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 2.0382775119617227,
|
| 1000 |
+
"grad_norm": 0.5205004811286926,
|
| 1001 |
+
"learning_rate": 2.72252606654683e-06,
|
| 1002 |
+
"loss": 0.7364,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 2.0526315789473686,
|
| 1007 |
+
"grad_norm": 0.4915616810321808,
|
| 1008 |
+
"learning_rate": 2.6476725969862227e-06,
|
| 1009 |
+
"loss": 0.6684,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 2.0669856459330145,
|
| 1014 |
+
"grad_norm": 0.4172745645046234,
|
| 1015 |
+
"learning_rate": 2.573490187344596e-06,
|
| 1016 |
+
"loss": 0.5368,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 2.0813397129186604,
|
| 1021 |
+
"grad_norm": 0.5156456828117371,
|
| 1022 |
+
"learning_rate": 2.5000000000000015e-06,
|
| 1023 |
+
"loss": 0.7555,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 2.0956937799043063,
|
| 1028 |
+
"grad_norm": 0.48493507504463196,
|
| 1029 |
+
"learning_rate": 2.4272229998568576e-06,
|
| 1030 |
+
"loss": 0.6411,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 2.110047846889952,
|
| 1035 |
+
"grad_norm": 0.4368244409561157,
|
| 1036 |
+
"learning_rate": 2.3551799483651894e-06,
|
| 1037 |
+
"loss": 0.6331,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 2.124401913875598,
|
| 1042 |
+
"grad_norm": 0.48422062397003174,
|
| 1043 |
+
"learning_rate": 2.283891397597908e-06,
|
| 1044 |
+
"loss": 0.605,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 2.138755980861244,
|
| 1049 |
+
"grad_norm": 0.5105732083320618,
|
| 1050 |
+
"learning_rate": 2.2133776843878185e-06,
|
| 1051 |
+
"loss": 0.742,
|
| 1052 |
+
"step": 149
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 2.15311004784689,
|
| 1056 |
+
"grad_norm": 0.4802730679512024,
|
| 1057 |
+
"learning_rate": 2.1436589245260375e-06,
|
| 1058 |
+
"loss": 0.6863,
|
| 1059 |
+
"step": 150
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 2.1674641148325358,
|
| 1063 |
+
"grad_norm": 0.3974132835865021,
|
| 1064 |
+
"learning_rate": 2.074755007023461e-06,
|
| 1065 |
+
"loss": 0.612,
|
| 1066 |
+
"step": 151
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 2.1818181818181817,
|
| 1070 |
+
"grad_norm": 0.46719783544540405,
|
| 1071 |
+
"learning_rate": 2.0066855884369246e-06,
|
| 1072 |
+
"loss": 0.6694,
|
| 1073 |
+
"step": 152
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 2.1961722488038276,
|
| 1077 |
+
"grad_norm": 0.47412195801734924,
|
| 1078 |
+
"learning_rate": 1.9394700872616856e-06,
|
| 1079 |
+
"loss": 0.6622,
|
| 1080 |
+
"step": 153
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 2.2105263157894735,
|
| 1084 |
+
"grad_norm": 0.41956526041030884,
|
| 1085 |
+
"learning_rate": 1.8731276783918162e-06,
|
| 1086 |
+
"loss": 0.6711,
|
| 1087 |
+
"step": 154
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 2.22488038277512,
|
| 1091 |
+
"grad_norm": 0.44608020782470703,
|
| 1092 |
+
"learning_rate": 1.8076772876500831e-06,
|
| 1093 |
+
"loss": 0.6175,
|
| 1094 |
+
"step": 155
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 2.2392344497607657,
|
| 1098 |
+
"grad_norm": 0.4763632118701935,
|
| 1099 |
+
"learning_rate": 1.74313758638889e-06,
|
| 1100 |
+
"loss": 0.6674,
|
| 1101 |
+
"step": 156
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 2.2535885167464116,
|
| 1105 |
+
"grad_norm": 0.46003472805023193,
|
| 1106 |
+
"learning_rate": 1.6795269861638041e-06,
|
| 1107 |
+
"loss": 0.6965,
|
| 1108 |
+
"step": 157
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 2.2679425837320575,
|
| 1112 |
+
"grad_norm": 0.4704546630382538,
|
| 1113 |
+
"learning_rate": 1.6168636334812126e-06,
|
| 1114 |
+
"loss": 0.7523,
|
| 1115 |
+
"step": 158
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 2.2822966507177034,
|
| 1119 |
+
"grad_norm": 0.4168799817562103,
|
| 1120 |
+
"learning_rate": 1.555165404621567e-06,
|
| 1121 |
+
"loss": 0.5923,
|
| 1122 |
+
"step": 159
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 2.2966507177033493,
|
| 1126 |
+
"grad_norm": 0.4823237657546997,
|
| 1127 |
+
"learning_rate": 1.4944499005397372e-06,
|
| 1128 |
+
"loss": 0.6462,
|
| 1129 |
+
"step": 160
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 2.311004784688995,
|
| 1133 |
+
"grad_norm": 0.4848882257938385,
|
| 1134 |
+
"learning_rate": 1.434734441843899e-06,
|
| 1135 |
+
"loss": 0.688,
|
| 1136 |
+
"step": 161
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 2.325358851674641,
|
| 1140 |
+
"grad_norm": 0.4492577314376831,
|
| 1141 |
+
"learning_rate": 1.3760360638544012e-06,
|
| 1142 |
+
"loss": 0.663,
|
| 1143 |
+
"step": 162
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 2.339712918660287,
|
| 1147 |
+
"grad_norm": 0.42550182342529297,
|
| 1148 |
+
"learning_rate": 1.3183715117440143e-06,
|
| 1149 |
+
"loss": 0.7095,
|
| 1150 |
+
"step": 163
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 2.354066985645933,
|
| 1154 |
+
"grad_norm": 0.4141203761100769,
|
| 1155 |
+
"learning_rate": 1.2617572357609565e-06,
|
| 1156 |
+
"loss": 0.6137,
|
| 1157 |
+
"step": 164
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 2.3684210526315788,
|
| 1161 |
+
"grad_norm": 0.4925439655780792,
|
| 1162 |
+
"learning_rate": 1.2062093865360458e-06,
|
| 1163 |
+
"loss": 0.7442,
|
| 1164 |
+
"step": 165
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 2.382775119617225,
|
| 1168 |
+
"grad_norm": 0.3656056821346283,
|
| 1169 |
+
"learning_rate": 1.1517438104753386e-06,
|
| 1170 |
+
"loss": 0.6041,
|
| 1171 |
+
"step": 166
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 2.397129186602871,
|
| 1175 |
+
"grad_norm": 0.3813127279281616,
|
| 1176 |
+
"learning_rate": 1.0983760452395415e-06,
|
| 1177 |
+
"loss": 0.651,
|
| 1178 |
+
"step": 167
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 2.411483253588517,
|
| 1182 |
+
"grad_norm": 0.4860974848270416,
|
| 1183 |
+
"learning_rate": 1.046121315311508e-06,
|
| 1184 |
+
"loss": 0.6922,
|
| 1185 |
+
"step": 168
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 2.425837320574163,
|
| 1189 |
+
"grad_norm": 0.445382684469223,
|
| 1190 |
+
"learning_rate": 9.949945276530782e-07,
|
| 1191 |
+
"loss": 0.6473,
|
| 1192 |
+
"step": 169
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 2.4401913875598087,
|
| 1196 |
+
"grad_norm": 0.4454602897167206,
|
| 1197 |
+
"learning_rate": 9.450102674524952e-07,
|
| 1198 |
+
"loss": 0.6628,
|
| 1199 |
+
"step": 170
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 2.4545454545454546,
|
| 1203 |
+
"grad_norm": 0.3988717496395111,
|
| 1204 |
+
"learning_rate": 8.961827939636198e-07,
|
| 1205 |
+
"loss": 0.6354,
|
| 1206 |
+
"step": 171
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 2.4688995215311005,
|
| 1210 |
+
"grad_norm": 0.42658305168151855,
|
| 1211 |
+
"learning_rate": 8.485260364381187e-07,
|
| 1212 |
+
"loss": 0.6546,
|
| 1213 |
+
"step": 172
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 2.4832535885167464,
|
| 1217 |
+
"grad_norm": 0.4457349479198456,
|
| 1218 |
+
"learning_rate": 8.02053590151805e-07,
|
| 1219 |
+
"loss": 0.6334,
|
| 1220 |
+
"step": 173
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 2.4976076555023923,
|
| 1224 |
+
"grad_norm": 0.4586748778820038,
|
| 1225 |
+
"learning_rate": 7.567787125262449e-07,
|
| 1226 |
+
"loss": 0.6522,
|
| 1227 |
+
"step": 174
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 2.511961722488038,
|
| 1231 |
+
"grad_norm": 0.4687344431877136,
|
| 1232 |
+
"learning_rate": 7.127143193467445e-07,
|
| 1233 |
+
"loss": 0.6983,
|
| 1234 |
+
"step": 175
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 2.526315789473684,
|
| 1238 |
+
"grad_norm": 0.4022500813007355,
|
| 1239 |
+
"learning_rate": 6.698729810778065e-07,
|
| 1240 |
+
"loss": 0.6803,
|
| 1241 |
+
"step": 176
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 2.5406698564593304,
|
| 1245 |
+
"grad_norm": 0.44155552983283997,
|
| 1246 |
+
"learning_rate": 6.282669192770896e-07,
|
| 1247 |
+
"loss": 0.6338,
|
| 1248 |
+
"step": 177
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 2.555023923444976,
|
| 1252 |
+
"grad_norm": 0.42168739438056946,
|
| 1253 |
+
"learning_rate": 5.879080031089047e-07,
|
| 1254 |
+
"loss": 0.6442,
|
| 1255 |
+
"step": 178
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 2.569377990430622,
|
| 1259 |
+
"grad_norm": 0.4079402685165405,
|
| 1260 |
+
"learning_rate": 5.488077459582425e-07,
|
| 1261 |
+
"loss": 0.6702,
|
| 1262 |
+
"step": 179
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 2.583732057416268,
|
| 1266 |
+
"grad_norm": 0.4314362108707428,
|
| 1267 |
+
"learning_rate": 5.109773021462921e-07,
|
| 1268 |
+
"loss": 0.6578,
|
| 1269 |
+
"step": 180
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 2.598086124401914,
|
| 1273 |
+
"grad_norm": 0.41576293110847473,
|
| 1274 |
+
"learning_rate": 4.7442746374839363e-07,
|
| 1275 |
+
"loss": 0.6506,
|
| 1276 |
+
"step": 181
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 2.61244019138756,
|
| 1280 |
+
"grad_norm": 0.44010618329048157,
|
| 1281 |
+
"learning_rate": 4.3916865751533313e-07,
|
| 1282 |
+
"loss": 0.7005,
|
| 1283 |
+
"step": 182
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 2.626794258373206,
|
| 1287 |
+
"grad_norm": 0.3917553424835205,
|
| 1288 |
+
"learning_rate": 4.05210941898847e-07,
|
| 1289 |
+
"loss": 0.5862,
|
| 1290 |
+
"step": 183
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 2.6411483253588517,
|
| 1294 |
+
"grad_norm": 0.3943141996860504,
|
| 1295 |
+
"learning_rate": 3.725640041822026e-07,
|
| 1296 |
+
"loss": 0.6294,
|
| 1297 |
+
"step": 184
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 2.6555023923444976,
|
| 1301 |
+
"grad_norm": 0.42908748984336853,
|
| 1302 |
+
"learning_rate": 3.4123715771665786e-07,
|
| 1303 |
+
"loss": 0.6718,
|
| 1304 |
+
"step": 185
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 2.6698564593301435,
|
| 1308 |
+
"grad_norm": 0.41469356417655945,
|
| 1309 |
+
"learning_rate": 3.112393392645985e-07,
|
| 1310 |
+
"loss": 0.6035,
|
| 1311 |
+
"step": 186
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 2.6842105263157894,
|
| 1315 |
+
"grad_norm": 0.392846941947937,
|
| 1316 |
+
"learning_rate": 2.8257910645009935e-07,
|
| 1317 |
+
"loss": 0.6878,
|
| 1318 |
+
"step": 187
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 2.6985645933014353,
|
| 1322 |
+
"grad_norm": 0.3842258155345917,
|
| 1323 |
+
"learning_rate": 2.5526463531765467e-07,
|
| 1324 |
+
"loss": 0.7033,
|
| 1325 |
+
"step": 188
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 2.712918660287081,
|
| 1329 |
+
"grad_norm": 0.40082886815071106,
|
| 1330 |
+
"learning_rate": 2.2930371799975593e-07,
|
| 1331 |
+
"loss": 0.6613,
|
| 1332 |
+
"step": 189
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 2.7272727272727275,
|
| 1336 |
+
"grad_norm": 0.4244035482406616,
|
| 1337 |
+
"learning_rate": 2.0470376049398944e-07,
|
| 1338 |
+
"loss": 0.7166,
|
| 1339 |
+
"step": 190
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 2.741626794258373,
|
| 1343 |
+
"grad_norm": 0.3917875289916992,
|
| 1344 |
+
"learning_rate": 1.814717805502958e-07,
|
| 1345 |
+
"loss": 0.6435,
|
| 1346 |
+
"step": 191
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 2.7559808612440193,
|
| 1350 |
+
"grad_norm": 0.4630082845687866,
|
| 1351 |
+
"learning_rate": 1.5961440566897913e-07,
|
| 1352 |
+
"loss": 0.6877,
|
| 1353 |
+
"step": 192
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 2.770334928229665,
|
| 1357 |
+
"grad_norm": 0.39388176798820496,
|
| 1358 |
+
"learning_rate": 1.3913787121004717e-07,
|
| 1359 |
+
"loss": 0.6212,
|
| 1360 |
+
"step": 193
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 2.784688995215311,
|
| 1364 |
+
"grad_norm": 0.38723188638687134,
|
| 1365 |
+
"learning_rate": 1.2004801861442373e-07,
|
| 1366 |
+
"loss": 0.6511,
|
| 1367 |
+
"step": 194
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 2.799043062200957,
|
| 1371 |
+
"grad_norm": 0.36711883544921875,
|
| 1372 |
+
"learning_rate": 1.0235029373752758e-07,
|
| 1373 |
+
"loss": 0.5578,
|
| 1374 |
+
"step": 195
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 2.813397129186603,
|
| 1378 |
+
"grad_norm": 0.45455777645111084,
|
| 1379 |
+
"learning_rate": 8.604974529571042e-08,
|
| 1380 |
+
"loss": 0.7044,
|
| 1381 |
+
"step": 196
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 2.827751196172249,
|
| 1385 |
+
"grad_norm": 0.4013150930404663,
|
| 1386 |
+
"learning_rate": 7.115102342598101e-08,
|
| 1387 |
+
"loss": 0.6089,
|
| 1388 |
+
"step": 197
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 2.8421052631578947,
|
| 1392 |
+
"grad_norm": 0.39588093757629395,
|
| 1393 |
+
"learning_rate": 5.7658378359443104e-08,
|
| 1394 |
+
"loss": 0.6637,
|
| 1395 |
+
"step": 198
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 2.8564593301435406,
|
| 1399 |
+
"grad_norm": 0.37376391887664795,
|
| 1400 |
+
"learning_rate": 4.55756592088058e-08,
|
| 1401 |
+
"loss": 0.6709,
|
| 1402 |
+
"step": 199
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 2.8708133971291865,
|
| 1406 |
+
"grad_norm": 0.39452144503593445,
|
| 1407 |
+
"learning_rate": 3.4906312870331973e-08,
|
| 1408 |
+
"loss": 0.6988,
|
| 1409 |
+
"step": 200
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 2.8851674641148324,
|
| 1413 |
+
"grad_norm": 0.44208845496177673,
|
| 1414 |
+
"learning_rate": 2.5653383040524228e-08,
|
| 1415 |
+
"loss": 0.7137,
|
| 1416 |
+
"step": 201
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 2.8995215311004783,
|
| 1420 |
+
"grad_norm": 0.4368894100189209,
|
| 1421 |
+
"learning_rate": 1.781950934783505e-08,
|
| 1422 |
+
"loss": 0.6376,
|
| 1423 |
+
"step": 202
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 2.9138755980861246,
|
| 1427 |
+
"grad_norm": 0.42071616649627686,
|
| 1428 |
+
"learning_rate": 1.1406926599646373e-08,
|
| 1429 |
+
"loss": 0.7062,
|
| 1430 |
+
"step": 203
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 2.92822966507177,
|
| 1434 |
+
"grad_norm": 0.41914495825767517,
|
| 1435 |
+
"learning_rate": 6.417464144736208e-09,
|
| 1436 |
+
"loss": 0.705,
|
| 1437 |
+
"step": 204
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 2.9425837320574164,
|
| 1441 |
+
"grad_norm": 0.36943504214286804,
|
| 1442 |
+
"learning_rate": 2.8525453514099966e-09,
|
| 1443 |
+
"loss": 0.5968,
|
| 1444 |
+
"step": 205
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 2.9569377990430623,
|
| 1448 |
+
"grad_norm": 0.44622164964675903,
|
| 1449 |
+
"learning_rate": 7.131872014509711e-10,
|
| 1450 |
+
"loss": 0.7064,
|
| 1451 |
+
"step": 206
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 2.971291866028708,
|
| 1455 |
+
"grad_norm": 0.3761054575443268,
|
| 1456 |
+
"learning_rate": 0.0,
|
| 1457 |
+
"loss": 0.6739,
|
| 1458 |
+
"step": 207
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 2.971291866028708,
|
| 1462 |
+
"step": 207,
|
| 1463 |
+
"total_flos": 188453441536000.0,
|
| 1464 |
+
"train_loss": 0.730322139562616,
|
| 1465 |
+
"train_runtime": 6590.3033,
|
| 1466 |
+
"train_samples_per_second": 3.031,
|
| 1467 |
+
"train_steps_per_second": 0.031
|
| 1468 |
+
}
|
| 1469 |
+
],
|
| 1470 |
+
"logging_steps": 1.0,
|
| 1471 |
+
"max_steps": 207,
|
| 1472 |
+
"num_input_tokens_seen": 0,
|
| 1473 |
+
"num_train_epochs": 3,
|
| 1474 |
+
"save_steps": 500,
|
| 1475 |
+
"stateful_callbacks": {
|
| 1476 |
+
"TrainerControl": {
|
| 1477 |
+
"args": {
|
| 1478 |
+
"should_epoch_stop": false,
|
| 1479 |
+
"should_evaluate": false,
|
| 1480 |
+
"should_log": false,
|
| 1481 |
+
"should_save": true,
|
| 1482 |
+
"should_training_stop": true
|
| 1483 |
+
},
|
| 1484 |
+
"attributes": {}
|
| 1485 |
+
}
|
| 1486 |
+
},
|
| 1487 |
+
"total_flos": 188453441536000.0,
|
| 1488 |
+
"train_batch_size": 1,
|
| 1489 |
+
"trial_name": null,
|
| 1490 |
+
"trial_params": null
|
| 1491 |
+
}
|
training_loss.png
ADDED
|