End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +3297 -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: openthoughts3_30k-remove-wait-keyword
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# openthoughts3_30k-remove-wait-keyword
|
| 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: openthoughts3_30k-remove-wait-keyword
|
|
|
|
| 16 |
|
| 17 |
# openthoughts3_30k-remove-wait-keyword
|
| 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/openthoughts3_30k-remove-wait-keyword dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.953395472703063,
|
| 3 |
+
"total_flos": 1.9803873717092352e+17,
|
| 4 |
+
"train_loss": 0.2650201372321575,
|
| 5 |
+
"train_runtime": 4985.2784,
|
| 6 |
+
"train_samples_per_second": 12.043,
|
| 7 |
+
"train_steps_per_second": 0.093
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.953395472703063,
|
| 3 |
+
"total_flos": 1.9803873717092352e+17,
|
| 4 |
+
"train_loss": 0.2650201372321575,
|
| 5 |
+
"train_runtime": 4985.2784,
|
| 6 |
+
"train_samples_per_second": 12.043,
|
| 7 |
+
"train_steps_per_second": 0.093
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3297 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.953395472703063,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 465,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.010652463382157125,
|
| 13 |
+
"grad_norm": 6.694582820260047,
|
| 14 |
+
"learning_rate": 8.510638297872341e-07,
|
| 15 |
+
"loss": 0.991,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.02130492676431425,
|
| 20 |
+
"grad_norm": 6.934525828023677,
|
| 21 |
+
"learning_rate": 1.7021276595744682e-06,
|
| 22 |
+
"loss": 1.0148,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03195739014647137,
|
| 27 |
+
"grad_norm": 6.814186428135231,
|
| 28 |
+
"learning_rate": 2.553191489361702e-06,
|
| 29 |
+
"loss": 1.0461,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0426098535286285,
|
| 34 |
+
"grad_norm": 5.720763900247745,
|
| 35 |
+
"learning_rate": 3.4042553191489363e-06,
|
| 36 |
+
"loss": 0.952,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.05326231691078562,
|
| 41 |
+
"grad_norm": 4.933349344813986,
|
| 42 |
+
"learning_rate": 4.255319148936171e-06,
|
| 43 |
+
"loss": 0.9508,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.06391478029294274,
|
| 48 |
+
"grad_norm": 2.84398418286523,
|
| 49 |
+
"learning_rate": 5.106382978723404e-06,
|
| 50 |
+
"loss": 0.8426,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.07456724367509987,
|
| 55 |
+
"grad_norm": 2.677627613259147,
|
| 56 |
+
"learning_rate": 5.957446808510638e-06,
|
| 57 |
+
"loss": 0.837,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.085219707057257,
|
| 62 |
+
"grad_norm": 2.413788313157835,
|
| 63 |
+
"learning_rate": 6.808510638297873e-06,
|
| 64 |
+
"loss": 0.8044,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.09587217043941411,
|
| 69 |
+
"grad_norm": 2.4206102286796756,
|
| 70 |
+
"learning_rate": 7.659574468085107e-06,
|
| 71 |
+
"loss": 0.7596,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.10652463382157124,
|
| 76 |
+
"grad_norm": 2.020878777586046,
|
| 77 |
+
"learning_rate": 8.510638297872341e-06,
|
| 78 |
+
"loss": 0.7289,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.11717709720372836,
|
| 83 |
+
"grad_norm": 1.866207727044734,
|
| 84 |
+
"learning_rate": 9.361702127659576e-06,
|
| 85 |
+
"loss": 0.6981,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.1278295605858855,
|
| 90 |
+
"grad_norm": 1.7287109860645355,
|
| 91 |
+
"learning_rate": 1.0212765957446808e-05,
|
| 92 |
+
"loss": 0.7082,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.1384820239680426,
|
| 97 |
+
"grad_norm": 1.6610028389369502,
|
| 98 |
+
"learning_rate": 1.1063829787234044e-05,
|
| 99 |
+
"loss": 0.7113,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.14913448735019974,
|
| 104 |
+
"grad_norm": 1.752463306790842,
|
| 105 |
+
"learning_rate": 1.1914893617021277e-05,
|
| 106 |
+
"loss": 0.7069,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.15978695073235685,
|
| 111 |
+
"grad_norm": 1.5587225319466516,
|
| 112 |
+
"learning_rate": 1.2765957446808513e-05,
|
| 113 |
+
"loss": 0.641,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.170439414114514,
|
| 118 |
+
"grad_norm": 1.3155839596862062,
|
| 119 |
+
"learning_rate": 1.3617021276595745e-05,
|
| 120 |
+
"loss": 0.6473,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.1810918774966711,
|
| 125 |
+
"grad_norm": 1.394090600704381,
|
| 126 |
+
"learning_rate": 1.4468085106382981e-05,
|
| 127 |
+
"loss": 0.693,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.19174434087882822,
|
| 132 |
+
"grad_norm": 1.5853517212384747,
|
| 133 |
+
"learning_rate": 1.5319148936170214e-05,
|
| 134 |
+
"loss": 0.6576,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.20239680426098536,
|
| 139 |
+
"grad_norm": 1.234578222049465,
|
| 140 |
+
"learning_rate": 1.6170212765957446e-05,
|
| 141 |
+
"loss": 0.6178,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.21304926764314247,
|
| 146 |
+
"grad_norm": 1.2163184411074526,
|
| 147 |
+
"learning_rate": 1.7021276595744682e-05,
|
| 148 |
+
"loss": 0.6735,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.2237017310252996,
|
| 153 |
+
"grad_norm": 1.3230219860993193,
|
| 154 |
+
"learning_rate": 1.7872340425531915e-05,
|
| 155 |
+
"loss": 0.6076,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.23435419440745672,
|
| 160 |
+
"grad_norm": 1.2488982306263348,
|
| 161 |
+
"learning_rate": 1.872340425531915e-05,
|
| 162 |
+
"loss": 0.6772,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.24500665778961384,
|
| 167 |
+
"grad_norm": 1.134842886185398,
|
| 168 |
+
"learning_rate": 1.9574468085106384e-05,
|
| 169 |
+
"loss": 0.6153,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.255659121171771,
|
| 174 |
+
"grad_norm": 1.0126133389489638,
|
| 175 |
+
"learning_rate": 2.0425531914893616e-05,
|
| 176 |
+
"loss": 0.5597,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.2663115845539281,
|
| 181 |
+
"grad_norm": 1.0471199169034155,
|
| 182 |
+
"learning_rate": 2.1276595744680852e-05,
|
| 183 |
+
"loss": 0.603,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.2769640479360852,
|
| 188 |
+
"grad_norm": 0.9867126329414225,
|
| 189 |
+
"learning_rate": 2.2127659574468088e-05,
|
| 190 |
+
"loss": 0.6395,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.28761651131824234,
|
| 195 |
+
"grad_norm": 0.8952834587992327,
|
| 196 |
+
"learning_rate": 2.2978723404255324e-05,
|
| 197 |
+
"loss": 0.6158,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.2982689747003995,
|
| 202 |
+
"grad_norm": 0.828052446949026,
|
| 203 |
+
"learning_rate": 2.3829787234042553e-05,
|
| 204 |
+
"loss": 0.6219,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.30892143808255657,
|
| 209 |
+
"grad_norm": 0.9690391719301804,
|
| 210 |
+
"learning_rate": 2.468085106382979e-05,
|
| 211 |
+
"loss": 0.6232,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.3195739014647137,
|
| 216 |
+
"grad_norm": 0.7991529058271261,
|
| 217 |
+
"learning_rate": 2.5531914893617025e-05,
|
| 218 |
+
"loss": 0.6181,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.33022636484687085,
|
| 223 |
+
"grad_norm": 0.768057849973364,
|
| 224 |
+
"learning_rate": 2.6382978723404255e-05,
|
| 225 |
+
"loss": 0.6266,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.340878828229028,
|
| 230 |
+
"grad_norm": 0.8886202481876829,
|
| 231 |
+
"learning_rate": 2.723404255319149e-05,
|
| 232 |
+
"loss": 0.6693,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.35153129161118507,
|
| 237 |
+
"grad_norm": 0.794323702445206,
|
| 238 |
+
"learning_rate": 2.8085106382978727e-05,
|
| 239 |
+
"loss": 0.6133,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.3621837549933422,
|
| 244 |
+
"grad_norm": 0.8319441008002462,
|
| 245 |
+
"learning_rate": 2.8936170212765963e-05,
|
| 246 |
+
"loss": 0.6235,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.37283621837549935,
|
| 251 |
+
"grad_norm": 0.8327561015577186,
|
| 252 |
+
"learning_rate": 2.9787234042553192e-05,
|
| 253 |
+
"loss": 0.5815,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.38348868175765644,
|
| 258 |
+
"grad_norm": 0.7446136950556361,
|
| 259 |
+
"learning_rate": 3.063829787234043e-05,
|
| 260 |
+
"loss": 0.5851,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.3941411451398136,
|
| 265 |
+
"grad_norm": 0.7934681920233486,
|
| 266 |
+
"learning_rate": 3.1489361702127664e-05,
|
| 267 |
+
"loss": 0.639,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.4047936085219707,
|
| 272 |
+
"grad_norm": 0.8433343276802733,
|
| 273 |
+
"learning_rate": 3.234042553191489e-05,
|
| 274 |
+
"loss": 0.6266,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.41544607190412786,
|
| 279 |
+
"grad_norm": 0.7571545758660359,
|
| 280 |
+
"learning_rate": 3.319148936170213e-05,
|
| 281 |
+
"loss": 0.5787,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.42609853528628494,
|
| 286 |
+
"grad_norm": 0.8477594508017096,
|
| 287 |
+
"learning_rate": 3.4042553191489365e-05,
|
| 288 |
+
"loss": 0.6132,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.4367509986684421,
|
| 293 |
+
"grad_norm": 0.9038718680156956,
|
| 294 |
+
"learning_rate": 3.48936170212766e-05,
|
| 295 |
+
"loss": 0.6179,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.4474034620505992,
|
| 300 |
+
"grad_norm": 0.7820035154892006,
|
| 301 |
+
"learning_rate": 3.574468085106383e-05,
|
| 302 |
+
"loss": 0.5945,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.4580559254327563,
|
| 307 |
+
"grad_norm": 0.8742594253268018,
|
| 308 |
+
"learning_rate": 3.6595744680851066e-05,
|
| 309 |
+
"loss": 0.5802,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.46870838881491345,
|
| 314 |
+
"grad_norm": 0.7817361370610609,
|
| 315 |
+
"learning_rate": 3.74468085106383e-05,
|
| 316 |
+
"loss": 0.5802,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.4793608521970706,
|
| 321 |
+
"grad_norm": 0.9654945348490969,
|
| 322 |
+
"learning_rate": 3.829787234042554e-05,
|
| 323 |
+
"loss": 0.6652,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.49001331557922767,
|
| 328 |
+
"grad_norm": 0.793589538371812,
|
| 329 |
+
"learning_rate": 3.914893617021277e-05,
|
| 330 |
+
"loss": 0.6015,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.5006657789613849,
|
| 335 |
+
"grad_norm": 0.8089846636941147,
|
| 336 |
+
"learning_rate": 4e-05,
|
| 337 |
+
"loss": 0.5485,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.511318242343542,
|
| 342 |
+
"grad_norm": 0.8236119108492971,
|
| 343 |
+
"learning_rate": 3.999943513438666e-05,
|
| 344 |
+
"loss": 0.6397,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.521970705725699,
|
| 349 |
+
"grad_norm": 0.7613794604490082,
|
| 350 |
+
"learning_rate": 3.9997740569453936e-05,
|
| 351 |
+
"loss": 0.5915,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.5326231691078562,
|
| 356 |
+
"grad_norm": 0.8112497601788959,
|
| 357 |
+
"learning_rate": 3.999491640092199e-05,
|
| 358 |
+
"loss": 0.6177,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.5432756324900133,
|
| 363 |
+
"grad_norm": 0.880950888784645,
|
| 364 |
+
"learning_rate": 3.999096278831838e-05,
|
| 365 |
+
"loss": 0.6163,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.5539280958721704,
|
| 370 |
+
"grad_norm": 0.7379143121906132,
|
| 371 |
+
"learning_rate": 3.998587995496908e-05,
|
| 372 |
+
"loss": 0.6182,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.5645805592543276,
|
| 377 |
+
"grad_norm": 0.7377408173935159,
|
| 378 |
+
"learning_rate": 3.997966818798589e-05,
|
| 379 |
+
"loss": 0.6132,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.5752330226364847,
|
| 384 |
+
"grad_norm": 0.7051300826491897,
|
| 385 |
+
"learning_rate": 3.9972327838250155e-05,
|
| 386 |
+
"loss": 0.6066,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.5858854860186418,
|
| 391 |
+
"grad_norm": 0.732126732322628,
|
| 392 |
+
"learning_rate": 3.9963859320392984e-05,
|
| 393 |
+
"loss": 0.6299,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.596537949400799,
|
| 398 |
+
"grad_norm": 0.7065578306021327,
|
| 399 |
+
"learning_rate": 3.995426311277184e-05,
|
| 400 |
+
"loss": 0.6434,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.607190412782956,
|
| 405 |
+
"grad_norm": 0.7469899885869034,
|
| 406 |
+
"learning_rate": 3.9943539757443494e-05,
|
| 407 |
+
"loss": 0.6381,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.6178428761651131,
|
| 412 |
+
"grad_norm": 0.6874803986574024,
|
| 413 |
+
"learning_rate": 3.99316898601334e-05,
|
| 414 |
+
"loss": 0.6073,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.6284953395472703,
|
| 419 |
+
"grad_norm": 0.7854737965676948,
|
| 420 |
+
"learning_rate": 3.991871409020153e-05,
|
| 421 |
+
"loss": 0.616,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.6391478029294274,
|
| 426 |
+
"grad_norm": 0.7692374923814914,
|
| 427 |
+
"learning_rate": 3.9904613180604493e-05,
|
| 428 |
+
"loss": 0.5792,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.6498002663115846,
|
| 433 |
+
"grad_norm": 0.71498427366643,
|
| 434 |
+
"learning_rate": 3.9889387927854184e-05,
|
| 435 |
+
"loss": 0.627,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.6604527296937417,
|
| 440 |
+
"grad_norm": 0.7346979399518049,
|
| 441 |
+
"learning_rate": 3.987303919197279e-05,
|
| 442 |
+
"loss": 0.6034,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.6711051930758988,
|
| 447 |
+
"grad_norm": 0.7297833699595513,
|
| 448 |
+
"learning_rate": 3.985556789644417e-05,
|
| 449 |
+
"loss": 0.5677,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.681757656458056,
|
| 454 |
+
"grad_norm": 0.7470894539401008,
|
| 455 |
+
"learning_rate": 3.9836975028161735e-05,
|
| 456 |
+
"loss": 0.6235,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.6924101198402131,
|
| 461 |
+
"grad_norm": 0.7614446032341707,
|
| 462 |
+
"learning_rate": 3.981726163737268e-05,
|
| 463 |
+
"loss": 0.5673,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.7030625832223701,
|
| 468 |
+
"grad_norm": 0.6779469410395942,
|
| 469 |
+
"learning_rate": 3.979642883761866e-05,
|
| 470 |
+
"loss": 0.5882,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.7137150466045273,
|
| 475 |
+
"grad_norm": 0.6640316107983828,
|
| 476 |
+
"learning_rate": 3.97744778056729e-05,
|
| 477 |
+
"loss": 0.6291,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.7243675099866844,
|
| 482 |
+
"grad_norm": 0.7081557965048705,
|
| 483 |
+
"learning_rate": 3.975140978147371e-05,
|
| 484 |
+
"loss": 0.6076,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.7350199733688415,
|
| 489 |
+
"grad_norm": 0.694454644625491,
|
| 490 |
+
"learning_rate": 3.972722606805445e-05,
|
| 491 |
+
"loss": 0.6376,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.7456724367509987,
|
| 496 |
+
"grad_norm": 0.6870418447207188,
|
| 497 |
+
"learning_rate": 3.970192803146994e-05,
|
| 498 |
+
"loss": 0.5903,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.7563249001331558,
|
| 503 |
+
"grad_norm": 0.6836159074080826,
|
| 504 |
+
"learning_rate": 3.9675517100719275e-05,
|
| 505 |
+
"loss": 0.6174,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.7669773635153129,
|
| 510 |
+
"grad_norm": 0.6996687482095345,
|
| 511 |
+
"learning_rate": 3.96479947676651e-05,
|
| 512 |
+
"loss": 0.568,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.7776298268974701,
|
| 517 |
+
"grad_norm": 0.7796487636295794,
|
| 518 |
+
"learning_rate": 3.9619362586949385e-05,
|
| 519 |
+
"loss": 0.5989,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.7882822902796272,
|
| 524 |
+
"grad_norm": 0.7200601244038982,
|
| 525 |
+
"learning_rate": 3.958962217590556e-05,
|
| 526 |
+
"loss": 0.6334,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.7989347536617842,
|
| 531 |
+
"grad_norm": 0.7597411418971725,
|
| 532 |
+
"learning_rate": 3.955877521446717e-05,
|
| 533 |
+
"loss": 0.5925,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.8095872170439414,
|
| 538 |
+
"grad_norm": 0.6407939868382735,
|
| 539 |
+
"learning_rate": 3.952682344507301e-05,
|
| 540 |
+
"loss": 0.6006,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.8202396804260985,
|
| 545 |
+
"grad_norm": 0.7858541438697079,
|
| 546 |
+
"learning_rate": 3.949376867256863e-05,
|
| 547 |
+
"loss": 0.6418,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.8308921438082557,
|
| 552 |
+
"grad_norm": 0.7093159715837254,
|
| 553 |
+
"learning_rate": 3.94596127641045e-05,
|
| 554 |
+
"loss": 0.5977,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.8415446071904128,
|
| 559 |
+
"grad_norm": 0.726278226692793,
|
| 560 |
+
"learning_rate": 3.942435764903042e-05,
|
| 561 |
+
"loss": 0.6384,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.8521970705725699,
|
| 566 |
+
"grad_norm": 0.7036056678460968,
|
| 567 |
+
"learning_rate": 3.938800531878661e-05,
|
| 568 |
+
"loss": 0.6144,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.8628495339547271,
|
| 573 |
+
"grad_norm": 0.6706553114803088,
|
| 574 |
+
"learning_rate": 3.935055782679121e-05,
|
| 575 |
+
"loss": 0.6264,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.8735019973368842,
|
| 580 |
+
"grad_norm": 0.6315758713393529,
|
| 581 |
+
"learning_rate": 3.931201728832427e-05,
|
| 582 |
+
"loss": 0.5466,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.8841544607190412,
|
| 587 |
+
"grad_norm": 0.6571221020229784,
|
| 588 |
+
"learning_rate": 3.927238588040827e-05,
|
| 589 |
+
"loss": 0.6366,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.8948069241011984,
|
| 594 |
+
"grad_norm": 0.6536459952965957,
|
| 595 |
+
"learning_rate": 3.923166584168518e-05,
|
| 596 |
+
"loss": 0.6014,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.9054593874833555,
|
| 601 |
+
"grad_norm": 0.68876294668073,
|
| 602 |
+
"learning_rate": 3.9189859472289956e-05,
|
| 603 |
+
"loss": 0.6437,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.9161118508655126,
|
| 608 |
+
"grad_norm": 0.6015832738312215,
|
| 609 |
+
"learning_rate": 3.914696913372064e-05,
|
| 610 |
+
"loss": 0.5745,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.9267643142476698,
|
| 615 |
+
"grad_norm": 0.6349782497201141,
|
| 616 |
+
"learning_rate": 3.9102997248704994e-05,
|
| 617 |
+
"loss": 0.5937,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.9374167776298269,
|
| 622 |
+
"grad_norm": 0.6694602546567809,
|
| 623 |
+
"learning_rate": 3.9057946301063573e-05,
|
| 624 |
+
"loss": 0.6533,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.948069241011984,
|
| 629 |
+
"grad_norm": 0.6318139844939943,
|
| 630 |
+
"learning_rate": 3.9011818835569516e-05,
|
| 631 |
+
"loss": 0.5759,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.9587217043941412,
|
| 636 |
+
"grad_norm": 0.6541944152732958,
|
| 637 |
+
"learning_rate": 3.8964617457804716e-05,
|
| 638 |
+
"loss": 0.6224,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.9693741677762983,
|
| 643 |
+
"grad_norm": 0.691703858533324,
|
| 644 |
+
"learning_rate": 3.8916344834012695e-05,
|
| 645 |
+
"loss": 0.624,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.9800266311584553,
|
| 650 |
+
"grad_norm": 0.6896051779788368,
|
| 651 |
+
"learning_rate": 3.886700369094799e-05,
|
| 652 |
+
"loss": 0.5995,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.9906790945406125,
|
| 657 |
+
"grad_norm": 0.783990137866763,
|
| 658 |
+
"learning_rate": 3.881659681572209e-05,
|
| 659 |
+
"loss": 0.6559,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.0013315579227697,
|
| 664 |
+
"grad_norm": 0.6393323225369558,
|
| 665 |
+
"learning_rate": 3.876512705564605e-05,
|
| 666 |
+
"loss": 0.6031,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.0119840213049267,
|
| 671 |
+
"grad_norm": 0.8078733724854775,
|
| 672 |
+
"learning_rate": 3.871259731806964e-05,
|
| 673 |
+
"loss": 0.4262,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.022636484687084,
|
| 678 |
+
"grad_norm": 0.6475808924691705,
|
| 679 |
+
"learning_rate": 3.865901057021709e-05,
|
| 680 |
+
"loss": 0.4225,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.033288948069241,
|
| 685 |
+
"grad_norm": 0.7124426858917078,
|
| 686 |
+
"learning_rate": 3.8604369839019515e-05,
|
| 687 |
+
"loss": 0.409,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.043941411451398,
|
| 692 |
+
"grad_norm": 0.7478623022254682,
|
| 693 |
+
"learning_rate": 3.854867821094394e-05,
|
| 694 |
+
"loss": 0.3785,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 1.0545938748335553,
|
| 699 |
+
"grad_norm": 0.7581534354456471,
|
| 700 |
+
"learning_rate": 3.849193883181893e-05,
|
| 701 |
+
"loss": 0.3891,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.0652463382157125,
|
| 706 |
+
"grad_norm": 0.7659604994928921,
|
| 707 |
+
"learning_rate": 3.84341549066569e-05,
|
| 708 |
+
"loss": 0.3586,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.0758988015978694,
|
| 713 |
+
"grad_norm": 0.6866738663397853,
|
| 714 |
+
"learning_rate": 3.8375329699473083e-05,
|
| 715 |
+
"loss": 0.3643,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 1.0865512649800266,
|
| 720 |
+
"grad_norm": 0.8748839151979945,
|
| 721 |
+
"learning_rate": 3.8315466533101154e-05,
|
| 722 |
+
"loss": 0.3703,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.0972037283621838,
|
| 727 |
+
"grad_norm": 0.7751831586867313,
|
| 728 |
+
"learning_rate": 3.825456878900553e-05,
|
| 729 |
+
"loss": 0.3968,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.1078561917443408,
|
| 734 |
+
"grad_norm": 0.6551120473097987,
|
| 735 |
+
"learning_rate": 3.819263990709037e-05,
|
| 736 |
+
"loss": 0.4043,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.118508655126498,
|
| 741 |
+
"grad_norm": 0.8089326816837956,
|
| 742 |
+
"learning_rate": 3.812968338550526e-05,
|
| 743 |
+
"loss": 0.3844,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.1291611185086552,
|
| 748 |
+
"grad_norm": 0.8239481281715038,
|
| 749 |
+
"learning_rate": 3.806570278044762e-05,
|
| 750 |
+
"loss": 0.4267,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.1398135818908122,
|
| 755 |
+
"grad_norm": 0.7184100343708437,
|
| 756 |
+
"learning_rate": 3.800070170596182e-05,
|
| 757 |
+
"loss": 0.387,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.1504660452729694,
|
| 762 |
+
"grad_norm": 0.7221070257677683,
|
| 763 |
+
"learning_rate": 3.793468383373504e-05,
|
| 764 |
+
"loss": 0.3916,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.1611185086551266,
|
| 769 |
+
"grad_norm": 0.7164528829044456,
|
| 770 |
+
"learning_rate": 3.7867652892889866e-05,
|
| 771 |
+
"loss": 0.3976,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 1.1717709720372835,
|
| 776 |
+
"grad_norm": 0.700725371255347,
|
| 777 |
+
"learning_rate": 3.779961266977366e-05,
|
| 778 |
+
"loss": 0.3915,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.1824234354194407,
|
| 783 |
+
"grad_norm": 0.7416951486930033,
|
| 784 |
+
"learning_rate": 3.773056700774465e-05,
|
| 785 |
+
"loss": 0.3732,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.193075898801598,
|
| 790 |
+
"grad_norm": 0.7068347406551115,
|
| 791 |
+
"learning_rate": 3.766051980695485e-05,
|
| 792 |
+
"loss": 0.4115,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.203728362183755,
|
| 797 |
+
"grad_norm": 0.7308269580159338,
|
| 798 |
+
"learning_rate": 3.758947502412978e-05,
|
| 799 |
+
"loss": 0.354,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 1.214380825565912,
|
| 804 |
+
"grad_norm": 0.6925826764401292,
|
| 805 |
+
"learning_rate": 3.7517436672344924e-05,
|
| 806 |
+
"loss": 0.3981,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.2250332889480693,
|
| 811 |
+
"grad_norm": 0.7361655302552005,
|
| 812 |
+
"learning_rate": 3.744440882079905e-05,
|
| 813 |
+
"loss": 0.3708,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 1.2356857523302263,
|
| 818 |
+
"grad_norm": 0.6414214849748002,
|
| 819 |
+
"learning_rate": 3.737039559458436e-05,
|
| 820 |
+
"loss": 0.3909,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 1.2463382157123835,
|
| 825 |
+
"grad_norm": 0.6832468213952014,
|
| 826 |
+
"learning_rate": 3.729540117445352e-05,
|
| 827 |
+
"loss": 0.3438,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 1.2569906790945407,
|
| 832 |
+
"grad_norm": 0.6680520098825485,
|
| 833 |
+
"learning_rate": 3.721942979658343e-05,
|
| 834 |
+
"loss": 0.3745,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 1.2676431424766976,
|
| 839 |
+
"grad_norm": 0.7107638071447948,
|
| 840 |
+
"learning_rate": 3.714248575233599e-05,
|
| 841 |
+
"loss": 0.4003,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 1.2782956058588548,
|
| 846 |
+
"grad_norm": 0.7048731664451507,
|
| 847 |
+
"learning_rate": 3.706457338801568e-05,
|
| 848 |
+
"loss": 0.3971,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.288948069241012,
|
| 853 |
+
"grad_norm": 0.671387329775309,
|
| 854 |
+
"learning_rate": 3.698569710462403e-05,
|
| 855 |
+
"loss": 0.416,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 1.299600532623169,
|
| 860 |
+
"grad_norm": 0.6923527864787764,
|
| 861 |
+
"learning_rate": 3.690586135761107e-05,
|
| 862 |
+
"loss": 0.3694,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 1.3102529960053262,
|
| 867 |
+
"grad_norm": 0.6671223662423846,
|
| 868 |
+
"learning_rate": 3.6825070656623626e-05,
|
| 869 |
+
"loss": 0.3686,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 1.3209054593874834,
|
| 874 |
+
"grad_norm": 0.6179002247676705,
|
| 875 |
+
"learning_rate": 3.6743329565250575e-05,
|
| 876 |
+
"loss": 0.3887,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 1.3315579227696404,
|
| 881 |
+
"grad_norm": 0.6275268085452516,
|
| 882 |
+
"learning_rate": 3.666064270076509e-05,
|
| 883 |
+
"loss": 0.3964,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 1.3422103861517976,
|
| 888 |
+
"grad_norm": 0.6245614761828496,
|
| 889 |
+
"learning_rate": 3.657701473386381e-05,
|
| 890 |
+
"loss": 0.3925,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 1.3528628495339547,
|
| 895 |
+
"grad_norm": 0.6395089453767527,
|
| 896 |
+
"learning_rate": 3.6492450388403034e-05,
|
| 897 |
+
"loss": 0.3848,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 1.3635153129161117,
|
| 902 |
+
"grad_norm": 0.635546813033603,
|
| 903 |
+
"learning_rate": 3.6406954441131825e-05,
|
| 904 |
+
"loss": 0.3542,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 1.374167776298269,
|
| 909 |
+
"grad_norm": 0.6411908185784543,
|
| 910 |
+
"learning_rate": 3.632053172142227e-05,
|
| 911 |
+
"loss": 0.4172,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 1.3848202396804261,
|
| 916 |
+
"grad_norm": 0.7666298135547305,
|
| 917 |
+
"learning_rate": 3.6233187110996615e-05,
|
| 918 |
+
"loss": 0.374,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 1.395472703062583,
|
| 923 |
+
"grad_norm": 0.6617741566842532,
|
| 924 |
+
"learning_rate": 3.614492554365156e-05,
|
| 925 |
+
"loss": 0.3911,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 1.4061251664447403,
|
| 930 |
+
"grad_norm": 0.6644494144999019,
|
| 931 |
+
"learning_rate": 3.605575200497954e-05,
|
| 932 |
+
"loss": 0.3825,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.4167776298268975,
|
| 937 |
+
"grad_norm": 0.6457857285572485,
|
| 938 |
+
"learning_rate": 3.596567153208712e-05,
|
| 939 |
+
"loss": 0.3892,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.4274300932090547,
|
| 944 |
+
"grad_norm": 0.7060653234701035,
|
| 945 |
+
"learning_rate": 3.5874689213310456e-05,
|
| 946 |
+
"loss": 0.3913,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.4380825565912116,
|
| 951 |
+
"grad_norm": 0.6418935089176939,
|
| 952 |
+
"learning_rate": 3.578281018792788e-05,
|
| 953 |
+
"loss": 0.367,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 1.4487350199733688,
|
| 958 |
+
"grad_norm": 0.6635217849381326,
|
| 959 |
+
"learning_rate": 3.569003964586958e-05,
|
| 960 |
+
"loss": 0.407,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 1.459387483355526,
|
| 965 |
+
"grad_norm": 0.6918013132372305,
|
| 966 |
+
"learning_rate": 3.559638282742449e-05,
|
| 967 |
+
"loss": 0.4089,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 1.470039946737683,
|
| 972 |
+
"grad_norm": 0.6691290363096077,
|
| 973 |
+
"learning_rate": 3.550184502294422e-05,
|
| 974 |
+
"loss": 0.3489,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 1.4806924101198402,
|
| 979 |
+
"grad_norm": 0.649679269488627,
|
| 980 |
+
"learning_rate": 3.540643157254426e-05,
|
| 981 |
+
"loss": 0.362,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 1.4913448735019974,
|
| 986 |
+
"grad_norm": 0.6870334313856638,
|
| 987 |
+
"learning_rate": 3.531014786580234e-05,
|
| 988 |
+
"loss": 0.3946,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 1.5019973368841546,
|
| 993 |
+
"grad_norm": 0.6630094947277725,
|
| 994 |
+
"learning_rate": 3.5212999341453943e-05,
|
| 995 |
+
"loss": 0.3681,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 1.5126498002663116,
|
| 1000 |
+
"grad_norm": 0.75626618474493,
|
| 1001 |
+
"learning_rate": 3.511499148708517e-05,
|
| 1002 |
+
"loss": 0.3756,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 1.5233022636484685,
|
| 1007 |
+
"grad_norm": 0.5856621666895204,
|
| 1008 |
+
"learning_rate": 3.501612983882269e-05,
|
| 1009 |
+
"loss": 0.3844,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 1.533954727030626,
|
| 1014 |
+
"grad_norm": 0.7204708435767242,
|
| 1015 |
+
"learning_rate": 3.491641998102106e-05,
|
| 1016 |
+
"loss": 0.389,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 1.544607190412783,
|
| 1021 |
+
"grad_norm": 0.7011406345108379,
|
| 1022 |
+
"learning_rate": 3.4815867545947276e-05,
|
| 1023 |
+
"loss": 0.389,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 1.5552596537949401,
|
| 1028 |
+
"grad_norm": 0.6117320896924393,
|
| 1029 |
+
"learning_rate": 3.471447821346264e-05,
|
| 1030 |
+
"loss": 0.4308,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 1.5659121171770973,
|
| 1035 |
+
"grad_norm": 0.6332570304405356,
|
| 1036 |
+
"learning_rate": 3.461225771070188e-05,
|
| 1037 |
+
"loss": 0.4041,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 1.5765645805592543,
|
| 1042 |
+
"grad_norm": 0.6228667901677301,
|
| 1043 |
+
"learning_rate": 3.4509211811749724e-05,
|
| 1044 |
+
"loss": 0.396,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 1.5872170439414115,
|
| 1049 |
+
"grad_norm": 0.5726497539128409,
|
| 1050 |
+
"learning_rate": 3.4405346337314635e-05,
|
| 1051 |
+
"loss": 0.3846,
|
| 1052 |
+
"step": 149
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 1.5978695073235687,
|
| 1056 |
+
"grad_norm": 0.599533905128129,
|
| 1057 |
+
"learning_rate": 3.4300667154400125e-05,
|
| 1058 |
+
"loss": 0.3931,
|
| 1059 |
+
"step": 150
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 1.6085219707057257,
|
| 1063 |
+
"grad_norm": 0.6886718332188476,
|
| 1064 |
+
"learning_rate": 3.419518017597326e-05,
|
| 1065 |
+
"loss": 0.4217,
|
| 1066 |
+
"step": 151
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 1.6191744340878829,
|
| 1070 |
+
"grad_norm": 0.6144658238325302,
|
| 1071 |
+
"learning_rate": 3.408889136063075e-05,
|
| 1072 |
+
"loss": 0.4018,
|
| 1073 |
+
"step": 152
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 1.62982689747004,
|
| 1077 |
+
"grad_norm": 0.6012487881941726,
|
| 1078 |
+
"learning_rate": 3.398180671226225e-05,
|
| 1079 |
+
"loss": 0.3969,
|
| 1080 |
+
"step": 153
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 1.640479360852197,
|
| 1084 |
+
"grad_norm": 0.6524870708546637,
|
| 1085 |
+
"learning_rate": 3.387393227971133e-05,
|
| 1086 |
+
"loss": 0.4037,
|
| 1087 |
+
"step": 154
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 1.6511318242343542,
|
| 1091 |
+
"grad_norm": 0.5883338993634286,
|
| 1092 |
+
"learning_rate": 3.376527415643373e-05,
|
| 1093 |
+
"loss": 0.3865,
|
| 1094 |
+
"step": 155
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 1.6617842876165114,
|
| 1098 |
+
"grad_norm": 0.6397426988376612,
|
| 1099 |
+
"learning_rate": 3.3655838480153224e-05,
|
| 1100 |
+
"loss": 0.396,
|
| 1101 |
+
"step": 156
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 1.6724367509986684,
|
| 1105 |
+
"grad_norm": 0.6103008620729216,
|
| 1106 |
+
"learning_rate": 3.354563143251483e-05,
|
| 1107 |
+
"loss": 0.3769,
|
| 1108 |
+
"step": 157
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 1.6830892143808256,
|
| 1112 |
+
"grad_norm": 0.6004255634499251,
|
| 1113 |
+
"learning_rate": 3.34346592387357e-05,
|
| 1114 |
+
"loss": 0.3645,
|
| 1115 |
+
"step": 158
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 1.6937416777629828,
|
| 1119 |
+
"grad_norm": 0.6036702426728494,
|
| 1120 |
+
"learning_rate": 3.332292816725347e-05,
|
| 1121 |
+
"loss": 0.3663,
|
| 1122 |
+
"step": 159
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 1.7043941411451398,
|
| 1126 |
+
"grad_norm": 0.6073712663772787,
|
| 1127 |
+
"learning_rate": 3.321044452937217e-05,
|
| 1128 |
+
"loss": 0.3902,
|
| 1129 |
+
"step": 160
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.715046604527297,
|
| 1133 |
+
"grad_norm": 0.6490214616313742,
|
| 1134 |
+
"learning_rate": 3.309721467890571e-05,
|
| 1135 |
+
"loss": 0.4044,
|
| 1136 |
+
"step": 161
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 1.7256990679094542,
|
| 1140 |
+
"grad_norm": 0.5940700008175323,
|
| 1141 |
+
"learning_rate": 3.2983245011818965e-05,
|
| 1142 |
+
"loss": 0.3911,
|
| 1143 |
+
"step": 162
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 1.7363515312916111,
|
| 1147 |
+
"grad_norm": 0.6423254107446698,
|
| 1148 |
+
"learning_rate": 3.2868541965866544e-05,
|
| 1149 |
+
"loss": 0.4094,
|
| 1150 |
+
"step": 163
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 1.7470039946737683,
|
| 1154 |
+
"grad_norm": 0.6147734618815144,
|
| 1155 |
+
"learning_rate": 3.275311202022908e-05,
|
| 1156 |
+
"loss": 0.4109,
|
| 1157 |
+
"step": 164
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.7576564580559255,
|
| 1161 |
+
"grad_norm": 0.5993696149303476,
|
| 1162 |
+
"learning_rate": 3.263696169514728e-05,
|
| 1163 |
+
"loss": 0.3874,
|
| 1164 |
+
"step": 165
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 1.7683089214380825,
|
| 1168 |
+
"grad_norm": 0.5945088036605433,
|
| 1169 |
+
"learning_rate": 3.252009755155361e-05,
|
| 1170 |
+
"loss": 0.4,
|
| 1171 |
+
"step": 166
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 1.7789613848202397,
|
| 1175 |
+
"grad_norm": 0.5997790822451702,
|
| 1176 |
+
"learning_rate": 3.2402526190701667e-05,
|
| 1177 |
+
"loss": 0.3624,
|
| 1178 |
+
"step": 167
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 1.7896138482023969,
|
| 1182 |
+
"grad_norm": 0.6127787295744731,
|
| 1183 |
+
"learning_rate": 3.2284254253793364e-05,
|
| 1184 |
+
"loss": 0.3898,
|
| 1185 |
+
"step": 168
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.8002663115845539,
|
| 1189 |
+
"grad_norm": 0.6316488250609642,
|
| 1190 |
+
"learning_rate": 3.216528842160369e-05,
|
| 1191 |
+
"loss": 0.3895,
|
| 1192 |
+
"step": 169
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 1.810918774966711,
|
| 1196 |
+
"grad_norm": 0.6245225342354399,
|
| 1197 |
+
"learning_rate": 3.204563541410344e-05,
|
| 1198 |
+
"loss": 0.389,
|
| 1199 |
+
"step": 170
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 1.8215712383488682,
|
| 1203 |
+
"grad_norm": 0.5599370106841661,
|
| 1204 |
+
"learning_rate": 3.192530199007957e-05,
|
| 1205 |
+
"loss": 0.3866,
|
| 1206 |
+
"step": 171
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 1.8322237017310252,
|
| 1210 |
+
"grad_norm": 0.5734064274240126,
|
| 1211 |
+
"learning_rate": 3.180429494675339e-05,
|
| 1212 |
+
"loss": 0.3867,
|
| 1213 |
+
"step": 172
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 1.8428761651131824,
|
| 1217 |
+
"grad_norm": 0.5961528708728638,
|
| 1218 |
+
"learning_rate": 3.168262111939669e-05,
|
| 1219 |
+
"loss": 0.3561,
|
| 1220 |
+
"step": 173
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 1.8535286284953396,
|
| 1224 |
+
"grad_norm": 0.6233196516283475,
|
| 1225 |
+
"learning_rate": 3.156028738094558e-05,
|
| 1226 |
+
"loss": 0.3837,
|
| 1227 |
+
"step": 174
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 1.8641810918774966,
|
| 1231 |
+
"grad_norm": 0.5992513664407727,
|
| 1232 |
+
"learning_rate": 3.143730064161229e-05,
|
| 1233 |
+
"loss": 0.425,
|
| 1234 |
+
"step": 175
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 1.8748335552596538,
|
| 1238 |
+
"grad_norm": 0.6292149686962109,
|
| 1239 |
+
"learning_rate": 3.13136678484948e-05,
|
| 1240 |
+
"loss": 0.4122,
|
| 1241 |
+
"step": 176
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 1.885486018641811,
|
| 1245 |
+
"grad_norm": 0.5741535677337039,
|
| 1246 |
+
"learning_rate": 3.1189395985184464e-05,
|
| 1247 |
+
"loss": 0.3728,
|
| 1248 |
+
"step": 177
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 1.896138482023968,
|
| 1252 |
+
"grad_norm": 0.5762229761063223,
|
| 1253 |
+
"learning_rate": 3.106449207137151e-05,
|
| 1254 |
+
"loss": 0.3523,
|
| 1255 |
+
"step": 178
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 1.9067909454061251,
|
| 1259 |
+
"grad_norm": 0.6127009897475462,
|
| 1260 |
+
"learning_rate": 3.093896316244855e-05,
|
| 1261 |
+
"loss": 0.4096,
|
| 1262 |
+
"step": 179
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 1.9174434087882823,
|
| 1266 |
+
"grad_norm": 0.6341727249160932,
|
| 1267 |
+
"learning_rate": 3.0812816349111956e-05,
|
| 1268 |
+
"loss": 0.4181,
|
| 1269 |
+
"step": 180
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.9280958721704393,
|
| 1273 |
+
"grad_norm": 0.6339469906630394,
|
| 1274 |
+
"learning_rate": 3.0686058756961465e-05,
|
| 1275 |
+
"loss": 0.4008,
|
| 1276 |
+
"step": 181
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 1.9387483355525965,
|
| 1280 |
+
"grad_norm": 0.5906461080186021,
|
| 1281 |
+
"learning_rate": 3.055869754609758e-05,
|
| 1282 |
+
"loss": 0.3888,
|
| 1283 |
+
"step": 182
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 1.9494007989347537,
|
| 1287 |
+
"grad_norm": 0.5667610861318522,
|
| 1288 |
+
"learning_rate": 3.0430739910717136e-05,
|
| 1289 |
+
"loss": 0.4155,
|
| 1290 |
+
"step": 183
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 1.9600532623169107,
|
| 1294 |
+
"grad_norm": 0.6093165171796999,
|
| 1295 |
+
"learning_rate": 3.0302193078706962e-05,
|
| 1296 |
+
"loss": 0.3726,
|
| 1297 |
+
"step": 184
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 1.9707057256990679,
|
| 1301 |
+
"grad_norm": 0.5790885779034644,
|
| 1302 |
+
"learning_rate": 3.017306431123557e-05,
|
| 1303 |
+
"loss": 0.4012,
|
| 1304 |
+
"step": 185
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 1.981358189081225,
|
| 1308 |
+
"grad_norm": 0.5992446721440852,
|
| 1309 |
+
"learning_rate": 3.0043360902342998e-05,
|
| 1310 |
+
"loss": 0.4017,
|
| 1311 |
+
"step": 186
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 1.992010652463382,
|
| 1315 |
+
"grad_norm": 0.6047912851670211,
|
| 1316 |
+
"learning_rate": 2.9913090178528815e-05,
|
| 1317 |
+
"loss": 0.4155,
|
| 1318 |
+
"step": 187
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 2.0026631158455395,
|
| 1322 |
+
"grad_norm": 0.6484645840218354,
|
| 1323 |
+
"learning_rate": 2.978225949833824e-05,
|
| 1324 |
+
"loss": 0.3281,
|
| 1325 |
+
"step": 188
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 2.0133155792276964,
|
| 1329 |
+
"grad_norm": 0.7475582754267378,
|
| 1330 |
+
"learning_rate": 2.9650876251946527e-05,
|
| 1331 |
+
"loss": 0.2252,
|
| 1332 |
+
"step": 189
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 2.0239680426098534,
|
| 1336 |
+
"grad_norm": 0.6039094193830512,
|
| 1337 |
+
"learning_rate": 2.9518947860741476e-05,
|
| 1338 |
+
"loss": 0.2134,
|
| 1339 |
+
"step": 190
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 2.034620505992011,
|
| 1343 |
+
"grad_norm": 0.9793944376714834,
|
| 1344 |
+
"learning_rate": 2.9386481776904242e-05,
|
| 1345 |
+
"loss": 0.1986,
|
| 1346 |
+
"step": 191
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 2.045272969374168,
|
| 1350 |
+
"grad_norm": 0.6522567331411916,
|
| 1351 |
+
"learning_rate": 2.9253485482988415e-05,
|
| 1352 |
+
"loss": 0.2006,
|
| 1353 |
+
"step": 192
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 2.0559254327563248,
|
| 1357 |
+
"grad_norm": 0.5784725849119551,
|
| 1358 |
+
"learning_rate": 2.9119966491497277e-05,
|
| 1359 |
+
"loss": 0.1833,
|
| 1360 |
+
"step": 193
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 2.066577896138482,
|
| 1364 |
+
"grad_norm": 0.5982816543254711,
|
| 1365 |
+
"learning_rate": 2.898593234445956e-05,
|
| 1366 |
+
"loss": 0.1679,
|
| 1367 |
+
"step": 194
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 2.077230359520639,
|
| 1371 |
+
"grad_norm": 0.5763170157269676,
|
| 1372 |
+
"learning_rate": 2.8851390613003313e-05,
|
| 1373 |
+
"loss": 0.1787,
|
| 1374 |
+
"step": 195
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 2.087882822902796,
|
| 1378 |
+
"grad_norm": 0.5429561072390091,
|
| 1379 |
+
"learning_rate": 2.871634889692831e-05,
|
| 1380 |
+
"loss": 0.1829,
|
| 1381 |
+
"step": 196
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 2.0985352862849536,
|
| 1385 |
+
"grad_norm": 0.5429329776671976,
|
| 1386 |
+
"learning_rate": 2.858081482427673e-05,
|
| 1387 |
+
"loss": 0.163,
|
| 1388 |
+
"step": 197
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 2.1091877496671105,
|
| 1392 |
+
"grad_norm": 0.6012276205072621,
|
| 1393 |
+
"learning_rate": 2.8444796050902274e-05,
|
| 1394 |
+
"loss": 0.185,
|
| 1395 |
+
"step": 198
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 2.1198402130492675,
|
| 1399 |
+
"grad_norm": 0.6149425838446878,
|
| 1400 |
+
"learning_rate": 2.8308300260037734e-05,
|
| 1401 |
+
"loss": 0.1906,
|
| 1402 |
+
"step": 199
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 2.130492676431425,
|
| 1406 |
+
"grad_norm": 0.553015523166273,
|
| 1407 |
+
"learning_rate": 2.8171335161860964e-05,
|
| 1408 |
+
"loss": 0.1779,
|
| 1409 |
+
"step": 200
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 2.141145139813582,
|
| 1413 |
+
"grad_norm": 0.5419852232199943,
|
| 1414 |
+
"learning_rate": 2.8033908493059394e-05,
|
| 1415 |
+
"loss": 0.1739,
|
| 1416 |
+
"step": 201
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 2.151797603195739,
|
| 1420 |
+
"grad_norm": 0.554102634186576,
|
| 1421 |
+
"learning_rate": 2.7896028016392973e-05,
|
| 1422 |
+
"loss": 0.2046,
|
| 1423 |
+
"step": 202
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 2.1624500665778963,
|
| 1427 |
+
"grad_norm": 0.513260424485721,
|
| 1428 |
+
"learning_rate": 2.7757701520255696e-05,
|
| 1429 |
+
"loss": 0.1912,
|
| 1430 |
+
"step": 203
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 2.1731025299600533,
|
| 1434 |
+
"grad_norm": 0.510256693515735,
|
| 1435 |
+
"learning_rate": 2.761893681823569e-05,
|
| 1436 |
+
"loss": 0.1739,
|
| 1437 |
+
"step": 204
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 2.1837549933422102,
|
| 1441 |
+
"grad_norm": 0.5664168722743783,
|
| 1442 |
+
"learning_rate": 2.7479741748673797e-05,
|
| 1443 |
+
"loss": 0.1804,
|
| 1444 |
+
"step": 205
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 2.1944074567243677,
|
| 1448 |
+
"grad_norm": 0.5480914537031347,
|
| 1449 |
+
"learning_rate": 2.7340124174220845e-05,
|
| 1450 |
+
"loss": 0.1944,
|
| 1451 |
+
"step": 206
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 2.2050599201065246,
|
| 1455 |
+
"grad_norm": 0.5303218062707495,
|
| 1456 |
+
"learning_rate": 2.7200091981393524e-05,
|
| 1457 |
+
"loss": 0.1836,
|
| 1458 |
+
"step": 207
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 2.2157123834886816,
|
| 1462 |
+
"grad_norm": 0.5534625599365391,
|
| 1463 |
+
"learning_rate": 2.705965308012888e-05,
|
| 1464 |
+
"loss": 0.1891,
|
| 1465 |
+
"step": 208
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 2.226364846870839,
|
| 1469 |
+
"grad_norm": 0.5579570401853269,
|
| 1470 |
+
"learning_rate": 2.6918815403337525e-05,
|
| 1471 |
+
"loss": 0.1801,
|
| 1472 |
+
"step": 209
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 2.237017310252996,
|
| 1476 |
+
"grad_norm": 0.5719734312761888,
|
| 1477 |
+
"learning_rate": 2.677758690645553e-05,
|
| 1478 |
+
"loss": 0.1883,
|
| 1479 |
+
"step": 210
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 2.247669773635153,
|
| 1483 |
+
"grad_norm": 0.5515481844210599,
|
| 1484 |
+
"learning_rate": 2.663597556699504e-05,
|
| 1485 |
+
"loss": 0.1811,
|
| 1486 |
+
"step": 211
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 2.2583222370173104,
|
| 1490 |
+
"grad_norm": 0.5297801288596432,
|
| 1491 |
+
"learning_rate": 2.6493989384093674e-05,
|
| 1492 |
+
"loss": 0.1764,
|
| 1493 |
+
"step": 212
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 2.2689747003994674,
|
| 1497 |
+
"grad_norm": 0.5634387961494656,
|
| 1498 |
+
"learning_rate": 2.635163637806265e-05,
|
| 1499 |
+
"loss": 0.1905,
|
| 1500 |
+
"step": 213
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 2.2796271637816243,
|
| 1504 |
+
"grad_norm": 0.5590590290261213,
|
| 1505 |
+
"learning_rate": 2.620892458993379e-05,
|
| 1506 |
+
"loss": 0.1804,
|
| 1507 |
+
"step": 214
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 2.2902796271637818,
|
| 1511 |
+
"grad_norm": 0.5421764954019398,
|
| 1512 |
+
"learning_rate": 2.6065862081005254e-05,
|
| 1513 |
+
"loss": 0.1786,
|
| 1514 |
+
"step": 215
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 2.3009320905459387,
|
| 1518 |
+
"grad_norm": 0.5937141170289384,
|
| 1519 |
+
"learning_rate": 2.5922456932386232e-05,
|
| 1520 |
+
"loss": 0.1794,
|
| 1521 |
+
"step": 216
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 2.3115845539280957,
|
| 1525 |
+
"grad_norm": 0.5522826407148838,
|
| 1526 |
+
"learning_rate": 2.577871724454045e-05,
|
| 1527 |
+
"loss": 0.1854,
|
| 1528 |
+
"step": 217
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 2.322237017310253,
|
| 1532 |
+
"grad_norm": 0.5368641885215816,
|
| 1533 |
+
"learning_rate": 2.5634651136828597e-05,
|
| 1534 |
+
"loss": 0.1659,
|
| 1535 |
+
"step": 218
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 2.33288948069241,
|
| 1539 |
+
"grad_norm": 0.5203994444934529,
|
| 1540 |
+
"learning_rate": 2.549026674704971e-05,
|
| 1541 |
+
"loss": 0.1728,
|
| 1542 |
+
"step": 219
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 2.343541944074567,
|
| 1546 |
+
"grad_norm": 0.5908959494234384,
|
| 1547 |
+
"learning_rate": 2.534557223098146e-05,
|
| 1548 |
+
"loss": 0.1715,
|
| 1549 |
+
"step": 220
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 2.3541944074567245,
|
| 1553 |
+
"grad_norm": 0.5416486760172659,
|
| 1554 |
+
"learning_rate": 2.5200575761919525e-05,
|
| 1555 |
+
"loss": 0.1717,
|
| 1556 |
+
"step": 221
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 2.3648468708388815,
|
| 1560 |
+
"grad_norm": 0.5213455376474552,
|
| 1561 |
+
"learning_rate": 2.5055285530215838e-05,
|
| 1562 |
+
"loss": 0.1764,
|
| 1563 |
+
"step": 222
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 2.3754993342210384,
|
| 1567 |
+
"grad_norm": 0.5732285706281826,
|
| 1568 |
+
"learning_rate": 2.4909709742815986e-05,
|
| 1569 |
+
"loss": 0.1999,
|
| 1570 |
+
"step": 223
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 2.386151797603196,
|
| 1574 |
+
"grad_norm": 0.5423129615985659,
|
| 1575 |
+
"learning_rate": 2.4763856622795613e-05,
|
| 1576 |
+
"loss": 0.1885,
|
| 1577 |
+
"step": 224
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 2.396804260985353,
|
| 1581 |
+
"grad_norm": 0.5188430365255767,
|
| 1582 |
+
"learning_rate": 2.4617734408895915e-05,
|
| 1583 |
+
"loss": 0.1699,
|
| 1584 |
+
"step": 225
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 2.40745672436751,
|
| 1588 |
+
"grad_norm": 0.5180608415611703,
|
| 1589 |
+
"learning_rate": 2.4471351355058316e-05,
|
| 1590 |
+
"loss": 0.1908,
|
| 1591 |
+
"step": 226
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 2.418109187749667,
|
| 1595 |
+
"grad_norm": 0.5532182145157059,
|
| 1596 |
+
"learning_rate": 2.4324715729958146e-05,
|
| 1597 |
+
"loss": 0.1854,
|
| 1598 |
+
"step": 227
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 2.428761651131824,
|
| 1602 |
+
"grad_norm": 0.5229367921999496,
|
| 1603 |
+
"learning_rate": 2.4177835816537643e-05,
|
| 1604 |
+
"loss": 0.186,
|
| 1605 |
+
"step": 228
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 2.4394141145139816,
|
| 1609 |
+
"grad_norm": 0.5230948698501948,
|
| 1610 |
+
"learning_rate": 2.4030719911538042e-05,
|
| 1611 |
+
"loss": 0.1829,
|
| 1612 |
+
"step": 229
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 2.4500665778961386,
|
| 1616 |
+
"grad_norm": 0.5401206129256607,
|
| 1617 |
+
"learning_rate": 2.3883376325030936e-05,
|
| 1618 |
+
"loss": 0.1853,
|
| 1619 |
+
"step": 230
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 2.4607190412782955,
|
| 1623 |
+
"grad_norm": 0.5136144882561599,
|
| 1624 |
+
"learning_rate": 2.373581337994886e-05,
|
| 1625 |
+
"loss": 0.1642,
|
| 1626 |
+
"step": 231
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 2.4713715046604525,
|
| 1630 |
+
"grad_norm": 0.5317683841227128,
|
| 1631 |
+
"learning_rate": 2.3588039411615168e-05,
|
| 1632 |
+
"loss": 0.1652,
|
| 1633 |
+
"step": 232
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 2.48202396804261,
|
| 1637 |
+
"grad_norm": 0.5315073533927748,
|
| 1638 |
+
"learning_rate": 2.344006276727317e-05,
|
| 1639 |
+
"loss": 0.1948,
|
| 1640 |
+
"step": 233
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 2.492676431424767,
|
| 1644 |
+
"grad_norm": 0.521528056498546,
|
| 1645 |
+
"learning_rate": 2.329189180561468e-05,
|
| 1646 |
+
"loss": 0.1837,
|
| 1647 |
+
"step": 234
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 2.5033288948069243,
|
| 1651 |
+
"grad_norm": 0.5305193341550172,
|
| 1652 |
+
"learning_rate": 2.31435348963078e-05,
|
| 1653 |
+
"loss": 0.1861,
|
| 1654 |
+
"step": 235
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 2.5139813581890813,
|
| 1658 |
+
"grad_norm": 0.5286204923609038,
|
| 1659 |
+
"learning_rate": 2.2995000419524203e-05,
|
| 1660 |
+
"loss": 0.1891,
|
| 1661 |
+
"step": 236
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 2.5246338215712383,
|
| 1665 |
+
"grad_norm": 0.5058472951976587,
|
| 1666 |
+
"learning_rate": 2.2846296765465708e-05,
|
| 1667 |
+
"loss": 0.1707,
|
| 1668 |
+
"step": 237
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 2.5352862849533953,
|
| 1672 |
+
"grad_norm": 0.5221736839514249,
|
| 1673 |
+
"learning_rate": 2.269743233389039e-05,
|
| 1674 |
+
"loss": 0.1712,
|
| 1675 |
+
"step": 238
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 2.5459387483355527,
|
| 1679 |
+
"grad_norm": 0.5104573828392779,
|
| 1680 |
+
"learning_rate": 2.25484155336381e-05,
|
| 1681 |
+
"loss": 0.1687,
|
| 1682 |
+
"step": 239
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 2.5565912117177096,
|
| 1686 |
+
"grad_norm": 0.5203302314667947,
|
| 1687 |
+
"learning_rate": 2.2399254782155463e-05,
|
| 1688 |
+
"loss": 0.1806,
|
| 1689 |
+
"step": 240
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 2.567243675099867,
|
| 1693 |
+
"grad_norm": 0.5363466660245324,
|
| 1694 |
+
"learning_rate": 2.2249958505020417e-05,
|
| 1695 |
+
"loss": 0.221,
|
| 1696 |
+
"step": 241
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 2.577896138482024,
|
| 1700 |
+
"grad_norm": 0.516075593435321,
|
| 1701 |
+
"learning_rate": 2.210053513546628e-05,
|
| 1702 |
+
"loss": 0.1811,
|
| 1703 |
+
"step": 242
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 2.588548601864181,
|
| 1707 |
+
"grad_norm": 0.5157352255559926,
|
| 1708 |
+
"learning_rate": 2.1950993113905367e-05,
|
| 1709 |
+
"loss": 0.1789,
|
| 1710 |
+
"step": 243
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 2.599201065246338,
|
| 1714 |
+
"grad_norm": 0.5540000068210599,
|
| 1715 |
+
"learning_rate": 2.1801340887452272e-05,
|
| 1716 |
+
"loss": 0.2094,
|
| 1717 |
+
"step": 244
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 2.6098535286284954,
|
| 1721 |
+
"grad_norm": 0.5462006198553626,
|
| 1722 |
+
"learning_rate": 2.165158690944665e-05,
|
| 1723 |
+
"loss": 0.1896,
|
| 1724 |
+
"step": 245
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 2.6205059920106524,
|
| 1728 |
+
"grad_norm": 0.49982079193433376,
|
| 1729 |
+
"learning_rate": 2.1501739638975768e-05,
|
| 1730 |
+
"loss": 0.1827,
|
| 1731 |
+
"step": 246
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 2.63115845539281,
|
| 1735 |
+
"grad_norm": 0.5350068942041161,
|
| 1736 |
+
"learning_rate": 2.1351807540396666e-05,
|
| 1737 |
+
"loss": 0.1724,
|
| 1738 |
+
"step": 247
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 2.6418109187749668,
|
| 1742 |
+
"grad_norm": 0.5040944860301062,
|
| 1743 |
+
"learning_rate": 2.1201799082858008e-05,
|
| 1744 |
+
"loss": 0.1657,
|
| 1745 |
+
"step": 248
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 2.6524633821571237,
|
| 1749 |
+
"grad_norm": 0.5038529963842291,
|
| 1750 |
+
"learning_rate": 2.1051722739821755e-05,
|
| 1751 |
+
"loss": 0.1793,
|
| 1752 |
+
"step": 249
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 2.6631158455392807,
|
| 1756 |
+
"grad_norm": 0.5462175529218323,
|
| 1757 |
+
"learning_rate": 2.0901586988584447e-05,
|
| 1758 |
+
"loss": 0.1849,
|
| 1759 |
+
"step": 250
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 2.673768308921438,
|
| 1763 |
+
"grad_norm": 0.49829252562111404,
|
| 1764 |
+
"learning_rate": 2.0751400309798417e-05,
|
| 1765 |
+
"loss": 0.1773,
|
| 1766 |
+
"step": 251
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 2.684420772303595,
|
| 1770 |
+
"grad_norm": 0.5241623803508092,
|
| 1771 |
+
"learning_rate": 2.0601171186992697e-05,
|
| 1772 |
+
"loss": 0.1745,
|
| 1773 |
+
"step": 252
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 2.6950732356857525,
|
| 1777 |
+
"grad_norm": 0.5365083590620205,
|
| 1778 |
+
"learning_rate": 2.0450908106093844e-05,
|
| 1779 |
+
"loss": 0.1796,
|
| 1780 |
+
"step": 253
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 2.7057256990679095,
|
| 1784 |
+
"grad_norm": 0.5223532767682934,
|
| 1785 |
+
"learning_rate": 2.030061955494661e-05,
|
| 1786 |
+
"loss": 0.1865,
|
| 1787 |
+
"step": 254
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 2.7163781624500665,
|
| 1791 |
+
"grad_norm": 0.5271908786887105,
|
| 1792 |
+
"learning_rate": 2.015031402283444e-05,
|
| 1793 |
+
"loss": 0.1879,
|
| 1794 |
+
"step": 255
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 2.7270306258322234,
|
| 1798 |
+
"grad_norm": 0.5520954284503321,
|
| 1799 |
+
"learning_rate": 2e-05,
|
| 1800 |
+
"loss": 0.1859,
|
| 1801 |
+
"step": 256
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 2.737683089214381,
|
| 1805 |
+
"grad_norm": 0.5342333406952676,
|
| 1806 |
+
"learning_rate": 1.9849685977165566e-05,
|
| 1807 |
+
"loss": 0.1895,
|
| 1808 |
+
"step": 257
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 2.748335552596538,
|
| 1812 |
+
"grad_norm": 0.5247957712616883,
|
| 1813 |
+
"learning_rate": 1.9699380445053396e-05,
|
| 1814 |
+
"loss": 0.1767,
|
| 1815 |
+
"step": 258
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 2.7589880159786953,
|
| 1819 |
+
"grad_norm": 0.4970671729438306,
|
| 1820 |
+
"learning_rate": 1.954909189390616e-05,
|
| 1821 |
+
"loss": 0.1851,
|
| 1822 |
+
"step": 259
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 2.7696404793608522,
|
| 1826 |
+
"grad_norm": 0.4882359073662009,
|
| 1827 |
+
"learning_rate": 1.939882881300731e-05,
|
| 1828 |
+
"loss": 0.1878,
|
| 1829 |
+
"step": 260
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 2.780292942743009,
|
| 1833 |
+
"grad_norm": 0.5067691127627982,
|
| 1834 |
+
"learning_rate": 1.924859969020159e-05,
|
| 1835 |
+
"loss": 0.1776,
|
| 1836 |
+
"step": 261
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 2.790945406125166,
|
| 1840 |
+
"grad_norm": 0.5418999255597677,
|
| 1841 |
+
"learning_rate": 1.9098413011415557e-05,
|
| 1842 |
+
"loss": 0.1943,
|
| 1843 |
+
"step": 262
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 2.8015978695073236,
|
| 1847 |
+
"grad_norm": 0.5134965449101414,
|
| 1848 |
+
"learning_rate": 1.894827726017825e-05,
|
| 1849 |
+
"loss": 0.1742,
|
| 1850 |
+
"step": 263
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 2.8122503328894806,
|
| 1854 |
+
"grad_norm": 0.529192085393146,
|
| 1855 |
+
"learning_rate": 1.8798200917141995e-05,
|
| 1856 |
+
"loss": 0.1829,
|
| 1857 |
+
"step": 264
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 2.822902796271638,
|
| 1861 |
+
"grad_norm": 0.5119696907508254,
|
| 1862 |
+
"learning_rate": 1.8648192459603347e-05,
|
| 1863 |
+
"loss": 0.1615,
|
| 1864 |
+
"step": 265
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 2.833555259653795,
|
| 1868 |
+
"grad_norm": 0.5537990670434169,
|
| 1869 |
+
"learning_rate": 1.8498260361024235e-05,
|
| 1870 |
+
"loss": 0.2,
|
| 1871 |
+
"step": 266
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 2.844207723035952,
|
| 1875 |
+
"grad_norm": 0.5031174132375092,
|
| 1876 |
+
"learning_rate": 1.8348413090553356e-05,
|
| 1877 |
+
"loss": 0.1942,
|
| 1878 |
+
"step": 267
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 2.8548601864181093,
|
| 1882 |
+
"grad_norm": 0.5204494280350305,
|
| 1883 |
+
"learning_rate": 1.819865911254773e-05,
|
| 1884 |
+
"loss": 0.1734,
|
| 1885 |
+
"step": 268
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 2.8655126498002663,
|
| 1889 |
+
"grad_norm": 0.48939658953904397,
|
| 1890 |
+
"learning_rate": 1.8049006886094637e-05,
|
| 1891 |
+
"loss": 0.1672,
|
| 1892 |
+
"step": 269
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 2.8761651131824233,
|
| 1896 |
+
"grad_norm": 0.5163196426150207,
|
| 1897 |
+
"learning_rate": 1.7899464864533734e-05,
|
| 1898 |
+
"loss": 0.1823,
|
| 1899 |
+
"step": 270
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 2.8868175765645807,
|
| 1903 |
+
"grad_norm": 0.5096325132098547,
|
| 1904 |
+
"learning_rate": 1.775004149497959e-05,
|
| 1905 |
+
"loss": 0.1637,
|
| 1906 |
+
"step": 271
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 2.8974700399467377,
|
| 1910 |
+
"grad_norm": 0.5526679970454356,
|
| 1911 |
+
"learning_rate": 1.7600745217844543e-05,
|
| 1912 |
+
"loss": 0.1918,
|
| 1913 |
+
"step": 272
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 2.9081225033288947,
|
| 1917 |
+
"grad_norm": 0.5150544731268503,
|
| 1918 |
+
"learning_rate": 1.74515844663619e-05,
|
| 1919 |
+
"loss": 0.169,
|
| 1920 |
+
"step": 273
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 2.918774966711052,
|
| 1924 |
+
"grad_norm": 0.5037947230084941,
|
| 1925 |
+
"learning_rate": 1.730256766610962e-05,
|
| 1926 |
+
"loss": 0.1663,
|
| 1927 |
+
"step": 274
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 2.929427430093209,
|
| 1931 |
+
"grad_norm": 0.7182845786149277,
|
| 1932 |
+
"learning_rate": 1.7153703234534302e-05,
|
| 1933 |
+
"loss": 0.1923,
|
| 1934 |
+
"step": 275
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 2.940079893475366,
|
| 1938 |
+
"grad_norm": 0.5282752675494763,
|
| 1939 |
+
"learning_rate": 1.70049995804758e-05,
|
| 1940 |
+
"loss": 0.1705,
|
| 1941 |
+
"step": 276
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 2.9507323568575234,
|
| 1945 |
+
"grad_norm": 0.5089486507076441,
|
| 1946 |
+
"learning_rate": 1.6856465103692203e-05,
|
| 1947 |
+
"loss": 0.1648,
|
| 1948 |
+
"step": 277
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 2.9613848202396804,
|
| 1952 |
+
"grad_norm": 0.5179230912512075,
|
| 1953 |
+
"learning_rate": 1.670810819438532e-05,
|
| 1954 |
+
"loss": 0.1757,
|
| 1955 |
+
"step": 278
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 2.9720372836218374,
|
| 1959 |
+
"grad_norm": 0.5281252352934472,
|
| 1960 |
+
"learning_rate": 1.6559937232726834e-05,
|
| 1961 |
+
"loss": 0.205,
|
| 1962 |
+
"step": 279
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 2.982689747003995,
|
| 1966 |
+
"grad_norm": 0.5151137960624935,
|
| 1967 |
+
"learning_rate": 1.6411960588384842e-05,
|
| 1968 |
+
"loss": 0.1729,
|
| 1969 |
+
"step": 280
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 2.993342210386152,
|
| 1973 |
+
"grad_norm": 0.5102588108212746,
|
| 1974 |
+
"learning_rate": 1.6264186620051144e-05,
|
| 1975 |
+
"loss": 0.1648,
|
| 1976 |
+
"step": 281
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 3.0039946737683088,
|
| 1980 |
+
"grad_norm": 0.4758684500998378,
|
| 1981 |
+
"learning_rate": 1.6116623674969074e-05,
|
| 1982 |
+
"loss": 0.1388,
|
| 1983 |
+
"step": 282
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 3.014647137150466,
|
| 1987 |
+
"grad_norm": 0.4515560159006812,
|
| 1988 |
+
"learning_rate": 1.5969280088461968e-05,
|
| 1989 |
+
"loss": 0.0776,
|
| 1990 |
+
"step": 283
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 3.025299600532623,
|
| 1994 |
+
"grad_norm": 0.4080106999838737,
|
| 1995 |
+
"learning_rate": 1.5822164183462363e-05,
|
| 1996 |
+
"loss": 0.0712,
|
| 1997 |
+
"step": 284
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 3.03595206391478,
|
| 2001 |
+
"grad_norm": 0.3703785049603402,
|
| 2002 |
+
"learning_rate": 1.5675284270041857e-05,
|
| 2003 |
+
"loss": 0.0699,
|
| 2004 |
+
"step": 285
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 3.0466045272969375,
|
| 2008 |
+
"grad_norm": 0.398758416572866,
|
| 2009 |
+
"learning_rate": 1.5528648644941684e-05,
|
| 2010 |
+
"loss": 0.0677,
|
| 2011 |
+
"step": 286
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 3.0572569906790945,
|
| 2015 |
+
"grad_norm": 0.4504518181000857,
|
| 2016 |
+
"learning_rate": 1.5382265591104088e-05,
|
| 2017 |
+
"loss": 0.0644,
|
| 2018 |
+
"step": 287
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 3.0679094540612515,
|
| 2022 |
+
"grad_norm": 0.5227671477516437,
|
| 2023 |
+
"learning_rate": 1.5236143377204397e-05,
|
| 2024 |
+
"loss": 0.0684,
|
| 2025 |
+
"step": 288
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 3.078561917443409,
|
| 2029 |
+
"grad_norm": 0.5010633494447794,
|
| 2030 |
+
"learning_rate": 1.5090290257184019e-05,
|
| 2031 |
+
"loss": 0.0754,
|
| 2032 |
+
"step": 289
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 3.089214380825566,
|
| 2036 |
+
"grad_norm": 0.5276445011100065,
|
| 2037 |
+
"learning_rate": 1.4944714469784165e-05,
|
| 2038 |
+
"loss": 0.0737,
|
| 2039 |
+
"step": 290
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 3.099866844207723,
|
| 2043 |
+
"grad_norm": 0.4530623376704263,
|
| 2044 |
+
"learning_rate": 1.4799424238080475e-05,
|
| 2045 |
+
"loss": 0.0655,
|
| 2046 |
+
"step": 291
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 3.1105193075898803,
|
| 2050 |
+
"grad_norm": 0.4055798073614495,
|
| 2051 |
+
"learning_rate": 1.4654427769018545e-05,
|
| 2052 |
+
"loss": 0.0708,
|
| 2053 |
+
"step": 292
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 3.1211717709720372,
|
| 2057 |
+
"grad_norm": 0.38274436151569,
|
| 2058 |
+
"learning_rate": 1.4509733252950304e-05,
|
| 2059 |
+
"loss": 0.0653,
|
| 2060 |
+
"step": 293
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 3.131824234354194,
|
| 2064 |
+
"grad_norm": 0.3759278093725999,
|
| 2065 |
+
"learning_rate": 1.4365348863171406e-05,
|
| 2066 |
+
"loss": 0.0608,
|
| 2067 |
+
"step": 294
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 3.1424766977363516,
|
| 2071 |
+
"grad_norm": 0.36289205677572584,
|
| 2072 |
+
"learning_rate": 1.4221282755459556e-05,
|
| 2073 |
+
"loss": 0.0659,
|
| 2074 |
+
"step": 295
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 3.1531291611185086,
|
| 2078 |
+
"grad_norm": 0.3612341064334079,
|
| 2079 |
+
"learning_rate": 1.4077543067613768e-05,
|
| 2080 |
+
"loss": 0.0668,
|
| 2081 |
+
"step": 296
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 3.1637816245006656,
|
| 2085 |
+
"grad_norm": 0.364562762019271,
|
| 2086 |
+
"learning_rate": 1.3934137918994753e-05,
|
| 2087 |
+
"loss": 0.0696,
|
| 2088 |
+
"step": 297
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 3.174434087882823,
|
| 2092 |
+
"grad_norm": 0.3897603118935574,
|
| 2093 |
+
"learning_rate": 1.3791075410066216e-05,
|
| 2094 |
+
"loss": 0.0693,
|
| 2095 |
+
"step": 298
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 3.18508655126498,
|
| 2099 |
+
"grad_norm": 0.39500114068528974,
|
| 2100 |
+
"learning_rate": 1.364836362193735e-05,
|
| 2101 |
+
"loss": 0.0756,
|
| 2102 |
+
"step": 299
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 3.195739014647137,
|
| 2106 |
+
"grad_norm": 0.3887487614385999,
|
| 2107 |
+
"learning_rate": 1.3506010615906333e-05,
|
| 2108 |
+
"loss": 0.0703,
|
| 2109 |
+
"step": 300
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 3.2063914780292944,
|
| 2113 |
+
"grad_norm": 0.37871522012648284,
|
| 2114 |
+
"learning_rate": 1.3364024433004969e-05,
|
| 2115 |
+
"loss": 0.0736,
|
| 2116 |
+
"step": 301
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 3.2170439414114513,
|
| 2120 |
+
"grad_norm": 0.3888433983297253,
|
| 2121 |
+
"learning_rate": 1.3222413093544475e-05,
|
| 2122 |
+
"loss": 0.0628,
|
| 2123 |
+
"step": 302
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 3.2276964047936083,
|
| 2127 |
+
"grad_norm": 0.426174936418348,
|
| 2128 |
+
"learning_rate": 1.3081184596662479e-05,
|
| 2129 |
+
"loss": 0.087,
|
| 2130 |
+
"step": 303
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 3.2383488681757657,
|
| 2134 |
+
"grad_norm": 0.4480390949867637,
|
| 2135 |
+
"learning_rate": 1.2940346919871121e-05,
|
| 2136 |
+
"loss": 0.0709,
|
| 2137 |
+
"step": 304
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 3.2490013315579227,
|
| 2141 |
+
"grad_norm": 0.37165746222035534,
|
| 2142 |
+
"learning_rate": 1.2799908018606479e-05,
|
| 2143 |
+
"loss": 0.0505,
|
| 2144 |
+
"step": 305
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 3.25965379494008,
|
| 2148 |
+
"grad_norm": 0.4145836684424107,
|
| 2149 |
+
"learning_rate": 1.2659875825779165e-05,
|
| 2150 |
+
"loss": 0.0824,
|
| 2151 |
+
"step": 306
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 3.270306258322237,
|
| 2155 |
+
"grad_norm": 0.42058392163377445,
|
| 2156 |
+
"learning_rate": 1.2520258251326212e-05,
|
| 2157 |
+
"loss": 0.0743,
|
| 2158 |
+
"step": 307
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 3.280958721704394,
|
| 2162 |
+
"grad_norm": 0.37715769532900006,
|
| 2163 |
+
"learning_rate": 1.2381063181764317e-05,
|
| 2164 |
+
"loss": 0.0788,
|
| 2165 |
+
"step": 308
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 3.291611185086551,
|
| 2169 |
+
"grad_norm": 0.3814781793605393,
|
| 2170 |
+
"learning_rate": 1.2242298479744302e-05,
|
| 2171 |
+
"loss": 0.0739,
|
| 2172 |
+
"step": 309
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 3.3022636484687085,
|
| 2176 |
+
"grad_norm": 0.36590750152439677,
|
| 2177 |
+
"learning_rate": 1.2103971983607034e-05,
|
| 2178 |
+
"loss": 0.0636,
|
| 2179 |
+
"step": 310
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 3.3129161118508654,
|
| 2183 |
+
"grad_norm": 0.3762365106070016,
|
| 2184 |
+
"learning_rate": 1.1966091506940616e-05,
|
| 2185 |
+
"loss": 0.0774,
|
| 2186 |
+
"step": 311
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 3.323568575233023,
|
| 2190 |
+
"grad_norm": 0.3812825354399514,
|
| 2191 |
+
"learning_rate": 1.182866483813904e-05,
|
| 2192 |
+
"loss": 0.0687,
|
| 2193 |
+
"step": 312
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 3.33422103861518,
|
| 2197 |
+
"grad_norm": 0.4105088493518934,
|
| 2198 |
+
"learning_rate": 1.1691699739962275e-05,
|
| 2199 |
+
"loss": 0.0738,
|
| 2200 |
+
"step": 313
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 3.344873501997337,
|
| 2204 |
+
"grad_norm": 0.366692903952499,
|
| 2205 |
+
"learning_rate": 1.1555203949097733e-05,
|
| 2206 |
+
"loss": 0.0618,
|
| 2207 |
+
"step": 314
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 3.3555259653794938,
|
| 2211 |
+
"grad_norm": 0.3794819663323805,
|
| 2212 |
+
"learning_rate": 1.1419185175723275e-05,
|
| 2213 |
+
"loss": 0.0628,
|
| 2214 |
+
"step": 315
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 3.366178428761651,
|
| 2218 |
+
"grad_norm": 0.39146582363883126,
|
| 2219 |
+
"learning_rate": 1.1283651103071698e-05,
|
| 2220 |
+
"loss": 0.065,
|
| 2221 |
+
"step": 316
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 3.376830892143808,
|
| 2225 |
+
"grad_norm": 0.36374203279401246,
|
| 2226 |
+
"learning_rate": 1.1148609386996692e-05,
|
| 2227 |
+
"loss": 0.0654,
|
| 2228 |
+
"step": 317
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 3.3874833555259656,
|
| 2232 |
+
"grad_norm": 0.3987903349658228,
|
| 2233 |
+
"learning_rate": 1.101406765554045e-05,
|
| 2234 |
+
"loss": 0.0724,
|
| 2235 |
+
"step": 318
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 3.3981358189081226,
|
| 2239 |
+
"grad_norm": 0.3707800772718991,
|
| 2240 |
+
"learning_rate": 1.0880033508502728e-05,
|
| 2241 |
+
"loss": 0.0853,
|
| 2242 |
+
"step": 319
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 3.4087882822902795,
|
| 2246 |
+
"grad_norm": 0.39525467089353417,
|
| 2247 |
+
"learning_rate": 1.0746514517011595e-05,
|
| 2248 |
+
"loss": 0.0634,
|
| 2249 |
+
"step": 320
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 3.419440745672437,
|
| 2253 |
+
"grad_norm": 0.3953291262592471,
|
| 2254 |
+
"learning_rate": 1.0613518223095763e-05,
|
| 2255 |
+
"loss": 0.0697,
|
| 2256 |
+
"step": 321
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 3.430093209054594,
|
| 2260 |
+
"grad_norm": 0.4247126984489118,
|
| 2261 |
+
"learning_rate": 1.048105213925853e-05,
|
| 2262 |
+
"loss": 0.0683,
|
| 2263 |
+
"step": 322
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 3.440745672436751,
|
| 2267 |
+
"grad_norm": 0.3678761781827026,
|
| 2268 |
+
"learning_rate": 1.0349123748053482e-05,
|
| 2269 |
+
"loss": 0.0675,
|
| 2270 |
+
"step": 323
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 3.4513981358189083,
|
| 2274 |
+
"grad_norm": 0.40228525902530937,
|
| 2275 |
+
"learning_rate": 1.0217740501661763e-05,
|
| 2276 |
+
"loss": 0.0722,
|
| 2277 |
+
"step": 324
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 3.4620505992010653,
|
| 2281 |
+
"grad_norm": 0.3623146542115812,
|
| 2282 |
+
"learning_rate": 1.008690982147119e-05,
|
| 2283 |
+
"loss": 0.0589,
|
| 2284 |
+
"step": 325
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 3.4727030625832223,
|
| 2288 |
+
"grad_norm": 0.40017902397706656,
|
| 2289 |
+
"learning_rate": 9.956639097657007e-06,
|
| 2290 |
+
"loss": 0.0606,
|
| 2291 |
+
"step": 326
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 3.4833555259653797,
|
| 2295 |
+
"grad_norm": 0.36734531255976316,
|
| 2296 |
+
"learning_rate": 9.826935688764434e-06,
|
| 2297 |
+
"loss": 0.0599,
|
| 2298 |
+
"step": 327
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 3.4940079893475366,
|
| 2302 |
+
"grad_norm": 0.36123484310831827,
|
| 2303 |
+
"learning_rate": 9.697806921293044e-06,
|
| 2304 |
+
"loss": 0.073,
|
| 2305 |
+
"step": 328
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 3.5046604527296936,
|
| 2309 |
+
"grad_norm": 0.3824877715376635,
|
| 2310 |
+
"learning_rate": 9.56926008928287e-06,
|
| 2311 |
+
"loss": 0.0731,
|
| 2312 |
+
"step": 329
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 3.515312916111851,
|
| 2316 |
+
"grad_norm": 0.37948734189702765,
|
| 2317 |
+
"learning_rate": 9.441302453902426e-06,
|
| 2318 |
+
"loss": 0.0659,
|
| 2319 |
+
"step": 330
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 3.525965379494008,
|
| 2323 |
+
"grad_norm": 0.3642722271316403,
|
| 2324 |
+
"learning_rate": 9.31394124303854e-06,
|
| 2325 |
+
"loss": 0.0631,
|
| 2326 |
+
"step": 331
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 3.536617842876165,
|
| 2330 |
+
"grad_norm": 0.35875602757884956,
|
| 2331 |
+
"learning_rate": 9.187183650888056e-06,
|
| 2332 |
+
"loss": 0.0659,
|
| 2333 |
+
"step": 332
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 3.5472703062583224,
|
| 2337 |
+
"grad_norm": 0.3639886849259028,
|
| 2338 |
+
"learning_rate": 9.061036837551467e-06,
|
| 2339 |
+
"loss": 0.0576,
|
| 2340 |
+
"step": 333
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 3.5579227696404794,
|
| 2344 |
+
"grad_norm": 0.3614512803984625,
|
| 2345 |
+
"learning_rate": 8.93550792862849e-06,
|
| 2346 |
+
"loss": 0.0669,
|
| 2347 |
+
"step": 334
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 3.5685752330226364,
|
| 2351 |
+
"grad_norm": 0.3817722350631916,
|
| 2352 |
+
"learning_rate": 8.81060401481554e-06,
|
| 2353 |
+
"loss": 0.0704,
|
| 2354 |
+
"step": 335
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 3.5792276964047938,
|
| 2358 |
+
"grad_norm": 0.39540809497217444,
|
| 2359 |
+
"learning_rate": 8.68633215150521e-06,
|
| 2360 |
+
"loss": 0.0612,
|
| 2361 |
+
"step": 336
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 3.5898801597869507,
|
| 2365 |
+
"grad_norm": 0.3868789303084368,
|
| 2366 |
+
"learning_rate": 8.562699358387723e-06,
|
| 2367 |
+
"loss": 0.0612,
|
| 2368 |
+
"step": 337
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 3.6005326231691077,
|
| 2372 |
+
"grad_norm": 0.37568433791432765,
|
| 2373 |
+
"learning_rate": 8.439712619054424e-06,
|
| 2374 |
+
"loss": 0.0622,
|
| 2375 |
+
"step": 338
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 3.611185086551265,
|
| 2379 |
+
"grad_norm": 0.35162466460658737,
|
| 2380 |
+
"learning_rate": 8.317378880603315e-06,
|
| 2381 |
+
"loss": 0.0654,
|
| 2382 |
+
"step": 339
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 3.621837549933422,
|
| 2386 |
+
"grad_norm": 0.39157849860942257,
|
| 2387 |
+
"learning_rate": 8.195705053246614e-06,
|
| 2388 |
+
"loss": 0.0653,
|
| 2389 |
+
"step": 340
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 3.632490013315579,
|
| 2393 |
+
"grad_norm": 0.3802787972967635,
|
| 2394 |
+
"learning_rate": 8.07469800992044e-06,
|
| 2395 |
+
"loss": 0.0644,
|
| 2396 |
+
"step": 341
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 3.6431424766977365,
|
| 2400 |
+
"grad_norm": 0.3928988975455323,
|
| 2401 |
+
"learning_rate": 7.954364585896565e-06,
|
| 2402 |
+
"loss": 0.0629,
|
| 2403 |
+
"step": 342
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 3.6537949400798935,
|
| 2407 |
+
"grad_norm": 0.41389059355141883,
|
| 2408 |
+
"learning_rate": 7.834711578396314e-06,
|
| 2409 |
+
"loss": 0.0622,
|
| 2410 |
+
"step": 343
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 3.6644474034620504,
|
| 2414 |
+
"grad_norm": 0.37623473850068356,
|
| 2415 |
+
"learning_rate": 7.715745746206644e-06,
|
| 2416 |
+
"loss": 0.0618,
|
| 2417 |
+
"step": 344
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 3.675099866844208,
|
| 2421 |
+
"grad_norm": 0.3803638485645304,
|
| 2422 |
+
"learning_rate": 7.597473809298337e-06,
|
| 2423 |
+
"loss": 0.0815,
|
| 2424 |
+
"step": 345
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 3.685752330226365,
|
| 2428 |
+
"grad_norm": 0.3553302636599296,
|
| 2429 |
+
"learning_rate": 7.479902448446399e-06,
|
| 2430 |
+
"loss": 0.069,
|
| 2431 |
+
"step": 346
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 3.696404793608522,
|
| 2435 |
+
"grad_norm": 0.3443719038029288,
|
| 2436 |
+
"learning_rate": 7.3630383048527255e-06,
|
| 2437 |
+
"loss": 0.0558,
|
| 2438 |
+
"step": 347
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 3.7070572569906792,
|
| 2442 |
+
"grad_norm": 0.3609811622989924,
|
| 2443 |
+
"learning_rate": 7.246887979770924e-06,
|
| 2444 |
+
"loss": 0.0621,
|
| 2445 |
+
"step": 348
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 3.717709720372836,
|
| 2449 |
+
"grad_norm": 0.3559362622124288,
|
| 2450 |
+
"learning_rate": 7.131458034133458e-06,
|
| 2451 |
+
"loss": 0.0749,
|
| 2452 |
+
"step": 349
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 3.728362183754993,
|
| 2456 |
+
"grad_norm": 0.37337607112599985,
|
| 2457 |
+
"learning_rate": 7.016754988181042e-06,
|
| 2458 |
+
"loss": 0.0633,
|
| 2459 |
+
"step": 350
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 3.7390146471371506,
|
| 2463 |
+
"grad_norm": 0.3609902434032474,
|
| 2464 |
+
"learning_rate": 6.902785321094301e-06,
|
| 2465 |
+
"loss": 0.0557,
|
| 2466 |
+
"step": 351
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 3.7496671105193076,
|
| 2470 |
+
"grad_norm": 0.367784990540754,
|
| 2471 |
+
"learning_rate": 6.7895554706278376e-06,
|
| 2472 |
+
"loss": 0.0657,
|
| 2473 |
+
"step": 352
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 3.760319573901465,
|
| 2477 |
+
"grad_norm": 0.3703864876515468,
|
| 2478 |
+
"learning_rate": 6.677071832746534e-06,
|
| 2479 |
+
"loss": 0.0658,
|
| 2480 |
+
"step": 353
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 3.770972037283622,
|
| 2484 |
+
"grad_norm": 0.3664704440114154,
|
| 2485 |
+
"learning_rate": 6.565340761264305e-06,
|
| 2486 |
+
"loss": 0.0554,
|
| 2487 |
+
"step": 354
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 3.781624500665779,
|
| 2491 |
+
"grad_norm": 0.3528101630655649,
|
| 2492 |
+
"learning_rate": 6.4543685674851834e-06,
|
| 2493 |
+
"loss": 0.0663,
|
| 2494 |
+
"step": 355
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 3.792276964047936,
|
| 2498 |
+
"grad_norm": 0.3468046911342091,
|
| 2499 |
+
"learning_rate": 6.3441615198467806e-06,
|
| 2500 |
+
"loss": 0.0601,
|
| 2501 |
+
"step": 356
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 3.8029294274300933,
|
| 2505 |
+
"grad_norm": 0.37666130005210396,
|
| 2506 |
+
"learning_rate": 6.234725843566269e-06,
|
| 2507 |
+
"loss": 0.0706,
|
| 2508 |
+
"step": 357
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 3.8135818908122503,
|
| 2512 |
+
"grad_norm": 0.34786071160278226,
|
| 2513 |
+
"learning_rate": 6.126067720288678e-06,
|
| 2514 |
+
"loss": 0.0593,
|
| 2515 |
+
"step": 358
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 3.8242343541944077,
|
| 2519 |
+
"grad_norm": 0.38092687122482244,
|
| 2520 |
+
"learning_rate": 6.018193287737755e-06,
|
| 2521 |
+
"loss": 0.0587,
|
| 2522 |
+
"step": 359
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 3.8348868175765647,
|
| 2526 |
+
"grad_norm": 0.37289236499523337,
|
| 2527 |
+
"learning_rate": 5.911108639369259e-06,
|
| 2528 |
+
"loss": 0.0716,
|
| 2529 |
+
"step": 360
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 3.8455392809587217,
|
| 2533 |
+
"grad_norm": 0.34244139958769465,
|
| 2534 |
+
"learning_rate": 5.804819824026735e-06,
|
| 2535 |
+
"loss": 0.0621,
|
| 2536 |
+
"step": 361
|
| 2537 |
+
},
|
| 2538 |
+
{
|
| 2539 |
+
"epoch": 3.8561917443408786,
|
| 2540 |
+
"grad_norm": 0.36899479337107105,
|
| 2541 |
+
"learning_rate": 5.699332845599883e-06,
|
| 2542 |
+
"loss": 0.0689,
|
| 2543 |
+
"step": 362
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 3.866844207723036,
|
| 2547 |
+
"grad_norm": 0.38245844026519915,
|
| 2548 |
+
"learning_rate": 5.594653662685367e-06,
|
| 2549 |
+
"loss": 0.0678,
|
| 2550 |
+
"step": 363
|
| 2551 |
+
},
|
| 2552 |
+
{
|
| 2553 |
+
"epoch": 3.877496671105193,
|
| 2554 |
+
"grad_norm": 0.38115702579381455,
|
| 2555 |
+
"learning_rate": 5.490788188250282e-06,
|
| 2556 |
+
"loss": 0.0736,
|
| 2557 |
+
"step": 364
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 3.8881491344873504,
|
| 2561 |
+
"grad_norm": 0.3755048401064129,
|
| 2562 |
+
"learning_rate": 5.387742289298121e-06,
|
| 2563 |
+
"loss": 0.0742,
|
| 2564 |
+
"step": 365
|
| 2565 |
+
},
|
| 2566 |
+
{
|
| 2567 |
+
"epoch": 3.8988015978695074,
|
| 2568 |
+
"grad_norm": 0.36242105419298654,
|
| 2569 |
+
"learning_rate": 5.285521786537368e-06,
|
| 2570 |
+
"loss": 0.0514,
|
| 2571 |
+
"step": 366
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 3.9094540612516644,
|
| 2575 |
+
"grad_norm": 1.3717998532944609,
|
| 2576 |
+
"learning_rate": 5.184132454052731e-06,
|
| 2577 |
+
"loss": 0.0788,
|
| 2578 |
+
"step": 367
|
| 2579 |
+
},
|
| 2580 |
+
{
|
| 2581 |
+
"epoch": 3.9201065246338214,
|
| 2582 |
+
"grad_norm": 0.35146240004431367,
|
| 2583 |
+
"learning_rate": 5.083580018978948e-06,
|
| 2584 |
+
"loss": 0.0633,
|
| 2585 |
+
"step": 368
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 3.930758988015979,
|
| 2589 |
+
"grad_norm": 0.3869469437585369,
|
| 2590 |
+
"learning_rate": 4.983870161177316e-06,
|
| 2591 |
+
"loss": 0.0687,
|
| 2592 |
+
"step": 369
|
| 2593 |
+
},
|
| 2594 |
+
{
|
| 2595 |
+
"epoch": 3.9414114513981358,
|
| 2596 |
+
"grad_norm": 0.3710684892619675,
|
| 2597 |
+
"learning_rate": 4.885008512914837e-06,
|
| 2598 |
+
"loss": 0.0733,
|
| 2599 |
+
"step": 370
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 3.952063914780293,
|
| 2603 |
+
"grad_norm": 0.365518095396254,
|
| 2604 |
+
"learning_rate": 4.787000658546059e-06,
|
| 2605 |
+
"loss": 0.0648,
|
| 2606 |
+
"step": 371
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 3.96271637816245,
|
| 2610 |
+
"grad_norm": 0.3631011018125059,
|
| 2611 |
+
"learning_rate": 4.689852134197672e-06,
|
| 2612 |
+
"loss": 0.0649,
|
| 2613 |
+
"step": 372
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 3.973368841544607,
|
| 2617 |
+
"grad_norm": 0.3593081345291371,
|
| 2618 |
+
"learning_rate": 4.593568427455741e-06,
|
| 2619 |
+
"loss": 0.0566,
|
| 2620 |
+
"step": 373
|
| 2621 |
+
},
|
| 2622 |
+
{
|
| 2623 |
+
"epoch": 3.984021304926764,
|
| 2624 |
+
"grad_norm": 0.3509263292062937,
|
| 2625 |
+
"learning_rate": 4.498154977055782e-06,
|
| 2626 |
+
"loss": 0.0562,
|
| 2627 |
+
"step": 374
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 3.9946737683089215,
|
| 2631 |
+
"grad_norm": 0.37011449569359833,
|
| 2632 |
+
"learning_rate": 4.403617172575514e-06,
|
| 2633 |
+
"loss": 0.0528,
|
| 2634 |
+
"step": 375
|
| 2635 |
+
},
|
| 2636 |
+
{
|
| 2637 |
+
"epoch": 4.005326231691079,
|
| 2638 |
+
"grad_norm": 0.3036164570674188,
|
| 2639 |
+
"learning_rate": 4.30996035413042e-06,
|
| 2640 |
+
"loss": 0.0577,
|
| 2641 |
+
"step": 376
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 4.015978695073236,
|
| 2645 |
+
"grad_norm": 0.2446228811669915,
|
| 2646 |
+
"learning_rate": 4.217189812072131e-06,
|
| 2647 |
+
"loss": 0.032,
|
| 2648 |
+
"step": 377
|
| 2649 |
+
},
|
| 2650 |
+
{
|
| 2651 |
+
"epoch": 4.026631158455393,
|
| 2652 |
+
"grad_norm": 0.3064473302194206,
|
| 2653 |
+
"learning_rate": 4.125310786689547e-06,
|
| 2654 |
+
"loss": 0.0266,
|
| 2655 |
+
"step": 378
|
| 2656 |
+
},
|
| 2657 |
+
{
|
| 2658 |
+
"epoch": 4.03728362183755,
|
| 2659 |
+
"grad_norm": 0.21957411226489054,
|
| 2660 |
+
"learning_rate": 4.03432846791288e-06,
|
| 2661 |
+
"loss": 0.0252,
|
| 2662 |
+
"step": 379
|
| 2663 |
+
},
|
| 2664 |
+
{
|
| 2665 |
+
"epoch": 4.047936085219707,
|
| 2666 |
+
"grad_norm": 0.21611510716746304,
|
| 2667 |
+
"learning_rate": 3.944247995020463e-06,
|
| 2668 |
+
"loss": 0.0231,
|
| 2669 |
+
"step": 380
|
| 2670 |
+
},
|
| 2671 |
+
{
|
| 2672 |
+
"epoch": 4.058588548601864,
|
| 2673 |
+
"grad_norm": 0.21994498548270944,
|
| 2674 |
+
"learning_rate": 3.8550744563484484e-06,
|
| 2675 |
+
"loss": 0.0241,
|
| 2676 |
+
"step": 381
|
| 2677 |
+
},
|
| 2678 |
+
{
|
| 2679 |
+
"epoch": 4.069241011984022,
|
| 2680 |
+
"grad_norm": 0.21584131714849436,
|
| 2681 |
+
"learning_rate": 3.7668128890033904e-06,
|
| 2682 |
+
"loss": 0.0245,
|
| 2683 |
+
"step": 382
|
| 2684 |
+
},
|
| 2685 |
+
{
|
| 2686 |
+
"epoch": 4.079893475366179,
|
| 2687 |
+
"grad_norm": 0.22226756504114142,
|
| 2688 |
+
"learning_rate": 3.6794682785777358e-06,
|
| 2689 |
+
"loss": 0.0266,
|
| 2690 |
+
"step": 383
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 4.090545938748336,
|
| 2694 |
+
"grad_norm": 0.22632275478074362,
|
| 2695 |
+
"learning_rate": 3.5930455588681758e-06,
|
| 2696 |
+
"loss": 0.0267,
|
| 2697 |
+
"step": 384
|
| 2698 |
+
},
|
| 2699 |
+
{
|
| 2700 |
+
"epoch": 4.101198402130493,
|
| 2701 |
+
"grad_norm": 0.18808966879355452,
|
| 2702 |
+
"learning_rate": 3.5075496115969723e-06,
|
| 2703 |
+
"loss": 0.0219,
|
| 2704 |
+
"step": 385
|
| 2705 |
+
},
|
| 2706 |
+
{
|
| 2707 |
+
"epoch": 4.1118508655126496,
|
| 2708 |
+
"grad_norm": 0.21464202167360366,
|
| 2709 |
+
"learning_rate": 3.4229852661361917e-06,
|
| 2710 |
+
"loss": 0.0286,
|
| 2711 |
+
"step": 386
|
| 2712 |
+
},
|
| 2713 |
+
{
|
| 2714 |
+
"epoch": 4.1225033288948065,
|
| 2715 |
+
"grad_norm": 0.21859877686120716,
|
| 2716 |
+
"learning_rate": 3.3393572992349156e-06,
|
| 2717 |
+
"loss": 0.0325,
|
| 2718 |
+
"step": 387
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 4.133155792276964,
|
| 2722 |
+
"grad_norm": 0.2162415124298462,
|
| 2723 |
+
"learning_rate": 3.2566704347494295e-06,
|
| 2724 |
+
"loss": 0.0296,
|
| 2725 |
+
"step": 388
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 4.143808255659121,
|
| 2729 |
+
"grad_norm": 0.23423071120371058,
|
| 2730 |
+
"learning_rate": 3.174929343376374e-06,
|
| 2731 |
+
"loss": 0.0248,
|
| 2732 |
+
"step": 389
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 4.154460719041278,
|
| 2736 |
+
"grad_norm": 0.22291522389877602,
|
| 2737 |
+
"learning_rate": 3.0941386423889287e-06,
|
| 2738 |
+
"loss": 0.0225,
|
| 2739 |
+
"step": 390
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 4.165113182423435,
|
| 2743 |
+
"grad_norm": 0.2385243731614469,
|
| 2744 |
+
"learning_rate": 3.0143028953759756e-06,
|
| 2745 |
+
"loss": 0.0234,
|
| 2746 |
+
"step": 391
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 4.175765645805592,
|
| 2750 |
+
"grad_norm": 0.2679435470327104,
|
| 2751 |
+
"learning_rate": 2.9354266119843268e-06,
|
| 2752 |
+
"loss": 0.0295,
|
| 2753 |
+
"step": 392
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 4.186418109187749,
|
| 2757 |
+
"grad_norm": 0.26211382280866685,
|
| 2758 |
+
"learning_rate": 2.8575142476640106e-06,
|
| 2759 |
+
"loss": 0.0266,
|
| 2760 |
+
"step": 393
|
| 2761 |
+
},
|
| 2762 |
+
{
|
| 2763 |
+
"epoch": 4.197070572569907,
|
| 2764 |
+
"grad_norm": 0.25959428131458057,
|
| 2765 |
+
"learning_rate": 2.7805702034165726e-06,
|
| 2766 |
+
"loss": 0.0266,
|
| 2767 |
+
"step": 394
|
| 2768 |
+
},
|
| 2769 |
+
{
|
| 2770 |
+
"epoch": 4.207723035952064,
|
| 2771 |
+
"grad_norm": 0.24410596759852662,
|
| 2772 |
+
"learning_rate": 2.704598825546483e-06,
|
| 2773 |
+
"loss": 0.0187,
|
| 2774 |
+
"step": 395
|
| 2775 |
+
},
|
| 2776 |
+
{
|
| 2777 |
+
"epoch": 4.218375499334221,
|
| 2778 |
+
"grad_norm": 0.21642926501699397,
|
| 2779 |
+
"learning_rate": 2.6296044054156446e-06,
|
| 2780 |
+
"loss": 0.0324,
|
| 2781 |
+
"step": 396
|
| 2782 |
+
},
|
| 2783 |
+
{
|
| 2784 |
+
"epoch": 4.229027962716378,
|
| 2785 |
+
"grad_norm": 0.23968887867505784,
|
| 2786 |
+
"learning_rate": 2.5555911792009624e-06,
|
| 2787 |
+
"loss": 0.0248,
|
| 2788 |
+
"step": 397
|
| 2789 |
+
},
|
| 2790 |
+
{
|
| 2791 |
+
"epoch": 4.239680426098535,
|
| 2792 |
+
"grad_norm": 0.25845303183790536,
|
| 2793 |
+
"learning_rate": 2.482563327655081e-06,
|
| 2794 |
+
"loss": 0.0315,
|
| 2795 |
+
"step": 398
|
| 2796 |
+
},
|
| 2797 |
+
{
|
| 2798 |
+
"epoch": 4.250332889480692,
|
| 2799 |
+
"grad_norm": 0.24715376785070522,
|
| 2800 |
+
"learning_rate": 2.410524975870221e-06,
|
| 2801 |
+
"loss": 0.0299,
|
| 2802 |
+
"step": 399
|
| 2803 |
+
},
|
| 2804 |
+
{
|
| 2805 |
+
"epoch": 4.26098535286285,
|
| 2806 |
+
"grad_norm": 0.2673353699220225,
|
| 2807 |
+
"learning_rate": 2.3394801930451492e-06,
|
| 2808 |
+
"loss": 0.0372,
|
| 2809 |
+
"step": 400
|
| 2810 |
+
},
|
| 2811 |
+
{
|
| 2812 |
+
"epoch": 4.271637816245007,
|
| 2813 |
+
"grad_norm": 0.24056700637644793,
|
| 2814 |
+
"learning_rate": 2.269432992255358e-06,
|
| 2815 |
+
"loss": 0.0228,
|
| 2816 |
+
"step": 401
|
| 2817 |
+
},
|
| 2818 |
+
{
|
| 2819 |
+
"epoch": 4.282290279627164,
|
| 2820 |
+
"grad_norm": 0.25010204825584204,
|
| 2821 |
+
"learning_rate": 2.2003873302263434e-06,
|
| 2822 |
+
"loss": 0.0244,
|
| 2823 |
+
"step": 402
|
| 2824 |
+
},
|
| 2825 |
+
{
|
| 2826 |
+
"epoch": 4.292942743009321,
|
| 2827 |
+
"grad_norm": 0.2366616531295655,
|
| 2828 |
+
"learning_rate": 2.132347107110133e-06,
|
| 2829 |
+
"loss": 0.039,
|
| 2830 |
+
"step": 403
|
| 2831 |
+
},
|
| 2832 |
+
{
|
| 2833 |
+
"epoch": 4.303595206391478,
|
| 2834 |
+
"grad_norm": 0.22179885738624133,
|
| 2835 |
+
"learning_rate": 2.0653161662649633e-06,
|
| 2836 |
+
"loss": 0.0248,
|
| 2837 |
+
"step": 404
|
| 2838 |
+
},
|
| 2839 |
+
{
|
| 2840 |
+
"epoch": 4.314247669773636,
|
| 2841 |
+
"grad_norm": 0.23030724407624087,
|
| 2842 |
+
"learning_rate": 1.9992982940381834e-06,
|
| 2843 |
+
"loss": 0.0302,
|
| 2844 |
+
"step": 405
|
| 2845 |
+
},
|
| 2846 |
+
{
|
| 2847 |
+
"epoch": 4.324900133155793,
|
| 2848 |
+
"grad_norm": 0.2046267249700779,
|
| 2849 |
+
"learning_rate": 1.9342972195523837e-06,
|
| 2850 |
+
"loss": 0.0222,
|
| 2851 |
+
"step": 406
|
| 2852 |
+
},
|
| 2853 |
+
{
|
| 2854 |
+
"epoch": 4.3355525965379496,
|
| 2855 |
+
"grad_norm": 0.21140616648198682,
|
| 2856 |
+
"learning_rate": 1.8703166144947427e-06,
|
| 2857 |
+
"loss": 0.0219,
|
| 2858 |
+
"step": 407
|
| 2859 |
+
},
|
| 2860 |
+
{
|
| 2861 |
+
"epoch": 4.3462050599201065,
|
| 2862 |
+
"grad_norm": 0.2161783630915959,
|
| 2863 |
+
"learning_rate": 1.8073600929096314e-06,
|
| 2864 |
+
"loss": 0.0278,
|
| 2865 |
+
"step": 408
|
| 2866 |
+
},
|
| 2867 |
+
{
|
| 2868 |
+
"epoch": 4.3568575233022635,
|
| 2869 |
+
"grad_norm": 0.2163939852716373,
|
| 2870 |
+
"learning_rate": 1.7454312109944749e-06,
|
| 2871 |
+
"loss": 0.0233,
|
| 2872 |
+
"step": 409
|
| 2873 |
+
},
|
| 2874 |
+
{
|
| 2875 |
+
"epoch": 4.3675099866844205,
|
| 2876 |
+
"grad_norm": 0.2274536942449813,
|
| 2877 |
+
"learning_rate": 1.68453346689885e-06,
|
| 2878 |
+
"loss": 0.024,
|
| 2879 |
+
"step": 410
|
| 2880 |
+
},
|
| 2881 |
+
{
|
| 2882 |
+
"epoch": 4.3781624500665774,
|
| 2883 |
+
"grad_norm": 0.2173312788958575,
|
| 2884 |
+
"learning_rate": 1.624670300526925e-06,
|
| 2885 |
+
"loss": 0.0241,
|
| 2886 |
+
"step": 411
|
| 2887 |
+
},
|
| 2888 |
+
{
|
| 2889 |
+
"epoch": 4.388814913448735,
|
| 2890 |
+
"grad_norm": 0.19126028161167793,
|
| 2891 |
+
"learning_rate": 1.5658450933431103e-06,
|
| 2892 |
+
"loss": 0.0203,
|
| 2893 |
+
"step": 412
|
| 2894 |
+
},
|
| 2895 |
+
{
|
| 2896 |
+
"epoch": 4.399467376830892,
|
| 2897 |
+
"grad_norm": 0.19454611612400988,
|
| 2898 |
+
"learning_rate": 1.5080611681810742e-06,
|
| 2899 |
+
"loss": 0.0267,
|
| 2900 |
+
"step": 413
|
| 2901 |
+
},
|
| 2902 |
+
{
|
| 2903 |
+
"epoch": 4.410119840213049,
|
| 2904 |
+
"grad_norm": 0.20207477869279994,
|
| 2905 |
+
"learning_rate": 1.4513217890560638e-06,
|
| 2906 |
+
"loss": 0.025,
|
| 2907 |
+
"step": 414
|
| 2908 |
+
},
|
| 2909 |
+
{
|
| 2910 |
+
"epoch": 4.420772303595206,
|
| 2911 |
+
"grad_norm": 0.20027065992776688,
|
| 2912 |
+
"learning_rate": 1.3956301609804901e-06,
|
| 2913 |
+
"loss": 0.0248,
|
| 2914 |
+
"step": 415
|
| 2915 |
+
},
|
| 2916 |
+
{
|
| 2917 |
+
"epoch": 4.431424766977363,
|
| 2918 |
+
"grad_norm": 0.18900243991098975,
|
| 2919 |
+
"learning_rate": 1.3409894297829217e-06,
|
| 2920 |
+
"loss": 0.0213,
|
| 2921 |
+
"step": 416
|
| 2922 |
+
},
|
| 2923 |
+
{
|
| 2924 |
+
"epoch": 4.442077230359521,
|
| 2925 |
+
"grad_norm": 0.1987608599254911,
|
| 2926 |
+
"learning_rate": 1.2874026819303698e-06,
|
| 2927 |
+
"loss": 0.0199,
|
| 2928 |
+
"step": 417
|
| 2929 |
+
},
|
| 2930 |
+
{
|
| 2931 |
+
"epoch": 4.452729693741678,
|
| 2932 |
+
"grad_norm": 0.22621192876984642,
|
| 2933 |
+
"learning_rate": 1.2348729443539487e-06,
|
| 2934 |
+
"loss": 0.0267,
|
| 2935 |
+
"step": 418
|
| 2936 |
+
},
|
| 2937 |
+
{
|
| 2938 |
+
"epoch": 4.463382157123835,
|
| 2939 |
+
"grad_norm": 0.2118731068093809,
|
| 2940 |
+
"learning_rate": 1.1834031842779137e-06,
|
| 2941 |
+
"loss": 0.0249,
|
| 2942 |
+
"step": 419
|
| 2943 |
+
},
|
| 2944 |
+
{
|
| 2945 |
+
"epoch": 4.474034620505992,
|
| 2946 |
+
"grad_norm": 0.22497375921476842,
|
| 2947 |
+
"learning_rate": 1.1329963090520147e-06,
|
| 2948 |
+
"loss": 0.0232,
|
| 2949 |
+
"step": 420
|
| 2950 |
+
},
|
| 2951 |
+
{
|
| 2952 |
+
"epoch": 4.484687083888149,
|
| 2953 |
+
"grad_norm": 0.2240853851155293,
|
| 2954 |
+
"learning_rate": 1.0836551659873073e-06,
|
| 2955 |
+
"loss": 0.0342,
|
| 2956 |
+
"step": 421
|
| 2957 |
+
},
|
| 2958 |
+
{
|
| 2959 |
+
"epoch": 4.495339547270306,
|
| 2960 |
+
"grad_norm": 0.2109857701959441,
|
| 2961 |
+
"learning_rate": 1.0353825421952935e-06,
|
| 2962 |
+
"loss": 0.0225,
|
| 2963 |
+
"step": 422
|
| 2964 |
+
},
|
| 2965 |
+
{
|
| 2966 |
+
"epoch": 4.505992010652463,
|
| 2967 |
+
"grad_norm": 0.202046027589495,
|
| 2968 |
+
"learning_rate": 9.881811644304907e-07,
|
| 2969 |
+
"loss": 0.0247,
|
| 2970 |
+
"step": 423
|
| 2971 |
+
},
|
| 2972 |
+
{
|
| 2973 |
+
"epoch": 4.516644474034621,
|
| 2974 |
+
"grad_norm": 0.19181148967786948,
|
| 2975 |
+
"learning_rate": 9.420536989364292e-07,
|
| 2976 |
+
"loss": 0.0206,
|
| 2977 |
+
"step": 424
|
| 2978 |
+
},
|
| 2979 |
+
{
|
| 2980 |
+
"epoch": 4.527296937416778,
|
| 2981 |
+
"grad_norm": 0.20358184842663327,
|
| 2982 |
+
"learning_rate": 8.970027512950152e-07,
|
| 2983 |
+
"loss": 0.0239,
|
| 2984 |
+
"step": 425
|
| 2985 |
+
},
|
| 2986 |
+
{
|
| 2987 |
+
"epoch": 4.537949400798935,
|
| 2988 |
+
"grad_norm": 0.22937053513198782,
|
| 2989 |
+
"learning_rate": 8.53030866279363e-07,
|
| 2990 |
+
"loss": 0.0298,
|
| 2991 |
+
"step": 426
|
| 2992 |
+
},
|
| 2993 |
+
{
|
| 2994 |
+
"epoch": 4.548601864181092,
|
| 2995 |
+
"grad_norm": 0.21239692041671754,
|
| 2996 |
+
"learning_rate": 8.101405277100549e-07,
|
| 2997 |
+
"loss": 0.0244,
|
| 2998 |
+
"step": 427
|
| 2999 |
+
},
|
| 3000 |
+
{
|
| 3001 |
+
"epoch": 4.559254327563249,
|
| 3002 |
+
"grad_norm": 0.2085559743079561,
|
| 3003 |
+
"learning_rate": 7.683341583148274e-07,
|
| 3004 |
+
"loss": 0.0252,
|
| 3005 |
+
"step": 428
|
| 3006 |
+
},
|
| 3007 |
+
{
|
| 3008 |
+
"epoch": 4.5699067909454065,
|
| 3009 |
+
"grad_norm": 0.20408209005614006,
|
| 3010 |
+
"learning_rate": 7.27614119591733e-07,
|
| 3011 |
+
"loss": 0.0213,
|
| 3012 |
+
"step": 429
|
| 3013 |
+
},
|
| 3014 |
+
{
|
| 3015 |
+
"epoch": 4.5805592543275635,
|
| 3016 |
+
"grad_norm": 0.20034192599952794,
|
| 3017 |
+
"learning_rate": 6.87982711675741e-07,
|
| 3018 |
+
"loss": 0.029,
|
| 3019 |
+
"step": 430
|
| 3020 |
+
},
|
| 3021 |
+
{
|
| 3022 |
+
"epoch": 4.5912117177097205,
|
| 3023 |
+
"grad_norm": 0.1945367781679877,
|
| 3024 |
+
"learning_rate": 6.494421732087941e-07,
|
| 3025 |
+
"loss": 0.0184,
|
| 3026 |
+
"step": 431
|
| 3027 |
+
},
|
| 3028 |
+
{
|
| 3029 |
+
"epoch": 4.6018641810918774,
|
| 3030 |
+
"grad_norm": 0.21391904309776966,
|
| 3031 |
+
"learning_rate": 6.119946812133926e-07,
|
| 3032 |
+
"loss": 0.0191,
|
| 3033 |
+
"step": 432
|
| 3034 |
+
},
|
| 3035 |
+
{
|
| 3036 |
+
"epoch": 4.612516644474034,
|
| 3037 |
+
"grad_norm": 0.2253406274074037,
|
| 3038 |
+
"learning_rate": 5.756423509695852e-07,
|
| 3039 |
+
"loss": 0.0279,
|
| 3040 |
+
"step": 433
|
| 3041 |
+
},
|
| 3042 |
+
{
|
| 3043 |
+
"epoch": 4.623169107856191,
|
| 3044 |
+
"grad_norm": 0.21027662038244524,
|
| 3045 |
+
"learning_rate": 5.403872358955031e-07,
|
| 3046 |
+
"loss": 0.0255,
|
| 3047 |
+
"step": 434
|
| 3048 |
+
},
|
| 3049 |
+
{
|
| 3050 |
+
"epoch": 4.633821571238348,
|
| 3051 |
+
"grad_norm": 0.21564900070035445,
|
| 3052 |
+
"learning_rate": 5.062313274313701e-07,
|
| 3053 |
+
"loss": 0.0264,
|
| 3054 |
+
"step": 435
|
| 3055 |
+
},
|
| 3056 |
+
{
|
| 3057 |
+
"epoch": 4.644474034620506,
|
| 3058 |
+
"grad_norm": 0.21707652956761478,
|
| 3059 |
+
"learning_rate": 4.7317655492699953e-07,
|
| 3060 |
+
"loss": 0.0277,
|
| 3061 |
+
"step": 436
|
| 3062 |
+
},
|
| 3063 |
+
{
|
| 3064 |
+
"epoch": 4.655126498002663,
|
| 3065 |
+
"grad_norm": 0.20859029797892978,
|
| 3066 |
+
"learning_rate": 4.412247855328322e-07,
|
| 3067 |
+
"loss": 0.0243,
|
| 3068 |
+
"step": 437
|
| 3069 |
+
},
|
| 3070 |
+
{
|
| 3071 |
+
"epoch": 4.66577896138482,
|
| 3072 |
+
"grad_norm": 0.23338199290705675,
|
| 3073 |
+
"learning_rate": 4.1037782409444337e-07,
|
| 3074 |
+
"loss": 0.0315,
|
| 3075 |
+
"step": 438
|
| 3076 |
+
},
|
| 3077 |
+
{
|
| 3078 |
+
"epoch": 4.676431424766977,
|
| 3079 |
+
"grad_norm": 0.2063830221854238,
|
| 3080 |
+
"learning_rate": 3.806374130506152e-07,
|
| 3081 |
+
"loss": 0.029,
|
| 3082 |
+
"step": 439
|
| 3083 |
+
},
|
| 3084 |
+
{
|
| 3085 |
+
"epoch": 4.687083888149134,
|
| 3086 |
+
"grad_norm": 0.22131666678732978,
|
| 3087 |
+
"learning_rate": 3.520052323349021e-07,
|
| 3088 |
+
"loss": 0.0199,
|
| 3089 |
+
"step": 440
|
| 3090 |
+
},
|
| 3091 |
+
{
|
| 3092 |
+
"epoch": 4.697736351531292,
|
| 3093 |
+
"grad_norm": 0.21250836151005104,
|
| 3094 |
+
"learning_rate": 3.244828992807336e-07,
|
| 3095 |
+
"loss": 0.0246,
|
| 3096 |
+
"step": 441
|
| 3097 |
+
},
|
| 3098 |
+
{
|
| 3099 |
+
"epoch": 4.708388814913449,
|
| 3100 |
+
"grad_norm": 0.21208913571414068,
|
| 3101 |
+
"learning_rate": 2.980719685300648e-07,
|
| 3102 |
+
"loss": 0.0223,
|
| 3103 |
+
"step": 442
|
| 3104 |
+
},
|
| 3105 |
+
{
|
| 3106 |
+
"epoch": 4.719041278295606,
|
| 3107 |
+
"grad_norm": 0.23029239103535618,
|
| 3108 |
+
"learning_rate": 2.7277393194555357e-07,
|
| 3109 |
+
"loss": 0.0244,
|
| 3110 |
+
"step": 443
|
| 3111 |
+
},
|
| 3112 |
+
{
|
| 3113 |
+
"epoch": 4.729693741677763,
|
| 3114 |
+
"grad_norm": 0.2122464689388818,
|
| 3115 |
+
"learning_rate": 2.485902185262967e-07,
|
| 3116 |
+
"loss": 0.0312,
|
| 3117 |
+
"step": 444
|
| 3118 |
+
},
|
| 3119 |
+
{
|
| 3120 |
+
"epoch": 4.74034620505992,
|
| 3121 |
+
"grad_norm": 0.20183346314204256,
|
| 3122 |
+
"learning_rate": 2.2552219432710577e-07,
|
| 3123 |
+
"loss": 0.0217,
|
| 3124 |
+
"step": 445
|
| 3125 |
+
},
|
| 3126 |
+
{
|
| 3127 |
+
"epoch": 4.750998668442077,
|
| 3128 |
+
"grad_norm": 0.25235608116063557,
|
| 3129 |
+
"learning_rate": 2.0357116238134633e-07,
|
| 3130 |
+
"loss": 0.0287,
|
| 3131 |
+
"step": 446
|
| 3132 |
+
},
|
| 3133 |
+
{
|
| 3134 |
+
"epoch": 4.761651131824235,
|
| 3135 |
+
"grad_norm": 0.2012631647176202,
|
| 3136 |
+
"learning_rate": 1.8273836262732824e-07,
|
| 3137 |
+
"loss": 0.0202,
|
| 3138 |
+
"step": 447
|
| 3139 |
+
},
|
| 3140 |
+
{
|
| 3141 |
+
"epoch": 4.772303595206392,
|
| 3142 |
+
"grad_norm": 0.22963114209872748,
|
| 3143 |
+
"learning_rate": 1.6302497183827038e-07,
|
| 3144 |
+
"loss": 0.0298,
|
| 3145 |
+
"step": 448
|
| 3146 |
+
},
|
| 3147 |
+
{
|
| 3148 |
+
"epoch": 4.782956058588549,
|
| 3149 |
+
"grad_norm": 0.22155546230476952,
|
| 3150 |
+
"learning_rate": 1.444321035558338e-07,
|
| 3151 |
+
"loss": 0.0304,
|
| 3152 |
+
"step": 449
|
| 3153 |
+
},
|
| 3154 |
+
{
|
| 3155 |
+
"epoch": 4.793608521970706,
|
| 3156 |
+
"grad_norm": 0.21625853776678494,
|
| 3157 |
+
"learning_rate": 1.2696080802721666e-07,
|
| 3158 |
+
"loss": 0.0254,
|
| 3159 |
+
"step": 450
|
| 3160 |
+
},
|
| 3161 |
+
{
|
| 3162 |
+
"epoch": 4.804260985352863,
|
| 3163 |
+
"grad_norm": 0.22811784534830712,
|
| 3164 |
+
"learning_rate": 1.1061207214581703e-07,
|
| 3165 |
+
"loss": 0.0236,
|
| 3166 |
+
"step": 451
|
| 3167 |
+
},
|
| 3168 |
+
{
|
| 3169 |
+
"epoch": 4.81491344873502,
|
| 3170 |
+
"grad_norm": 0.24724721763324703,
|
| 3171 |
+
"learning_rate": 9.538681939551319e-08,
|
| 3172 |
+
"loss": 0.0401,
|
| 3173 |
+
"step": 452
|
| 3174 |
+
},
|
| 3175 |
+
{
|
| 3176 |
+
"epoch": 4.8255659121171774,
|
| 3177 |
+
"grad_norm": 0.2108995991759665,
|
| 3178 |
+
"learning_rate": 8.128590979847639e-08,
|
| 3179 |
+
"loss": 0.0285,
|
| 3180 |
+
"step": 453
|
| 3181 |
+
},
|
| 3182 |
+
{
|
| 3183 |
+
"epoch": 4.836218375499334,
|
| 3184 |
+
"grad_norm": 0.1982730144838422,
|
| 3185 |
+
"learning_rate": 6.831013986660307e-08,
|
| 3186 |
+
"loss": 0.0212,
|
| 3187 |
+
"step": 454
|
| 3188 |
+
},
|
| 3189 |
+
{
|
| 3190 |
+
"epoch": 4.846870838881491,
|
| 3191 |
+
"grad_norm": 0.21152978929562719,
|
| 3192 |
+
"learning_rate": 5.646024255651528e-08,
|
| 3193 |
+
"loss": 0.0226,
|
| 3194 |
+
"step": 455
|
| 3195 |
+
},
|
| 3196 |
+
{
|
| 3197 |
+
"epoch": 4.857523302263648,
|
| 3198 |
+
"grad_norm": 0.22107861686685087,
|
| 3199 |
+
"learning_rate": 4.5736887228164936e-08,
|
| 3200 |
+
"loss": 0.0303,
|
| 3201 |
+
"step": 456
|
| 3202 |
+
},
|
| 3203 |
+
{
|
| 3204 |
+
"epoch": 4.868175765645805,
|
| 3205 |
+
"grad_norm": 0.21310043240841559,
|
| 3206 |
+
"learning_rate": 3.614067960701961e-08,
|
| 3207 |
+
"loss": 0.0345,
|
| 3208 |
+
"step": 457
|
| 3209 |
+
},
|
| 3210 |
+
{
|
| 3211 |
+
"epoch": 4.878828229027963,
|
| 3212 |
+
"grad_norm": 0.24643345670811295,
|
| 3213 |
+
"learning_rate": 2.76721617498521e-08,
|
| 3214 |
+
"loss": 0.0252,
|
| 3215 |
+
"step": 458
|
| 3216 |
+
},
|
| 3217 |
+
{
|
| 3218 |
+
"epoch": 4.88948069241012,
|
| 3219 |
+
"grad_norm": 0.22655401247121135,
|
| 3220 |
+
"learning_rate": 2.0331812014113828e-08,
|
| 3221 |
+
"loss": 0.0278,
|
| 3222 |
+
"step": 459
|
| 3223 |
+
},
|
| 3224 |
+
{
|
| 3225 |
+
"epoch": 4.900133155792277,
|
| 3226 |
+
"grad_norm": 0.2365830083346805,
|
| 3227 |
+
"learning_rate": 1.4120045030920904e-08,
|
| 3228 |
+
"loss": 0.0317,
|
| 3229 |
+
"step": 460
|
| 3230 |
+
},
|
| 3231 |
+
{
|
| 3232 |
+
"epoch": 4.910785619174434,
|
| 3233 |
+
"grad_norm": 0.20510037379028764,
|
| 3234 |
+
"learning_rate": 9.037211681630631e-09,
|
| 3235 |
+
"loss": 0.0237,
|
| 3236 |
+
"step": 461
|
| 3237 |
+
},
|
| 3238 |
+
{
|
| 3239 |
+
"epoch": 4.921438082556591,
|
| 3240 |
+
"grad_norm": 0.21398685281952687,
|
| 3241 |
+
"learning_rate": 5.083599078017365e-09,
|
| 3242 |
+
"loss": 0.0235,
|
| 3243 |
+
"step": 462
|
| 3244 |
+
},
|
| 3245 |
+
{
|
| 3246 |
+
"epoch": 4.932090545938748,
|
| 3247 |
+
"grad_norm": 0.21639856984683478,
|
| 3248 |
+
"learning_rate": 2.259430546067698e-09,
|
| 3249 |
+
"loss": 0.021,
|
| 3250 |
+
"step": 463
|
| 3251 |
+
},
|
| 3252 |
+
{
|
| 3253 |
+
"epoch": 4.942743009320905,
|
| 3254 |
+
"grad_norm": 0.2248212654081011,
|
| 3255 |
+
"learning_rate": 5.648656133461217e-10,
|
| 3256 |
+
"loss": 0.0212,
|
| 3257 |
+
"step": 464
|
| 3258 |
+
},
|
| 3259 |
+
{
|
| 3260 |
+
"epoch": 4.953395472703063,
|
| 3261 |
+
"grad_norm": 0.22980739471505854,
|
| 3262 |
+
"learning_rate": 0.0,
|
| 3263 |
+
"loss": 0.0345,
|
| 3264 |
+
"step": 465
|
| 3265 |
+
},
|
| 3266 |
+
{
|
| 3267 |
+
"epoch": 4.953395472703063,
|
| 3268 |
+
"step": 465,
|
| 3269 |
+
"total_flos": 1.9803873717092352e+17,
|
| 3270 |
+
"train_loss": 0.2650201372321575,
|
| 3271 |
+
"train_runtime": 4985.2784,
|
| 3272 |
+
"train_samples_per_second": 12.043,
|
| 3273 |
+
"train_steps_per_second": 0.093
|
| 3274 |
+
}
|
| 3275 |
+
],
|
| 3276 |
+
"logging_steps": 1,
|
| 3277 |
+
"max_steps": 465,
|
| 3278 |
+
"num_input_tokens_seen": 0,
|
| 3279 |
+
"num_train_epochs": 5,
|
| 3280 |
+
"save_steps": 500,
|
| 3281 |
+
"stateful_callbacks": {
|
| 3282 |
+
"TrainerControl": {
|
| 3283 |
+
"args": {
|
| 3284 |
+
"should_epoch_stop": false,
|
| 3285 |
+
"should_evaluate": false,
|
| 3286 |
+
"should_log": false,
|
| 3287 |
+
"should_save": true,
|
| 3288 |
+
"should_training_stop": true
|
| 3289 |
+
},
|
| 3290 |
+
"attributes": {}
|
| 3291 |
+
}
|
| 3292 |
+
},
|
| 3293 |
+
"total_flos": 1.9803873717092352e+17,
|
| 3294 |
+
"train_batch_size": 1,
|
| 3295 |
+
"trial_name": null,
|
| 3296 |
+
"trial_params": null
|
| 3297 |
+
}
|
training_loss.png
ADDED
|