End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +3836 -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: qwen_7b_instruct_extra_verified
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# qwen_7b_instruct_extra_verified
|
| 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: qwen_7b_instruct_extra_verified
|
|
|
|
| 16 |
|
| 17 |
# qwen_7b_instruct_extra_verified
|
| 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/extra_verified dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.999447004608295,
|
| 3 |
+
"total_flos": 8192265561309184.0,
|
| 4 |
+
"train_loss": 0.4416485577162388,
|
| 5 |
+
"train_runtime": 91348.8221,
|
| 6 |
+
"train_samples_per_second": 5.7,
|
| 7 |
+
"train_steps_per_second": 0.059
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.999447004608295,
|
| 3 |
+
"total_flos": 8192265561309184.0,
|
| 4 |
+
"train_loss": 0.4416485577162388,
|
| 5 |
+
"train_runtime": 91348.8221,
|
| 6 |
+
"train_samples_per_second": 5.7,
|
| 7 |
+
"train_steps_per_second": 0.059
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3836 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.999447004608295,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 5424,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.005529953917050691,
|
| 13 |
+
"grad_norm": 6.0903776907776255,
|
| 14 |
+
"learning_rate": 1.8416206261510132e-07,
|
| 15 |
+
"loss": 0.8665,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.011059907834101382,
|
| 20 |
+
"grad_norm": 5.453075517812696,
|
| 21 |
+
"learning_rate": 3.6832412523020263e-07,
|
| 22 |
+
"loss": 0.8531,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.016589861751152075,
|
| 27 |
+
"grad_norm": 3.537343733022185,
|
| 28 |
+
"learning_rate": 5.524861878453039e-07,
|
| 29 |
+
"loss": 0.8281,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.022119815668202765,
|
| 34 |
+
"grad_norm": 1.7050757720044358,
|
| 35 |
+
"learning_rate": 7.366482504604053e-07,
|
| 36 |
+
"loss": 0.7589,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.027649769585253458,
|
| 41 |
+
"grad_norm": 1.4012843364617489,
|
| 42 |
+
"learning_rate": 9.208103130755065e-07,
|
| 43 |
+
"loss": 0.715,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.03317972350230415,
|
| 48 |
+
"grad_norm": 0.8011478929925271,
|
| 49 |
+
"learning_rate": 1.1049723756906078e-06,
|
| 50 |
+
"loss": 0.6922,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03870967741935484,
|
| 55 |
+
"grad_norm": 0.5699780949895114,
|
| 56 |
+
"learning_rate": 1.289134438305709e-06,
|
| 57 |
+
"loss": 0.6497,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.04423963133640553,
|
| 62 |
+
"grad_norm": 0.4520674784173067,
|
| 63 |
+
"learning_rate": 1.4732965009208105e-06,
|
| 64 |
+
"loss": 0.6281,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.04976958525345622,
|
| 69 |
+
"grad_norm": 0.39365714402711754,
|
| 70 |
+
"learning_rate": 1.6574585635359118e-06,
|
| 71 |
+
"loss": 0.611,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.055299539170506916,
|
| 76 |
+
"grad_norm": 0.4304728776273806,
|
| 77 |
+
"learning_rate": 1.841620626151013e-06,
|
| 78 |
+
"loss": 0.594,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.060829493087557605,
|
| 83 |
+
"grad_norm": 0.36773866506240127,
|
| 84 |
+
"learning_rate": 2.0257826887661147e-06,
|
| 85 |
+
"loss": 0.5946,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.0663594470046083,
|
| 90 |
+
"grad_norm": 0.40144795349227336,
|
| 91 |
+
"learning_rate": 2.2099447513812157e-06,
|
| 92 |
+
"loss": 0.5758,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.07188940092165899,
|
| 97 |
+
"grad_norm": 0.3650630134248591,
|
| 98 |
+
"learning_rate": 2.394106813996317e-06,
|
| 99 |
+
"loss": 0.5774,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.07741935483870968,
|
| 104 |
+
"grad_norm": 0.40858596339929243,
|
| 105 |
+
"learning_rate": 2.578268876611418e-06,
|
| 106 |
+
"loss": 0.5811,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.08294930875576037,
|
| 111 |
+
"grad_norm": 0.3915180921441105,
|
| 112 |
+
"learning_rate": 2.7624309392265196e-06,
|
| 113 |
+
"loss": 0.5567,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.08847926267281106,
|
| 118 |
+
"grad_norm": 0.38045253569441917,
|
| 119 |
+
"learning_rate": 2.946593001841621e-06,
|
| 120 |
+
"loss": 0.5558,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.09400921658986175,
|
| 125 |
+
"grad_norm": 0.37413606476610706,
|
| 126 |
+
"learning_rate": 3.130755064456722e-06,
|
| 127 |
+
"loss": 0.5493,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.09953917050691244,
|
| 132 |
+
"grad_norm": 0.42201408210941044,
|
| 133 |
+
"learning_rate": 3.3149171270718235e-06,
|
| 134 |
+
"loss": 0.5517,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.10506912442396313,
|
| 139 |
+
"grad_norm": 0.4095688421864769,
|
| 140 |
+
"learning_rate": 3.4990791896869245e-06,
|
| 141 |
+
"loss": 0.5463,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.11059907834101383,
|
| 146 |
+
"grad_norm": 0.4463086469391698,
|
| 147 |
+
"learning_rate": 3.683241252302026e-06,
|
| 148 |
+
"loss": 0.547,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.11612903225806452,
|
| 153 |
+
"grad_norm": 0.3760139550501188,
|
| 154 |
+
"learning_rate": 3.867403314917128e-06,
|
| 155 |
+
"loss": 0.5393,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.12165898617511521,
|
| 160 |
+
"grad_norm": 0.4078492489838482,
|
| 161 |
+
"learning_rate": 4.051565377532229e-06,
|
| 162 |
+
"loss": 0.5329,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.1271889400921659,
|
| 167 |
+
"grad_norm": 0.3908887647799372,
|
| 168 |
+
"learning_rate": 4.23572744014733e-06,
|
| 169 |
+
"loss": 0.5431,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.1327188940092166,
|
| 174 |
+
"grad_norm": 0.3761589181214343,
|
| 175 |
+
"learning_rate": 4.419889502762431e-06,
|
| 176 |
+
"loss": 0.5381,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.1382488479262673,
|
| 181 |
+
"grad_norm": 0.41027742174158294,
|
| 182 |
+
"learning_rate": 4.604051565377533e-06,
|
| 183 |
+
"loss": 0.5339,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.14377880184331798,
|
| 188 |
+
"grad_norm": 0.3993047304895881,
|
| 189 |
+
"learning_rate": 4.788213627992634e-06,
|
| 190 |
+
"loss": 0.5337,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.14930875576036867,
|
| 195 |
+
"grad_norm": 0.4267384725056861,
|
| 196 |
+
"learning_rate": 4.972375690607736e-06,
|
| 197 |
+
"loss": 0.5325,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.15483870967741936,
|
| 202 |
+
"grad_norm": 0.3741112789490821,
|
| 203 |
+
"learning_rate": 5.156537753222836e-06,
|
| 204 |
+
"loss": 0.5347,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.16036866359447005,
|
| 209 |
+
"grad_norm": 0.5001650422449634,
|
| 210 |
+
"learning_rate": 5.340699815837938e-06,
|
| 211 |
+
"loss": 0.5264,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.16589861751152074,
|
| 216 |
+
"grad_norm": 0.40870225399677257,
|
| 217 |
+
"learning_rate": 5.524861878453039e-06,
|
| 218 |
+
"loss": 0.5295,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.17142857142857143,
|
| 223 |
+
"grad_norm": 0.4489579942156596,
|
| 224 |
+
"learning_rate": 5.709023941068141e-06,
|
| 225 |
+
"loss": 0.5267,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.17695852534562212,
|
| 230 |
+
"grad_norm": 0.4576001899146063,
|
| 231 |
+
"learning_rate": 5.893186003683242e-06,
|
| 232 |
+
"loss": 0.5208,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.1824884792626728,
|
| 237 |
+
"grad_norm": 0.42765306743716647,
|
| 238 |
+
"learning_rate": 6.077348066298343e-06,
|
| 239 |
+
"loss": 0.5188,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.1880184331797235,
|
| 244 |
+
"grad_norm": 0.43147440269952797,
|
| 245 |
+
"learning_rate": 6.261510128913444e-06,
|
| 246 |
+
"loss": 0.5154,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.1935483870967742,
|
| 251 |
+
"grad_norm": 0.4497751095330459,
|
| 252 |
+
"learning_rate": 6.445672191528546e-06,
|
| 253 |
+
"loss": 0.5048,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.19907834101382488,
|
| 258 |
+
"grad_norm": 0.5327826362213908,
|
| 259 |
+
"learning_rate": 6.629834254143647e-06,
|
| 260 |
+
"loss": 0.5128,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.20460829493087557,
|
| 265 |
+
"grad_norm": 0.4115996357259951,
|
| 266 |
+
"learning_rate": 6.8139963167587485e-06,
|
| 267 |
+
"loss": 0.5178,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.21013824884792626,
|
| 272 |
+
"grad_norm": 0.40196263236255503,
|
| 273 |
+
"learning_rate": 6.998158379373849e-06,
|
| 274 |
+
"loss": 0.514,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.21566820276497695,
|
| 279 |
+
"grad_norm": 0.42296446460219156,
|
| 280 |
+
"learning_rate": 7.182320441988951e-06,
|
| 281 |
+
"loss": 0.5085,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.22119815668202766,
|
| 286 |
+
"grad_norm": 0.45986207995548617,
|
| 287 |
+
"learning_rate": 7.366482504604052e-06,
|
| 288 |
+
"loss": 0.5139,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.22672811059907835,
|
| 293 |
+
"grad_norm": 0.44973185296884877,
|
| 294 |
+
"learning_rate": 7.5506445672191534e-06,
|
| 295 |
+
"loss": 0.5103,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.23225806451612904,
|
| 300 |
+
"grad_norm": 0.5306307382931725,
|
| 301 |
+
"learning_rate": 7.734806629834256e-06,
|
| 302 |
+
"loss": 0.506,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.23778801843317973,
|
| 307 |
+
"grad_norm": 0.42387585926266613,
|
| 308 |
+
"learning_rate": 7.918968692449355e-06,
|
| 309 |
+
"loss": 0.508,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.24331797235023042,
|
| 314 |
+
"grad_norm": 0.4600172141091088,
|
| 315 |
+
"learning_rate": 8.103130755064459e-06,
|
| 316 |
+
"loss": 0.5053,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.2488479262672811,
|
| 321 |
+
"grad_norm": 0.5063886096298784,
|
| 322 |
+
"learning_rate": 8.287292817679558e-06,
|
| 323 |
+
"loss": 0.505,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.2543778801843318,
|
| 328 |
+
"grad_norm": 0.45595110131670297,
|
| 329 |
+
"learning_rate": 8.47145488029466e-06,
|
| 330 |
+
"loss": 0.4994,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.25990783410138246,
|
| 335 |
+
"grad_norm": 0.3979219166043402,
|
| 336 |
+
"learning_rate": 8.655616942909761e-06,
|
| 337 |
+
"loss": 0.5003,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.2654377880184332,
|
| 342 |
+
"grad_norm": 0.47071002002813517,
|
| 343 |
+
"learning_rate": 8.839779005524863e-06,
|
| 344 |
+
"loss": 0.4971,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.2709677419354839,
|
| 349 |
+
"grad_norm": 0.4204629206638486,
|
| 350 |
+
"learning_rate": 9.023941068139964e-06,
|
| 351 |
+
"loss": 0.5032,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.2764976958525346,
|
| 356 |
+
"grad_norm": 0.4755494443427242,
|
| 357 |
+
"learning_rate": 9.208103130755066e-06,
|
| 358 |
+
"loss": 0.4999,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.2820276497695853,
|
| 363 |
+
"grad_norm": 0.41495435521999285,
|
| 364 |
+
"learning_rate": 9.392265193370167e-06,
|
| 365 |
+
"loss": 0.5035,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.28755760368663597,
|
| 370 |
+
"grad_norm": 0.405511787171205,
|
| 371 |
+
"learning_rate": 9.576427255985269e-06,
|
| 372 |
+
"loss": 0.4999,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.29308755760368665,
|
| 377 |
+
"grad_norm": 0.47131810224352805,
|
| 378 |
+
"learning_rate": 9.760589318600368e-06,
|
| 379 |
+
"loss": 0.5089,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.29861751152073734,
|
| 384 |
+
"grad_norm": 0.4504585902565694,
|
| 385 |
+
"learning_rate": 9.944751381215471e-06,
|
| 386 |
+
"loss": 0.499,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.30414746543778803,
|
| 391 |
+
"grad_norm": 0.5477004156365718,
|
| 392 |
+
"learning_rate": 9.999949252169092e-06,
|
| 393 |
+
"loss": 0.5006,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.3096774193548387,
|
| 398 |
+
"grad_norm": 0.5531038596543296,
|
| 399 |
+
"learning_rate": 9.999700693844523e-06,
|
| 400 |
+
"loss": 0.4882,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.3152073732718894,
|
| 405 |
+
"grad_norm": 0.5330112235228269,
|
| 406 |
+
"learning_rate": 9.99924501428021e-06,
|
| 407 |
+
"loss": 0.4916,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.3207373271889401,
|
| 412 |
+
"grad_norm": 0.4577766765611679,
|
| 413 |
+
"learning_rate": 9.99858223235347e-06,
|
| 414 |
+
"loss": 0.4924,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.3262672811059908,
|
| 419 |
+
"grad_norm": 0.40765286650009175,
|
| 420 |
+
"learning_rate": 9.997712375521187e-06,
|
| 421 |
+
"loss": 0.4895,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.3317972350230415,
|
| 426 |
+
"grad_norm": 0.47974015373170437,
|
| 427 |
+
"learning_rate": 9.996635479818683e-06,
|
| 428 |
+
"loss": 0.4933,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.33732718894009217,
|
| 433 |
+
"grad_norm": 0.44956075853602034,
|
| 434 |
+
"learning_rate": 9.995351589858227e-06,
|
| 435 |
+
"loss": 0.4954,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.34285714285714286,
|
| 440 |
+
"grad_norm": 0.4619350325798451,
|
| 441 |
+
"learning_rate": 9.993860758827171e-06,
|
| 442 |
+
"loss": 0.4918,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.34838709677419355,
|
| 447 |
+
"grad_norm": 0.49495275870753425,
|
| 448 |
+
"learning_rate": 9.992163048485776e-06,
|
| 449 |
+
"loss": 0.4928,
|
| 450 |
+
"step": 630
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.35391705069124424,
|
| 454 |
+
"grad_norm": 0.3640423564274247,
|
| 455 |
+
"learning_rate": 9.990258529164618e-06,
|
| 456 |
+
"loss": 0.4838,
|
| 457 |
+
"step": 640
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.35944700460829493,
|
| 461 |
+
"grad_norm": 0.4420987239801644,
|
| 462 |
+
"learning_rate": 9.988147279761706e-06,
|
| 463 |
+
"loss": 0.488,
|
| 464 |
+
"step": 650
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.3649769585253456,
|
| 468 |
+
"grad_norm": 0.4511577371212687,
|
| 469 |
+
"learning_rate": 9.985829387739192e-06,
|
| 470 |
+
"loss": 0.4985,
|
| 471 |
+
"step": 660
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.3705069124423963,
|
| 475 |
+
"grad_norm": 0.4396075419107915,
|
| 476 |
+
"learning_rate": 9.98330494911976e-06,
|
| 477 |
+
"loss": 0.4915,
|
| 478 |
+
"step": 670
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.376036866359447,
|
| 482 |
+
"grad_norm": 0.4704848369571105,
|
| 483 |
+
"learning_rate": 9.980574068482635e-06,
|
| 484 |
+
"loss": 0.4878,
|
| 485 |
+
"step": 680
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.3815668202764977,
|
| 489 |
+
"grad_norm": 0.4763102579576698,
|
| 490 |
+
"learning_rate": 9.977636858959274e-06,
|
| 491 |
+
"loss": 0.4957,
|
| 492 |
+
"step": 690
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.3870967741935484,
|
| 496 |
+
"grad_norm": 0.45436384650049316,
|
| 497 |
+
"learning_rate": 9.974493442228653e-06,
|
| 498 |
+
"loss": 0.4871,
|
| 499 |
+
"step": 700
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.39262672811059907,
|
| 503 |
+
"grad_norm": 0.4546113951664281,
|
| 504 |
+
"learning_rate": 9.971143948512239e-06,
|
| 505 |
+
"loss": 0.4839,
|
| 506 |
+
"step": 710
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.39815668202764976,
|
| 510 |
+
"grad_norm": 0.3942291564886981,
|
| 511 |
+
"learning_rate": 9.967588516568601e-06,
|
| 512 |
+
"loss": 0.4817,
|
| 513 |
+
"step": 720
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.40368663594470044,
|
| 517 |
+
"grad_norm": 0.42410341959833237,
|
| 518 |
+
"learning_rate": 9.963827293687648e-06,
|
| 519 |
+
"loss": 0.4926,
|
| 520 |
+
"step": 730
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.40921658986175113,
|
| 524 |
+
"grad_norm": 0.5249360145309199,
|
| 525 |
+
"learning_rate": 9.959860435684534e-06,
|
| 526 |
+
"loss": 0.4855,
|
| 527 |
+
"step": 740
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.4147465437788018,
|
| 531 |
+
"grad_norm": 0.44333787753063203,
|
| 532 |
+
"learning_rate": 9.95568810689321e-06,
|
| 533 |
+
"loss": 0.4909,
|
| 534 |
+
"step": 750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.4202764976958525,
|
| 538 |
+
"grad_norm": 0.4571044299213202,
|
| 539 |
+
"learning_rate": 9.951310480159605e-06,
|
| 540 |
+
"loss": 0.4808,
|
| 541 |
+
"step": 760
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.4258064516129032,
|
| 545 |
+
"grad_norm": 0.404103839654976,
|
| 546 |
+
"learning_rate": 9.946727736834467e-06,
|
| 547 |
+
"loss": 0.4816,
|
| 548 |
+
"step": 770
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.4313364055299539,
|
| 552 |
+
"grad_norm": 0.4725053041297357,
|
| 553 |
+
"learning_rate": 9.94194006676586e-06,
|
| 554 |
+
"loss": 0.4888,
|
| 555 |
+
"step": 780
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.4368663594470046,
|
| 559 |
+
"grad_norm": 0.46985417927228335,
|
| 560 |
+
"learning_rate": 9.936947668291284e-06,
|
| 561 |
+
"loss": 0.4877,
|
| 562 |
+
"step": 790
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.4423963133640553,
|
| 566 |
+
"grad_norm": 0.49996822002708025,
|
| 567 |
+
"learning_rate": 9.931750748229475e-06,
|
| 568 |
+
"loss": 0.4804,
|
| 569 |
+
"step": 800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.447926267281106,
|
| 573 |
+
"grad_norm": 0.4531834191607307,
|
| 574 |
+
"learning_rate": 9.926349521871824e-06,
|
| 575 |
+
"loss": 0.4795,
|
| 576 |
+
"step": 810
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.4534562211981567,
|
| 580 |
+
"grad_norm": 0.37802138341323005,
|
| 581 |
+
"learning_rate": 9.920744212973468e-06,
|
| 582 |
+
"loss": 0.4756,
|
| 583 |
+
"step": 820
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.4589861751152074,
|
| 587 |
+
"grad_norm": 0.4243052863598972,
|
| 588 |
+
"learning_rate": 9.91493505374401e-06,
|
| 589 |
+
"loss": 0.4852,
|
| 590 |
+
"step": 830
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.4645161290322581,
|
| 594 |
+
"grad_norm": 0.38897153286113667,
|
| 595 |
+
"learning_rate": 9.908922284837911e-06,
|
| 596 |
+
"loss": 0.4816,
|
| 597 |
+
"step": 840
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.4700460829493088,
|
| 601 |
+
"grad_norm": 0.39229328262545654,
|
| 602 |
+
"learning_rate": 9.90270615534451e-06,
|
| 603 |
+
"loss": 0.485,
|
| 604 |
+
"step": 850
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.47557603686635946,
|
| 608 |
+
"grad_norm": 0.4195538643886297,
|
| 609 |
+
"learning_rate": 9.89628692277771e-06,
|
| 610 |
+
"loss": 0.4791,
|
| 611 |
+
"step": 860
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.48110599078341015,
|
| 615 |
+
"grad_norm": 0.45215319555762606,
|
| 616 |
+
"learning_rate": 9.889664853065315e-06,
|
| 617 |
+
"loss": 0.4749,
|
| 618 |
+
"step": 870
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.48663594470046084,
|
| 622 |
+
"grad_norm": 0.3934282464522341,
|
| 623 |
+
"learning_rate": 9.882840220538002e-06,
|
| 624 |
+
"loss": 0.4847,
|
| 625 |
+
"step": 880
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.49216589861751153,
|
| 629 |
+
"grad_norm": 0.45882453815542523,
|
| 630 |
+
"learning_rate": 9.875813307917966e-06,
|
| 631 |
+
"loss": 0.4823,
|
| 632 |
+
"step": 890
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.4976958525345622,
|
| 636 |
+
"grad_norm": 0.4171659335530635,
|
| 637 |
+
"learning_rate": 9.8685844063072e-06,
|
| 638 |
+
"loss": 0.4791,
|
| 639 |
+
"step": 900
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.5032258064516129,
|
| 643 |
+
"grad_norm": 0.36877001843415697,
|
| 644 |
+
"learning_rate": 9.86115381517545e-06,
|
| 645 |
+
"loss": 0.48,
|
| 646 |
+
"step": 910
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.5087557603686635,
|
| 650 |
+
"grad_norm": 0.4248437155717216,
|
| 651 |
+
"learning_rate": 9.853521842347787e-06,
|
| 652 |
+
"loss": 0.4821,
|
| 653 |
+
"step": 920
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.5142857142857142,
|
| 657 |
+
"grad_norm": 0.3865550402068234,
|
| 658 |
+
"learning_rate": 9.845688803991873e-06,
|
| 659 |
+
"loss": 0.4778,
|
| 660 |
+
"step": 930
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.5198156682027649,
|
| 664 |
+
"grad_norm": 0.4048712896727712,
|
| 665 |
+
"learning_rate": 9.837655024604856e-06,
|
| 666 |
+
"loss": 0.4771,
|
| 667 |
+
"step": 940
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.5253456221198156,
|
| 671 |
+
"grad_norm": 0.3928080223641722,
|
| 672 |
+
"learning_rate": 9.82942083699993e-06,
|
| 673 |
+
"loss": 0.4711,
|
| 674 |
+
"step": 950
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.5308755760368664,
|
| 678 |
+
"grad_norm": 0.4073506281198024,
|
| 679 |
+
"learning_rate": 9.82098658229254e-06,
|
| 680 |
+
"loss": 0.4773,
|
| 681 |
+
"step": 960
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.5364055299539171,
|
| 685 |
+
"grad_norm": 0.3799265930738453,
|
| 686 |
+
"learning_rate": 9.812352609886261e-06,
|
| 687 |
+
"loss": 0.4633,
|
| 688 |
+
"step": 970
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.5419354838709678,
|
| 692 |
+
"grad_norm": 0.3791754783762012,
|
| 693 |
+
"learning_rate": 9.803519277458323e-06,
|
| 694 |
+
"loss": 0.4786,
|
| 695 |
+
"step": 980
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.5474654377880185,
|
| 699 |
+
"grad_norm": 0.3724177446979329,
|
| 700 |
+
"learning_rate": 9.794486950944775e-06,
|
| 701 |
+
"loss": 0.4706,
|
| 702 |
+
"step": 990
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.5529953917050692,
|
| 706 |
+
"grad_norm": 0.39011612493597525,
|
| 707 |
+
"learning_rate": 9.785256004525357e-06,
|
| 708 |
+
"loss": 0.472,
|
| 709 |
+
"step": 1000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.5585253456221199,
|
| 713 |
+
"grad_norm": 0.4159910634501067,
|
| 714 |
+
"learning_rate": 9.775826820607967e-06,
|
| 715 |
+
"loss": 0.4684,
|
| 716 |
+
"step": 1010
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.5640552995391706,
|
| 720 |
+
"grad_norm": 0.35305967243893827,
|
| 721 |
+
"learning_rate": 9.766199789812845e-06,
|
| 722 |
+
"loss": 0.4705,
|
| 723 |
+
"step": 1020
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.5695852534562212,
|
| 727 |
+
"grad_norm": 0.3826755145391677,
|
| 728 |
+
"learning_rate": 9.756375310956375e-06,
|
| 729 |
+
"loss": 0.4759,
|
| 730 |
+
"step": 1030
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.5751152073732719,
|
| 734 |
+
"grad_norm": 0.44126945362012004,
|
| 735 |
+
"learning_rate": 9.746353791034566e-06,
|
| 736 |
+
"loss": 0.468,
|
| 737 |
+
"step": 1040
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.5806451612903226,
|
| 741 |
+
"grad_norm": 0.3594904638993689,
|
| 742 |
+
"learning_rate": 9.736135645206198e-06,
|
| 743 |
+
"loss": 0.4718,
|
| 744 |
+
"step": 1050
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.5861751152073733,
|
| 748 |
+
"grad_norm": 0.3757559330794908,
|
| 749 |
+
"learning_rate": 9.725721296775616e-06,
|
| 750 |
+
"loss": 0.4727,
|
| 751 |
+
"step": 1060
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.591705069124424,
|
| 755 |
+
"grad_norm": 0.39116446398772703,
|
| 756 |
+
"learning_rate": 9.7151111771752e-06,
|
| 757 |
+
"loss": 0.4697,
|
| 758 |
+
"step": 1070
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.5972350230414747,
|
| 762 |
+
"grad_norm": 0.3968279194826454,
|
| 763 |
+
"learning_rate": 9.704305725947483e-06,
|
| 764 |
+
"loss": 0.4698,
|
| 765 |
+
"step": 1080
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.6027649769585254,
|
| 769 |
+
"grad_norm": 0.40587146268322655,
|
| 770 |
+
"learning_rate": 9.693305390726952e-06,
|
| 771 |
+
"loss": 0.4685,
|
| 772 |
+
"step": 1090
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.6082949308755761,
|
| 776 |
+
"grad_norm": 0.377035786368524,
|
| 777 |
+
"learning_rate": 9.682110627221503e-06,
|
| 778 |
+
"loss": 0.4654,
|
| 779 |
+
"step": 1100
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.6138248847926268,
|
| 783 |
+
"grad_norm": 0.4003895929403935,
|
| 784 |
+
"learning_rate": 9.670721899193556e-06,
|
| 785 |
+
"loss": 0.4769,
|
| 786 |
+
"step": 1110
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.6193548387096774,
|
| 790 |
+
"grad_norm": 0.45185844229175914,
|
| 791 |
+
"learning_rate": 9.659139678440845e-06,
|
| 792 |
+
"loss": 0.4684,
|
| 793 |
+
"step": 1120
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.6248847926267281,
|
| 797 |
+
"grad_norm": 0.37936262857073433,
|
| 798 |
+
"learning_rate": 9.647364444776877e-06,
|
| 799 |
+
"loss": 0.478,
|
| 800 |
+
"step": 1130
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.6304147465437788,
|
| 804 |
+
"grad_norm": 0.42159273587503454,
|
| 805 |
+
"learning_rate": 9.635396686011052e-06,
|
| 806 |
+
"loss": 0.4731,
|
| 807 |
+
"step": 1140
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.6359447004608295,
|
| 811 |
+
"grad_norm": 0.43046479239329904,
|
| 812 |
+
"learning_rate": 9.623236897928456e-06,
|
| 813 |
+
"loss": 0.4685,
|
| 814 |
+
"step": 1150
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.6414746543778802,
|
| 818 |
+
"grad_norm": 0.4148842353858753,
|
| 819 |
+
"learning_rate": 9.61088558426932e-06,
|
| 820 |
+
"loss": 0.4659,
|
| 821 |
+
"step": 1160
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.6470046082949309,
|
| 825 |
+
"grad_norm": 0.39473737868525427,
|
| 826 |
+
"learning_rate": 9.59834325670815e-06,
|
| 827 |
+
"loss": 0.4709,
|
| 828 |
+
"step": 1170
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.6525345622119816,
|
| 832 |
+
"grad_norm": 0.4015353344240955,
|
| 833 |
+
"learning_rate": 9.58561043483254e-06,
|
| 834 |
+
"loss": 0.4751,
|
| 835 |
+
"step": 1180
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.6580645161290323,
|
| 839 |
+
"grad_norm": 0.42994188947795353,
|
| 840 |
+
"learning_rate": 9.572687646121632e-06,
|
| 841 |
+
"loss": 0.4732,
|
| 842 |
+
"step": 1190
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.663594470046083,
|
| 846 |
+
"grad_norm": 0.42736852075339316,
|
| 847 |
+
"learning_rate": 9.559575425924279e-06,
|
| 848 |
+
"loss": 0.4665,
|
| 849 |
+
"step": 1200
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.6691244239631337,
|
| 853 |
+
"grad_norm": 0.34722978632130697,
|
| 854 |
+
"learning_rate": 9.546274317436858e-06,
|
| 855 |
+
"loss": 0.4608,
|
| 856 |
+
"step": 1210
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.6746543778801843,
|
| 860 |
+
"grad_norm": 0.37549780094613294,
|
| 861 |
+
"learning_rate": 9.53278487168077e-06,
|
| 862 |
+
"loss": 0.4759,
|
| 863 |
+
"step": 1220
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.680184331797235,
|
| 867 |
+
"grad_norm": 0.5132407412202136,
|
| 868 |
+
"learning_rate": 9.519107647479609e-06,
|
| 869 |
+
"loss": 0.4662,
|
| 870 |
+
"step": 1230
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.6857142857142857,
|
| 874 |
+
"grad_norm": 0.4174412166764788,
|
| 875 |
+
"learning_rate": 9.505243211436023e-06,
|
| 876 |
+
"loss": 0.4594,
|
| 877 |
+
"step": 1240
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.6912442396313364,
|
| 881 |
+
"grad_norm": 0.3916564363860535,
|
| 882 |
+
"learning_rate": 9.49119213790823e-06,
|
| 883 |
+
"loss": 0.4715,
|
| 884 |
+
"step": 1250
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.6967741935483871,
|
| 888 |
+
"grad_norm": 0.3997293166106522,
|
| 889 |
+
"learning_rate": 9.476955008986228e-06,
|
| 890 |
+
"loss": 0.4683,
|
| 891 |
+
"step": 1260
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.7023041474654378,
|
| 895 |
+
"grad_norm": 0.3308300953282631,
|
| 896 |
+
"learning_rate": 9.46253241446768e-06,
|
| 897 |
+
"loss": 0.4633,
|
| 898 |
+
"step": 1270
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.7078341013824885,
|
| 902 |
+
"grad_norm": 0.43602935959437467,
|
| 903 |
+
"learning_rate": 9.447924951833483e-06,
|
| 904 |
+
"loss": 0.4656,
|
| 905 |
+
"step": 1280
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.7133640552995392,
|
| 909 |
+
"grad_norm": 0.36016668450990325,
|
| 910 |
+
"learning_rate": 9.433133226223018e-06,
|
| 911 |
+
"loss": 0.4768,
|
| 912 |
+
"step": 1290
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.7188940092165899,
|
| 916 |
+
"grad_norm": 0.3965741821184055,
|
| 917 |
+
"learning_rate": 9.418157850409075e-06,
|
| 918 |
+
"loss": 0.4669,
|
| 919 |
+
"step": 1300
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.7244239631336405,
|
| 923 |
+
"grad_norm": 0.38734403985392707,
|
| 924 |
+
"learning_rate": 9.40299944477247e-06,
|
| 925 |
+
"loss": 0.4765,
|
| 926 |
+
"step": 1310
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.7299539170506912,
|
| 930 |
+
"grad_norm": 0.3563445657533695,
|
| 931 |
+
"learning_rate": 9.387658637276348e-06,
|
| 932 |
+
"loss": 0.4655,
|
| 933 |
+
"step": 1320
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.7354838709677419,
|
| 937 |
+
"grad_norm": 0.3410984943251049,
|
| 938 |
+
"learning_rate": 9.372136063440165e-06,
|
| 939 |
+
"loss": 0.4669,
|
| 940 |
+
"step": 1330
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.7410138248847926,
|
| 944 |
+
"grad_norm": 0.43850058902455336,
|
| 945 |
+
"learning_rate": 9.356432366313362e-06,
|
| 946 |
+
"loss": 0.4601,
|
| 947 |
+
"step": 1340
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.7465437788018433,
|
| 951 |
+
"grad_norm": 0.39491440886088125,
|
| 952 |
+
"learning_rate": 9.340548196448729e-06,
|
| 953 |
+
"loss": 0.4762,
|
| 954 |
+
"step": 1350
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.752073732718894,
|
| 958 |
+
"grad_norm": 0.3843586922714567,
|
| 959 |
+
"learning_rate": 9.324484211875442e-06,
|
| 960 |
+
"loss": 0.4639,
|
| 961 |
+
"step": 1360
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.7576036866359447,
|
| 965 |
+
"grad_norm": 0.37491204324406624,
|
| 966 |
+
"learning_rate": 9.30824107807182e-06,
|
| 967 |
+
"loss": 0.4654,
|
| 968 |
+
"step": 1370
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.7631336405529954,
|
| 972 |
+
"grad_norm": 0.4576626954126291,
|
| 973 |
+
"learning_rate": 9.291819467937746e-06,
|
| 974 |
+
"loss": 0.4611,
|
| 975 |
+
"step": 1380
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.7686635944700461,
|
| 979 |
+
"grad_norm": 0.4394756523970031,
|
| 980 |
+
"learning_rate": 9.275220061766793e-06,
|
| 981 |
+
"loss": 0.4619,
|
| 982 |
+
"step": 1390
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.7741935483870968,
|
| 986 |
+
"grad_norm": 0.3687712612876861,
|
| 987 |
+
"learning_rate": 9.258443547218041e-06,
|
| 988 |
+
"loss": 0.4601,
|
| 989 |
+
"step": 1400
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.7797235023041474,
|
| 993 |
+
"grad_norm": 0.37939730644811315,
|
| 994 |
+
"learning_rate": 9.241490619287593e-06,
|
| 995 |
+
"loss": 0.4671,
|
| 996 |
+
"step": 1410
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.7852534562211981,
|
| 1000 |
+
"grad_norm": 0.4503285510527914,
|
| 1001 |
+
"learning_rate": 9.224361980279779e-06,
|
| 1002 |
+
"loss": 0.4631,
|
| 1003 |
+
"step": 1420
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.7907834101382488,
|
| 1007 |
+
"grad_norm": 0.45715075255423665,
|
| 1008 |
+
"learning_rate": 9.207058339778065e-06,
|
| 1009 |
+
"loss": 0.4681,
|
| 1010 |
+
"step": 1430
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.7963133640552995,
|
| 1014 |
+
"grad_norm": 0.3541259878976316,
|
| 1015 |
+
"learning_rate": 9.189580414615658e-06,
|
| 1016 |
+
"loss": 0.457,
|
| 1017 |
+
"step": 1440
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.8018433179723502,
|
| 1021 |
+
"grad_norm": 0.4085052745840183,
|
| 1022 |
+
"learning_rate": 9.171928928845802e-06,
|
| 1023 |
+
"loss": 0.4541,
|
| 1024 |
+
"step": 1450
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.8073732718894009,
|
| 1028 |
+
"grad_norm": 0.3616899823860361,
|
| 1029 |
+
"learning_rate": 9.154104613711798e-06,
|
| 1030 |
+
"loss": 0.4575,
|
| 1031 |
+
"step": 1460
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.8129032258064516,
|
| 1035 |
+
"grad_norm": 0.39971875774962656,
|
| 1036 |
+
"learning_rate": 9.136108207616694e-06,
|
| 1037 |
+
"loss": 0.4695,
|
| 1038 |
+
"step": 1470
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.8184331797235023,
|
| 1042 |
+
"grad_norm": 0.4179584638146379,
|
| 1043 |
+
"learning_rate": 9.117940456092706e-06,
|
| 1044 |
+
"loss": 0.4659,
|
| 1045 |
+
"step": 1480
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.823963133640553,
|
| 1049 |
+
"grad_norm": 0.3835155006911313,
|
| 1050 |
+
"learning_rate": 9.099602111770336e-06,
|
| 1051 |
+
"loss": 0.458,
|
| 1052 |
+
"step": 1490
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.8294930875576036,
|
| 1056 |
+
"grad_norm": 0.36547715603099723,
|
| 1057 |
+
"learning_rate": 9.081093934347178e-06,
|
| 1058 |
+
"loss": 0.4646,
|
| 1059 |
+
"step": 1500
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.8350230414746543,
|
| 1063 |
+
"grad_norm": 0.3295307717464045,
|
| 1064 |
+
"learning_rate": 9.062416690556463e-06,
|
| 1065 |
+
"loss": 0.4602,
|
| 1066 |
+
"step": 1510
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.840552995391705,
|
| 1070 |
+
"grad_norm": 0.34026406181637314,
|
| 1071 |
+
"learning_rate": 9.043571154135285e-06,
|
| 1072 |
+
"loss": 0.4543,
|
| 1073 |
+
"step": 1520
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.8460829493087557,
|
| 1077 |
+
"grad_norm": 0.40280573682285203,
|
| 1078 |
+
"learning_rate": 9.02455810579255e-06,
|
| 1079 |
+
"loss": 0.4669,
|
| 1080 |
+
"step": 1530
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.8516129032258064,
|
| 1084 |
+
"grad_norm": 0.34345937973887686,
|
| 1085 |
+
"learning_rate": 9.005378333176637e-06,
|
| 1086 |
+
"loss": 0.4616,
|
| 1087 |
+
"step": 1540
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.8571428571428571,
|
| 1091 |
+
"grad_norm": 0.34245350990620255,
|
| 1092 |
+
"learning_rate": 8.986032630842767e-06,
|
| 1093 |
+
"loss": 0.4623,
|
| 1094 |
+
"step": 1550
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.8626728110599078,
|
| 1098 |
+
"grad_norm": 0.3852027478756217,
|
| 1099 |
+
"learning_rate": 8.966521800220084e-06,
|
| 1100 |
+
"loss": 0.4629,
|
| 1101 |
+
"step": 1560
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.8682027649769585,
|
| 1105 |
+
"grad_norm": 0.4686461690105208,
|
| 1106 |
+
"learning_rate": 8.946846649578457e-06,
|
| 1107 |
+
"loss": 0.4606,
|
| 1108 |
+
"step": 1570
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.8737327188940092,
|
| 1112 |
+
"grad_norm": 0.3405054745038256,
|
| 1113 |
+
"learning_rate": 8.927007993994997e-06,
|
| 1114 |
+
"loss": 0.4562,
|
| 1115 |
+
"step": 1580
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.8792626728110599,
|
| 1119 |
+
"grad_norm": 0.3692693675496781,
|
| 1120 |
+
"learning_rate": 8.907006655320287e-06,
|
| 1121 |
+
"loss": 0.4558,
|
| 1122 |
+
"step": 1590
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.8847926267281107,
|
| 1126 |
+
"grad_norm": 0.3379877106135158,
|
| 1127 |
+
"learning_rate": 8.886843462144343e-06,
|
| 1128 |
+
"loss": 0.4605,
|
| 1129 |
+
"step": 1600
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.8903225806451613,
|
| 1133 |
+
"grad_norm": 0.36146892614586007,
|
| 1134 |
+
"learning_rate": 8.866519249762275e-06,
|
| 1135 |
+
"loss": 0.464,
|
| 1136 |
+
"step": 1610
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.895852534562212,
|
| 1140 |
+
"grad_norm": 0.3979151729935212,
|
| 1141 |
+
"learning_rate": 8.846034860139706e-06,
|
| 1142 |
+
"loss": 0.465,
|
| 1143 |
+
"step": 1620
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.9013824884792627,
|
| 1147 |
+
"grad_norm": 0.3488713134537118,
|
| 1148 |
+
"learning_rate": 8.82539114187786e-06,
|
| 1149 |
+
"loss": 0.4545,
|
| 1150 |
+
"step": 1630
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.9069124423963134,
|
| 1154 |
+
"grad_norm": 0.37006007621420706,
|
| 1155 |
+
"learning_rate": 8.804588950178439e-06,
|
| 1156 |
+
"loss": 0.4592,
|
| 1157 |
+
"step": 1640
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.9124423963133641,
|
| 1161 |
+
"grad_norm": 0.4218977786755043,
|
| 1162 |
+
"learning_rate": 8.783629146808175e-06,
|
| 1163 |
+
"loss": 0.4623,
|
| 1164 |
+
"step": 1650
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.9179723502304148,
|
| 1168 |
+
"grad_norm": 0.36142612348312186,
|
| 1169 |
+
"learning_rate": 8.762512600063136e-06,
|
| 1170 |
+
"loss": 0.4597,
|
| 1171 |
+
"step": 1660
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.9235023041474655,
|
| 1175 |
+
"grad_norm": 0.37743894605389894,
|
| 1176 |
+
"learning_rate": 8.74124018473276e-06,
|
| 1177 |
+
"loss": 0.4538,
|
| 1178 |
+
"step": 1670
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.9290322580645162,
|
| 1182 |
+
"grad_norm": 0.37370963533147783,
|
| 1183 |
+
"learning_rate": 8.719812782063603e-06,
|
| 1184 |
+
"loss": 0.4547,
|
| 1185 |
+
"step": 1680
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.9345622119815669,
|
| 1189 |
+
"grad_norm": 0.40809993391643884,
|
| 1190 |
+
"learning_rate": 8.698231279722845e-06,
|
| 1191 |
+
"loss": 0.462,
|
| 1192 |
+
"step": 1690
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.9400921658986175,
|
| 1196 |
+
"grad_norm": 0.3756284623011763,
|
| 1197 |
+
"learning_rate": 8.676496571761507e-06,
|
| 1198 |
+
"loss": 0.4513,
|
| 1199 |
+
"step": 1700
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.9456221198156682,
|
| 1203 |
+
"grad_norm": 0.3390495467924666,
|
| 1204 |
+
"learning_rate": 8.65460955857742e-06,
|
| 1205 |
+
"loss": 0.4574,
|
| 1206 |
+
"step": 1710
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.9511520737327189,
|
| 1210 |
+
"grad_norm": 0.3968064162366307,
|
| 1211 |
+
"learning_rate": 8.632571146877924e-06,
|
| 1212 |
+
"loss": 0.4587,
|
| 1213 |
+
"step": 1720
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.9566820276497696,
|
| 1217 |
+
"grad_norm": 0.37489260177502365,
|
| 1218 |
+
"learning_rate": 8.6103822496423e-06,
|
| 1219 |
+
"loss": 0.4614,
|
| 1220 |
+
"step": 1730
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.9622119815668203,
|
| 1224 |
+
"grad_norm": 0.3468923282438075,
|
| 1225 |
+
"learning_rate": 8.588043786083952e-06,
|
| 1226 |
+
"loss": 0.4561,
|
| 1227 |
+
"step": 1740
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.967741935483871,
|
| 1231 |
+
"grad_norm": 0.3742022627413655,
|
| 1232 |
+
"learning_rate": 8.565556681612335e-06,
|
| 1233 |
+
"loss": 0.4521,
|
| 1234 |
+
"step": 1750
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.9732718894009217,
|
| 1238 |
+
"grad_norm": 0.35327369319565305,
|
| 1239 |
+
"learning_rate": 8.542921867794597e-06,
|
| 1240 |
+
"loss": 0.4534,
|
| 1241 |
+
"step": 1760
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.9788018433179724,
|
| 1245 |
+
"grad_norm": 0.39149761577819314,
|
| 1246 |
+
"learning_rate": 8.520140282317018e-06,
|
| 1247 |
+
"loss": 0.4561,
|
| 1248 |
+
"step": 1770
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.9843317972350231,
|
| 1252 |
+
"grad_norm": 0.42419710853826387,
|
| 1253 |
+
"learning_rate": 8.497212868946132e-06,
|
| 1254 |
+
"loss": 0.4496,
|
| 1255 |
+
"step": 1780
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.9898617511520738,
|
| 1259 |
+
"grad_norm": 0.370513055308333,
|
| 1260 |
+
"learning_rate": 8.474140577489652e-06,
|
| 1261 |
+
"loss": 0.4512,
|
| 1262 |
+
"step": 1790
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.9953917050691244,
|
| 1266 |
+
"grad_norm": 0.46731006937418296,
|
| 1267 |
+
"learning_rate": 8.45092436375712e-06,
|
| 1268 |
+
"loss": 0.447,
|
| 1269 |
+
"step": 1800
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.0009216589861751,
|
| 1273 |
+
"grad_norm": 0.43527476672720355,
|
| 1274 |
+
"learning_rate": 8.4275651895203e-06,
|
| 1275 |
+
"loss": 0.4858,
|
| 1276 |
+
"step": 1810
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 1.0064516129032257,
|
| 1280 |
+
"grad_norm": 0.3927852344244657,
|
| 1281 |
+
"learning_rate": 8.404064022473344e-06,
|
| 1282 |
+
"loss": 0.433,
|
| 1283 |
+
"step": 1820
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 1.0119815668202765,
|
| 1287 |
+
"grad_norm": 0.44790042998448304,
|
| 1288 |
+
"learning_rate": 8.380421836192705e-06,
|
| 1289 |
+
"loss": 0.4299,
|
| 1290 |
+
"step": 1830
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 1.017511520737327,
|
| 1294 |
+
"grad_norm": 0.36665409180864517,
|
| 1295 |
+
"learning_rate": 8.356639610096799e-06,
|
| 1296 |
+
"loss": 0.4372,
|
| 1297 |
+
"step": 1840
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 1.023041474654378,
|
| 1301 |
+
"grad_norm": 0.4154548719085105,
|
| 1302 |
+
"learning_rate": 8.33271832940543e-06,
|
| 1303 |
+
"loss": 0.4153,
|
| 1304 |
+
"step": 1850
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 1.0285714285714285,
|
| 1308 |
+
"grad_norm": 0.3498424106524037,
|
| 1309 |
+
"learning_rate": 8.308658985098983e-06,
|
| 1310 |
+
"loss": 0.4365,
|
| 1311 |
+
"step": 1860
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 1.0341013824884793,
|
| 1315 |
+
"grad_norm": 0.3527496476806808,
|
| 1316 |
+
"learning_rate": 8.284462573877367e-06,
|
| 1317 |
+
"loss": 0.4414,
|
| 1318 |
+
"step": 1870
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 1.0396313364055298,
|
| 1322 |
+
"grad_norm": 0.34095264970889066,
|
| 1323 |
+
"learning_rate": 8.260130098118724e-06,
|
| 1324 |
+
"loss": 0.4373,
|
| 1325 |
+
"step": 1880
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.0451612903225806,
|
| 1329 |
+
"grad_norm": 0.3525020261906649,
|
| 1330 |
+
"learning_rate": 8.235662565837901e-06,
|
| 1331 |
+
"loss": 0.446,
|
| 1332 |
+
"step": 1890
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 1.0506912442396312,
|
| 1336 |
+
"grad_norm": 0.30559116702498945,
|
| 1337 |
+
"learning_rate": 8.211060990644699e-06,
|
| 1338 |
+
"loss": 0.4293,
|
| 1339 |
+
"step": 1900
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 1.056221198156682,
|
| 1343 |
+
"grad_norm": 0.37541049203915616,
|
| 1344 |
+
"learning_rate": 8.18632639170188e-06,
|
| 1345 |
+
"loss": 0.4306,
|
| 1346 |
+
"step": 1910
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 1.0617511520737328,
|
| 1350 |
+
"grad_norm": 0.3896683499442952,
|
| 1351 |
+
"learning_rate": 8.161459793682937e-06,
|
| 1352 |
+
"loss": 0.4338,
|
| 1353 |
+
"step": 1920
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 1.0672811059907834,
|
| 1357 |
+
"grad_norm": 0.35556240560090524,
|
| 1358 |
+
"learning_rate": 8.136462226729663e-06,
|
| 1359 |
+
"loss": 0.4273,
|
| 1360 |
+
"step": 1930
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 1.072811059907834,
|
| 1364 |
+
"grad_norm": 0.33870684965626063,
|
| 1365 |
+
"learning_rate": 8.111334726409453e-06,
|
| 1366 |
+
"loss": 0.4275,
|
| 1367 |
+
"step": 1940
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 1.0783410138248848,
|
| 1371 |
+
"grad_norm": 0.32599049999370167,
|
| 1372 |
+
"learning_rate": 8.08607833367243e-06,
|
| 1373 |
+
"loss": 0.4344,
|
| 1374 |
+
"step": 1950
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 1.0838709677419356,
|
| 1378 |
+
"grad_norm": 0.37446391533889434,
|
| 1379 |
+
"learning_rate": 8.060694094808295e-06,
|
| 1380 |
+
"loss": 0.4376,
|
| 1381 |
+
"step": 1960
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 1.0894009216589862,
|
| 1385 |
+
"grad_norm": 0.33002930959463256,
|
| 1386 |
+
"learning_rate": 8.035183061403006e-06,
|
| 1387 |
+
"loss": 0.434,
|
| 1388 |
+
"step": 1970
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 1.094930875576037,
|
| 1392 |
+
"grad_norm": 0.35423865601253207,
|
| 1393 |
+
"learning_rate": 8.0095462902952e-06,
|
| 1394 |
+
"loss": 0.4201,
|
| 1395 |
+
"step": 1980
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 1.1004608294930875,
|
| 1399 |
+
"grad_norm": 0.3248427195938627,
|
| 1400 |
+
"learning_rate": 7.983784843532415e-06,
|
| 1401 |
+
"loss": 0.4253,
|
| 1402 |
+
"step": 1990
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 1.1059907834101383,
|
| 1406 |
+
"grad_norm": 0.34623653882886374,
|
| 1407 |
+
"learning_rate": 7.957899788327092e-06,
|
| 1408 |
+
"loss": 0.4323,
|
| 1409 |
+
"step": 2000
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 1.111520737327189,
|
| 1413 |
+
"grad_norm": 0.3599295805789168,
|
| 1414 |
+
"learning_rate": 7.93189219701237e-06,
|
| 1415 |
+
"loss": 0.4259,
|
| 1416 |
+
"step": 2010
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 1.1170506912442397,
|
| 1420 |
+
"grad_norm": 0.38414283548649564,
|
| 1421 |
+
"learning_rate": 7.905763146997652e-06,
|
| 1422 |
+
"loss": 0.4335,
|
| 1423 |
+
"step": 2020
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 1.1225806451612903,
|
| 1427 |
+
"grad_norm": 0.32382155481213737,
|
| 1428 |
+
"learning_rate": 7.879513720723984e-06,
|
| 1429 |
+
"loss": 0.4395,
|
| 1430 |
+
"step": 2030
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 1.128110599078341,
|
| 1434 |
+
"grad_norm": 0.32042378851107606,
|
| 1435 |
+
"learning_rate": 7.853145005619199e-06,
|
| 1436 |
+
"loss": 0.426,
|
| 1437 |
+
"step": 2040
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 1.1336405529953917,
|
| 1441 |
+
"grad_norm": 0.33755347609978986,
|
| 1442 |
+
"learning_rate": 7.826658094052884e-06,
|
| 1443 |
+
"loss": 0.4362,
|
| 1444 |
+
"step": 2050
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 1.1391705069124425,
|
| 1448 |
+
"grad_norm": 0.39877451031067934,
|
| 1449 |
+
"learning_rate": 7.800054083291114e-06,
|
| 1450 |
+
"loss": 0.428,
|
| 1451 |
+
"step": 2060
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 1.144700460829493,
|
| 1455 |
+
"grad_norm": 0.31738937325882993,
|
| 1456 |
+
"learning_rate": 7.773334075451e-06,
|
| 1457 |
+
"loss": 0.4413,
|
| 1458 |
+
"step": 2070
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 1.1502304147465439,
|
| 1462 |
+
"grad_norm": 0.34047775678025793,
|
| 1463 |
+
"learning_rate": 7.746499177455036e-06,
|
| 1464 |
+
"loss": 0.4309,
|
| 1465 |
+
"step": 2080
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 1.1557603686635944,
|
| 1469 |
+
"grad_norm": 0.324338242448013,
|
| 1470 |
+
"learning_rate": 7.719550500985234e-06,
|
| 1471 |
+
"loss": 0.4315,
|
| 1472 |
+
"step": 2090
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 1.1612903225806452,
|
| 1476 |
+
"grad_norm": 0.33430643506460095,
|
| 1477 |
+
"learning_rate": 7.69248916243708e-06,
|
| 1478 |
+
"loss": 0.4329,
|
| 1479 |
+
"step": 2100
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 1.1668202764976958,
|
| 1483 |
+
"grad_norm": 0.3641478085283545,
|
| 1484 |
+
"learning_rate": 7.665316282873281e-06,
|
| 1485 |
+
"loss": 0.4286,
|
| 1486 |
+
"step": 2110
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 1.1723502304147466,
|
| 1490 |
+
"grad_norm": 0.43045384768424416,
|
| 1491 |
+
"learning_rate": 7.638032987977322e-06,
|
| 1492 |
+
"loss": 0.4247,
|
| 1493 |
+
"step": 2120
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 1.1778801843317972,
|
| 1497 |
+
"grad_norm": 0.4742558814490241,
|
| 1498 |
+
"learning_rate": 7.610640408006832e-06,
|
| 1499 |
+
"loss": 0.4358,
|
| 1500 |
+
"step": 2130
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 1.183410138248848,
|
| 1504 |
+
"grad_norm": 0.3728801367095553,
|
| 1505 |
+
"learning_rate": 7.583139677746769e-06,
|
| 1506 |
+
"loss": 0.4261,
|
| 1507 |
+
"step": 2140
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 1.1889400921658986,
|
| 1511 |
+
"grad_norm": 0.3946467119158356,
|
| 1512 |
+
"learning_rate": 7.555531936462398e-06,
|
| 1513 |
+
"loss": 0.4215,
|
| 1514 |
+
"step": 2150
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 1.1944700460829494,
|
| 1518 |
+
"grad_norm": 0.42194525138871064,
|
| 1519 |
+
"learning_rate": 7.527818327852101e-06,
|
| 1520 |
+
"loss": 0.4413,
|
| 1521 |
+
"step": 2160
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 1.2,
|
| 1525 |
+
"grad_norm": 0.3362981808853216,
|
| 1526 |
+
"learning_rate": 7.500000000000001e-06,
|
| 1527 |
+
"loss": 0.4268,
|
| 1528 |
+
"step": 2170
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 1.2055299539170508,
|
| 1532 |
+
"grad_norm": 0.3603451029762717,
|
| 1533 |
+
"learning_rate": 7.472078105328391e-06,
|
| 1534 |
+
"loss": 0.4264,
|
| 1535 |
+
"step": 2180
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 1.2110599078341013,
|
| 1539 |
+
"grad_norm": 0.4138525995577666,
|
| 1540 |
+
"learning_rate": 7.444053800550004e-06,
|
| 1541 |
+
"loss": 0.4366,
|
| 1542 |
+
"step": 2190
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 1.2165898617511521,
|
| 1546 |
+
"grad_norm": 0.39448869972439937,
|
| 1547 |
+
"learning_rate": 7.415928246620086e-06,
|
| 1548 |
+
"loss": 0.4294,
|
| 1549 |
+
"step": 2200
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 1.2221198156682027,
|
| 1553 |
+
"grad_norm": 0.33343622855975236,
|
| 1554 |
+
"learning_rate": 7.387702608688302e-06,
|
| 1555 |
+
"loss": 0.42,
|
| 1556 |
+
"step": 2210
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 1.2276497695852535,
|
| 1560 |
+
"grad_norm": 0.33564499515032403,
|
| 1561 |
+
"learning_rate": 7.359378056050472e-06,
|
| 1562 |
+
"loss": 0.4382,
|
| 1563 |
+
"step": 2220
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 1.233179723502304,
|
| 1567 |
+
"grad_norm": 0.3305094552462621,
|
| 1568 |
+
"learning_rate": 7.3309557621001295e-06,
|
| 1569 |
+
"loss": 0.4362,
|
| 1570 |
+
"step": 2230
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 1.238709677419355,
|
| 1574 |
+
"grad_norm": 0.3505064540471358,
|
| 1575 |
+
"learning_rate": 7.3024369042799094e-06,
|
| 1576 |
+
"loss": 0.4315,
|
| 1577 |
+
"step": 2240
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 1.2442396313364055,
|
| 1581 |
+
"grad_norm": 0.4175232059230619,
|
| 1582 |
+
"learning_rate": 7.273822664032771e-06,
|
| 1583 |
+
"loss": 0.4333,
|
| 1584 |
+
"step": 2250
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 1.2497695852534563,
|
| 1588 |
+
"grad_norm": 0.31440206686096517,
|
| 1589 |
+
"learning_rate": 7.245114226753055e-06,
|
| 1590 |
+
"loss": 0.4302,
|
| 1591 |
+
"step": 2260
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 1.2552995391705069,
|
| 1595 |
+
"grad_norm": 0.3799967479589324,
|
| 1596 |
+
"learning_rate": 7.2163127817373815e-06,
|
| 1597 |
+
"loss": 0.4416,
|
| 1598 |
+
"step": 2270
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 1.2608294930875577,
|
| 1602 |
+
"grad_norm": 0.34246345630017244,
|
| 1603 |
+
"learning_rate": 7.1874195221353706e-06,
|
| 1604 |
+
"loss": 0.4315,
|
| 1605 |
+
"step": 2280
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 1.2663594470046082,
|
| 1609 |
+
"grad_norm": 0.2952208188222985,
|
| 1610 |
+
"learning_rate": 7.158435644900226e-06,
|
| 1611 |
+
"loss": 0.4308,
|
| 1612 |
+
"step": 2290
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 1.271889400921659,
|
| 1616 |
+
"grad_norm": 0.3364601276348195,
|
| 1617 |
+
"learning_rate": 7.129362350739138e-06,
|
| 1618 |
+
"loss": 0.4271,
|
| 1619 |
+
"step": 2300
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 1.2774193548387096,
|
| 1623 |
+
"grad_norm": 0.3474139278148847,
|
| 1624 |
+
"learning_rate": 7.1002008440635515e-06,
|
| 1625 |
+
"loss": 0.4305,
|
| 1626 |
+
"step": 2310
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 1.2829493087557604,
|
| 1630 |
+
"grad_norm": 0.3280092320348997,
|
| 1631 |
+
"learning_rate": 7.070952332939266e-06,
|
| 1632 |
+
"loss": 0.4331,
|
| 1633 |
+
"step": 2320
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 1.288479262672811,
|
| 1637 |
+
"grad_norm": 0.4223833613636633,
|
| 1638 |
+
"learning_rate": 7.04161802903639e-06,
|
| 1639 |
+
"loss": 0.4327,
|
| 1640 |
+
"step": 2330
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 1.2940092165898618,
|
| 1644 |
+
"grad_norm": 0.3448536879815269,
|
| 1645 |
+
"learning_rate": 7.012199147579146e-06,
|
| 1646 |
+
"loss": 0.4246,
|
| 1647 |
+
"step": 2340
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 1.2995391705069124,
|
| 1651 |
+
"grad_norm": 0.3207441765420925,
|
| 1652 |
+
"learning_rate": 6.98269690729553e-06,
|
| 1653 |
+
"loss": 0.4301,
|
| 1654 |
+
"step": 2350
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 1.3050691244239632,
|
| 1658 |
+
"grad_norm": 0.3165222151173208,
|
| 1659 |
+
"learning_rate": 6.953112530366818e-06,
|
| 1660 |
+
"loss": 0.4261,
|
| 1661 |
+
"step": 2360
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 1.3105990783410137,
|
| 1665 |
+
"grad_norm": 0.3876615485028844,
|
| 1666 |
+
"learning_rate": 6.923447242376942e-06,
|
| 1667 |
+
"loss": 0.4316,
|
| 1668 |
+
"step": 2370
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 1.3161290322580645,
|
| 1672 |
+
"grad_norm": 0.37232768341887623,
|
| 1673 |
+
"learning_rate": 6.893702272261711e-06,
|
| 1674 |
+
"loss": 0.4212,
|
| 1675 |
+
"step": 2380
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 1.3216589861751151,
|
| 1679 |
+
"grad_norm": 0.34637683615909776,
|
| 1680 |
+
"learning_rate": 6.863878852257908e-06,
|
| 1681 |
+
"loss": 0.4334,
|
| 1682 |
+
"step": 2390
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 1.327188940092166,
|
| 1686 |
+
"grad_norm": 0.35731944832213297,
|
| 1687 |
+
"learning_rate": 6.833978217852233e-06,
|
| 1688 |
+
"loss": 0.4225,
|
| 1689 |
+
"step": 2400
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 1.3327188940092167,
|
| 1693 |
+
"grad_norm": 0.31517156848331396,
|
| 1694 |
+
"learning_rate": 6.80400160773013e-06,
|
| 1695 |
+
"loss": 0.4254,
|
| 1696 |
+
"step": 2410
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 1.3382488479262673,
|
| 1700 |
+
"grad_norm": 0.31675935891661117,
|
| 1701 |
+
"learning_rate": 6.773950263724467e-06,
|
| 1702 |
+
"loss": 0.4267,
|
| 1703 |
+
"step": 2420
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 1.3437788018433179,
|
| 1707 |
+
"grad_norm": 0.35820405964245244,
|
| 1708 |
+
"learning_rate": 6.743825430764091e-06,
|
| 1709 |
+
"loss": 0.4369,
|
| 1710 |
+
"step": 2430
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 1.3493087557603687,
|
| 1714 |
+
"grad_norm": 0.3198735130417677,
|
| 1715 |
+
"learning_rate": 6.713628356822259e-06,
|
| 1716 |
+
"loss": 0.4334,
|
| 1717 |
+
"step": 2440
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 1.3548387096774195,
|
| 1721 |
+
"grad_norm": 0.35391376983158945,
|
| 1722 |
+
"learning_rate": 6.683360292864933e-06,
|
| 1723 |
+
"loss": 0.4298,
|
| 1724 |
+
"step": 2450
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 1.36036866359447,
|
| 1728 |
+
"grad_norm": 0.3447181141751271,
|
| 1729 |
+
"learning_rate": 6.653022492798959e-06,
|
| 1730 |
+
"loss": 0.429,
|
| 1731 |
+
"step": 2460
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 1.3658986175115206,
|
| 1735 |
+
"grad_norm": 0.32591032190478314,
|
| 1736 |
+
"learning_rate": 6.622616213420125e-06,
|
| 1737 |
+
"loss": 0.4242,
|
| 1738 |
+
"step": 2470
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 1.3714285714285714,
|
| 1742 |
+
"grad_norm": 0.35079358158009544,
|
| 1743 |
+
"learning_rate": 6.592142714361085e-06,
|
| 1744 |
+
"loss": 0.4299,
|
| 1745 |
+
"step": 2480
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 1.3769585253456222,
|
| 1749 |
+
"grad_norm": 0.3105061790757026,
|
| 1750 |
+
"learning_rate": 6.561603258039195e-06,
|
| 1751 |
+
"loss": 0.4315,
|
| 1752 |
+
"step": 2490
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 1.3824884792626728,
|
| 1756 |
+
"grad_norm": 0.366393325245765,
|
| 1757 |
+
"learning_rate": 6.530999109604197e-06,
|
| 1758 |
+
"loss": 0.4244,
|
| 1759 |
+
"step": 2500
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 1.3880184331797234,
|
| 1763 |
+
"grad_norm": 0.354855687477892,
|
| 1764 |
+
"learning_rate": 6.500331536885819e-06,
|
| 1765 |
+
"loss": 0.425,
|
| 1766 |
+
"step": 2510
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 1.3935483870967742,
|
| 1770 |
+
"grad_norm": 0.29867754767506527,
|
| 1771 |
+
"learning_rate": 6.469601810341247e-06,
|
| 1772 |
+
"loss": 0.4314,
|
| 1773 |
+
"step": 2520
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 1.399078341013825,
|
| 1777 |
+
"grad_norm": 0.3631093513648162,
|
| 1778 |
+
"learning_rate": 6.438811203002499e-06,
|
| 1779 |
+
"loss": 0.4246,
|
| 1780 |
+
"step": 2530
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 1.4046082949308756,
|
| 1784 |
+
"grad_norm": 0.3467860388407693,
|
| 1785 |
+
"learning_rate": 6.407960990423683e-06,
|
| 1786 |
+
"loss": 0.4344,
|
| 1787 |
+
"step": 2540
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 1.4101382488479262,
|
| 1791 |
+
"grad_norm": 0.31828964825920697,
|
| 1792 |
+
"learning_rate": 6.377052450628159e-06,
|
| 1793 |
+
"loss": 0.4158,
|
| 1794 |
+
"step": 2550
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 1.415668202764977,
|
| 1798 |
+
"grad_norm": 0.31023813410711815,
|
| 1799 |
+
"learning_rate": 6.346086864055594e-06,
|
| 1800 |
+
"loss": 0.4356,
|
| 1801 |
+
"step": 2560
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 1.4211981566820278,
|
| 1805 |
+
"grad_norm": 0.332473917922917,
|
| 1806 |
+
"learning_rate": 6.31506551350891e-06,
|
| 1807 |
+
"loss": 0.43,
|
| 1808 |
+
"step": 2570
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 1.4267281105990783,
|
| 1812 |
+
"grad_norm": 0.3409141756767579,
|
| 1813 |
+
"learning_rate": 6.283989684101155e-06,
|
| 1814 |
+
"loss": 0.4296,
|
| 1815 |
+
"step": 2580
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 1.432258064516129,
|
| 1819 |
+
"grad_norm": 0.3385052993526194,
|
| 1820 |
+
"learning_rate": 6.252860663202254e-06,
|
| 1821 |
+
"loss": 0.4297,
|
| 1822 |
+
"step": 2590
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 1.4377880184331797,
|
| 1826 |
+
"grad_norm": 0.32236622569856693,
|
| 1827 |
+
"learning_rate": 6.221679740385684e-06,
|
| 1828 |
+
"loss": 0.4274,
|
| 1829 |
+
"step": 2600
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 1.4433179723502305,
|
| 1833 |
+
"grad_norm": 0.315316876619347,
|
| 1834 |
+
"learning_rate": 6.190448207375046e-06,
|
| 1835 |
+
"loss": 0.4162,
|
| 1836 |
+
"step": 2610
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 1.448847926267281,
|
| 1840 |
+
"grad_norm": 0.3376657547389814,
|
| 1841 |
+
"learning_rate": 6.159167357990555e-06,
|
| 1842 |
+
"loss": 0.433,
|
| 1843 |
+
"step": 2620
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 1.4543778801843317,
|
| 1847 |
+
"grad_norm": 0.32358782865643143,
|
| 1848 |
+
"learning_rate": 6.127838488095448e-06,
|
| 1849 |
+
"loss": 0.4267,
|
| 1850 |
+
"step": 2630
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 1.4599078341013825,
|
| 1854 |
+
"grad_norm": 0.3756530225009165,
|
| 1855 |
+
"learning_rate": 6.096462895542288e-06,
|
| 1856 |
+
"loss": 0.4373,
|
| 1857 |
+
"step": 2640
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 1.4654377880184333,
|
| 1861 |
+
"grad_norm": 0.38682543540126985,
|
| 1862 |
+
"learning_rate": 6.065041880119209e-06,
|
| 1863 |
+
"loss": 0.4227,
|
| 1864 |
+
"step": 2650
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 1.4709677419354839,
|
| 1868 |
+
"grad_norm": 0.38616555341944436,
|
| 1869 |
+
"learning_rate": 6.0335767434960625e-06,
|
| 1870 |
+
"loss": 0.4185,
|
| 1871 |
+
"step": 2660
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 1.4764976958525344,
|
| 1875 |
+
"grad_norm": 0.3602473989547172,
|
| 1876 |
+
"learning_rate": 6.002068789170497e-06,
|
| 1877 |
+
"loss": 0.4229,
|
| 1878 |
+
"step": 2670
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 1.4820276497695852,
|
| 1882 |
+
"grad_norm": 0.34024391453280106,
|
| 1883 |
+
"learning_rate": 5.970519322413965e-06,
|
| 1884 |
+
"loss": 0.4325,
|
| 1885 |
+
"step": 2680
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 1.487557603686636,
|
| 1889 |
+
"grad_norm": 0.334874165318193,
|
| 1890 |
+
"learning_rate": 5.938929650217636e-06,
|
| 1891 |
+
"loss": 0.4325,
|
| 1892 |
+
"step": 2690
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 1.4930875576036866,
|
| 1896 |
+
"grad_norm": 0.29562689064173814,
|
| 1897 |
+
"learning_rate": 5.9073010812382595e-06,
|
| 1898 |
+
"loss": 0.4171,
|
| 1899 |
+
"step": 2700
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 1.4986175115207372,
|
| 1903 |
+
"grad_norm": 0.30805696197429483,
|
| 1904 |
+
"learning_rate": 5.875634925743955e-06,
|
| 1905 |
+
"loss": 0.428,
|
| 1906 |
+
"step": 2710
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 1.504147465437788,
|
| 1910 |
+
"grad_norm": 0.32622309094002283,
|
| 1911 |
+
"learning_rate": 5.843932495559925e-06,
|
| 1912 |
+
"loss": 0.4181,
|
| 1913 |
+
"step": 2720
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 1.5096774193548388,
|
| 1917 |
+
"grad_norm": 0.33140067437976467,
|
| 1918 |
+
"learning_rate": 5.812195104014119e-06,
|
| 1919 |
+
"loss": 0.4359,
|
| 1920 |
+
"step": 2730
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 1.5152073732718894,
|
| 1924 |
+
"grad_norm": 0.3233776164901754,
|
| 1925 |
+
"learning_rate": 5.780424065882817e-06,
|
| 1926 |
+
"loss": 0.4241,
|
| 1927 |
+
"step": 2740
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 1.52073732718894,
|
| 1931 |
+
"grad_norm": 0.3295175080953441,
|
| 1932 |
+
"learning_rate": 5.748620697336165e-06,
|
| 1933 |
+
"loss": 0.4276,
|
| 1934 |
+
"step": 2750
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 1.5262672811059907,
|
| 1938 |
+
"grad_norm": 0.3051493556807249,
|
| 1939 |
+
"learning_rate": 5.716786315883657e-06,
|
| 1940 |
+
"loss": 0.4332,
|
| 1941 |
+
"step": 2760
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 1.5317972350230415,
|
| 1945 |
+
"grad_norm": 0.32518469758621127,
|
| 1946 |
+
"learning_rate": 5.6849222403195455e-06,
|
| 1947 |
+
"loss": 0.427,
|
| 1948 |
+
"step": 2770
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 1.5373271889400921,
|
| 1952 |
+
"grad_norm": 0.3502785279432566,
|
| 1953 |
+
"learning_rate": 5.653029790668221e-06,
|
| 1954 |
+
"loss": 0.4228,
|
| 1955 |
+
"step": 2780
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 1.5428571428571427,
|
| 1959 |
+
"grad_norm": 0.328626841799296,
|
| 1960 |
+
"learning_rate": 5.621110288129509e-06,
|
| 1961 |
+
"loss": 0.4254,
|
| 1962 |
+
"step": 2790
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 1.5483870967741935,
|
| 1966 |
+
"grad_norm": 0.34919486039336417,
|
| 1967 |
+
"learning_rate": 5.5891650550239555e-06,
|
| 1968 |
+
"loss": 0.4333,
|
| 1969 |
+
"step": 2800
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 1.5539170506912443,
|
| 1973 |
+
"grad_norm": 0.31813515025326766,
|
| 1974 |
+
"learning_rate": 5.5571954147380355e-06,
|
| 1975 |
+
"loss": 0.4246,
|
| 1976 |
+
"step": 2810
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 1.5594470046082949,
|
| 1980 |
+
"grad_norm": 0.33770710120288266,
|
| 1981 |
+
"learning_rate": 5.525202691669335e-06,
|
| 1982 |
+
"loss": 0.4289,
|
| 1983 |
+
"step": 2820
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 1.5649769585253455,
|
| 1987 |
+
"grad_norm": 0.3169850413623026,
|
| 1988 |
+
"learning_rate": 5.493188211171688e-06,
|
| 1989 |
+
"loss": 0.4303,
|
| 1990 |
+
"step": 2830
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 1.5705069124423963,
|
| 1994 |
+
"grad_norm": 0.3593536785787455,
|
| 1995 |
+
"learning_rate": 5.461153299500261e-06,
|
| 1996 |
+
"loss": 0.4286,
|
| 1997 |
+
"step": 2840
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 1.576036866359447,
|
| 2001 |
+
"grad_norm": 0.30079605129375003,
|
| 2002 |
+
"learning_rate": 5.429099283756618e-06,
|
| 2003 |
+
"loss": 0.4299,
|
| 2004 |
+
"step": 2850
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 1.5815668202764976,
|
| 2008 |
+
"grad_norm": 0.3239103063739578,
|
| 2009 |
+
"learning_rate": 5.3970274918337464e-06,
|
| 2010 |
+
"loss": 0.4162,
|
| 2011 |
+
"step": 2860
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 1.5870967741935482,
|
| 2015 |
+
"grad_norm": 0.3255485670024084,
|
| 2016 |
+
"learning_rate": 5.364939252361041e-06,
|
| 2017 |
+
"loss": 0.4276,
|
| 2018 |
+
"step": 2870
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 1.592626728110599,
|
| 2022 |
+
"grad_norm": 0.3301274211586159,
|
| 2023 |
+
"learning_rate": 5.3328358946492634e-06,
|
| 2024 |
+
"loss": 0.4192,
|
| 2025 |
+
"step": 2880
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 1.5981566820276498,
|
| 2029 |
+
"grad_norm": 0.316100975989548,
|
| 2030 |
+
"learning_rate": 5.3007187486354735e-06,
|
| 2031 |
+
"loss": 0.4283,
|
| 2032 |
+
"step": 2890
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 1.6036866359447006,
|
| 2036 |
+
"grad_norm": 0.3340521867756924,
|
| 2037 |
+
"learning_rate": 5.268589144827939e-06,
|
| 2038 |
+
"loss": 0.4387,
|
| 2039 |
+
"step": 2900
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 1.6092165898617512,
|
| 2043 |
+
"grad_norm": 0.298422914640259,
|
| 2044 |
+
"learning_rate": 5.236448414251012e-06,
|
| 2045 |
+
"loss": 0.4332,
|
| 2046 |
+
"step": 2910
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 1.6147465437788018,
|
| 2050 |
+
"grad_norm": 0.3397319884556222,
|
| 2051 |
+
"learning_rate": 5.204297888389988e-06,
|
| 2052 |
+
"loss": 0.4248,
|
| 2053 |
+
"step": 2920
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 1.6202764976958526,
|
| 2057 |
+
"grad_norm": 0.30762817141809806,
|
| 2058 |
+
"learning_rate": 5.17213889913595e-06,
|
| 2059 |
+
"loss": 0.4207,
|
| 2060 |
+
"step": 2930
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 1.6258064516129034,
|
| 2064 |
+
"grad_norm": 0.30525042043948947,
|
| 2065 |
+
"learning_rate": 5.139972778730593e-06,
|
| 2066 |
+
"loss": 0.4232,
|
| 2067 |
+
"step": 2940
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 1.631336405529954,
|
| 2071 |
+
"grad_norm": 0.38997729074598075,
|
| 2072 |
+
"learning_rate": 5.107800859711032e-06,
|
| 2073 |
+
"loss": 0.4271,
|
| 2074 |
+
"step": 2950
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 1.6368663594470045,
|
| 2078 |
+
"grad_norm": 0.36592419956378963,
|
| 2079 |
+
"learning_rate": 5.075624474854599e-06,
|
| 2080 |
+
"loss": 0.4247,
|
| 2081 |
+
"step": 2960
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 1.6423963133640553,
|
| 2085 |
+
"grad_norm": 0.29950858149943177,
|
| 2086 |
+
"learning_rate": 5.0434449571236314e-06,
|
| 2087 |
+
"loss": 0.4168,
|
| 2088 |
+
"step": 2970
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 1.6479262672811061,
|
| 2092 |
+
"grad_norm": 0.32408588211542844,
|
| 2093 |
+
"learning_rate": 5.01126363961025e-06,
|
| 2094 |
+
"loss": 0.4287,
|
| 2095 |
+
"step": 2980
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 1.6534562211981567,
|
| 2099 |
+
"grad_norm": 0.3199409766199922,
|
| 2100 |
+
"learning_rate": 4.979081855481136e-06,
|
| 2101 |
+
"loss": 0.4223,
|
| 2102 |
+
"step": 2990
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 1.6589861751152073,
|
| 2106 |
+
"grad_norm": 0.3308561884228066,
|
| 2107 |
+
"learning_rate": 4.946900937922302e-06,
|
| 2108 |
+
"loss": 0.4219,
|
| 2109 |
+
"step": 3000
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 1.664516129032258,
|
| 2113 |
+
"grad_norm": 0.316626858385731,
|
| 2114 |
+
"learning_rate": 4.914722220083859e-06,
|
| 2115 |
+
"loss": 0.4331,
|
| 2116 |
+
"step": 3010
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 1.670046082949309,
|
| 2120 |
+
"grad_norm": 0.40665900945253314,
|
| 2121 |
+
"learning_rate": 4.8825470350247925e-06,
|
| 2122 |
+
"loss": 0.4246,
|
| 2123 |
+
"step": 3020
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 1.6755760368663595,
|
| 2127 |
+
"grad_norm": 0.3780339341762518,
|
| 2128 |
+
"learning_rate": 4.850376715657736e-06,
|
| 2129 |
+
"loss": 0.4295,
|
| 2130 |
+
"step": 3030
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 1.68110599078341,
|
| 2134 |
+
"grad_norm": 0.33553921665146924,
|
| 2135 |
+
"learning_rate": 4.81821259469375e-06,
|
| 2136 |
+
"loss": 0.4298,
|
| 2137 |
+
"step": 3040
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 1.6866359447004609,
|
| 2141 |
+
"grad_norm": 0.34374298733619857,
|
| 2142 |
+
"learning_rate": 4.786056004587125e-06,
|
| 2143 |
+
"loss": 0.423,
|
| 2144 |
+
"step": 3050
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 1.6921658986175117,
|
| 2148 |
+
"grad_norm": 0.3151480951742569,
|
| 2149 |
+
"learning_rate": 4.753908277480162e-06,
|
| 2150 |
+
"loss": 0.413,
|
| 2151 |
+
"step": 3060
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 1.6976958525345622,
|
| 2155 |
+
"grad_norm": 0.30161164918082994,
|
| 2156 |
+
"learning_rate": 4.721770745148003e-06,
|
| 2157 |
+
"loss": 0.4278,
|
| 2158 |
+
"step": 3070
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 1.7032258064516128,
|
| 2162 |
+
"grad_norm": 0.31750652806344676,
|
| 2163 |
+
"learning_rate": 4.689644738943451e-06,
|
| 2164 |
+
"loss": 0.4245,
|
| 2165 |
+
"step": 3080
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 1.7087557603686636,
|
| 2169 |
+
"grad_norm": 0.3494801701281207,
|
| 2170 |
+
"learning_rate": 4.657531589741822e-06,
|
| 2171 |
+
"loss": 0.4236,
|
| 2172 |
+
"step": 3090
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 1.7142857142857144,
|
| 2176 |
+
"grad_norm": 0.3449639569803028,
|
| 2177 |
+
"learning_rate": 4.6254326278858056e-06,
|
| 2178 |
+
"loss": 0.4261,
|
| 2179 |
+
"step": 3100
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 1.719815668202765,
|
| 2183 |
+
"grad_norm": 0.32166503784245665,
|
| 2184 |
+
"learning_rate": 4.593349183130359e-06,
|
| 2185 |
+
"loss": 0.4255,
|
| 2186 |
+
"step": 3110
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 1.7253456221198156,
|
| 2190 |
+
"grad_norm": 0.3318579047371131,
|
| 2191 |
+
"learning_rate": 4.561282584587612e-06,
|
| 2192 |
+
"loss": 0.4319,
|
| 2193 |
+
"step": 3120
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 1.7308755760368664,
|
| 2197 |
+
"grad_norm": 0.3194685879222433,
|
| 2198 |
+
"learning_rate": 4.529234160671814e-06,
|
| 2199 |
+
"loss": 0.4206,
|
| 2200 |
+
"step": 3130
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 1.7364055299539172,
|
| 2204 |
+
"grad_norm": 0.2942895639419189,
|
| 2205 |
+
"learning_rate": 4.497205239044305e-06,
|
| 2206 |
+
"loss": 0.4228,
|
| 2207 |
+
"step": 3140
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 1.7419354838709677,
|
| 2211 |
+
"grad_norm": 0.357982132475268,
|
| 2212 |
+
"learning_rate": 4.465197146558498e-06,
|
| 2213 |
+
"loss": 0.426,
|
| 2214 |
+
"step": 3150
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 1.7474654377880183,
|
| 2218 |
+
"grad_norm": 0.3165760814177771,
|
| 2219 |
+
"learning_rate": 4.433211209204928e-06,
|
| 2220 |
+
"loss": 0.4259,
|
| 2221 |
+
"step": 3160
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 1.7529953917050691,
|
| 2225 |
+
"grad_norm": 0.3275533345265724,
|
| 2226 |
+
"learning_rate": 4.401248752056317e-06,
|
| 2227 |
+
"loss": 0.419,
|
| 2228 |
+
"step": 3170
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 1.75852534562212,
|
| 2232 |
+
"grad_norm": 0.35208363382480495,
|
| 2233 |
+
"learning_rate": 4.369311099212676e-06,
|
| 2234 |
+
"loss": 0.4285,
|
| 2235 |
+
"step": 3180
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 1.7640552995391705,
|
| 2239 |
+
"grad_norm": 0.3322400582949709,
|
| 2240 |
+
"learning_rate": 4.337399573746457e-06,
|
| 2241 |
+
"loss": 0.4227,
|
| 2242 |
+
"step": 3190
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 1.769585253456221,
|
| 2246 |
+
"grad_norm": 0.3318593706128403,
|
| 2247 |
+
"learning_rate": 4.305515497647739e-06,
|
| 2248 |
+
"loss": 0.4169,
|
| 2249 |
+
"step": 3200
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 1.7751152073732719,
|
| 2253 |
+
"grad_norm": 0.3342118085075894,
|
| 2254 |
+
"learning_rate": 4.273660191769463e-06,
|
| 2255 |
+
"loss": 0.4156,
|
| 2256 |
+
"step": 3210
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 1.7806451612903227,
|
| 2260 |
+
"grad_norm": 0.3243982851428786,
|
| 2261 |
+
"learning_rate": 4.241834975772715e-06,
|
| 2262 |
+
"loss": 0.4296,
|
| 2263 |
+
"step": 3220
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 1.7861751152073733,
|
| 2267 |
+
"grad_norm": 0.30024745550956594,
|
| 2268 |
+
"learning_rate": 4.210041168072055e-06,
|
| 2269 |
+
"loss": 0.4155,
|
| 2270 |
+
"step": 3230
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 1.7917050691244238,
|
| 2274 |
+
"grad_norm": 0.31137799931917143,
|
| 2275 |
+
"learning_rate": 4.1782800857809025e-06,
|
| 2276 |
+
"loss": 0.423,
|
| 2277 |
+
"step": 3240
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 1.7972350230414746,
|
| 2281 |
+
"grad_norm": 0.34187401190050304,
|
| 2282 |
+
"learning_rate": 4.146553044656967e-06,
|
| 2283 |
+
"loss": 0.4222,
|
| 2284 |
+
"step": 3250
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 1.8027649769585254,
|
| 2288 |
+
"grad_norm": 0.3233685519538971,
|
| 2289 |
+
"learning_rate": 4.114861359047744e-06,
|
| 2290 |
+
"loss": 0.411,
|
| 2291 |
+
"step": 3260
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 1.808294930875576,
|
| 2295 |
+
"grad_norm": 0.31178793164096785,
|
| 2296 |
+
"learning_rate": 4.083206341836069e-06,
|
| 2297 |
+
"loss": 0.4244,
|
| 2298 |
+
"step": 3270
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 1.8138248847926266,
|
| 2302 |
+
"grad_norm": 0.31269926393343633,
|
| 2303 |
+
"learning_rate": 4.051589304385723e-06,
|
| 2304 |
+
"loss": 0.4163,
|
| 2305 |
+
"step": 3280
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 1.8193548387096774,
|
| 2309 |
+
"grad_norm": 0.3184909825619447,
|
| 2310 |
+
"learning_rate": 4.02001155648711e-06,
|
| 2311 |
+
"loss": 0.4292,
|
| 2312 |
+
"step": 3290
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 1.8248847926267282,
|
| 2316 |
+
"grad_norm": 0.3028954525575807,
|
| 2317 |
+
"learning_rate": 3.988474406302995e-06,
|
| 2318 |
+
"loss": 0.4258,
|
| 2319 |
+
"step": 3300
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 1.8304147465437788,
|
| 2323 |
+
"grad_norm": 0.3155454356334078,
|
| 2324 |
+
"learning_rate": 3.956979160314318e-06,
|
| 2325 |
+
"loss": 0.4131,
|
| 2326 |
+
"step": 3310
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 1.8359447004608294,
|
| 2330 |
+
"grad_norm": 0.28622990953618355,
|
| 2331 |
+
"learning_rate": 3.925527123266059e-06,
|
| 2332 |
+
"loss": 0.4161,
|
| 2333 |
+
"step": 3320
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 1.8414746543778802,
|
| 2337 |
+
"grad_norm": 0.2945156841734928,
|
| 2338 |
+
"learning_rate": 3.894119598113196e-06,
|
| 2339 |
+
"loss": 0.4298,
|
| 2340 |
+
"step": 3330
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 1.847004608294931,
|
| 2344 |
+
"grad_norm": 0.33440108206239455,
|
| 2345 |
+
"learning_rate": 3.862757885966726e-06,
|
| 2346 |
+
"loss": 0.4281,
|
| 2347 |
+
"step": 3340
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 1.8525345622119815,
|
| 2351 |
+
"grad_norm": 0.31936860050567883,
|
| 2352 |
+
"learning_rate": 3.83144328603976e-06,
|
| 2353 |
+
"loss": 0.4212,
|
| 2354 |
+
"step": 3350
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 1.8580645161290321,
|
| 2358 |
+
"grad_norm": 0.35312174535698115,
|
| 2359 |
+
"learning_rate": 3.800177095593706e-06,
|
| 2360 |
+
"loss": 0.4227,
|
| 2361 |
+
"step": 3360
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 1.863594470046083,
|
| 2365 |
+
"grad_norm": 0.34861457106320726,
|
| 2366 |
+
"learning_rate": 3.7689606098845264e-06,
|
| 2367 |
+
"loss": 0.431,
|
| 2368 |
+
"step": 3370
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 1.8691244239631337,
|
| 2372 |
+
"grad_norm": 0.27435811268943505,
|
| 2373 |
+
"learning_rate": 3.737795122109075e-06,
|
| 2374 |
+
"loss": 0.408,
|
| 2375 |
+
"step": 3380
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 1.8746543778801843,
|
| 2379 |
+
"grad_norm": 0.2838590192840328,
|
| 2380 |
+
"learning_rate": 3.706681923351533e-06,
|
| 2381 |
+
"loss": 0.4181,
|
| 2382 |
+
"step": 3390
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 1.8801843317972349,
|
| 2386 |
+
"grad_norm": 0.2829660341227658,
|
| 2387 |
+
"learning_rate": 3.675622302529914e-06,
|
| 2388 |
+
"loss": 0.4221,
|
| 2389 |
+
"step": 3400
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 1.8857142857142857,
|
| 2393 |
+
"grad_norm": 0.3274364986529272,
|
| 2394 |
+
"learning_rate": 3.644617546342678e-06,
|
| 2395 |
+
"loss": 0.4269,
|
| 2396 |
+
"step": 3410
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 1.8912442396313365,
|
| 2400 |
+
"grad_norm": 0.30334659787980706,
|
| 2401 |
+
"learning_rate": 3.6136689392154186e-06,
|
| 2402 |
+
"loss": 0.4218,
|
| 2403 |
+
"step": 3420
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 1.896774193548387,
|
| 2407 |
+
"grad_norm": 0.2997371229134624,
|
| 2408 |
+
"learning_rate": 3.582777763247659e-06,
|
| 2409 |
+
"loss": 0.4271,
|
| 2410 |
+
"step": 3430
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 1.9023041474654376,
|
| 2414 |
+
"grad_norm": 0.2912936491731307,
|
| 2415 |
+
"learning_rate": 3.5519452981597386e-06,
|
| 2416 |
+
"loss": 0.4261,
|
| 2417 |
+
"step": 3440
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 1.9078341013824884,
|
| 2421 |
+
"grad_norm": 0.31304519994194124,
|
| 2422 |
+
"learning_rate": 3.521172821239796e-06,
|
| 2423 |
+
"loss": 0.4237,
|
| 2424 |
+
"step": 3450
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 1.9133640552995392,
|
| 2428 |
+
"grad_norm": 0.29223645004148463,
|
| 2429 |
+
"learning_rate": 3.490461607290857e-06,
|
| 2430 |
+
"loss": 0.4206,
|
| 2431 |
+
"step": 3460
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 1.9188940092165898,
|
| 2435 |
+
"grad_norm": 0.2767982303480485,
|
| 2436 |
+
"learning_rate": 3.4598129285780214e-06,
|
| 2437 |
+
"loss": 0.4239,
|
| 2438 |
+
"step": 3470
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 1.9244239631336404,
|
| 2442 |
+
"grad_norm": 0.2857900663137054,
|
| 2443 |
+
"learning_rate": 3.4292280547757586e-06,
|
| 2444 |
+
"loss": 0.4274,
|
| 2445 |
+
"step": 3480
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 1.9299539170506912,
|
| 2449 |
+
"grad_norm": 0.30735872690033156,
|
| 2450 |
+
"learning_rate": 3.398708252915312e-06,
|
| 2451 |
+
"loss": 0.4249,
|
| 2452 |
+
"step": 3490
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 1.935483870967742,
|
| 2456 |
+
"grad_norm": 0.35018152107887573,
|
| 2457 |
+
"learning_rate": 3.368254787332206e-06,
|
| 2458 |
+
"loss": 0.4224,
|
| 2459 |
+
"step": 3500
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 1.9410138248847926,
|
| 2463 |
+
"grad_norm": 0.32130245581445155,
|
| 2464 |
+
"learning_rate": 3.337868919613869e-06,
|
| 2465 |
+
"loss": 0.4273,
|
| 2466 |
+
"step": 3510
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 1.9465437788018434,
|
| 2470 |
+
"grad_norm": 0.3399875563122416,
|
| 2471 |
+
"learning_rate": 3.3075519085473746e-06,
|
| 2472 |
+
"loss": 0.416,
|
| 2473 |
+
"step": 3520
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 1.952073732718894,
|
| 2477 |
+
"grad_norm": 0.2975964678653707,
|
| 2478 |
+
"learning_rate": 3.277305010067282e-06,
|
| 2479 |
+
"loss": 0.4161,
|
| 2480 |
+
"step": 3530
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 1.9576036866359448,
|
| 2484 |
+
"grad_norm": 0.32352875000727493,
|
| 2485 |
+
"learning_rate": 3.2471294772036287e-06,
|
| 2486 |
+
"loss": 0.4338,
|
| 2487 |
+
"step": 3540
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 1.9631336405529956,
|
| 2491 |
+
"grad_norm": 0.26327310896150496,
|
| 2492 |
+
"learning_rate": 3.2170265600299977e-06,
|
| 2493 |
+
"loss": 0.4231,
|
| 2494 |
+
"step": 3550
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 1.9686635944700461,
|
| 2498 |
+
"grad_norm": 0.30483497487890593,
|
| 2499 |
+
"learning_rate": 3.186997505611745e-06,
|
| 2500 |
+
"loss": 0.4244,
|
| 2501 |
+
"step": 3560
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 1.9741935483870967,
|
| 2505 |
+
"grad_norm": 0.33975972239987273,
|
| 2506 |
+
"learning_rate": 3.1570435579543333e-06,
|
| 2507 |
+
"loss": 0.4238,
|
| 2508 |
+
"step": 3570
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 1.9797235023041475,
|
| 2512 |
+
"grad_norm": 0.3449206346574356,
|
| 2513 |
+
"learning_rate": 3.1271659579518e-06,
|
| 2514 |
+
"loss": 0.4251,
|
| 2515 |
+
"step": 3580
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 1.9852534562211983,
|
| 2519 |
+
"grad_norm": 0.28831583716824516,
|
| 2520 |
+
"learning_rate": 3.097365943335347e-06,
|
| 2521 |
+
"loss": 0.4216,
|
| 2522 |
+
"step": 3590
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 1.9907834101382489,
|
| 2526 |
+
"grad_norm": 0.3144096706683747,
|
| 2527 |
+
"learning_rate": 3.0676447486220705e-06,
|
| 2528 |
+
"loss": 0.4285,
|
| 2529 |
+
"step": 3600
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 1.9963133640552995,
|
| 2533 |
+
"grad_norm": 0.290045183909965,
|
| 2534 |
+
"learning_rate": 3.0380036050638106e-06,
|
| 2535 |
+
"loss": 0.4197,
|
| 2536 |
+
"step": 3610
|
| 2537 |
+
},
|
| 2538 |
+
{
|
| 2539 |
+
"epoch": 2.0018433179723503,
|
| 2540 |
+
"grad_norm": 0.3238458773243826,
|
| 2541 |
+
"learning_rate": 3.008443740596153e-06,
|
| 2542 |
+
"loss": 0.4474,
|
| 2543 |
+
"step": 3620
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 2.007373271889401,
|
| 2547 |
+
"grad_norm": 0.3287019922620765,
|
| 2548 |
+
"learning_rate": 2.9789663797875614e-06,
|
| 2549 |
+
"loss": 0.4023,
|
| 2550 |
+
"step": 3630
|
| 2551 |
+
},
|
| 2552 |
+
{
|
| 2553 |
+
"epoch": 2.0129032258064514,
|
| 2554 |
+
"grad_norm": 0.29141383184538444,
|
| 2555 |
+
"learning_rate": 2.9495727437886355e-06,
|
| 2556 |
+
"loss": 0.3943,
|
| 2557 |
+
"step": 3640
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 2.0184331797235022,
|
| 2561 |
+
"grad_norm": 0.29646707994500565,
|
| 2562 |
+
"learning_rate": 2.920264050281533e-06,
|
| 2563 |
+
"loss": 0.4023,
|
| 2564 |
+
"step": 3650
|
| 2565 |
+
},
|
| 2566 |
+
{
|
| 2567 |
+
"epoch": 2.023963133640553,
|
| 2568 |
+
"grad_norm": 0.30655398704765174,
|
| 2569 |
+
"learning_rate": 2.8910415134295216e-06,
|
| 2570 |
+
"loss": 0.3968,
|
| 2571 |
+
"step": 3660
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 2.029493087557604,
|
| 2575 |
+
"grad_norm": 0.2833005227781744,
|
| 2576 |
+
"learning_rate": 2.8619063438266846e-06,
|
| 2577 |
+
"loss": 0.4101,
|
| 2578 |
+
"step": 3670
|
| 2579 |
+
},
|
| 2580 |
+
{
|
| 2581 |
+
"epoch": 2.035023041474654,
|
| 2582 |
+
"grad_norm": 0.2968009733215101,
|
| 2583 |
+
"learning_rate": 2.8328597484477582e-06,
|
| 2584 |
+
"loss": 0.3935,
|
| 2585 |
+
"step": 3680
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 2.040552995391705,
|
| 2589 |
+
"grad_norm": 0.2839483708587392,
|
| 2590 |
+
"learning_rate": 2.803902930598144e-06,
|
| 2591 |
+
"loss": 0.4034,
|
| 2592 |
+
"step": 3690
|
| 2593 |
+
},
|
| 2594 |
+
{
|
| 2595 |
+
"epoch": 2.046082949308756,
|
| 2596 |
+
"grad_norm": 0.2707519826472345,
|
| 2597 |
+
"learning_rate": 2.775037089864054e-06,
|
| 2598 |
+
"loss": 0.3941,
|
| 2599 |
+
"step": 3700
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 2.0516129032258066,
|
| 2603 |
+
"grad_norm": 0.30059219330904746,
|
| 2604 |
+
"learning_rate": 2.7462634220628146e-06,
|
| 2605 |
+
"loss": 0.3981,
|
| 2606 |
+
"step": 3710
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 2.057142857142857,
|
| 2610 |
+
"grad_norm": 0.29397070675360604,
|
| 2611 |
+
"learning_rate": 2.7175831191933275e-06,
|
| 2612 |
+
"loss": 0.4004,
|
| 2613 |
+
"step": 3720
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 2.0626728110599077,
|
| 2617 |
+
"grad_norm": 0.3320584432373214,
|
| 2618 |
+
"learning_rate": 2.688997369386698e-06,
|
| 2619 |
+
"loss": 0.3934,
|
| 2620 |
+
"step": 3730
|
| 2621 |
+
},
|
| 2622 |
+
{
|
| 2623 |
+
"epoch": 2.0682027649769585,
|
| 2624 |
+
"grad_norm": 0.31494300922463103,
|
| 2625 |
+
"learning_rate": 2.6605073568569993e-06,
|
| 2626 |
+
"loss": 0.394,
|
| 2627 |
+
"step": 3740
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 2.0737327188940093,
|
| 2631 |
+
"grad_norm": 0.29583460527636174,
|
| 2632 |
+
"learning_rate": 2.6321142618522288e-06,
|
| 2633 |
+
"loss": 0.3989,
|
| 2634 |
+
"step": 3750
|
| 2635 |
+
},
|
| 2636 |
+
{
|
| 2637 |
+
"epoch": 2.0792626728110597,
|
| 2638 |
+
"grad_norm": 0.32390817110689435,
|
| 2639 |
+
"learning_rate": 2.603819260605399e-06,
|
| 2640 |
+
"loss": 0.4019,
|
| 2641 |
+
"step": 3760
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 2.0847926267281105,
|
| 2645 |
+
"grad_norm": 0.2672110867976394,
|
| 2646 |
+
"learning_rate": 2.5756235252858288e-06,
|
| 2647 |
+
"loss": 0.4003,
|
| 2648 |
+
"step": 3770
|
| 2649 |
+
},
|
| 2650 |
+
{
|
| 2651 |
+
"epoch": 2.0903225806451613,
|
| 2652 |
+
"grad_norm": 0.3123455250583991,
|
| 2653 |
+
"learning_rate": 2.5475282239505685e-06,
|
| 2654 |
+
"loss": 0.4018,
|
| 2655 |
+
"step": 3780
|
| 2656 |
+
},
|
| 2657 |
+
{
|
| 2658 |
+
"epoch": 2.095852534562212,
|
| 2659 |
+
"grad_norm": 0.27691159250970976,
|
| 2660 |
+
"learning_rate": 2.5195345204960196e-06,
|
| 2661 |
+
"loss": 0.4008,
|
| 2662 |
+
"step": 3790
|
| 2663 |
+
},
|
| 2664 |
+
{
|
| 2665 |
+
"epoch": 2.1013824884792625,
|
| 2666 |
+
"grad_norm": 0.26123816601956984,
|
| 2667 |
+
"learning_rate": 2.4916435746097166e-06,
|
| 2668 |
+
"loss": 0.3876,
|
| 2669 |
+
"step": 3800
|
| 2670 |
+
},
|
| 2671 |
+
{
|
| 2672 |
+
"epoch": 2.1069124423963133,
|
| 2673 |
+
"grad_norm": 0.30637053965231187,
|
| 2674 |
+
"learning_rate": 2.4638565417222816e-06,
|
| 2675 |
+
"loss": 0.3982,
|
| 2676 |
+
"step": 3810
|
| 2677 |
+
},
|
| 2678 |
+
{
|
| 2679 |
+
"epoch": 2.112442396313364,
|
| 2680 |
+
"grad_norm": 0.3315750567953371,
|
| 2681 |
+
"learning_rate": 2.436174572959561e-06,
|
| 2682 |
+
"loss": 0.4073,
|
| 2683 |
+
"step": 3820
|
| 2684 |
+
},
|
| 2685 |
+
{
|
| 2686 |
+
"epoch": 2.117972350230415,
|
| 2687 |
+
"grad_norm": 0.3105020636320244,
|
| 2688 |
+
"learning_rate": 2.408598815094944e-06,
|
| 2689 |
+
"loss": 0.399,
|
| 2690 |
+
"step": 3830
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 2.1235023041474657,
|
| 2694 |
+
"grad_norm": 0.27435494573021874,
|
| 2695 |
+
"learning_rate": 2.381130410501845e-06,
|
| 2696 |
+
"loss": 0.4009,
|
| 2697 |
+
"step": 3840
|
| 2698 |
+
},
|
| 2699 |
+
{
|
| 2700 |
+
"epoch": 2.129032258064516,
|
| 2701 |
+
"grad_norm": 0.2663389329232196,
|
| 2702 |
+
"learning_rate": 2.353770497106381e-06,
|
| 2703 |
+
"loss": 0.3967,
|
| 2704 |
+
"step": 3850
|
| 2705 |
+
},
|
| 2706 |
+
{
|
| 2707 |
+
"epoch": 2.134562211981567,
|
| 2708 |
+
"grad_norm": 0.3194906899085194,
|
| 2709 |
+
"learning_rate": 2.3265202083402376e-06,
|
| 2710 |
+
"loss": 0.4001,
|
| 2711 |
+
"step": 3860
|
| 2712 |
+
},
|
| 2713 |
+
{
|
| 2714 |
+
"epoch": 2.1400921658986176,
|
| 2715 |
+
"grad_norm": 0.31197437534194744,
|
| 2716 |
+
"learning_rate": 2.299380673093712e-06,
|
| 2717 |
+
"loss": 0.4033,
|
| 2718 |
+
"step": 3870
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 2.145622119815668,
|
| 2722 |
+
"grad_norm": 0.29924705453864847,
|
| 2723 |
+
"learning_rate": 2.272353015668942e-06,
|
| 2724 |
+
"loss": 0.3994,
|
| 2725 |
+
"step": 3880
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 2.1511520737327188,
|
| 2729 |
+
"grad_norm": 0.29115026537537425,
|
| 2730 |
+
"learning_rate": 2.2454383557333358e-06,
|
| 2731 |
+
"loss": 0.4014,
|
| 2732 |
+
"step": 3890
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 2.1566820276497696,
|
| 2736 |
+
"grad_norm": 0.2834889760546468,
|
| 2737 |
+
"learning_rate": 2.218637808273184e-06,
|
| 2738 |
+
"loss": 0.3998,
|
| 2739 |
+
"step": 3900
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 2.1622119815668204,
|
| 2743 |
+
"grad_norm": 0.2910305450411384,
|
| 2744 |
+
"learning_rate": 2.1919524835474713e-06,
|
| 2745 |
+
"loss": 0.405,
|
| 2746 |
+
"step": 3910
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 2.167741935483871,
|
| 2750 |
+
"grad_norm": 0.289932930612974,
|
| 2751 |
+
"learning_rate": 2.1653834870418807e-06,
|
| 2752 |
+
"loss": 0.3896,
|
| 2753 |
+
"step": 3920
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 2.1732718894009215,
|
| 2757 |
+
"grad_norm": 0.2722298839273463,
|
| 2758 |
+
"learning_rate": 2.1389319194230017e-06,
|
| 2759 |
+
"loss": 0.4003,
|
| 2760 |
+
"step": 3930
|
| 2761 |
+
},
|
| 2762 |
+
{
|
| 2763 |
+
"epoch": 2.1788018433179723,
|
| 2764 |
+
"grad_norm": 0.28486359542042644,
|
| 2765 |
+
"learning_rate": 2.1125988764927225e-06,
|
| 2766 |
+
"loss": 0.4013,
|
| 2767 |
+
"step": 3940
|
| 2768 |
+
},
|
| 2769 |
+
{
|
| 2770 |
+
"epoch": 2.184331797235023,
|
| 2771 |
+
"grad_norm": 0.29750089176475963,
|
| 2772 |
+
"learning_rate": 2.0863854491428454e-06,
|
| 2773 |
+
"loss": 0.3989,
|
| 2774 |
+
"step": 3950
|
| 2775 |
+
},
|
| 2776 |
+
{
|
| 2777 |
+
"epoch": 2.189861751152074,
|
| 2778 |
+
"grad_norm": 0.2766502298353407,
|
| 2779 |
+
"learning_rate": 2.0602927233098908e-06,
|
| 2780 |
+
"loss": 0.3921,
|
| 2781 |
+
"step": 3960
|
| 2782 |
+
},
|
| 2783 |
+
{
|
| 2784 |
+
"epoch": 2.1953917050691243,
|
| 2785 |
+
"grad_norm": 0.2789326319161608,
|
| 2786 |
+
"learning_rate": 2.034321779930109e-06,
|
| 2787 |
+
"loss": 0.4001,
|
| 2788 |
+
"step": 3970
|
| 2789 |
+
},
|
| 2790 |
+
{
|
| 2791 |
+
"epoch": 2.200921658986175,
|
| 2792 |
+
"grad_norm": 0.3371618622489858,
|
| 2793 |
+
"learning_rate": 2.0084736948947027e-06,
|
| 2794 |
+
"loss": 0.4049,
|
| 2795 |
+
"step": 3980
|
| 2796 |
+
},
|
| 2797 |
+
{
|
| 2798 |
+
"epoch": 2.206451612903226,
|
| 2799 |
+
"grad_norm": 0.2783901912695157,
|
| 2800 |
+
"learning_rate": 1.982749539005254e-06,
|
| 2801 |
+
"loss": 0.4041,
|
| 2802 |
+
"step": 3990
|
| 2803 |
+
},
|
| 2804 |
+
{
|
| 2805 |
+
"epoch": 2.2119815668202767,
|
| 2806 |
+
"grad_norm": 0.279176756791974,
|
| 2807 |
+
"learning_rate": 1.9571503779293683e-06,
|
| 2808 |
+
"loss": 0.3978,
|
| 2809 |
+
"step": 4000
|
| 2810 |
+
},
|
| 2811 |
+
{
|
| 2812 |
+
"epoch": 2.217511520737327,
|
| 2813 |
+
"grad_norm": 0.30608460679313365,
|
| 2814 |
+
"learning_rate": 1.93167727215652e-06,
|
| 2815 |
+
"loss": 0.406,
|
| 2816 |
+
"step": 4010
|
| 2817 |
+
},
|
| 2818 |
+
{
|
| 2819 |
+
"epoch": 2.223041474654378,
|
| 2820 |
+
"grad_norm": 0.3151983208092032,
|
| 2821 |
+
"learning_rate": 1.9063312769541348e-06,
|
| 2822 |
+
"loss": 0.3956,
|
| 2823 |
+
"step": 4020
|
| 2824 |
+
},
|
| 2825 |
+
{
|
| 2826 |
+
"epoch": 2.2285714285714286,
|
| 2827 |
+
"grad_norm": 0.3005770395178785,
|
| 2828 |
+
"learning_rate": 1.8811134423238513e-06,
|
| 2829 |
+
"loss": 0.3966,
|
| 2830 |
+
"step": 4030
|
| 2831 |
+
},
|
| 2832 |
+
{
|
| 2833 |
+
"epoch": 2.2341013824884794,
|
| 2834 |
+
"grad_norm": 0.2940499233107073,
|
| 2835 |
+
"learning_rate": 1.8560248129580422e-06,
|
| 2836 |
+
"loss": 0.4043,
|
| 2837 |
+
"step": 4040
|
| 2838 |
+
},
|
| 2839 |
+
{
|
| 2840 |
+
"epoch": 2.23963133640553,
|
| 2841 |
+
"grad_norm": 0.28429612401283494,
|
| 2842 |
+
"learning_rate": 1.8310664281965268e-06,
|
| 2843 |
+
"loss": 0.4076,
|
| 2844 |
+
"step": 4050
|
| 2845 |
+
},
|
| 2846 |
+
{
|
| 2847 |
+
"epoch": 2.2451612903225806,
|
| 2848 |
+
"grad_norm": 0.3064049873744565,
|
| 2849 |
+
"learning_rate": 1.8062393219835173e-06,
|
| 2850 |
+
"loss": 0.3972,
|
| 2851 |
+
"step": 4060
|
| 2852 |
+
},
|
| 2853 |
+
{
|
| 2854 |
+
"epoch": 2.2506912442396314,
|
| 2855 |
+
"grad_norm": 0.29946204785644764,
|
| 2856 |
+
"learning_rate": 1.7815445228247851e-06,
|
| 2857 |
+
"loss": 0.3945,
|
| 2858 |
+
"step": 4070
|
| 2859 |
+
},
|
| 2860 |
+
{
|
| 2861 |
+
"epoch": 2.256221198156682,
|
| 2862 |
+
"grad_norm": 0.2715437304149103,
|
| 2863 |
+
"learning_rate": 1.7569830537450533e-06,
|
| 2864 |
+
"loss": 0.4033,
|
| 2865 |
+
"step": 4080
|
| 2866 |
+
},
|
| 2867 |
+
{
|
| 2868 |
+
"epoch": 2.2617511520737326,
|
| 2869 |
+
"grad_norm": 0.2854830351871705,
|
| 2870 |
+
"learning_rate": 1.732555932245616e-06,
|
| 2871 |
+
"loss": 0.3955,
|
| 2872 |
+
"step": 4090
|
| 2873 |
+
},
|
| 2874 |
+
{
|
| 2875 |
+
"epoch": 2.2672811059907834,
|
| 2876 |
+
"grad_norm": 0.3147639419603036,
|
| 2877 |
+
"learning_rate": 1.7082641702621856e-06,
|
| 2878 |
+
"loss": 0.3953,
|
| 2879 |
+
"step": 4100
|
| 2880 |
+
},
|
| 2881 |
+
{
|
| 2882 |
+
"epoch": 2.272811059907834,
|
| 2883 |
+
"grad_norm": 0.27518159279482673,
|
| 2884 |
+
"learning_rate": 1.6841087741229745e-06,
|
| 2885 |
+
"loss": 0.4021,
|
| 2886 |
+
"step": 4110
|
| 2887 |
+
},
|
| 2888 |
+
{
|
| 2889 |
+
"epoch": 2.278341013824885,
|
| 2890 |
+
"grad_norm": 0.3039597096572996,
|
| 2891 |
+
"learning_rate": 1.660090744507003e-06,
|
| 2892 |
+
"loss": 0.4013,
|
| 2893 |
+
"step": 4120
|
| 2894 |
+
},
|
| 2895 |
+
{
|
| 2896 |
+
"epoch": 2.2838709677419353,
|
| 2897 |
+
"grad_norm": 0.2998615031450226,
|
| 2898 |
+
"learning_rate": 1.6362110764026473e-06,
|
| 2899 |
+
"loss": 0.4112,
|
| 2900 |
+
"step": 4130
|
| 2901 |
+
},
|
| 2902 |
+
{
|
| 2903 |
+
"epoch": 2.289400921658986,
|
| 2904 |
+
"grad_norm": 0.3022483293545665,
|
| 2905 |
+
"learning_rate": 1.6124707590664168e-06,
|
| 2906 |
+
"loss": 0.3993,
|
| 2907 |
+
"step": 4140
|
| 2908 |
+
},
|
| 2909 |
+
{
|
| 2910 |
+
"epoch": 2.294930875576037,
|
| 2911 |
+
"grad_norm": 0.2724443752633973,
|
| 2912 |
+
"learning_rate": 1.5888707759819766e-06,
|
| 2913 |
+
"loss": 0.4078,
|
| 2914 |
+
"step": 4150
|
| 2915 |
+
},
|
| 2916 |
+
{
|
| 2917 |
+
"epoch": 2.3004608294930877,
|
| 2918 |
+
"grad_norm": 0.30699585205563196,
|
| 2919 |
+
"learning_rate": 1.5654121048194016e-06,
|
| 2920 |
+
"loss": 0.3966,
|
| 2921 |
+
"step": 4160
|
| 2922 |
+
},
|
| 2923 |
+
{
|
| 2924 |
+
"epoch": 2.305990783410138,
|
| 2925 |
+
"grad_norm": 0.2774026863139645,
|
| 2926 |
+
"learning_rate": 1.5420957173946772e-06,
|
| 2927 |
+
"loss": 0.3931,
|
| 2928 |
+
"step": 4170
|
| 2929 |
+
},
|
| 2930 |
+
{
|
| 2931 |
+
"epoch": 2.311520737327189,
|
| 2932 |
+
"grad_norm": 0.30520288048797833,
|
| 2933 |
+
"learning_rate": 1.5189225796294383e-06,
|
| 2934 |
+
"loss": 0.3963,
|
| 2935 |
+
"step": 4180
|
| 2936 |
+
},
|
| 2937 |
+
{
|
| 2938 |
+
"epoch": 2.3170506912442397,
|
| 2939 |
+
"grad_norm": 0.25456512857000035,
|
| 2940 |
+
"learning_rate": 1.4958936515109551e-06,
|
| 2941 |
+
"loss": 0.3937,
|
| 2942 |
+
"step": 4190
|
| 2943 |
+
},
|
| 2944 |
+
{
|
| 2945 |
+
"epoch": 2.3225806451612905,
|
| 2946 |
+
"grad_norm": 0.26955539407811574,
|
| 2947 |
+
"learning_rate": 1.4730098870523652e-06,
|
| 2948 |
+
"loss": 0.4004,
|
| 2949 |
+
"step": 4200
|
| 2950 |
+
},
|
| 2951 |
+
{
|
| 2952 |
+
"epoch": 2.328110599078341,
|
| 2953 |
+
"grad_norm": 0.2793395228272683,
|
| 2954 |
+
"learning_rate": 1.450272234253149e-06,
|
| 2955 |
+
"loss": 0.4014,
|
| 2956 |
+
"step": 4210
|
| 2957 |
+
},
|
| 2958 |
+
{
|
| 2959 |
+
"epoch": 2.3336405529953916,
|
| 2960 |
+
"grad_norm": 0.2670008731741953,
|
| 2961 |
+
"learning_rate": 1.427681635059861e-06,
|
| 2962 |
+
"loss": 0.399,
|
| 2963 |
+
"step": 4220
|
| 2964 |
+
},
|
| 2965 |
+
{
|
| 2966 |
+
"epoch": 2.3391705069124424,
|
| 2967 |
+
"grad_norm": 0.26366634919045073,
|
| 2968 |
+
"learning_rate": 1.4052390253271037e-06,
|
| 2969 |
+
"loss": 0.3967,
|
| 2970 |
+
"step": 4230
|
| 2971 |
+
},
|
| 2972 |
+
{
|
| 2973 |
+
"epoch": 2.3447004608294932,
|
| 2974 |
+
"grad_norm": 0.2736550342611439,
|
| 2975 |
+
"learning_rate": 1.3829453347787626e-06,
|
| 2976 |
+
"loss": 0.4053,
|
| 2977 |
+
"step": 4240
|
| 2978 |
+
},
|
| 2979 |
+
{
|
| 2980 |
+
"epoch": 2.3502304147465436,
|
| 2981 |
+
"grad_norm": 0.2658041185832838,
|
| 2982 |
+
"learning_rate": 1.3608014869694869e-06,
|
| 2983 |
+
"loss": 0.3965,
|
| 2984 |
+
"step": 4250
|
| 2985 |
+
},
|
| 2986 |
+
{
|
| 2987 |
+
"epoch": 2.3557603686635944,
|
| 2988 |
+
"grad_norm": 0.2663003739913603,
|
| 2989 |
+
"learning_rate": 1.3388083992464335e-06,
|
| 2990 |
+
"loss": 0.408,
|
| 2991 |
+
"step": 4260
|
| 2992 |
+
},
|
| 2993 |
+
{
|
| 2994 |
+
"epoch": 2.361290322580645,
|
| 2995 |
+
"grad_norm": 0.3046466052962007,
|
| 2996 |
+
"learning_rate": 1.3169669827112603e-06,
|
| 2997 |
+
"loss": 0.4036,
|
| 2998 |
+
"step": 4270
|
| 2999 |
+
},
|
| 3000 |
+
{
|
| 3001 |
+
"epoch": 2.366820276497696,
|
| 3002 |
+
"grad_norm": 0.2895481931800935,
|
| 3003 |
+
"learning_rate": 1.2952781421823846e-06,
|
| 3004 |
+
"loss": 0.3936,
|
| 3005 |
+
"step": 4280
|
| 3006 |
+
},
|
| 3007 |
+
{
|
| 3008 |
+
"epoch": 2.3723502304147464,
|
| 3009 |
+
"grad_norm": 0.2677071356544069,
|
| 3010 |
+
"learning_rate": 1.2737427761575006e-06,
|
| 3011 |
+
"loss": 0.4006,
|
| 3012 |
+
"step": 4290
|
| 3013 |
+
},
|
| 3014 |
+
{
|
| 3015 |
+
"epoch": 2.377880184331797,
|
| 3016 |
+
"grad_norm": 0.29306704953880125,
|
| 3017 |
+
"learning_rate": 1.2523617767763535e-06,
|
| 3018 |
+
"loss": 0.3994,
|
| 3019 |
+
"step": 4300
|
| 3020 |
+
},
|
| 3021 |
+
{
|
| 3022 |
+
"epoch": 2.383410138248848,
|
| 3023 |
+
"grad_norm": 0.2739530738988769,
|
| 3024 |
+
"learning_rate": 1.2311360297837849e-06,
|
| 3025 |
+
"loss": 0.4001,
|
| 3026 |
+
"step": 4310
|
| 3027 |
+
},
|
| 3028 |
+
{
|
| 3029 |
+
"epoch": 2.3889400921658988,
|
| 3030 |
+
"grad_norm": 0.27681408852313116,
|
| 3031 |
+
"learning_rate": 1.210066414493039e-06,
|
| 3032 |
+
"loss": 0.3924,
|
| 3033 |
+
"step": 4320
|
| 3034 |
+
},
|
| 3035 |
+
{
|
| 3036 |
+
"epoch": 2.394470046082949,
|
| 3037 |
+
"grad_norm": 0.30545245080294625,
|
| 3038 |
+
"learning_rate": 1.1891538037493322e-06,
|
| 3039 |
+
"loss": 0.4044,
|
| 3040 |
+
"step": 4330
|
| 3041 |
+
},
|
| 3042 |
+
{
|
| 3043 |
+
"epoch": 2.4,
|
| 3044 |
+
"grad_norm": 0.26864664635574714,
|
| 3045 |
+
"learning_rate": 1.1683990638936981e-06,
|
| 3046 |
+
"loss": 0.4017,
|
| 3047 |
+
"step": 4340
|
| 3048 |
+
},
|
| 3049 |
+
{
|
| 3050 |
+
"epoch": 2.4055299539170507,
|
| 3051 |
+
"grad_norm": 0.2944152586026279,
|
| 3052 |
+
"learning_rate": 1.147803054727095e-06,
|
| 3053 |
+
"loss": 0.401,
|
| 3054 |
+
"step": 4350
|
| 3055 |
+
},
|
| 3056 |
+
{
|
| 3057 |
+
"epoch": 2.4110599078341015,
|
| 3058 |
+
"grad_norm": 0.282595000728746,
|
| 3059 |
+
"learning_rate": 1.1273666294747886e-06,
|
| 3060 |
+
"loss": 0.4003,
|
| 3061 |
+
"step": 4360
|
| 3062 |
+
},
|
| 3063 |
+
{
|
| 3064 |
+
"epoch": 2.4165898617511523,
|
| 3065 |
+
"grad_norm": 0.28429008222935853,
|
| 3066 |
+
"learning_rate": 1.1070906347510051e-06,
|
| 3067 |
+
"loss": 0.3955,
|
| 3068 |
+
"step": 4370
|
| 3069 |
+
},
|
| 3070 |
+
{
|
| 3071 |
+
"epoch": 2.4221198156682027,
|
| 3072 |
+
"grad_norm": 0.2831830240980828,
|
| 3073 |
+
"learning_rate": 1.0869759105238592e-06,
|
| 3074 |
+
"loss": 0.3981,
|
| 3075 |
+
"step": 4380
|
| 3076 |
+
},
|
| 3077 |
+
{
|
| 3078 |
+
"epoch": 2.4276497695852535,
|
| 3079 |
+
"grad_norm": 0.30047729151565855,
|
| 3080 |
+
"learning_rate": 1.0670232900805561e-06,
|
| 3081 |
+
"loss": 0.3979,
|
| 3082 |
+
"step": 4390
|
| 3083 |
+
},
|
| 3084 |
+
{
|
| 3085 |
+
"epoch": 2.4331797235023043,
|
| 3086 |
+
"grad_norm": 0.27151153552568635,
|
| 3087 |
+
"learning_rate": 1.0472335999928712e-06,
|
| 3088 |
+
"loss": 0.398,
|
| 3089 |
+
"step": 4400
|
| 3090 |
+
},
|
| 3091 |
+
{
|
| 3092 |
+
"epoch": 2.4387096774193546,
|
| 3093 |
+
"grad_norm": 0.26079113997988657,
|
| 3094 |
+
"learning_rate": 1.0276076600829094e-06,
|
| 3095 |
+
"loss": 0.3928,
|
| 3096 |
+
"step": 4410
|
| 3097 |
+
},
|
| 3098 |
+
{
|
| 3099 |
+
"epoch": 2.4442396313364054,
|
| 3100 |
+
"grad_norm": 0.2943190568488448,
|
| 3101 |
+
"learning_rate": 1.008146283389142e-06,
|
| 3102 |
+
"loss": 0.4051,
|
| 3103 |
+
"step": 4420
|
| 3104 |
+
},
|
| 3105 |
+
{
|
| 3106 |
+
"epoch": 2.4497695852534562,
|
| 3107 |
+
"grad_norm": 0.29471175081496465,
|
| 3108 |
+
"learning_rate": 9.888502761327235e-07,
|
| 3109 |
+
"loss": 0.4016,
|
| 3110 |
+
"step": 4430
|
| 3111 |
+
},
|
| 3112 |
+
{
|
| 3113 |
+
"epoch": 2.455299539170507,
|
| 3114 |
+
"grad_norm": 0.2828161001369082,
|
| 3115 |
+
"learning_rate": 9.697204376840936e-07,
|
| 3116 |
+
"loss": 0.3955,
|
| 3117 |
+
"step": 4440
|
| 3118 |
+
},
|
| 3119 |
+
{
|
| 3120 |
+
"epoch": 2.460829493087558,
|
| 3121 |
+
"grad_norm": 0.2700457496469629,
|
| 3122 |
+
"learning_rate": 9.50757560529863e-07,
|
| 3123 |
+
"loss": 0.3999,
|
| 3124 |
+
"step": 4450
|
| 3125 |
+
},
|
| 3126 |
+
{
|
| 3127 |
+
"epoch": 2.466359447004608,
|
| 3128 |
+
"grad_norm": 0.28527113567956547,
|
| 3129 |
+
"learning_rate": 9.319624302399827e-07,
|
| 3130 |
+
"loss": 0.3976,
|
| 3131 |
+
"step": 4460
|
| 3132 |
+
},
|
| 3133 |
+
{
|
| 3134 |
+
"epoch": 2.471889400921659,
|
| 3135 |
+
"grad_norm": 0.2913598279022557,
|
| 3136 |
+
"learning_rate": 9.133358254351982e-07,
|
| 3137 |
+
"loss": 0.3959,
|
| 3138 |
+
"step": 4470
|
| 3139 |
+
},
|
| 3140 |
+
{
|
| 3141 |
+
"epoch": 2.47741935483871,
|
| 3142 |
+
"grad_norm": 0.2528128242967444,
|
| 3143 |
+
"learning_rate": 8.948785177547975e-07,
|
| 3144 |
+
"loss": 0.3999,
|
| 3145 |
+
"step": 4480
|
| 3146 |
+
},
|
| 3147 |
+
{
|
| 3148 |
+
"epoch": 2.48294930875576,
|
| 3149 |
+
"grad_norm": 0.28379973900510885,
|
| 3150 |
+
"learning_rate": 8.765912718246423e-07,
|
| 3151 |
+
"loss": 0.3943,
|
| 3152 |
+
"step": 4490
|
| 3153 |
+
},
|
| 3154 |
+
{
|
| 3155 |
+
"epoch": 2.488479262672811,
|
| 3156 |
+
"grad_norm": 0.3067123055839093,
|
| 3157 |
+
"learning_rate": 8.584748452254888e-07,
|
| 3158 |
+
"loss": 0.3979,
|
| 3159 |
+
"step": 4500
|
| 3160 |
+
},
|
| 3161 |
+
{
|
| 3162 |
+
"epoch": 2.4940092165898617,
|
| 3163 |
+
"grad_norm": 0.2753166288210943,
|
| 3164 |
+
"learning_rate": 8.405299884616142e-07,
|
| 3165 |
+
"loss": 0.3942,
|
| 3166 |
+
"step": 4510
|
| 3167 |
+
},
|
| 3168 |
+
{
|
| 3169 |
+
"epoch": 2.4995391705069125,
|
| 3170 |
+
"grad_norm": 0.28727455911235195,
|
| 3171 |
+
"learning_rate": 8.227574449297137e-07,
|
| 3172 |
+
"loss": 0.4003,
|
| 3173 |
+
"step": 4520
|
| 3174 |
+
},
|
| 3175 |
+
{
|
| 3176 |
+
"epoch": 2.5050691244239633,
|
| 3177 |
+
"grad_norm": 0.2743598195044324,
|
| 3178 |
+
"learning_rate": 8.051579508881107e-07,
|
| 3179 |
+
"loss": 0.3952,
|
| 3180 |
+
"step": 4530
|
| 3181 |
+
},
|
| 3182 |
+
{
|
| 3183 |
+
"epoch": 2.5105990783410137,
|
| 3184 |
+
"grad_norm": 0.2693576075557049,
|
| 3185 |
+
"learning_rate": 7.877322354262545e-07,
|
| 3186 |
+
"loss": 0.4033,
|
| 3187 |
+
"step": 4540
|
| 3188 |
+
},
|
| 3189 |
+
{
|
| 3190 |
+
"epoch": 2.5161290322580645,
|
| 3191 |
+
"grad_norm": 0.2896358229000151,
|
| 3192 |
+
"learning_rate": 7.704810204345154e-07,
|
| 3193 |
+
"loss": 0.4005,
|
| 3194 |
+
"step": 4550
|
| 3195 |
+
},
|
| 3196 |
+
{
|
| 3197 |
+
"epoch": 2.5216589861751153,
|
| 3198 |
+
"grad_norm": 0.28471183419181173,
|
| 3199 |
+
"learning_rate": 7.534050205742827e-07,
|
| 3200 |
+
"loss": 0.3914,
|
| 3201 |
+
"step": 4560
|
| 3202 |
+
},
|
| 3203 |
+
{
|
| 3204 |
+
"epoch": 2.5271889400921657,
|
| 3205 |
+
"grad_norm": 0.2594303056396339,
|
| 3206 |
+
"learning_rate": 7.365049432483529e-07,
|
| 3207 |
+
"loss": 0.4032,
|
| 3208 |
+
"step": 4570
|
| 3209 |
+
},
|
| 3210 |
+
{
|
| 3211 |
+
"epoch": 2.5327188940092165,
|
| 3212 |
+
"grad_norm": 0.29975502440359814,
|
| 3213 |
+
"learning_rate": 7.19781488571632e-07,
|
| 3214 |
+
"loss": 0.4039,
|
| 3215 |
+
"step": 4580
|
| 3216 |
+
},
|
| 3217 |
+
{
|
| 3218 |
+
"epoch": 2.5382488479262673,
|
| 3219 |
+
"grad_norm": 0.272206139015925,
|
| 3220 |
+
"learning_rate": 7.032353493421213e-07,
|
| 3221 |
+
"loss": 0.403,
|
| 3222 |
+
"step": 4590
|
| 3223 |
+
},
|
| 3224 |
+
{
|
| 3225 |
+
"epoch": 2.543778801843318,
|
| 3226 |
+
"grad_norm": 0.27442194973354395,
|
| 3227 |
+
"learning_rate": 6.868672110122271e-07,
|
| 3228 |
+
"loss": 0.4,
|
| 3229 |
+
"step": 4600
|
| 3230 |
+
},
|
| 3231 |
+
{
|
| 3232 |
+
"epoch": 2.549308755760369,
|
| 3233 |
+
"grad_norm": 0.26622819466668635,
|
| 3234 |
+
"learning_rate": 6.706777516603636e-07,
|
| 3235 |
+
"loss": 0.4064,
|
| 3236 |
+
"step": 4610
|
| 3237 |
+
},
|
| 3238 |
+
{
|
| 3239 |
+
"epoch": 2.554838709677419,
|
| 3240 |
+
"grad_norm": 0.2921603411199283,
|
| 3241 |
+
"learning_rate": 6.546676419628545e-07,
|
| 3242 |
+
"loss": 0.398,
|
| 3243 |
+
"step": 4620
|
| 3244 |
+
},
|
| 3245 |
+
{
|
| 3246 |
+
"epoch": 2.56036866359447,
|
| 3247 |
+
"grad_norm": 0.2634896902237433,
|
| 3248 |
+
"learning_rate": 6.388375451661578e-07,
|
| 3249 |
+
"loss": 0.3958,
|
| 3250 |
+
"step": 4630
|
| 3251 |
+
},
|
| 3252 |
+
{
|
| 3253 |
+
"epoch": 2.565898617511521,
|
| 3254 |
+
"grad_norm": 0.2578581966184642,
|
| 3255 |
+
"learning_rate": 6.231881170593828e-07,
|
| 3256 |
+
"loss": 0.3983,
|
| 3257 |
+
"step": 4640
|
| 3258 |
+
},
|
| 3259 |
+
{
|
| 3260 |
+
"epoch": 2.571428571428571,
|
| 3261 |
+
"grad_norm": 0.2816419136865501,
|
| 3262 |
+
"learning_rate": 6.077200059471289e-07,
|
| 3263 |
+
"loss": 0.3993,
|
| 3264 |
+
"step": 4650
|
| 3265 |
+
},
|
| 3266 |
+
{
|
| 3267 |
+
"epoch": 2.576958525345622,
|
| 3268 |
+
"grad_norm": 0.25487527822128436,
|
| 3269 |
+
"learning_rate": 5.924338526226259e-07,
|
| 3270 |
+
"loss": 0.3856,
|
| 3271 |
+
"step": 4660
|
| 3272 |
+
},
|
| 3273 |
+
{
|
| 3274 |
+
"epoch": 2.5824884792626728,
|
| 3275 |
+
"grad_norm": 0.25615420713688475,
|
| 3276 |
+
"learning_rate": 5.773302903411848e-07,
|
| 3277 |
+
"loss": 0.3943,
|
| 3278 |
+
"step": 4670
|
| 3279 |
+
},
|
| 3280 |
+
{
|
| 3281 |
+
"epoch": 2.5880184331797236,
|
| 3282 |
+
"grad_norm": 0.25869788749142564,
|
| 3283 |
+
"learning_rate": 5.624099447939696e-07,
|
| 3284 |
+
"loss": 0.3997,
|
| 3285 |
+
"step": 4680
|
| 3286 |
+
},
|
| 3287 |
+
{
|
| 3288 |
+
"epoch": 2.5935483870967744,
|
| 3289 |
+
"grad_norm": 0.27630938101238434,
|
| 3290 |
+
"learning_rate": 5.476734340820738e-07,
|
| 3291 |
+
"loss": 0.3914,
|
| 3292 |
+
"step": 4690
|
| 3293 |
+
},
|
| 3294 |
+
{
|
| 3295 |
+
"epoch": 2.5990783410138247,
|
| 3296 |
+
"grad_norm": 0.29080902856797114,
|
| 3297 |
+
"learning_rate": 5.331213686909159e-07,
|
| 3298 |
+
"loss": 0.4052,
|
| 3299 |
+
"step": 4700
|
| 3300 |
+
},
|
| 3301 |
+
{
|
| 3302 |
+
"epoch": 2.6046082949308755,
|
| 3303 |
+
"grad_norm": 0.27150428918656966,
|
| 3304 |
+
"learning_rate": 5.187543514649479e-07,
|
| 3305 |
+
"loss": 0.3987,
|
| 3306 |
+
"step": 4710
|
| 3307 |
+
},
|
| 3308 |
+
{
|
| 3309 |
+
"epoch": 2.6101382488479263,
|
| 3310 |
+
"grad_norm": 0.2814113138950482,
|
| 3311 |
+
"learning_rate": 5.045729775826818e-07,
|
| 3312 |
+
"loss": 0.4,
|
| 3313 |
+
"step": 4720
|
| 3314 |
+
},
|
| 3315 |
+
{
|
| 3316 |
+
"epoch": 2.6156682027649767,
|
| 3317 |
+
"grad_norm": 0.26628699037750947,
|
| 3318 |
+
"learning_rate": 4.905778345320339e-07,
|
| 3319 |
+
"loss": 0.4046,
|
| 3320 |
+
"step": 4730
|
| 3321 |
+
},
|
| 3322 |
+
{
|
| 3323 |
+
"epoch": 2.6211981566820275,
|
| 3324 |
+
"grad_norm": 0.2679284474349017,
|
| 3325 |
+
"learning_rate": 4.767695020859847e-07,
|
| 3326 |
+
"loss": 0.3989,
|
| 3327 |
+
"step": 4740
|
| 3328 |
+
},
|
| 3329 |
+
{
|
| 3330 |
+
"epoch": 2.6267281105990783,
|
| 3331 |
+
"grad_norm": 0.304861228416287,
|
| 3332 |
+
"learning_rate": 4.6314855227856505e-07,
|
| 3333 |
+
"loss": 0.3966,
|
| 3334 |
+
"step": 4750
|
| 3335 |
+
},
|
| 3336 |
+
{
|
| 3337 |
+
"epoch": 2.632258064516129,
|
| 3338 |
+
"grad_norm": 0.28378340208874464,
|
| 3339 |
+
"learning_rate": 4.497155493811539e-07,
|
| 3340 |
+
"loss": 0.3923,
|
| 3341 |
+
"step": 4760
|
| 3342 |
+
},
|
| 3343 |
+
{
|
| 3344 |
+
"epoch": 2.63778801843318,
|
| 3345 |
+
"grad_norm": 0.2720375532229136,
|
| 3346 |
+
"learning_rate": 4.3647104987910636e-07,
|
| 3347 |
+
"loss": 0.3983,
|
| 3348 |
+
"step": 4770
|
| 3349 |
+
},
|
| 3350 |
+
{
|
| 3351 |
+
"epoch": 2.6433179723502302,
|
| 3352 |
+
"grad_norm": 0.2648120126986214,
|
| 3353 |
+
"learning_rate": 4.2341560244869797e-07,
|
| 3354 |
+
"loss": 0.3925,
|
| 3355 |
+
"step": 4780
|
| 3356 |
+
},
|
| 3357 |
+
{
|
| 3358 |
+
"epoch": 2.648847926267281,
|
| 3359 |
+
"grad_norm": 0.30311062145568735,
|
| 3360 |
+
"learning_rate": 4.1054974793439504e-07,
|
| 3361 |
+
"loss": 0.3986,
|
| 3362 |
+
"step": 4790
|
| 3363 |
+
},
|
| 3364 |
+
{
|
| 3365 |
+
"epoch": 2.654377880184332,
|
| 3366 |
+
"grad_norm": 0.26568936508620244,
|
| 3367 |
+
"learning_rate": 3.978740193264524e-07,
|
| 3368 |
+
"loss": 0.3921,
|
| 3369 |
+
"step": 4800
|
| 3370 |
+
},
|
| 3371 |
+
{
|
| 3372 |
+
"epoch": 2.6599078341013827,
|
| 3373 |
+
"grad_norm": 0.2710800781363938,
|
| 3374 |
+
"learning_rate": 3.853889417388279e-07,
|
| 3375 |
+
"loss": 0.3984,
|
| 3376 |
+
"step": 4810
|
| 3377 |
+
},
|
| 3378 |
+
{
|
| 3379 |
+
"epoch": 2.6654377880184335,
|
| 3380 |
+
"grad_norm": 0.2676349044854644,
|
| 3381 |
+
"learning_rate": 3.730950323874322e-07,
|
| 3382 |
+
"loss": 0.3977,
|
| 3383 |
+
"step": 4820
|
| 3384 |
+
},
|
| 3385 |
+
{
|
| 3386 |
+
"epoch": 2.670967741935484,
|
| 3387 |
+
"grad_norm": 0.28364404186426295,
|
| 3388 |
+
"learning_rate": 3.6099280056870136e-07,
|
| 3389 |
+
"loss": 0.4008,
|
| 3390 |
+
"step": 4830
|
| 3391 |
+
},
|
| 3392 |
+
{
|
| 3393 |
+
"epoch": 2.6764976958525346,
|
| 3394 |
+
"grad_norm": 0.27479432043235197,
|
| 3395 |
+
"learning_rate": 3.490827476385006e-07,
|
| 3396 |
+
"loss": 0.4006,
|
| 3397 |
+
"step": 4840
|
| 3398 |
+
},
|
| 3399 |
+
{
|
| 3400 |
+
"epoch": 2.6820276497695854,
|
| 3401 |
+
"grad_norm": 0.2801115377310389,
|
| 3402 |
+
"learning_rate": 3.373653669913479e-07,
|
| 3403 |
+
"loss": 0.3973,
|
| 3404 |
+
"step": 4850
|
| 3405 |
+
},
|
| 3406 |
+
{
|
| 3407 |
+
"epoch": 2.6875576036866358,
|
| 3408 |
+
"grad_norm": 0.26687736410074,
|
| 3409 |
+
"learning_rate": 3.258411440399839e-07,
|
| 3410 |
+
"loss": 0.3921,
|
| 3411 |
+
"step": 4860
|
| 3412 |
+
},
|
| 3413 |
+
{
|
| 3414 |
+
"epoch": 2.6930875576036866,
|
| 3415 |
+
"grad_norm": 0.26749077132763405,
|
| 3416 |
+
"learning_rate": 3.1451055619525495e-07,
|
| 3417 |
+
"loss": 0.401,
|
| 3418 |
+
"step": 4870
|
| 3419 |
+
},
|
| 3420 |
+
{
|
| 3421 |
+
"epoch": 2.6986175115207374,
|
| 3422 |
+
"grad_norm": 0.2477585356057615,
|
| 3423 |
+
"learning_rate": 3.0337407284634023e-07,
|
| 3424 |
+
"loss": 0.4003,
|
| 3425 |
+
"step": 4880
|
| 3426 |
+
},
|
| 3427 |
+
{
|
| 3428 |
+
"epoch": 2.704147465437788,
|
| 3429 |
+
"grad_norm": 0.2577396288674699,
|
| 3430 |
+
"learning_rate": 2.924321553413029e-07,
|
| 3431 |
+
"loss": 0.4003,
|
| 3432 |
+
"step": 4890
|
| 3433 |
+
},
|
| 3434 |
+
{
|
| 3435 |
+
"epoch": 2.709677419354839,
|
| 3436 |
+
"grad_norm": 0.25584827001987803,
|
| 3437 |
+
"learning_rate": 2.8168525696798287e-07,
|
| 3438 |
+
"loss": 0.3932,
|
| 3439 |
+
"step": 4900
|
| 3440 |
+
},
|
| 3441 |
+
{
|
| 3442 |
+
"epoch": 2.7152073732718893,
|
| 3443 |
+
"grad_norm": 0.24937840132532715,
|
| 3444 |
+
"learning_rate": 2.7113382293521285e-07,
|
| 3445 |
+
"loss": 0.3935,
|
| 3446 |
+
"step": 4910
|
| 3447 |
+
},
|
| 3448 |
+
{
|
| 3449 |
+
"epoch": 2.72073732718894,
|
| 3450 |
+
"grad_norm": 0.27907536990926873,
|
| 3451 |
+
"learning_rate": 2.607782903543782e-07,
|
| 3452 |
+
"loss": 0.4059,
|
| 3453 |
+
"step": 4920
|
| 3454 |
+
},
|
| 3455 |
+
{
|
| 3456 |
+
"epoch": 2.726267281105991,
|
| 3457 |
+
"grad_norm": 0.2646543562986845,
|
| 3458 |
+
"learning_rate": 2.5061908822131e-07,
|
| 3459 |
+
"loss": 0.3842,
|
| 3460 |
+
"step": 4930
|
| 3461 |
+
},
|
| 3462 |
+
{
|
| 3463 |
+
"epoch": 2.7317972350230413,
|
| 3464 |
+
"grad_norm": 0.2471190703893049,
|
| 3465 |
+
"learning_rate": 2.406566373985075e-07,
|
| 3466 |
+
"loss": 0.3952,
|
| 3467 |
+
"step": 4940
|
| 3468 |
+
},
|
| 3469 |
+
{
|
| 3470 |
+
"epoch": 2.737327188940092,
|
| 3471 |
+
"grad_norm": 0.31897120592126615,
|
| 3472 |
+
"learning_rate": 2.3089135059771007e-07,
|
| 3473 |
+
"loss": 0.4097,
|
| 3474 |
+
"step": 4950
|
| 3475 |
+
},
|
| 3476 |
+
{
|
| 3477 |
+
"epoch": 2.742857142857143,
|
| 3478 |
+
"grad_norm": 0.2805170269928884,
|
| 3479 |
+
"learning_rate": 2.2132363236279654e-07,
|
| 3480 |
+
"loss": 0.402,
|
| 3481 |
+
"step": 4960
|
| 3482 |
+
},
|
| 3483 |
+
{
|
| 3484 |
+
"epoch": 2.7483870967741937,
|
| 3485 |
+
"grad_norm": 0.2653861937229007,
|
| 3486 |
+
"learning_rate": 2.1195387905302511e-07,
|
| 3487 |
+
"loss": 0.3986,
|
| 3488 |
+
"step": 4970
|
| 3489 |
+
},
|
| 3490 |
+
{
|
| 3491 |
+
"epoch": 2.7539170506912445,
|
| 3492 |
+
"grad_norm": 0.2730399737644054,
|
| 3493 |
+
"learning_rate": 2.0278247882661584e-07,
|
| 3494 |
+
"loss": 0.3925,
|
| 3495 |
+
"step": 4980
|
| 3496 |
+
},
|
| 3497 |
+
{
|
| 3498 |
+
"epoch": 2.759447004608295,
|
| 3499 |
+
"grad_norm": 0.26909939634669794,
|
| 3500 |
+
"learning_rate": 1.9380981162466895e-07,
|
| 3501 |
+
"loss": 0.3967,
|
| 3502 |
+
"step": 4990
|
| 3503 |
+
},
|
| 3504 |
+
{
|
| 3505 |
+
"epoch": 2.7649769585253456,
|
| 3506 |
+
"grad_norm": 0.25520919828788585,
|
| 3507 |
+
"learning_rate": 1.8503624915542805e-07,
|
| 3508 |
+
"loss": 0.3958,
|
| 3509 |
+
"step": 5000
|
| 3510 |
+
},
|
| 3511 |
+
{
|
| 3512 |
+
"epoch": 2.7705069124423964,
|
| 3513 |
+
"grad_norm": 0.2671702254098107,
|
| 3514 |
+
"learning_rate": 1.7646215487887587e-07,
|
| 3515 |
+
"loss": 0.3972,
|
| 3516 |
+
"step": 5010
|
| 3517 |
+
},
|
| 3518 |
+
{
|
| 3519 |
+
"epoch": 2.776036866359447,
|
| 3520 |
+
"grad_norm": 0.27339509483158747,
|
| 3521 |
+
"learning_rate": 1.680878839916833e-07,
|
| 3522 |
+
"loss": 0.3954,
|
| 3523 |
+
"step": 5020
|
| 3524 |
+
},
|
| 3525 |
+
{
|
| 3526 |
+
"epoch": 2.7815668202764976,
|
| 3527 |
+
"grad_norm": 0.26926037978444856,
|
| 3528 |
+
"learning_rate": 1.5991378341249032e-07,
|
| 3529 |
+
"loss": 0.3909,
|
| 3530 |
+
"step": 5030
|
| 3531 |
+
},
|
| 3532 |
+
{
|
| 3533 |
+
"epoch": 2.7870967741935484,
|
| 3534 |
+
"grad_norm": 0.2829092539377384,
|
| 3535 |
+
"learning_rate": 1.5194019176753615e-07,
|
| 3536 |
+
"loss": 0.3987,
|
| 3537 |
+
"step": 5040
|
| 3538 |
+
},
|
| 3539 |
+
{
|
| 3540 |
+
"epoch": 2.792626728110599,
|
| 3541 |
+
"grad_norm": 0.3050896133507036,
|
| 3542 |
+
"learning_rate": 1.441674393766318e-07,
|
| 3543 |
+
"loss": 0.4025,
|
| 3544 |
+
"step": 5050
|
| 3545 |
+
},
|
| 3546 |
+
{
|
| 3547 |
+
"epoch": 2.79815668202765,
|
| 3548 |
+
"grad_norm": 0.2856518392105625,
|
| 3549 |
+
"learning_rate": 1.3659584823947524e-07,
|
| 3550 |
+
"loss": 0.3959,
|
| 3551 |
+
"step": 5060
|
| 3552 |
+
},
|
| 3553 |
+
{
|
| 3554 |
+
"epoch": 2.8036866359447004,
|
| 3555 |
+
"grad_norm": 0.2687721431412885,
|
| 3556 |
+
"learning_rate": 1.2922573202231114e-07,
|
| 3557 |
+
"loss": 0.3981,
|
| 3558 |
+
"step": 5070
|
| 3559 |
+
},
|
| 3560 |
+
{
|
| 3561 |
+
"epoch": 2.809216589861751,
|
| 3562 |
+
"grad_norm": 0.26981891331331803,
|
| 3563 |
+
"learning_rate": 1.2205739604493838e-07,
|
| 3564 |
+
"loss": 0.4043,
|
| 3565 |
+
"step": 5080
|
| 3566 |
+
},
|
| 3567 |
+
{
|
| 3568 |
+
"epoch": 2.814746543778802,
|
| 3569 |
+
"grad_norm": 0.27405104128549934,
|
| 3570 |
+
"learning_rate": 1.1509113726805965e-07,
|
| 3571 |
+
"loss": 0.3903,
|
| 3572 |
+
"step": 5090
|
| 3573 |
+
},
|
| 3574 |
+
{
|
| 3575 |
+
"epoch": 2.8202764976958523,
|
| 3576 |
+
"grad_norm": 0.28208244890965906,
|
| 3577 |
+
"learning_rate": 1.0832724428098185e-07,
|
| 3578 |
+
"loss": 0.3964,
|
| 3579 |
+
"step": 5100
|
| 3580 |
+
},
|
| 3581 |
+
{
|
| 3582 |
+
"epoch": 2.825806451612903,
|
| 3583 |
+
"grad_norm": 0.2763730332681255,
|
| 3584 |
+
"learning_rate": 1.0176599728965842e-07,
|
| 3585 |
+
"loss": 0.3975,
|
| 3586 |
+
"step": 5110
|
| 3587 |
+
},
|
| 3588 |
+
{
|
| 3589 |
+
"epoch": 2.831336405529954,
|
| 3590 |
+
"grad_norm": 0.2678730622209392,
|
| 3591 |
+
"learning_rate": 9.540766810508196e-08,
|
| 3592 |
+
"loss": 0.3966,
|
| 3593 |
+
"step": 5120
|
| 3594 |
+
},
|
| 3595 |
+
{
|
| 3596 |
+
"epoch": 2.8368663594470047,
|
| 3597 |
+
"grad_norm": 0.2701400907907813,
|
| 3598 |
+
"learning_rate": 8.925252013202545e-08,
|
| 3599 |
+
"loss": 0.3974,
|
| 3600 |
+
"step": 5130
|
| 3601 |
+
},
|
| 3602 |
+
{
|
| 3603 |
+
"epoch": 2.8423963133640555,
|
| 3604 |
+
"grad_norm": 0.2585458146463293,
|
| 3605 |
+
"learning_rate": 8.330080835812826e-08,
|
| 3606 |
+
"loss": 0.3915,
|
| 3607 |
+
"step": 5140
|
| 3608 |
+
},
|
| 3609 |
+
{
|
| 3610 |
+
"epoch": 2.847926267281106,
|
| 3611 |
+
"grad_norm": 0.23930472824369428,
|
| 3612 |
+
"learning_rate": 7.75527793433345e-08,
|
| 3613 |
+
"loss": 0.3959,
|
| 3614 |
+
"step": 5150
|
| 3615 |
+
},
|
| 3616 |
+
{
|
| 3617 |
+
"epoch": 2.8534562211981567,
|
| 3618 |
+
"grad_norm": 0.27899399555881804,
|
| 3619 |
+
"learning_rate": 7.20086712096768e-08,
|
| 3620 |
+
"loss": 0.4048,
|
| 3621 |
+
"step": 5160
|
| 3622 |
+
},
|
| 3623 |
+
{
|
| 3624 |
+
"epoch": 2.8589861751152075,
|
| 3625 |
+
"grad_norm": 0.834759001453546,
|
| 3626 |
+
"learning_rate": 6.666871363141426e-08,
|
| 3627 |
+
"loss": 0.4008,
|
| 3628 |
+
"step": 5170
|
| 3629 |
+
},
|
| 3630 |
+
{
|
| 3631 |
+
"epoch": 2.864516129032258,
|
| 3632 |
+
"grad_norm": 0.26729552891819924,
|
| 3633 |
+
"learning_rate": 6.153312782551546e-08,
|
| 3634 |
+
"loss": 0.3943,
|
| 3635 |
+
"step": 5180
|
| 3636 |
+
},
|
| 3637 |
+
{
|
| 3638 |
+
"epoch": 2.8700460829493086,
|
| 3639 |
+
"grad_norm": 0.28300940951846,
|
| 3640 |
+
"learning_rate": 5.6602126542496525e-08,
|
| 3641 |
+
"loss": 0.4068,
|
| 3642 |
+
"step": 5190
|
| 3643 |
+
},
|
| 3644 |
+
{
|
| 3645 |
+
"epoch": 2.8755760368663594,
|
| 3646 |
+
"grad_norm": 0.2863970268789953,
|
| 3647 |
+
"learning_rate": 5.187591405760528e-08,
|
| 3648 |
+
"loss": 0.3978,
|
| 3649 |
+
"step": 5200
|
| 3650 |
+
},
|
| 3651 |
+
{
|
| 3652 |
+
"epoch": 2.8811059907834102,
|
| 3653 |
+
"grad_norm": 0.25831402266128894,
|
| 3654 |
+
"learning_rate": 4.7354686162359165e-08,
|
| 3655 |
+
"loss": 0.4013,
|
| 3656 |
+
"step": 5210
|
| 3657 |
+
},
|
| 3658 |
+
{
|
| 3659 |
+
"epoch": 2.886635944700461,
|
| 3660 |
+
"grad_norm": 0.28023244054969493,
|
| 3661 |
+
"learning_rate": 4.3038630156436166e-08,
|
| 3662 |
+
"loss": 0.3905,
|
| 3663 |
+
"step": 5220
|
| 3664 |
+
},
|
| 3665 |
+
{
|
| 3666 |
+
"epoch": 2.8921658986175114,
|
| 3667 |
+
"grad_norm": 0.2661529733653034,
|
| 3668 |
+
"learning_rate": 3.8927924839913257e-08,
|
| 3669 |
+
"loss": 0.393,
|
| 3670 |
+
"step": 5230
|
| 3671 |
+
},
|
| 3672 |
+
{
|
| 3673 |
+
"epoch": 2.897695852534562,
|
| 3674 |
+
"grad_norm": 0.25493956535145407,
|
| 3675 |
+
"learning_rate": 3.502274050586063e-08,
|
| 3676 |
+
"loss": 0.4006,
|
| 3677 |
+
"step": 5240
|
| 3678 |
+
},
|
| 3679 |
+
{
|
| 3680 |
+
"epoch": 2.903225806451613,
|
| 3681 |
+
"grad_norm": 0.26543797268631775,
|
| 3682 |
+
"learning_rate": 3.1323238933286814e-08,
|
| 3683 |
+
"loss": 0.3978,
|
| 3684 |
+
"step": 5250
|
| 3685 |
+
},
|
| 3686 |
+
{
|
| 3687 |
+
"epoch": 2.9087557603686633,
|
| 3688 |
+
"grad_norm": 0.26274051264290293,
|
| 3689 |
+
"learning_rate": 2.7829573380436793e-08,
|
| 3690 |
+
"loss": 0.4029,
|
| 3691 |
+
"step": 5260
|
| 3692 |
+
},
|
| 3693 |
+
{
|
| 3694 |
+
"epoch": 2.914285714285714,
|
| 3695 |
+
"grad_norm": 0.281124942017121,
|
| 3696 |
+
"learning_rate": 2.4541888578442085e-08,
|
| 3697 |
+
"loss": 0.3915,
|
| 3698 |
+
"step": 5270
|
| 3699 |
+
},
|
| 3700 |
+
{
|
| 3701 |
+
"epoch": 2.919815668202765,
|
| 3702 |
+
"grad_norm": 0.2560745200044448,
|
| 3703 |
+
"learning_rate": 2.1460320725326113e-08,
|
| 3704 |
+
"loss": 0.392,
|
| 3705 |
+
"step": 5280
|
| 3706 |
+
},
|
| 3707 |
+
{
|
| 3708 |
+
"epoch": 2.9253456221198157,
|
| 3709 |
+
"grad_norm": 0.2679757306919012,
|
| 3710 |
+
"learning_rate": 1.8584997480361467e-08,
|
| 3711 |
+
"loss": 0.4023,
|
| 3712 |
+
"step": 5290
|
| 3713 |
+
},
|
| 3714 |
+
{
|
| 3715 |
+
"epoch": 2.9308755760368665,
|
| 3716 |
+
"grad_norm": 0.26744986991724706,
|
| 3717 |
+
"learning_rate": 1.5916037958781938e-08,
|
| 3718 |
+
"loss": 0.3966,
|
| 3719 |
+
"step": 5300
|
| 3720 |
+
},
|
| 3721 |
+
{
|
| 3722 |
+
"epoch": 2.936405529953917,
|
| 3723 |
+
"grad_norm": 0.25508086605530733,
|
| 3724 |
+
"learning_rate": 1.3453552726847008e-08,
|
| 3725 |
+
"loss": 0.4018,
|
| 3726 |
+
"step": 5310
|
| 3727 |
+
},
|
| 3728 |
+
{
|
| 3729 |
+
"epoch": 2.9419354838709677,
|
| 3730 |
+
"grad_norm": 0.27916128301046206,
|
| 3731 |
+
"learning_rate": 1.1197643797261626e-08,
|
| 3732 |
+
"loss": 0.4027,
|
| 3733 |
+
"step": 5320
|
| 3734 |
+
},
|
| 3735 |
+
{
|
| 3736 |
+
"epoch": 2.9474654377880185,
|
| 3737 |
+
"grad_norm": 0.2750137090266509,
|
| 3738 |
+
"learning_rate": 9.148404624951812e-09,
|
| 3739 |
+
"loss": 0.4033,
|
| 3740 |
+
"step": 5330
|
| 3741 |
+
},
|
| 3742 |
+
{
|
| 3743 |
+
"epoch": 2.952995391705069,
|
| 3744 |
+
"grad_norm": 0.2725446012014818,
|
| 3745 |
+
"learning_rate": 7.3059201031899786e-09,
|
| 3746 |
+
"loss": 0.3962,
|
| 3747 |
+
"step": 5340
|
| 3748 |
+
},
|
| 3749 |
+
{
|
| 3750 |
+
"epoch": 2.9585253456221197,
|
| 3751 |
+
"grad_norm": 0.2815517448254806,
|
| 3752 |
+
"learning_rate": 5.670266560081628e-09,
|
| 3753 |
+
"loss": 0.4014,
|
| 3754 |
+
"step": 5350
|
| 3755 |
+
},
|
| 3756 |
+
{
|
| 3757 |
+
"epoch": 2.9640552995391705,
|
| 3758 |
+
"grad_norm": 0.27490789785492287,
|
| 3759 |
+
"learning_rate": 4.241511755400662e-09,
|
| 3760 |
+
"loss": 0.4113,
|
| 3761 |
+
"step": 5360
|
| 3762 |
+
},
|
| 3763 |
+
{
|
| 3764 |
+
"epoch": 2.9695852534562213,
|
| 3765 |
+
"grad_norm": 0.2939191489301333,
|
| 3766 |
+
"learning_rate": 3.0197148777838524e-09,
|
| 3767 |
+
"loss": 0.3967,
|
| 3768 |
+
"step": 5370
|
| 3769 |
+
},
|
| 3770 |
+
{
|
| 3771 |
+
"epoch": 2.975115207373272,
|
| 3772 |
+
"grad_norm": 0.271422595495557,
|
| 3773 |
+
"learning_rate": 2.0049265422772414e-09,
|
| 3774 |
+
"loss": 0.3993,
|
| 3775 |
+
"step": 5380
|
| 3776 |
+
},
|
| 3777 |
+
{
|
| 3778 |
+
"epoch": 2.9806451612903224,
|
| 3779 |
+
"grad_norm": 0.26327553337631326,
|
| 3780 |
+
"learning_rate": 1.1971887882405997e-09,
|
| 3781 |
+
"loss": 0.4024,
|
| 3782 |
+
"step": 5390
|
| 3783 |
+
},
|
| 3784 |
+
{
|
| 3785 |
+
"epoch": 2.986175115207373,
|
| 3786 |
+
"grad_norm": 0.2805409873853394,
|
| 3787 |
+
"learning_rate": 5.965350776071521e-10,
|
| 3788 |
+
"loss": 0.4049,
|
| 3789 |
+
"step": 5400
|
| 3790 |
+
},
|
| 3791 |
+
{
|
| 3792 |
+
"epoch": 2.991705069124424,
|
| 3793 |
+
"grad_norm": 0.25201401300926546,
|
| 3794 |
+
"learning_rate": 2.029902934941319e-10,
|
| 3795 |
+
"loss": 0.3993,
|
| 3796 |
+
"step": 5410
|
| 3797 |
+
},
|
| 3798 |
+
{
|
| 3799 |
+
"epoch": 2.9972350230414744,
|
| 3800 |
+
"grad_norm": 0.2495374923869934,
|
| 3801 |
+
"learning_rate": 1.6570739174714967e-11,
|
| 3802 |
+
"loss": 0.3964,
|
| 3803 |
+
"step": 5420
|
| 3804 |
+
},
|
| 3805 |
+
{
|
| 3806 |
+
"epoch": 2.999447004608295,
|
| 3807 |
+
"step": 5424,
|
| 3808 |
+
"total_flos": 8192265561309184.0,
|
| 3809 |
+
"train_loss": 0.4416485577162388,
|
| 3810 |
+
"train_runtime": 91348.8221,
|
| 3811 |
+
"train_samples_per_second": 5.7,
|
| 3812 |
+
"train_steps_per_second": 0.059
|
| 3813 |
+
}
|
| 3814 |
+
],
|
| 3815 |
+
"logging_steps": 10,
|
| 3816 |
+
"max_steps": 5424,
|
| 3817 |
+
"num_input_tokens_seen": 0,
|
| 3818 |
+
"num_train_epochs": 3,
|
| 3819 |
+
"save_steps": 500,
|
| 3820 |
+
"stateful_callbacks": {
|
| 3821 |
+
"TrainerControl": {
|
| 3822 |
+
"args": {
|
| 3823 |
+
"should_epoch_stop": false,
|
| 3824 |
+
"should_evaluate": false,
|
| 3825 |
+
"should_log": false,
|
| 3826 |
+
"should_save": true,
|
| 3827 |
+
"should_training_stop": true
|
| 3828 |
+
},
|
| 3829 |
+
"attributes": {}
|
| 3830 |
+
}
|
| 3831 |
+
},
|
| 3832 |
+
"total_flos": 8192265561309184.0,
|
| 3833 |
+
"train_batch_size": 1,
|
| 3834 |
+
"trial_name": null,
|
| 3835 |
+
"trial_params": null
|
| 3836 |
+
}
|
training_loss.png
ADDED
|