End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +3318 -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: 10k_globalbatchsize64_lr2e5_epochs3
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# 10k_globalbatchsize64_lr2e5_epochs3
|
| 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: 10k_globalbatchsize64_lr2e5_epochs3
|
|
|
|
| 16 |
|
| 17 |
# 10k_globalbatchsize64_lr2e5_epochs3
|
| 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/openthoughts_10000 dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9904153354632586,
|
| 3 |
+
"total_flos": 3.310734730054861e+17,
|
| 4 |
+
"train_loss": 0.4434524042229367,
|
| 5 |
+
"train_runtime": 10205.5973,
|
| 6 |
+
"train_samples_per_second": 2.939,
|
| 7 |
+
"train_steps_per_second": 0.046
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9904153354632586,
|
| 3 |
+
"total_flos": 3.310734730054861e+17,
|
| 4 |
+
"train_loss": 0.4434524042229367,
|
| 5 |
+
"train_runtime": 10205.5973,
|
| 6 |
+
"train_samples_per_second": 2.939,
|
| 7 |
+
"train_steps_per_second": 0.046
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3318 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9904153354632586,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 468,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.006389776357827476,
|
| 13 |
+
"grad_norm": 5.939312845608103,
|
| 14 |
+
"learning_rate": 4.2553191489361704e-07,
|
| 15 |
+
"loss": 0.8883,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.012779552715654952,
|
| 20 |
+
"grad_norm": 5.6459943274568385,
|
| 21 |
+
"learning_rate": 8.510638297872341e-07,
|
| 22 |
+
"loss": 0.8365,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.019169329073482427,
|
| 27 |
+
"grad_norm": 6.290489665408837,
|
| 28 |
+
"learning_rate": 1.276595744680851e-06,
|
| 29 |
+
"loss": 0.8864,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.025559105431309903,
|
| 34 |
+
"grad_norm": 5.8544636560570735,
|
| 35 |
+
"learning_rate": 1.7021276595744682e-06,
|
| 36 |
+
"loss": 0.879,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.03194888178913738,
|
| 41 |
+
"grad_norm": 5.478170251266386,
|
| 42 |
+
"learning_rate": 2.1276595744680853e-06,
|
| 43 |
+
"loss": 0.8245,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.038338658146964855,
|
| 48 |
+
"grad_norm": 4.688336713722404,
|
| 49 |
+
"learning_rate": 2.553191489361702e-06,
|
| 50 |
+
"loss": 0.849,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.04472843450479233,
|
| 55 |
+
"grad_norm": 4.278233500376253,
|
| 56 |
+
"learning_rate": 2.978723404255319e-06,
|
| 57 |
+
"loss": 0.8151,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.051118210862619806,
|
| 62 |
+
"grad_norm": 2.367029075074496,
|
| 63 |
+
"learning_rate": 3.4042553191489363e-06,
|
| 64 |
+
"loss": 0.7566,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.05750798722044728,
|
| 69 |
+
"grad_norm": 2.0707237905380484,
|
| 70 |
+
"learning_rate": 3.8297872340425535e-06,
|
| 71 |
+
"loss": 0.7551,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.06389776357827476,
|
| 76 |
+
"grad_norm": 1.7866725538131587,
|
| 77 |
+
"learning_rate": 4.255319148936171e-06,
|
| 78 |
+
"loss": 0.7457,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.07028753993610223,
|
| 83 |
+
"grad_norm": 3.404477977029493,
|
| 84 |
+
"learning_rate": 4.680851063829788e-06,
|
| 85 |
+
"loss": 0.699,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.07667731629392971,
|
| 90 |
+
"grad_norm": 3.8759087344215093,
|
| 91 |
+
"learning_rate": 5.106382978723404e-06,
|
| 92 |
+
"loss": 0.8106,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.08306709265175719,
|
| 97 |
+
"grad_norm": 4.206484510948959,
|
| 98 |
+
"learning_rate": 5.531914893617022e-06,
|
| 99 |
+
"loss": 0.7639,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.08945686900958466,
|
| 104 |
+
"grad_norm": 3.597855342218176,
|
| 105 |
+
"learning_rate": 5.957446808510638e-06,
|
| 106 |
+
"loss": 0.7143,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.09584664536741214,
|
| 111 |
+
"grad_norm": 3.493223809169224,
|
| 112 |
+
"learning_rate": 6.382978723404256e-06,
|
| 113 |
+
"loss": 0.7495,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.10223642172523961,
|
| 118 |
+
"grad_norm": 2.7730036124678588,
|
| 119 |
+
"learning_rate": 6.808510638297873e-06,
|
| 120 |
+
"loss": 0.7079,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.10862619808306709,
|
| 125 |
+
"grad_norm": 1.99917862715565,
|
| 126 |
+
"learning_rate": 7.234042553191491e-06,
|
| 127 |
+
"loss": 0.6637,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.11501597444089456,
|
| 132 |
+
"grad_norm": 1.7234540912576959,
|
| 133 |
+
"learning_rate": 7.659574468085107e-06,
|
| 134 |
+
"loss": 0.6563,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.12140575079872204,
|
| 139 |
+
"grad_norm": 1.9632219810386513,
|
| 140 |
+
"learning_rate": 8.085106382978723e-06,
|
| 141 |
+
"loss": 0.6753,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.12779552715654952,
|
| 146 |
+
"grad_norm": 2.1614567368781157,
|
| 147 |
+
"learning_rate": 8.510638297872341e-06,
|
| 148 |
+
"loss": 0.6063,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.134185303514377,
|
| 153 |
+
"grad_norm": 1.932507047332365,
|
| 154 |
+
"learning_rate": 8.936170212765958e-06,
|
| 155 |
+
"loss": 0.629,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.14057507987220447,
|
| 160 |
+
"grad_norm": 1.5481507427216847,
|
| 161 |
+
"learning_rate": 9.361702127659576e-06,
|
| 162 |
+
"loss": 0.6444,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.14696485623003194,
|
| 167 |
+
"grad_norm": 1.2177329752055572,
|
| 168 |
+
"learning_rate": 9.787234042553192e-06,
|
| 169 |
+
"loss": 0.641,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.15335463258785942,
|
| 174 |
+
"grad_norm": 1.4206725631658237,
|
| 175 |
+
"learning_rate": 1.0212765957446808e-05,
|
| 176 |
+
"loss": 0.6496,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.1597444089456869,
|
| 181 |
+
"grad_norm": 1.4667519530084758,
|
| 182 |
+
"learning_rate": 1.0638297872340426e-05,
|
| 183 |
+
"loss": 0.6304,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.16613418530351437,
|
| 188 |
+
"grad_norm": 1.2452708214307595,
|
| 189 |
+
"learning_rate": 1.1063829787234044e-05,
|
| 190 |
+
"loss": 0.6413,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.17252396166134185,
|
| 195 |
+
"grad_norm": 0.7759167145812482,
|
| 196 |
+
"learning_rate": 1.1489361702127662e-05,
|
| 197 |
+
"loss": 0.5927,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.17891373801916932,
|
| 202 |
+
"grad_norm": 1.0321850071310563,
|
| 203 |
+
"learning_rate": 1.1914893617021277e-05,
|
| 204 |
+
"loss": 0.5898,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.1853035143769968,
|
| 209 |
+
"grad_norm": 1.0266703283162124,
|
| 210 |
+
"learning_rate": 1.2340425531914895e-05,
|
| 211 |
+
"loss": 0.5895,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.19169329073482427,
|
| 216 |
+
"grad_norm": 0.9674925840183656,
|
| 217 |
+
"learning_rate": 1.2765957446808513e-05,
|
| 218 |
+
"loss": 0.5853,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.19808306709265175,
|
| 223 |
+
"grad_norm": 0.9805374530460067,
|
| 224 |
+
"learning_rate": 1.3191489361702127e-05,
|
| 225 |
+
"loss": 0.5756,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.20447284345047922,
|
| 230 |
+
"grad_norm": 0.9258462587522315,
|
| 231 |
+
"learning_rate": 1.3617021276595745e-05,
|
| 232 |
+
"loss": 0.585,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.2108626198083067,
|
| 237 |
+
"grad_norm": 0.8925757909283792,
|
| 238 |
+
"learning_rate": 1.4042553191489363e-05,
|
| 239 |
+
"loss": 0.584,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.21725239616613418,
|
| 244 |
+
"grad_norm": 0.7738950177471798,
|
| 245 |
+
"learning_rate": 1.4468085106382981e-05,
|
| 246 |
+
"loss": 0.553,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.22364217252396165,
|
| 251 |
+
"grad_norm": 0.823063478968403,
|
| 252 |
+
"learning_rate": 1.4893617021276596e-05,
|
| 253 |
+
"loss": 0.605,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.23003194888178913,
|
| 258 |
+
"grad_norm": 0.7769591687125452,
|
| 259 |
+
"learning_rate": 1.5319148936170214e-05,
|
| 260 |
+
"loss": 0.5398,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.2364217252396166,
|
| 265 |
+
"grad_norm": 0.724085749329525,
|
| 266 |
+
"learning_rate": 1.5744680851063832e-05,
|
| 267 |
+
"loss": 0.5541,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.24281150159744408,
|
| 272 |
+
"grad_norm": 0.7937699708520545,
|
| 273 |
+
"learning_rate": 1.6170212765957446e-05,
|
| 274 |
+
"loss": 0.5516,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.24920127795527156,
|
| 279 |
+
"grad_norm": 0.838915436660047,
|
| 280 |
+
"learning_rate": 1.6595744680851064e-05,
|
| 281 |
+
"loss": 0.5335,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.25559105431309903,
|
| 286 |
+
"grad_norm": 0.7447841608522099,
|
| 287 |
+
"learning_rate": 1.7021276595744682e-05,
|
| 288 |
+
"loss": 0.5414,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.26198083067092653,
|
| 293 |
+
"grad_norm": 0.8714110715774589,
|
| 294 |
+
"learning_rate": 1.74468085106383e-05,
|
| 295 |
+
"loss": 0.556,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.268370607028754,
|
| 300 |
+
"grad_norm": 0.7411083091257032,
|
| 301 |
+
"learning_rate": 1.7872340425531915e-05,
|
| 302 |
+
"loss": 0.5113,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.2747603833865815,
|
| 307 |
+
"grad_norm": 0.7680242229988357,
|
| 308 |
+
"learning_rate": 1.8297872340425533e-05,
|
| 309 |
+
"loss": 0.5684,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.28115015974440893,
|
| 314 |
+
"grad_norm": 0.7374046719973165,
|
| 315 |
+
"learning_rate": 1.872340425531915e-05,
|
| 316 |
+
"loss": 0.577,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.28753993610223644,
|
| 321 |
+
"grad_norm": 0.7709945486266545,
|
| 322 |
+
"learning_rate": 1.914893617021277e-05,
|
| 323 |
+
"loss": 0.5251,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.2939297124600639,
|
| 328 |
+
"grad_norm": 0.7420014515431359,
|
| 329 |
+
"learning_rate": 1.9574468085106384e-05,
|
| 330 |
+
"loss": 0.5358,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.3003194888178914,
|
| 335 |
+
"grad_norm": 0.7321704500165183,
|
| 336 |
+
"learning_rate": 2e-05,
|
| 337 |
+
"loss": 0.56,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.30670926517571884,
|
| 342 |
+
"grad_norm": 0.7855274459068936,
|
| 343 |
+
"learning_rate": 1.9999721578003894e-05,
|
| 344 |
+
"loss": 0.5427,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.31309904153354634,
|
| 349 |
+
"grad_norm": 0.7731901448013743,
|
| 350 |
+
"learning_rate": 1.9998886327519337e-05,
|
| 351 |
+
"loss": 0.5517,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.3194888178913738,
|
| 356 |
+
"grad_norm": 0.7327331638939495,
|
| 357 |
+
"learning_rate": 1.999749429505675e-05,
|
| 358 |
+
"loss": 0.5468,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.3258785942492013,
|
| 363 |
+
"grad_norm": 0.7419176272941636,
|
| 364 |
+
"learning_rate": 1.9995545558130624e-05,
|
| 365 |
+
"loss": 0.548,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.33226837060702874,
|
| 370 |
+
"grad_norm": 0.7873113572745489,
|
| 371 |
+
"learning_rate": 1.9993040225255205e-05,
|
| 372 |
+
"loss": 0.5403,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.33865814696485624,
|
| 377 |
+
"grad_norm": 0.6658693818077654,
|
| 378 |
+
"learning_rate": 1.998997843593845e-05,
|
| 379 |
+
"loss": 0.5054,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.3450479233226837,
|
| 384 |
+
"grad_norm": 0.7409323699660156,
|
| 385 |
+
"learning_rate": 1.9986360360674252e-05,
|
| 386 |
+
"loss": 0.5555,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.3514376996805112,
|
| 391 |
+
"grad_norm": 0.7094024540386773,
|
| 392 |
+
"learning_rate": 1.9982186200932964e-05,
|
| 393 |
+
"loss": 0.535,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.35782747603833864,
|
| 398 |
+
"grad_norm": 0.9538171828161622,
|
| 399 |
+
"learning_rate": 1.9977456189150164e-05,
|
| 400 |
+
"loss": 0.5788,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.36421725239616615,
|
| 405 |
+
"grad_norm": 0.7395956073936416,
|
| 406 |
+
"learning_rate": 1.9972170588713715e-05,
|
| 407 |
+
"loss": 0.5836,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.3706070287539936,
|
| 412 |
+
"grad_norm": 0.8649724098491106,
|
| 413 |
+
"learning_rate": 1.9966329693949098e-05,
|
| 414 |
+
"loss": 0.4918,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.3769968051118211,
|
| 419 |
+
"grad_norm": 0.8838321465136332,
|
| 420 |
+
"learning_rate": 1.9959933830103034e-05,
|
| 421 |
+
"loss": 0.514,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.38338658146964855,
|
| 426 |
+
"grad_norm": 0.7993190296372936,
|
| 427 |
+
"learning_rate": 1.9952983353325358e-05,
|
| 428 |
+
"loss": 0.5191,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.38977635782747605,
|
| 433 |
+
"grad_norm": 1.0003320683454586,
|
| 434 |
+
"learning_rate": 1.9945478650649192e-05,
|
| 435 |
+
"loss": 0.5395,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.3961661341853035,
|
| 440 |
+
"grad_norm": 0.8174378430731664,
|
| 441 |
+
"learning_rate": 1.9937420139969397e-05,
|
| 442 |
+
"loss": 0.5428,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.402555910543131,
|
| 447 |
+
"grad_norm": 0.7497946237416347,
|
| 448 |
+
"learning_rate": 1.9928808270019297e-05,
|
| 449 |
+
"loss": 0.5826,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.40894568690095845,
|
| 454 |
+
"grad_norm": 0.8640015891418493,
|
| 455 |
+
"learning_rate": 1.9919643520345698e-05,
|
| 456 |
+
"loss": 0.5343,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.41533546325878595,
|
| 461 |
+
"grad_norm": 1.0033449675940591,
|
| 462 |
+
"learning_rate": 1.990992640128218e-05,
|
| 463 |
+
"loss": 0.5623,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.4217252396166134,
|
| 468 |
+
"grad_norm": 0.7213392023439573,
|
| 469 |
+
"learning_rate": 1.989965745392068e-05,
|
| 470 |
+
"loss": 0.5314,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.4281150159744409,
|
| 475 |
+
"grad_norm": 0.8863830620435368,
|
| 476 |
+
"learning_rate": 1.988883725008136e-05,
|
| 477 |
+
"loss": 0.5458,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.43450479233226835,
|
| 482 |
+
"grad_norm": 0.7362416113857194,
|
| 483 |
+
"learning_rate": 1.9877466392280773e-05,
|
| 484 |
+
"loss": 0.5428,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.44089456869009586,
|
| 489 |
+
"grad_norm": 0.9788737478764125,
|
| 490 |
+
"learning_rate": 1.9865545513698304e-05,
|
| 491 |
+
"loss": 0.5412,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.4472843450479233,
|
| 496 |
+
"grad_norm": 0.8021931238319318,
|
| 497 |
+
"learning_rate": 1.9853075278140913e-05,
|
| 498 |
+
"loss": 0.5522,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.4536741214057508,
|
| 503 |
+
"grad_norm": 0.85887825826516,
|
| 504 |
+
"learning_rate": 1.984005638000618e-05,
|
| 505 |
+
"loss": 0.5702,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.46006389776357826,
|
| 510 |
+
"grad_norm": 0.7815409304110528,
|
| 511 |
+
"learning_rate": 1.9826489544243623e-05,
|
| 512 |
+
"loss": 0.5482,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.46645367412140576,
|
| 517 |
+
"grad_norm": 0.7632274039193099,
|
| 518 |
+
"learning_rate": 1.981237552631434e-05,
|
| 519 |
+
"loss": 0.5387,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.4728434504792332,
|
| 524 |
+
"grad_norm": 0.7141397681245097,
|
| 525 |
+
"learning_rate": 1.9797715112148937e-05,
|
| 526 |
+
"loss": 0.5546,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.4792332268370607,
|
| 531 |
+
"grad_norm": 0.9775621975797985,
|
| 532 |
+
"learning_rate": 1.9782509118103773e-05,
|
| 533 |
+
"loss": 0.5308,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.48562300319488816,
|
| 538 |
+
"grad_norm": 0.7330287655613912,
|
| 539 |
+
"learning_rate": 1.9766758390915494e-05,
|
| 540 |
+
"loss": 0.5431,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.49201277955271566,
|
| 545 |
+
"grad_norm": 0.8510881793812443,
|
| 546 |
+
"learning_rate": 1.9750463807653873e-05,
|
| 547 |
+
"loss": 0.5187,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.4984025559105431,
|
| 552 |
+
"grad_norm": 0.8486211359598791,
|
| 553 |
+
"learning_rate": 1.9733626275673e-05,
|
| 554 |
+
"loss": 0.55,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.5047923322683706,
|
| 559 |
+
"grad_norm": 0.7806116343240348,
|
| 560 |
+
"learning_rate": 1.9716246732560715e-05,
|
| 561 |
+
"loss": 0.4813,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.5111821086261981,
|
| 566 |
+
"grad_norm": 0.6353268171693698,
|
| 567 |
+
"learning_rate": 1.9698326146086446e-05,
|
| 568 |
+
"loss": 0.5078,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.5175718849840255,
|
| 573 |
+
"grad_norm": 0.8766273238149929,
|
| 574 |
+
"learning_rate": 1.967986551414728e-05,
|
| 575 |
+
"loss": 0.544,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.5239616613418531,
|
| 580 |
+
"grad_norm": 0.7124929308186037,
|
| 581 |
+
"learning_rate": 1.9660865864712413e-05,
|
| 582 |
+
"loss": 0.5547,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.5303514376996805,
|
| 587 |
+
"grad_norm": 0.7985052392042088,
|
| 588 |
+
"learning_rate": 1.9641328255765916e-05,
|
| 589 |
+
"loss": 0.5215,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.536741214057508,
|
| 594 |
+
"grad_norm": 0.6406165534662566,
|
| 595 |
+
"learning_rate": 1.96212537752478e-05,
|
| 596 |
+
"loss": 0.4978,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.5431309904153354,
|
| 601 |
+
"grad_norm": 0.7351154516097609,
|
| 602 |
+
"learning_rate": 1.9600643540993453e-05,
|
| 603 |
+
"loss": 0.5498,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.549520766773163,
|
| 608 |
+
"grad_norm": 0.7023736701907295,
|
| 609 |
+
"learning_rate": 1.9579498700671386e-05,
|
| 610 |
+
"loss": 0.5271,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.5559105431309904,
|
| 615 |
+
"grad_norm": 0.7585882232459317,
|
| 616 |
+
"learning_rate": 1.9557820431719333e-05,
|
| 617 |
+
"loss": 0.5419,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.5623003194888179,
|
| 622 |
+
"grad_norm": 0.7609703576418915,
|
| 623 |
+
"learning_rate": 1.9535609941278676e-05,
|
| 624 |
+
"loss": 0.5115,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.5686900958466453,
|
| 629 |
+
"grad_norm": 0.8355505315864735,
|
| 630 |
+
"learning_rate": 1.9512868466127232e-05,
|
| 631 |
+
"loss": 0.5214,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.5750798722044729,
|
| 636 |
+
"grad_norm": 0.8985531652526637,
|
| 637 |
+
"learning_rate": 1.9489597272610377e-05,
|
| 638 |
+
"loss": 0.5217,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.5814696485623003,
|
| 643 |
+
"grad_norm": 0.8296453033353365,
|
| 644 |
+
"learning_rate": 1.9465797656570546e-05,
|
| 645 |
+
"loss": 0.5235,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.5878594249201278,
|
| 650 |
+
"grad_norm": 0.8400305646818227,
|
| 651 |
+
"learning_rate": 1.944147094327506e-05,
|
| 652 |
+
"loss": 0.5028,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.5942492012779552,
|
| 657 |
+
"grad_norm": 0.8027178786911765,
|
| 658 |
+
"learning_rate": 1.9416618487342333e-05,
|
| 659 |
+
"loss": 0.4932,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.6006389776357828,
|
| 664 |
+
"grad_norm": 0.831774187088593,
|
| 665 |
+
"learning_rate": 1.9391241672666438e-05,
|
| 666 |
+
"loss": 0.5015,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.6070287539936102,
|
| 671 |
+
"grad_norm": 0.6880013029770987,
|
| 672 |
+
"learning_rate": 1.936534191234006e-05,
|
| 673 |
+
"loss": 0.4851,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.6134185303514377,
|
| 678 |
+
"grad_norm": 0.7874317799707009,
|
| 679 |
+
"learning_rate": 1.9338920648575798e-05,
|
| 680 |
+
"loss": 0.4993,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.6198083067092651,
|
| 685 |
+
"grad_norm": 0.8086603460274078,
|
| 686 |
+
"learning_rate": 1.9311979352625837e-05,
|
| 687 |
+
"loss": 0.5472,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.6261980830670927,
|
| 692 |
+
"grad_norm": 0.7330826956678399,
|
| 693 |
+
"learning_rate": 1.928451952470007e-05,
|
| 694 |
+
"loss": 0.5267,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.6325878594249201,
|
| 699 |
+
"grad_norm": 0.6774581525725395,
|
| 700 |
+
"learning_rate": 1.9256542693882505e-05,
|
| 701 |
+
"loss": 0.4964,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.6389776357827476,
|
| 706 |
+
"grad_norm": 0.699096603267482,
|
| 707 |
+
"learning_rate": 1.922805041804617e-05,
|
| 708 |
+
"loss": 0.5051,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.645367412140575,
|
| 713 |
+
"grad_norm": 0.7625712048870313,
|
| 714 |
+
"learning_rate": 1.919904428376632e-05,
|
| 715 |
+
"loss": 0.5301,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.6517571884984026,
|
| 720 |
+
"grad_norm": 0.7442243954348883,
|
| 721 |
+
"learning_rate": 1.916952590623212e-05,
|
| 722 |
+
"loss": 0.5114,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.65814696485623,
|
| 727 |
+
"grad_norm": 0.6319971486530133,
|
| 728 |
+
"learning_rate": 1.9139496929156685e-05,
|
| 729 |
+
"loss": 0.5106,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.6645367412140575,
|
| 734 |
+
"grad_norm": 0.6634321632909197,
|
| 735 |
+
"learning_rate": 1.910895902468557e-05,
|
| 736 |
+
"loss": 0.5211,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.670926517571885,
|
| 741 |
+
"grad_norm": 0.5959863886093508,
|
| 742 |
+
"learning_rate": 1.907791389330363e-05,
|
| 743 |
+
"loss": 0.5124,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.6773162939297125,
|
| 748 |
+
"grad_norm": 0.7995435481771501,
|
| 749 |
+
"learning_rate": 1.904636326374036e-05,
|
| 750 |
+
"loss": 0.52,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.6837060702875399,
|
| 755 |
+
"grad_norm": 0.7383352863257084,
|
| 756 |
+
"learning_rate": 1.9014308892873612e-05,
|
| 757 |
+
"loss": 0.5516,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.6900958466453674,
|
| 762 |
+
"grad_norm": 0.8315686682034763,
|
| 763 |
+
"learning_rate": 1.8981752565631767e-05,
|
| 764 |
+
"loss": 0.4891,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.6964856230031949,
|
| 769 |
+
"grad_norm": 0.6508951908046772,
|
| 770 |
+
"learning_rate": 1.8948696094894354e-05,
|
| 771 |
+
"loss": 0.5591,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.7028753993610224,
|
| 776 |
+
"grad_norm": 0.8009701429333234,
|
| 777 |
+
"learning_rate": 1.8915141321391083e-05,
|
| 778 |
+
"loss": 0.5305,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.7092651757188498,
|
| 783 |
+
"grad_norm": 0.7308231155353043,
|
| 784 |
+
"learning_rate": 1.8881090113599353e-05,
|
| 785 |
+
"loss": 0.5191,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.7156549520766773,
|
| 790 |
+
"grad_norm": 0.7808253591246626,
|
| 791 |
+
"learning_rate": 1.8846544367640218e-05,
|
| 792 |
+
"loss": 0.4906,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.7220447284345048,
|
| 797 |
+
"grad_norm": 0.8760149164716509,
|
| 798 |
+
"learning_rate": 1.881150600717279e-05,
|
| 799 |
+
"loss": 0.532,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.7284345047923323,
|
| 804 |
+
"grad_norm": 0.6776840820965584,
|
| 805 |
+
"learning_rate": 1.8775976983287117e-05,
|
| 806 |
+
"loss": 0.521,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.7348242811501597,
|
| 811 |
+
"grad_norm": 0.8898200759371685,
|
| 812 |
+
"learning_rate": 1.873995927439555e-05,
|
| 813 |
+
"loss": 0.5251,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.7412140575079872,
|
| 818 |
+
"grad_norm": 0.7499195664294598,
|
| 819 |
+
"learning_rate": 1.8703454886122568e-05,
|
| 820 |
+
"loss": 0.5348,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.7476038338658147,
|
| 825 |
+
"grad_norm": 0.8505865320259214,
|
| 826 |
+
"learning_rate": 1.86664658511931e-05,
|
| 827 |
+
"loss": 0.5054,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.7539936102236422,
|
| 832 |
+
"grad_norm": 0.6522705814194051,
|
| 833 |
+
"learning_rate": 1.862899422931934e-05,
|
| 834 |
+
"loss": 0.4996,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.7603833865814696,
|
| 839 |
+
"grad_norm": 0.6577321085300217,
|
| 840 |
+
"learning_rate": 1.859104210708604e-05,
|
| 841 |
+
"loss": 0.5106,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.7667731629392971,
|
| 846 |
+
"grad_norm": 0.6237691862811225,
|
| 847 |
+
"learning_rate": 1.855261159783432e-05,
|
| 848 |
+
"loss": 0.4952,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.7731629392971247,
|
| 853 |
+
"grad_norm": 0.7454463301186427,
|
| 854 |
+
"learning_rate": 1.8513704841543997e-05,
|
| 855 |
+
"loss": 0.5026,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.7795527156549521,
|
| 860 |
+
"grad_norm": 0.7934145741008819,
|
| 861 |
+
"learning_rate": 1.847432400471443e-05,
|
| 862 |
+
"loss": 0.549,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.7859424920127795,
|
| 867 |
+
"grad_norm": 0.6802649460778195,
|
| 868 |
+
"learning_rate": 1.8434471280243854e-05,
|
| 869 |
+
"loss": 0.506,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.792332268370607,
|
| 874 |
+
"grad_norm": 0.7304620814404005,
|
| 875 |
+
"learning_rate": 1.8394148887307286e-05,
|
| 876 |
+
"loss": 0.5383,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.7987220447284346,
|
| 881 |
+
"grad_norm": 0.6957782218041328,
|
| 882 |
+
"learning_rate": 1.8353359071232954e-05,
|
| 883 |
+
"loss": 0.5019,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.805111821086262,
|
| 888 |
+
"grad_norm": 0.6826820301754135,
|
| 889 |
+
"learning_rate": 1.8312104103377266e-05,
|
| 890 |
+
"loss": 0.4937,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.8115015974440895,
|
| 895 |
+
"grad_norm": 0.598906813674708,
|
| 896 |
+
"learning_rate": 1.827038628099831e-05,
|
| 897 |
+
"loss": 0.488,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.8178913738019169,
|
| 902 |
+
"grad_norm": 0.6633449549765212,
|
| 903 |
+
"learning_rate": 1.822820792712797e-05,
|
| 904 |
+
"loss": 0.4971,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.8242811501597445,
|
| 909 |
+
"grad_norm": 0.6710913601976871,
|
| 910 |
+
"learning_rate": 1.8185571390442542e-05,
|
| 911 |
+
"loss": 0.4836,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.8306709265175719,
|
| 916 |
+
"grad_norm": 0.5762592167913351,
|
| 917 |
+
"learning_rate": 1.8142479045131956e-05,
|
| 918 |
+
"loss": 0.5192,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.8370607028753994,
|
| 923 |
+
"grad_norm": 0.6738150719804582,
|
| 924 |
+
"learning_rate": 1.809893329076757e-05,
|
| 925 |
+
"loss": 0.5228,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.8434504792332268,
|
| 930 |
+
"grad_norm": 0.6500141385276138,
|
| 931 |
+
"learning_rate": 1.8054936552168548e-05,
|
| 932 |
+
"loss": 0.5332,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.8498402555910544,
|
| 937 |
+
"grad_norm": 0.5886713445337487,
|
| 938 |
+
"learning_rate": 1.801049127926686e-05,
|
| 939 |
+
"loss": 0.4787,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.8562300319488818,
|
| 944 |
+
"grad_norm": 0.7649082888316344,
|
| 945 |
+
"learning_rate": 1.7965599946970814e-05,
|
| 946 |
+
"loss": 0.4914,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.8626198083067093,
|
| 951 |
+
"grad_norm": 0.8014082101971098,
|
| 952 |
+
"learning_rate": 1.7920265055027285e-05,
|
| 953 |
+
"loss": 0.5171,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.8690095846645367,
|
| 958 |
+
"grad_norm": 0.7706425976997076,
|
| 959 |
+
"learning_rate": 1.7874489127882496e-05,
|
| 960 |
+
"loss": 0.5267,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.8753993610223643,
|
| 965 |
+
"grad_norm": 0.9916919676402002,
|
| 966 |
+
"learning_rate": 1.7828274714541445e-05,
|
| 967 |
+
"loss": 0.5225,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.8817891373801917,
|
| 972 |
+
"grad_norm": 0.7510268200588113,
|
| 973 |
+
"learning_rate": 1.7781624388425974e-05,
|
| 974 |
+
"loss": 0.5056,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.8881789137380192,
|
| 979 |
+
"grad_norm": 1.0622441121039243,
|
| 980 |
+
"learning_rate": 1.773454074723147e-05,
|
| 981 |
+
"loss": 0.4773,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.8945686900958466,
|
| 986 |
+
"grad_norm": 0.8430739649427611,
|
| 987 |
+
"learning_rate": 1.76870264127822e-05,
|
| 988 |
+
"loss": 0.5384,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.9009584664536742,
|
| 993 |
+
"grad_norm": 0.7217579935144164,
|
| 994 |
+
"learning_rate": 1.763908403088534e-05,
|
| 995 |
+
"loss": 0.5108,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.9073482428115016,
|
| 1000 |
+
"grad_norm": 1.0377962316213807,
|
| 1001 |
+
"learning_rate": 1.759071627118362e-05,
|
| 1002 |
+
"loss": 0.4961,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.9137380191693291,
|
| 1007 |
+
"grad_norm": 0.6423592379266523,
|
| 1008 |
+
"learning_rate": 1.754192582700668e-05,
|
| 1009 |
+
"loss": 0.5061,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.9201277955271565,
|
| 1014 |
+
"grad_norm": 0.7302473302785821,
|
| 1015 |
+
"learning_rate": 1.7492715415221087e-05,
|
| 1016 |
+
"loss": 0.5074,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.9265175718849841,
|
| 1021 |
+
"grad_norm": 0.709358335589859,
|
| 1022 |
+
"learning_rate": 1.7443087776079068e-05,
|
| 1023 |
+
"loss": 0.4867,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.9329073482428115,
|
| 1028 |
+
"grad_norm": 0.6708691396098521,
|
| 1029 |
+
"learning_rate": 1.739304567306588e-05,
|
| 1030 |
+
"loss": 0.4955,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.939297124600639,
|
| 1035 |
+
"grad_norm": 0.7224681216999947,
|
| 1036 |
+
"learning_rate": 1.7342591892745978e-05,
|
| 1037 |
+
"loss": 0.5063,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.9456869009584664,
|
| 1042 |
+
"grad_norm": 0.692060343253805,
|
| 1043 |
+
"learning_rate": 1.72917292446078e-05,
|
| 1044 |
+
"loss": 0.5395,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.952076677316294,
|
| 1049 |
+
"grad_norm": 0.6503466417528021,
|
| 1050 |
+
"learning_rate": 1.7240460560907345e-05,
|
| 1051 |
+
"loss": 0.502,
|
| 1052 |
+
"step": 149
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.9584664536741214,
|
| 1056 |
+
"grad_norm": 0.7852299377720712,
|
| 1057 |
+
"learning_rate": 1.7188788696510477e-05,
|
| 1058 |
+
"loss": 0.4982,
|
| 1059 |
+
"step": 150
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.9648562300319489,
|
| 1063 |
+
"grad_norm": 0.6487201669982385,
|
| 1064 |
+
"learning_rate": 1.7136716528733916e-05,
|
| 1065 |
+
"loss": 0.491,
|
| 1066 |
+
"step": 151
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.9712460063897763,
|
| 1070 |
+
"grad_norm": 0.7162643954228396,
|
| 1071 |
+
"learning_rate": 1.7084246957185036e-05,
|
| 1072 |
+
"loss": 0.4715,
|
| 1073 |
+
"step": 152
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.9776357827476039,
|
| 1077 |
+
"grad_norm": 0.6882308824929978,
|
| 1078 |
+
"learning_rate": 1.703138290360041e-05,
|
| 1079 |
+
"loss": 0.4884,
|
| 1080 |
+
"step": 153
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.9840255591054313,
|
| 1084 |
+
"grad_norm": 0.6558983320574183,
|
| 1085 |
+
"learning_rate": 1.6978127311683103e-05,
|
| 1086 |
+
"loss": 0.5053,
|
| 1087 |
+
"step": 154
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.9904153354632588,
|
| 1091 |
+
"grad_norm": 0.7793396179424056,
|
| 1092 |
+
"learning_rate": 1.6924483146938756e-05,
|
| 1093 |
+
"loss": 0.4891,
|
| 1094 |
+
"step": 155
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.9968051118210862,
|
| 1098 |
+
"grad_norm": 0.6408866926804856,
|
| 1099 |
+
"learning_rate": 1.6870453396510456e-05,
|
| 1100 |
+
"loss": 0.5253,
|
| 1101 |
+
"step": 156
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 1.0031948881789137,
|
| 1105 |
+
"grad_norm": 1.219315523607184,
|
| 1106 |
+
"learning_rate": 1.681604106901239e-05,
|
| 1107 |
+
"loss": 0.7727,
|
| 1108 |
+
"step": 157
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 1.0095846645367412,
|
| 1112 |
+
"grad_norm": 0.7363761093026954,
|
| 1113 |
+
"learning_rate": 1.676124919436233e-05,
|
| 1114 |
+
"loss": 0.4369,
|
| 1115 |
+
"step": 158
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 1.0159744408945688,
|
| 1119 |
+
"grad_norm": 0.6104584236502094,
|
| 1120 |
+
"learning_rate": 1.6706080823612897e-05,
|
| 1121 |
+
"loss": 0.4074,
|
| 1122 |
+
"step": 159
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 1.0223642172523961,
|
| 1126 |
+
"grad_norm": 0.6688279966321403,
|
| 1127 |
+
"learning_rate": 1.665053902878167e-05,
|
| 1128 |
+
"loss": 0.3875,
|
| 1129 |
+
"step": 160
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.0287539936102237,
|
| 1133 |
+
"grad_norm": 0.7714442502018793,
|
| 1134 |
+
"learning_rate": 1.659462690268013e-05,
|
| 1135 |
+
"loss": 0.4693,
|
| 1136 |
+
"step": 161
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 1.035143769968051,
|
| 1140 |
+
"grad_norm": 0.6581337601062037,
|
| 1141 |
+
"learning_rate": 1.6538347558741424e-05,
|
| 1142 |
+
"loss": 0.4088,
|
| 1143 |
+
"step": 162
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 1.0415335463258786,
|
| 1147 |
+
"grad_norm": 0.8907132608840105,
|
| 1148 |
+
"learning_rate": 1.6481704130847013e-05,
|
| 1149 |
+
"loss": 0.4421,
|
| 1150 |
+
"step": 163
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 1.0479233226837061,
|
| 1154 |
+
"grad_norm": 0.7281123005456749,
|
| 1155 |
+
"learning_rate": 1.642469977315214e-05,
|
| 1156 |
+
"loss": 0.4466,
|
| 1157 |
+
"step": 164
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.0543130990415335,
|
| 1161 |
+
"grad_norm": 0.8713456380104283,
|
| 1162 |
+
"learning_rate": 1.6367337659910223e-05,
|
| 1163 |
+
"loss": 0.4205,
|
| 1164 |
+
"step": 165
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 1.060702875399361,
|
| 1168 |
+
"grad_norm": 0.8221934081375099,
|
| 1169 |
+
"learning_rate": 1.6309620985296075e-05,
|
| 1170 |
+
"loss": 0.4811,
|
| 1171 |
+
"step": 166
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 1.0670926517571886,
|
| 1175 |
+
"grad_norm": 0.6414871893647255,
|
| 1176 |
+
"learning_rate": 1.625155296322805e-05,
|
| 1177 |
+
"loss": 0.3994,
|
| 1178 |
+
"step": 167
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 1.073482428115016,
|
| 1182 |
+
"grad_norm": 0.6020141646779518,
|
| 1183 |
+
"learning_rate": 1.6193136827189067e-05,
|
| 1184 |
+
"loss": 0.3544,
|
| 1185 |
+
"step": 168
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.0798722044728435,
|
| 1189 |
+
"grad_norm": 0.6620341470772692,
|
| 1190 |
+
"learning_rate": 1.6134375830046566e-05,
|
| 1191 |
+
"loss": 0.3865,
|
| 1192 |
+
"step": 169
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 1.0862619808306708,
|
| 1196 |
+
"grad_norm": 0.7529504403287007,
|
| 1197 |
+
"learning_rate": 1.607527324387137e-05,
|
| 1198 |
+
"loss": 0.5138,
|
| 1199 |
+
"step": 170
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 1.0926517571884984,
|
| 1203 |
+
"grad_norm": 0.5746068027715405,
|
| 1204 |
+
"learning_rate": 1.6015832359755483e-05,
|
| 1205 |
+
"loss": 0.4053,
|
| 1206 |
+
"step": 171
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 1.099041533546326,
|
| 1210 |
+
"grad_norm": 0.6423681462846987,
|
| 1211 |
+
"learning_rate": 1.5956056487628832e-05,
|
| 1212 |
+
"loss": 0.4878,
|
| 1213 |
+
"step": 172
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 1.1054313099041533,
|
| 1217 |
+
"grad_norm": 0.6192258722203541,
|
| 1218 |
+
"learning_rate": 1.5895948956074937e-05,
|
| 1219 |
+
"loss": 0.4188,
|
| 1220 |
+
"step": 173
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 1.1118210862619808,
|
| 1224 |
+
"grad_norm": 0.6163929815962566,
|
| 1225 |
+
"learning_rate": 1.5835513112145583e-05,
|
| 1226 |
+
"loss": 0.3854,
|
| 1227 |
+
"step": 174
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 1.1182108626198084,
|
| 1231 |
+
"grad_norm": 0.5697582130826278,
|
| 1232 |
+
"learning_rate": 1.5774752321174428e-05,
|
| 1233 |
+
"loss": 0.4073,
|
| 1234 |
+
"step": 175
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 1.1246006389776357,
|
| 1238 |
+
"grad_norm": 0.6223679982213549,
|
| 1239 |
+
"learning_rate": 1.571366996658962e-05,
|
| 1240 |
+
"loss": 0.4224,
|
| 1241 |
+
"step": 176
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 1.1309904153354633,
|
| 1245 |
+
"grad_norm": 0.6320866995001497,
|
| 1246 |
+
"learning_rate": 1.5652269449725375e-05,
|
| 1247 |
+
"loss": 0.4248,
|
| 1248 |
+
"step": 177
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 1.1373801916932909,
|
| 1252 |
+
"grad_norm": 0.5297458143137096,
|
| 1253 |
+
"learning_rate": 1.5590554189632585e-05,
|
| 1254 |
+
"loss": 0.3748,
|
| 1255 |
+
"step": 178
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 1.1437699680511182,
|
| 1259 |
+
"grad_norm": 0.6358623803264093,
|
| 1260 |
+
"learning_rate": 1.552852762288843e-05,
|
| 1261 |
+
"loss": 0.4747,
|
| 1262 |
+
"step": 179
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 1.1501597444089458,
|
| 1266 |
+
"grad_norm": 0.6278673693951984,
|
| 1267 |
+
"learning_rate": 1.5466193203405017e-05,
|
| 1268 |
+
"loss": 0.4036,
|
| 1269 |
+
"step": 180
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.156549520766773,
|
| 1273 |
+
"grad_norm": 0.6151559404690766,
|
| 1274 |
+
"learning_rate": 1.540355440223704e-05,
|
| 1275 |
+
"loss": 0.4124,
|
| 1276 |
+
"step": 181
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 1.1629392971246006,
|
| 1280 |
+
"grad_norm": 0.5891168526046718,
|
| 1281 |
+
"learning_rate": 1.534061470738852e-05,
|
| 1282 |
+
"loss": 0.4637,
|
| 1283 |
+
"step": 182
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 1.1693290734824282,
|
| 1287 |
+
"grad_norm": 0.6184989510741438,
|
| 1288 |
+
"learning_rate": 1.527737762361855e-05,
|
| 1289 |
+
"loss": 0.4161,
|
| 1290 |
+
"step": 183
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 1.1757188498402555,
|
| 1294 |
+
"grad_norm": 0.6419175983144096,
|
| 1295 |
+
"learning_rate": 1.5213846672246139e-05,
|
| 1296 |
+
"loss": 0.4533,
|
| 1297 |
+
"step": 184
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 1.182108626198083,
|
| 1301 |
+
"grad_norm": 0.5120065057835093,
|
| 1302 |
+
"learning_rate": 1.5150025390954153e-05,
|
| 1303 |
+
"loss": 0.375,
|
| 1304 |
+
"step": 185
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 1.1884984025559104,
|
| 1308 |
+
"grad_norm": 0.698299656514935,
|
| 1309 |
+
"learning_rate": 1.5085917333592299e-05,
|
| 1310 |
+
"loss": 0.4193,
|
| 1311 |
+
"step": 186
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 1.194888178913738,
|
| 1315 |
+
"grad_norm": 0.6532253196374253,
|
| 1316 |
+
"learning_rate": 1.5021526069979232e-05,
|
| 1317 |
+
"loss": 0.4596,
|
| 1318 |
+
"step": 187
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 1.2012779552715656,
|
| 1322 |
+
"grad_norm": 0.6028992706390495,
|
| 1323 |
+
"learning_rate": 1.4956855185703787e-05,
|
| 1324 |
+
"loss": 0.4207,
|
| 1325 |
+
"step": 188
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.207667731629393,
|
| 1329 |
+
"grad_norm": 0.6185875205322425,
|
| 1330 |
+
"learning_rate": 1.48919082819253e-05,
|
| 1331 |
+
"loss": 0.4243,
|
| 1332 |
+
"step": 189
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 1.2140575079872205,
|
| 1336 |
+
"grad_norm": 0.6043057260440954,
|
| 1337 |
+
"learning_rate": 1.4826688975173085e-05,
|
| 1338 |
+
"loss": 0.437,
|
| 1339 |
+
"step": 190
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 1.220447284345048,
|
| 1343 |
+
"grad_norm": 0.6821203725825057,
|
| 1344 |
+
"learning_rate": 1.4761200897145063e-05,
|
| 1345 |
+
"loss": 0.5037,
|
| 1346 |
+
"step": 191
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 1.2268370607028753,
|
| 1350 |
+
"grad_norm": 0.6008298374460067,
|
| 1351 |
+
"learning_rate": 1.4695447694505512e-05,
|
| 1352 |
+
"loss": 0.3661,
|
| 1353 |
+
"step": 192
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 1.233226837060703,
|
| 1357 |
+
"grad_norm": 0.7199503911011816,
|
| 1358 |
+
"learning_rate": 1.4629433028682014e-05,
|
| 1359 |
+
"loss": 0.5043,
|
| 1360 |
+
"step": 193
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 1.2396166134185305,
|
| 1364 |
+
"grad_norm": 0.5180806806501965,
|
| 1365 |
+
"learning_rate": 1.456316057566158e-05,
|
| 1366 |
+
"loss": 0.3819,
|
| 1367 |
+
"step": 194
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 1.2460063897763578,
|
| 1371 |
+
"grad_norm": 0.6928136290488852,
|
| 1372 |
+
"learning_rate": 1.4496634025785938e-05,
|
| 1373 |
+
"loss": 0.4263,
|
| 1374 |
+
"step": 195
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 1.2523961661341854,
|
| 1378 |
+
"grad_norm": 0.5665537937081578,
|
| 1379 |
+
"learning_rate": 1.4429857083546054e-05,
|
| 1380 |
+
"loss": 0.4844,
|
| 1381 |
+
"step": 196
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 1.2587859424920127,
|
| 1385 |
+
"grad_norm": 0.5563376996661965,
|
| 1386 |
+
"learning_rate": 1.4362833467375839e-05,
|
| 1387 |
+
"loss": 0.4156,
|
| 1388 |
+
"step": 197
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 1.2651757188498403,
|
| 1392 |
+
"grad_norm": 0.5377783142222045,
|
| 1393 |
+
"learning_rate": 1.429556690944509e-05,
|
| 1394 |
+
"loss": 0.4025,
|
| 1395 |
+
"step": 198
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 1.2715654952076676,
|
| 1399 |
+
"grad_norm": 0.5413290657480134,
|
| 1400 |
+
"learning_rate": 1.4228061155451671e-05,
|
| 1401 |
+
"loss": 0.4066,
|
| 1402 |
+
"step": 199
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 1.2779552715654952,
|
| 1406 |
+
"grad_norm": 0.5854137012981868,
|
| 1407 |
+
"learning_rate": 1.4160319964412943e-05,
|
| 1408 |
+
"loss": 0.4631,
|
| 1409 |
+
"step": 200
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 1.2843450479233227,
|
| 1413 |
+
"grad_norm": 0.5549643478979397,
|
| 1414 |
+
"learning_rate": 1.4092347108456425e-05,
|
| 1415 |
+
"loss": 0.4203,
|
| 1416 |
+
"step": 201
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 1.29073482428115,
|
| 1420 |
+
"grad_norm": 0.6090412261860937,
|
| 1421 |
+
"learning_rate": 1.402414637260977e-05,
|
| 1422 |
+
"loss": 0.4818,
|
| 1423 |
+
"step": 202
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 1.2971246006389776,
|
| 1427 |
+
"grad_norm": 0.5907663028777652,
|
| 1428 |
+
"learning_rate": 1.3955721554589979e-05,
|
| 1429 |
+
"loss": 0.4253,
|
| 1430 |
+
"step": 203
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 1.3035143769968052,
|
| 1434 |
+
"grad_norm": 0.6715293474231077,
|
| 1435 |
+
"learning_rate": 1.388707646459193e-05,
|
| 1436 |
+
"loss": 0.418,
|
| 1437 |
+
"step": 204
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 1.3099041533546325,
|
| 1441 |
+
"grad_norm": 0.6297284099203906,
|
| 1442 |
+
"learning_rate": 1.3818214925076226e-05,
|
| 1443 |
+
"loss": 0.4147,
|
| 1444 |
+
"step": 205
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 1.31629392971246,
|
| 1448 |
+
"grad_norm": 0.5667392659435537,
|
| 1449 |
+
"learning_rate": 1.3749140770556322e-05,
|
| 1450 |
+
"loss": 0.4311,
|
| 1451 |
+
"step": 206
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 1.3226837060702876,
|
| 1455 |
+
"grad_norm": 0.6322500298227558,
|
| 1456 |
+
"learning_rate": 1.367985784738501e-05,
|
| 1457 |
+
"loss": 0.4203,
|
| 1458 |
+
"step": 207
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 1.329073482428115,
|
| 1462 |
+
"grad_norm": 0.6001231519749656,
|
| 1463 |
+
"learning_rate": 1.361037001354025e-05,
|
| 1464 |
+
"loss": 0.4476,
|
| 1465 |
+
"step": 208
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 1.3354632587859425,
|
| 1469 |
+
"grad_norm": 0.5824816964719087,
|
| 1470 |
+
"learning_rate": 1.3540681138410317e-05,
|
| 1471 |
+
"loss": 0.3966,
|
| 1472 |
+
"step": 209
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 1.34185303514377,
|
| 1476 |
+
"grad_norm": 0.6931574895039062,
|
| 1477 |
+
"learning_rate": 1.3470795102578358e-05,
|
| 1478 |
+
"loss": 0.5033,
|
| 1479 |
+
"step": 210
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 1.3482428115015974,
|
| 1483 |
+
"grad_norm": 0.5416798455387101,
|
| 1484 |
+
"learning_rate": 1.3400715797606293e-05,
|
| 1485 |
+
"loss": 0.4008,
|
| 1486 |
+
"step": 211
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 1.354632587859425,
|
| 1490 |
+
"grad_norm": 0.6524420733651487,
|
| 1491 |
+
"learning_rate": 1.3330447125818115e-05,
|
| 1492 |
+
"loss": 0.4436,
|
| 1493 |
+
"step": 212
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 1.3610223642172525,
|
| 1497 |
+
"grad_norm": 0.6109732592249346,
|
| 1498 |
+
"learning_rate": 1.3259993000082599e-05,
|
| 1499 |
+
"loss": 0.4139,
|
| 1500 |
+
"step": 213
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 1.3674121405750799,
|
| 1504 |
+
"grad_norm": 0.6089156914272807,
|
| 1505 |
+
"learning_rate": 1.3189357343595405e-05,
|
| 1506 |
+
"loss": 0.4287,
|
| 1507 |
+
"step": 214
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 1.3738019169329074,
|
| 1511 |
+
"grad_norm": 0.5100478253771064,
|
| 1512 |
+
"learning_rate": 1.3118544089660635e-05,
|
| 1513 |
+
"loss": 0.3773,
|
| 1514 |
+
"step": 215
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 1.3801916932907348,
|
| 1518 |
+
"grad_norm": 0.665636694875197,
|
| 1519 |
+
"learning_rate": 1.3047557181471784e-05,
|
| 1520 |
+
"loss": 0.3922,
|
| 1521 |
+
"step": 216
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 1.3865814696485623,
|
| 1525 |
+
"grad_norm": 0.6421315985345839,
|
| 1526 |
+
"learning_rate": 1.2976400571892189e-05,
|
| 1527 |
+
"loss": 0.4432,
|
| 1528 |
+
"step": 217
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 1.3929712460063897,
|
| 1532 |
+
"grad_norm": 0.5630313538184247,
|
| 1533 |
+
"learning_rate": 1.2905078223234907e-05,
|
| 1534 |
+
"loss": 0.4191,
|
| 1535 |
+
"step": 218
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 1.3993610223642172,
|
| 1539 |
+
"grad_norm": 0.6745179299688657,
|
| 1540 |
+
"learning_rate": 1.2833594107042078e-05,
|
| 1541 |
+
"loss": 0.4333,
|
| 1542 |
+
"step": 219
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 1.4057507987220448,
|
| 1546 |
+
"grad_norm": 0.5454374317298349,
|
| 1547 |
+
"learning_rate": 1.2761952203863759e-05,
|
| 1548 |
+
"loss": 0.4277,
|
| 1549 |
+
"step": 220
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 1.4121405750798721,
|
| 1553 |
+
"grad_norm": 0.5789898470817271,
|
| 1554 |
+
"learning_rate": 1.2690156503036288e-05,
|
| 1555 |
+
"loss": 0.4036,
|
| 1556 |
+
"step": 221
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 1.4185303514376997,
|
| 1560 |
+
"grad_norm": 0.5949332555607629,
|
| 1561 |
+
"learning_rate": 1.2618211002460135e-05,
|
| 1562 |
+
"loss": 0.4785,
|
| 1563 |
+
"step": 222
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 1.4249201277955272,
|
| 1567 |
+
"grad_norm": 0.5587473061257787,
|
| 1568 |
+
"learning_rate": 1.2546119708377273e-05,
|
| 1569 |
+
"loss": 0.4109,
|
| 1570 |
+
"step": 223
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 1.4313099041533546,
|
| 1574 |
+
"grad_norm": 0.5092986860891325,
|
| 1575 |
+
"learning_rate": 1.2473886635148109e-05,
|
| 1576 |
+
"loss": 0.4375,
|
| 1577 |
+
"step": 224
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 1.4376996805111821,
|
| 1581 |
+
"grad_norm": 0.49324268916930714,
|
| 1582 |
+
"learning_rate": 1.2401515805027924e-05,
|
| 1583 |
+
"loss": 0.4339,
|
| 1584 |
+
"step": 225
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 1.4440894568690097,
|
| 1588 |
+
"grad_norm": 0.521973180886398,
|
| 1589 |
+
"learning_rate": 1.2329011247942915e-05,
|
| 1590 |
+
"loss": 0.3929,
|
| 1591 |
+
"step": 226
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 1.450479233226837,
|
| 1595 |
+
"grad_norm": 0.49449177011483986,
|
| 1596 |
+
"learning_rate": 1.2256377001265785e-05,
|
| 1597 |
+
"loss": 0.3688,
|
| 1598 |
+
"step": 227
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 1.4568690095846646,
|
| 1602 |
+
"grad_norm": 0.688803254610615,
|
| 1603 |
+
"learning_rate": 1.2183617109590925e-05,
|
| 1604 |
+
"loss": 0.5054,
|
| 1605 |
+
"step": 228
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 1.4632587859424921,
|
| 1609 |
+
"grad_norm": 0.5222053229962778,
|
| 1610 |
+
"learning_rate": 1.2110735624509184e-05,
|
| 1611 |
+
"loss": 0.3946,
|
| 1612 |
+
"step": 229
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 1.4696485623003195,
|
| 1616 |
+
"grad_norm": 0.5032950143354372,
|
| 1617 |
+
"learning_rate": 1.2037736604382279e-05,
|
| 1618 |
+
"loss": 0.4158,
|
| 1619 |
+
"step": 230
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 1.476038338658147,
|
| 1623 |
+
"grad_norm": 0.5739740428574489,
|
| 1624 |
+
"learning_rate": 1.1964624114116784e-05,
|
| 1625 |
+
"loss": 0.3794,
|
| 1626 |
+
"step": 231
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 1.4824281150159744,
|
| 1630 |
+
"grad_norm": 0.6710884805647371,
|
| 1631 |
+
"learning_rate": 1.1891402224937805e-05,
|
| 1632 |
+
"loss": 0.466,
|
| 1633 |
+
"step": 232
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 1.488817891373802,
|
| 1637 |
+
"grad_norm": 0.4582879331386117,
|
| 1638 |
+
"learning_rate": 1.1818075014162243e-05,
|
| 1639 |
+
"loss": 0.3585,
|
| 1640 |
+
"step": 233
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 1.4952076677316293,
|
| 1644 |
+
"grad_norm": 0.5448073298830566,
|
| 1645 |
+
"learning_rate": 1.1744646564971777e-05,
|
| 1646 |
+
"loss": 0.4238,
|
| 1647 |
+
"step": 234
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 1.5015974440894568,
|
| 1651 |
+
"grad_norm": 0.5760693930458392,
|
| 1652 |
+
"learning_rate": 1.1671120966185486e-05,
|
| 1653 |
+
"loss": 0.4324,
|
| 1654 |
+
"step": 235
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 1.5079872204472844,
|
| 1658 |
+
"grad_norm": 0.49993740420542576,
|
| 1659 |
+
"learning_rate": 1.159750231203217e-05,
|
| 1660 |
+
"loss": 0.4078,
|
| 1661 |
+
"step": 236
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 1.5143769968051117,
|
| 1665 |
+
"grad_norm": 0.563168928495261,
|
| 1666 |
+
"learning_rate": 1.1523794701922351e-05,
|
| 1667 |
+
"loss": 0.4351,
|
| 1668 |
+
"step": 237
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 1.5207667731629393,
|
| 1672 |
+
"grad_norm": 0.5313983639628916,
|
| 1673 |
+
"learning_rate": 1.145000224022002e-05,
|
| 1674 |
+
"loss": 0.3571,
|
| 1675 |
+
"step": 238
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 1.5271565495207668,
|
| 1679 |
+
"grad_norm": 0.501524364831029,
|
| 1680 |
+
"learning_rate": 1.1376129036014073e-05,
|
| 1681 |
+
"loss": 0.4304,
|
| 1682 |
+
"step": 239
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 1.5335463258785942,
|
| 1686 |
+
"grad_norm": 0.44709921144798975,
|
| 1687 |
+
"learning_rate": 1.1302179202889505e-05,
|
| 1688 |
+
"loss": 0.3948,
|
| 1689 |
+
"step": 240
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 1.5399361022364217,
|
| 1693 |
+
"grad_norm": 0.6024736966395187,
|
| 1694 |
+
"learning_rate": 1.1228156858698344e-05,
|
| 1695 |
+
"loss": 0.5055,
|
| 1696 |
+
"step": 241
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 1.5463258785942493,
|
| 1700 |
+
"grad_norm": 0.5039190418971187,
|
| 1701 |
+
"learning_rate": 1.1154066125330358e-05,
|
| 1702 |
+
"loss": 0.3853,
|
| 1703 |
+
"step": 242
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 1.5527156549520766,
|
| 1707 |
+
"grad_norm": 0.5082416278400913,
|
| 1708 |
+
"learning_rate": 1.107991112848352e-05,
|
| 1709 |
+
"loss": 0.365,
|
| 1710 |
+
"step": 243
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 1.5591054313099042,
|
| 1714 |
+
"grad_norm": 0.571424017024242,
|
| 1715 |
+
"learning_rate": 1.100569599743428e-05,
|
| 1716 |
+
"loss": 0.4157,
|
| 1717 |
+
"step": 244
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 1.5654952076677318,
|
| 1721 |
+
"grad_norm": 0.5185521716853748,
|
| 1722 |
+
"learning_rate": 1.0931424864807624e-05,
|
| 1723 |
+
"loss": 0.4278,
|
| 1724 |
+
"step": 245
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 1.571884984025559,
|
| 1728 |
+
"grad_norm": 0.48800280720450917,
|
| 1729 |
+
"learning_rate": 1.0857101866346953e-05,
|
| 1730 |
+
"loss": 0.3713,
|
| 1731 |
+
"step": 246
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 1.5782747603833864,
|
| 1735 |
+
"grad_norm": 0.6095490026665179,
|
| 1736 |
+
"learning_rate": 1.0782731140683786e-05,
|
| 1737 |
+
"loss": 0.4746,
|
| 1738 |
+
"step": 247
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 1.5846645367412142,
|
| 1742 |
+
"grad_norm": 0.44928616025284457,
|
| 1743 |
+
"learning_rate": 1.0708316829107295e-05,
|
| 1744 |
+
"loss": 0.3991,
|
| 1745 |
+
"step": 248
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 1.5910543130990416,
|
| 1749 |
+
"grad_norm": 0.527002704565493,
|
| 1750 |
+
"learning_rate": 1.0633863075333713e-05,
|
| 1751 |
+
"loss": 0.4499,
|
| 1752 |
+
"step": 249
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 1.5974440894568689,
|
| 1756 |
+
"grad_norm": 0.5073694564198865,
|
| 1757 |
+
"learning_rate": 1.0559374025275597e-05,
|
| 1758 |
+
"loss": 0.4451,
|
| 1759 |
+
"step": 250
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 1.6038338658146964,
|
| 1763 |
+
"grad_norm": 0.43991601364268823,
|
| 1764 |
+
"learning_rate": 1.0484853826810942e-05,
|
| 1765 |
+
"loss": 0.3585,
|
| 1766 |
+
"step": 251
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 1.610223642172524,
|
| 1770 |
+
"grad_norm": 0.5793726292991741,
|
| 1771 |
+
"learning_rate": 1.0410306629552231e-05,
|
| 1772 |
+
"loss": 0.4504,
|
| 1773 |
+
"step": 252
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 1.6166134185303513,
|
| 1777 |
+
"grad_norm": 0.5109980782065752,
|
| 1778 |
+
"learning_rate": 1.0335736584615357e-05,
|
| 1779 |
+
"loss": 0.4323,
|
| 1780 |
+
"step": 253
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 1.623003194888179,
|
| 1784 |
+
"grad_norm": 0.5541438519921948,
|
| 1785 |
+
"learning_rate": 1.0261147844388472e-05,
|
| 1786 |
+
"loss": 0.4108,
|
| 1787 |
+
"step": 254
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 1.6293929712460065,
|
| 1791 |
+
"grad_norm": 0.49521914364363934,
|
| 1792 |
+
"learning_rate": 1.0186544562300766e-05,
|
| 1793 |
+
"loss": 0.3646,
|
| 1794 |
+
"step": 255
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 1.6357827476038338,
|
| 1798 |
+
"grad_norm": 0.5712895311131073,
|
| 1799 |
+
"learning_rate": 1.011193089259118e-05,
|
| 1800 |
+
"loss": 0.4436,
|
| 1801 |
+
"step": 256
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 1.6421725239616614,
|
| 1805 |
+
"grad_norm": 0.4759908770222787,
|
| 1806 |
+
"learning_rate": 1.0037310990077083e-05,
|
| 1807 |
+
"loss": 0.4114,
|
| 1808 |
+
"step": 257
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 1.648562300319489,
|
| 1812 |
+
"grad_norm": 0.5916396180237442,
|
| 1813 |
+
"learning_rate": 9.962689009922918e-06,
|
| 1814 |
+
"loss": 0.4351,
|
| 1815 |
+
"step": 258
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 1.6549520766773163,
|
| 1819 |
+
"grad_norm": 0.5121135747386429,
|
| 1820 |
+
"learning_rate": 9.888069107408824e-06,
|
| 1821 |
+
"loss": 0.4054,
|
| 1822 |
+
"step": 259
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 1.6613418530351438,
|
| 1826 |
+
"grad_norm": 0.5138320946770819,
|
| 1827 |
+
"learning_rate": 9.813455437699238e-06,
|
| 1828 |
+
"loss": 0.3825,
|
| 1829 |
+
"step": 260
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 1.6677316293929714,
|
| 1833 |
+
"grad_norm": 0.6049983944001385,
|
| 1834 |
+
"learning_rate": 9.738852155611531e-06,
|
| 1835 |
+
"loss": 0.4499,
|
| 1836 |
+
"step": 261
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 1.6741214057507987,
|
| 1840 |
+
"grad_norm": 0.5783031442949135,
|
| 1841 |
+
"learning_rate": 9.664263415384644e-06,
|
| 1842 |
+
"loss": 0.4481,
|
| 1843 |
+
"step": 262
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 1.680511182108626,
|
| 1847 |
+
"grad_norm": 0.5079212196836366,
|
| 1848 |
+
"learning_rate": 9.589693370447769e-06,
|
| 1849 |
+
"loss": 0.4215,
|
| 1850 |
+
"step": 263
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 1.6869009584664538,
|
| 1854 |
+
"grad_norm": 0.5362072676088528,
|
| 1855 |
+
"learning_rate": 9.515146173189058e-06,
|
| 1856 |
+
"loss": 0.382,
|
| 1857 |
+
"step": 264
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 1.6932907348242812,
|
| 1861 |
+
"grad_norm": 0.5939862572487508,
|
| 1862 |
+
"learning_rate": 9.440625974724408e-06,
|
| 1863 |
+
"loss": 0.4359,
|
| 1864 |
+
"step": 265
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 1.6996805111821085,
|
| 1868 |
+
"grad_norm": 0.509251006459368,
|
| 1869 |
+
"learning_rate": 9.366136924666289e-06,
|
| 1870 |
+
"loss": 0.4187,
|
| 1871 |
+
"step": 266
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 1.706070287539936,
|
| 1875 |
+
"grad_norm": 0.5360988896841928,
|
| 1876 |
+
"learning_rate": 9.291683170892712e-06,
|
| 1877 |
+
"loss": 0.4397,
|
| 1878 |
+
"step": 267
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 1.7124600638977636,
|
| 1882 |
+
"grad_norm": 0.4969550304271485,
|
| 1883 |
+
"learning_rate": 9.217268859316219e-06,
|
| 1884 |
+
"loss": 0.4203,
|
| 1885 |
+
"step": 268
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 1.718849840255591,
|
| 1889 |
+
"grad_norm": 0.5191197891519107,
|
| 1890 |
+
"learning_rate": 9.142898133653049e-06,
|
| 1891 |
+
"loss": 0.3609,
|
| 1892 |
+
"step": 269
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 1.7252396166134185,
|
| 1896 |
+
"grad_norm": 0.4714057411588144,
|
| 1897 |
+
"learning_rate": 9.068575135192377e-06,
|
| 1898 |
+
"loss": 0.4465,
|
| 1899 |
+
"step": 270
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 1.731629392971246,
|
| 1903 |
+
"grad_norm": 0.4652015886422851,
|
| 1904 |
+
"learning_rate": 8.994304002565723e-06,
|
| 1905 |
+
"loss": 0.4304,
|
| 1906 |
+
"step": 271
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 1.7380191693290734,
|
| 1910 |
+
"grad_norm": 0.5542538380015932,
|
| 1911 |
+
"learning_rate": 8.920088871516482e-06,
|
| 1912 |
+
"loss": 0.4401,
|
| 1913 |
+
"step": 272
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 1.744408945686901,
|
| 1917 |
+
"grad_norm": 0.5308379584880095,
|
| 1918 |
+
"learning_rate": 8.845933874669645e-06,
|
| 1919 |
+
"loss": 0.4408,
|
| 1920 |
+
"step": 273
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 1.7507987220447285,
|
| 1924 |
+
"grad_norm": 0.5930183810947137,
|
| 1925 |
+
"learning_rate": 8.771843141301659e-06,
|
| 1926 |
+
"loss": 0.4715,
|
| 1927 |
+
"step": 274
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 1.7571884984025559,
|
| 1931 |
+
"grad_norm": 0.5544444716982725,
|
| 1932 |
+
"learning_rate": 8.697820797110499e-06,
|
| 1933 |
+
"loss": 0.4054,
|
| 1934 |
+
"step": 275
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 1.7635782747603834,
|
| 1938 |
+
"grad_norm": 0.5332926586542652,
|
| 1939 |
+
"learning_rate": 8.62387096398593e-06,
|
| 1940 |
+
"loss": 0.4075,
|
| 1941 |
+
"step": 276
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 1.769968051118211,
|
| 1945 |
+
"grad_norm": 0.46783125273604637,
|
| 1946 |
+
"learning_rate": 8.549997759779981e-06,
|
| 1947 |
+
"loss": 0.383,
|
| 1948 |
+
"step": 277
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 1.7763578274760383,
|
| 1952 |
+
"grad_norm": 0.5521530233312871,
|
| 1953 |
+
"learning_rate": 8.47620529807765e-06,
|
| 1954 |
+
"loss": 0.4533,
|
| 1955 |
+
"step": 278
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 1.7827476038338657,
|
| 1959 |
+
"grad_norm": 0.5736693711263415,
|
| 1960 |
+
"learning_rate": 8.402497687967837e-06,
|
| 1961 |
+
"loss": 0.4041,
|
| 1962 |
+
"step": 279
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 1.7891373801916934,
|
| 1966 |
+
"grad_norm": 0.5178503013621817,
|
| 1967 |
+
"learning_rate": 8.328879033814516e-06,
|
| 1968 |
+
"loss": 0.397,
|
| 1969 |
+
"step": 280
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 1.7955271565495208,
|
| 1973 |
+
"grad_norm": 0.5005614658444079,
|
| 1974 |
+
"learning_rate": 8.255353435028228e-06,
|
| 1975 |
+
"loss": 0.432,
|
| 1976 |
+
"step": 281
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 1.8019169329073481,
|
| 1980 |
+
"grad_norm": 0.466589550480172,
|
| 1981 |
+
"learning_rate": 8.181924985837762e-06,
|
| 1982 |
+
"loss": 0.3921,
|
| 1983 |
+
"step": 282
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 1.8083067092651757,
|
| 1987 |
+
"grad_norm": 0.492210299786068,
|
| 1988 |
+
"learning_rate": 8.108597775062198e-06,
|
| 1989 |
+
"loss": 0.3952,
|
| 1990 |
+
"step": 283
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 1.8146964856230032,
|
| 1994 |
+
"grad_norm": 0.5488180113006943,
|
| 1995 |
+
"learning_rate": 8.035375885883217e-06,
|
| 1996 |
+
"loss": 0.4721,
|
| 1997 |
+
"step": 284
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 1.8210862619808306,
|
| 2001 |
+
"grad_norm": 0.46872330736771156,
|
| 2002 |
+
"learning_rate": 7.962263395617724e-06,
|
| 2003 |
+
"loss": 0.4027,
|
| 2004 |
+
"step": 285
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 1.8274760383386581,
|
| 2008 |
+
"grad_norm": 0.5921155853332334,
|
| 2009 |
+
"learning_rate": 7.88926437549082e-06,
|
| 2010 |
+
"loss": 0.4784,
|
| 2011 |
+
"step": 286
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 1.8338658146964857,
|
| 2015 |
+
"grad_norm": 0.44822680013304916,
|
| 2016 |
+
"learning_rate": 7.81638289040908e-06,
|
| 2017 |
+
"loss": 0.3745,
|
| 2018 |
+
"step": 287
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 1.840255591054313,
|
| 2022 |
+
"grad_norm": 0.5070334055575236,
|
| 2023 |
+
"learning_rate": 7.743622998734217e-06,
|
| 2024 |
+
"loss": 0.4493,
|
| 2025 |
+
"step": 288
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 1.8466453674121406,
|
| 2029 |
+
"grad_norm": 0.45829357905039364,
|
| 2030 |
+
"learning_rate": 7.670988752057088e-06,
|
| 2031 |
+
"loss": 0.3906,
|
| 2032 |
+
"step": 289
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 1.8530351437699681,
|
| 2036 |
+
"grad_norm": 0.4401957393457272,
|
| 2037 |
+
"learning_rate": 7.598484194972076e-06,
|
| 2038 |
+
"loss": 0.4351,
|
| 2039 |
+
"step": 290
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 1.8594249201277955,
|
| 2043 |
+
"grad_norm": 0.45173410773764394,
|
| 2044 |
+
"learning_rate": 7.526113364851891e-06,
|
| 2045 |
+
"loss": 0.404,
|
| 2046 |
+
"step": 291
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 1.865814696485623,
|
| 2050 |
+
"grad_norm": 0.48332838338770834,
|
| 2051 |
+
"learning_rate": 7.453880291622726e-06,
|
| 2052 |
+
"loss": 0.39,
|
| 2053 |
+
"step": 292
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 1.8722044728434506,
|
| 2057 |
+
"grad_norm": 0.49775533365807295,
|
| 2058 |
+
"learning_rate": 7.381788997539869e-06,
|
| 2059 |
+
"loss": 0.4263,
|
| 2060 |
+
"step": 293
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 1.878594249201278,
|
| 2064 |
+
"grad_norm": 0.45957391883705206,
|
| 2065 |
+
"learning_rate": 7.309843496963715e-06,
|
| 2066 |
+
"loss": 0.362,
|
| 2067 |
+
"step": 294
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 1.8849840255591053,
|
| 2071 |
+
"grad_norm": 0.5317384668186387,
|
| 2072 |
+
"learning_rate": 7.238047796136247e-06,
|
| 2073 |
+
"loss": 0.4593,
|
| 2074 |
+
"step": 295
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 1.891373801916933,
|
| 2078 |
+
"grad_norm": 0.4766410704227857,
|
| 2079 |
+
"learning_rate": 7.166405892957926e-06,
|
| 2080 |
+
"loss": 0.3991,
|
| 2081 |
+
"step": 296
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 1.8977635782747604,
|
| 2085 |
+
"grad_norm": 0.4468475803781737,
|
| 2086 |
+
"learning_rate": 7.094921776765095e-06,
|
| 2087 |
+
"loss": 0.4128,
|
| 2088 |
+
"step": 297
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 1.9041533546325877,
|
| 2092 |
+
"grad_norm": 0.5191666964746032,
|
| 2093 |
+
"learning_rate": 7.023599428107815e-06,
|
| 2094 |
+
"loss": 0.457,
|
| 2095 |
+
"step": 298
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 1.9105431309904153,
|
| 2099 |
+
"grad_norm": 0.44496722949584133,
|
| 2100 |
+
"learning_rate": 6.95244281852822e-06,
|
| 2101 |
+
"loss": 0.3908,
|
| 2102 |
+
"step": 299
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 1.9169329073482428,
|
| 2106 |
+
"grad_norm": 0.4827518065178973,
|
| 2107 |
+
"learning_rate": 6.881455910339369e-06,
|
| 2108 |
+
"loss": 0.4515,
|
| 2109 |
+
"step": 300
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 1.9233226837060702,
|
| 2113 |
+
"grad_norm": 0.5066972710057507,
|
| 2114 |
+
"learning_rate": 6.8106426564045965e-06,
|
| 2115 |
+
"loss": 0.4084,
|
| 2116 |
+
"step": 301
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 1.9297124600638977,
|
| 2120 |
+
"grad_norm": 0.468517851202735,
|
| 2121 |
+
"learning_rate": 6.740006999917406e-06,
|
| 2122 |
+
"loss": 0.4292,
|
| 2123 |
+
"step": 302
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 1.9361022364217253,
|
| 2127 |
+
"grad_norm": 0.5620319742163961,
|
| 2128 |
+
"learning_rate": 6.669552874181888e-06,
|
| 2129 |
+
"loss": 0.4285,
|
| 2130 |
+
"step": 303
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 1.9424920127795526,
|
| 2134 |
+
"grad_norm": 0.46212229948639855,
|
| 2135 |
+
"learning_rate": 6.599284202393709e-06,
|
| 2136 |
+
"loss": 0.4009,
|
| 2137 |
+
"step": 304
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 1.9488817891373802,
|
| 2141 |
+
"grad_norm": 0.4618831752703247,
|
| 2142 |
+
"learning_rate": 6.529204897421644e-06,
|
| 2143 |
+
"loss": 0.471,
|
| 2144 |
+
"step": 305
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 1.9552715654952078,
|
| 2148 |
+
"grad_norm": 0.4453523115078921,
|
| 2149 |
+
"learning_rate": 6.4593188615896855e-06,
|
| 2150 |
+
"loss": 0.4149,
|
| 2151 |
+
"step": 306
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 1.961661341853035,
|
| 2155 |
+
"grad_norm": 0.5565537423113835,
|
| 2156 |
+
"learning_rate": 6.389629986459756e-06,
|
| 2157 |
+
"loss": 0.4595,
|
| 2158 |
+
"step": 307
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 1.9680511182108626,
|
| 2162 |
+
"grad_norm": 0.4817525299898893,
|
| 2163 |
+
"learning_rate": 6.3201421526149945e-06,
|
| 2164 |
+
"loss": 0.351,
|
| 2165 |
+
"step": 308
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 1.9744408945686902,
|
| 2169 |
+
"grad_norm": 0.49529548437523874,
|
| 2170 |
+
"learning_rate": 6.250859229443684e-06,
|
| 2171 |
+
"loss": 0.4219,
|
| 2172 |
+
"step": 309
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 1.9808306709265175,
|
| 2176 |
+
"grad_norm": 0.4677244453368462,
|
| 2177 |
+
"learning_rate": 6.181785074923778e-06,
|
| 2178 |
+
"loss": 0.4204,
|
| 2179 |
+
"step": 310
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 1.9872204472843449,
|
| 2183 |
+
"grad_norm": 0.5533811435739016,
|
| 2184 |
+
"learning_rate": 6.112923535408074e-06,
|
| 2185 |
+
"loss": 0.4005,
|
| 2186 |
+
"step": 311
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 1.9936102236421727,
|
| 2190 |
+
"grad_norm": 0.6829408529085472,
|
| 2191 |
+
"learning_rate": 6.044278445410025e-06,
|
| 2192 |
+
"loss": 0.457,
|
| 2193 |
+
"step": 312
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 2.0,
|
| 2197 |
+
"grad_norm": 0.7425708478665342,
|
| 2198 |
+
"learning_rate": 5.975853627390233e-06,
|
| 2199 |
+
"loss": 0.5428,
|
| 2200 |
+
"step": 313
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 2.0063897763578273,
|
| 2204 |
+
"grad_norm": 0.6185014849673437,
|
| 2205 |
+
"learning_rate": 5.907652891543576e-06,
|
| 2206 |
+
"loss": 0.3446,
|
| 2207 |
+
"step": 314
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 2.012779552715655,
|
| 2211 |
+
"grad_norm": 0.550249298005834,
|
| 2212 |
+
"learning_rate": 5.839680035587061e-06,
|
| 2213 |
+
"loss": 0.3567,
|
| 2214 |
+
"step": 315
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 2.0191693290734825,
|
| 2218 |
+
"grad_norm": 0.6406389855268264,
|
| 2219 |
+
"learning_rate": 5.771938844548331e-06,
|
| 2220 |
+
"loss": 0.3439,
|
| 2221 |
+
"step": 316
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 2.02555910543131,
|
| 2225 |
+
"grad_norm": 0.7498793828860592,
|
| 2226 |
+
"learning_rate": 5.704433090554912e-06,
|
| 2227 |
+
"loss": 0.3525,
|
| 2228 |
+
"step": 317
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 2.0319488817891376,
|
| 2232 |
+
"grad_norm": 0.6058522485872244,
|
| 2233 |
+
"learning_rate": 5.6371665326241635e-06,
|
| 2234 |
+
"loss": 0.3493,
|
| 2235 |
+
"step": 318
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 2.038338658146965,
|
| 2239 |
+
"grad_norm": 0.4684273692024481,
|
| 2240 |
+
"learning_rate": 5.570142916453944e-06,
|
| 2241 |
+
"loss": 0.3529,
|
| 2242 |
+
"step": 319
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 2.0447284345047922,
|
| 2246 |
+
"grad_norm": 0.5736798457088337,
|
| 2247 |
+
"learning_rate": 5.503365974214059e-06,
|
| 2248 |
+
"loss": 0.3601,
|
| 2249 |
+
"step": 320
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 2.0511182108626196,
|
| 2253 |
+
"grad_norm": 0.6933501821794038,
|
| 2254 |
+
"learning_rate": 5.436839424338426e-06,
|
| 2255 |
+
"loss": 0.3495,
|
| 2256 |
+
"step": 321
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 2.0575079872204474,
|
| 2260 |
+
"grad_norm": 0.5220030865474038,
|
| 2261 |
+
"learning_rate": 5.37056697131799e-06,
|
| 2262 |
+
"loss": 0.3313,
|
| 2263 |
+
"step": 322
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 2.0638977635782747,
|
| 2267 |
+
"grad_norm": 0.48932445764444477,
|
| 2268 |
+
"learning_rate": 5.304552305494493e-06,
|
| 2269 |
+
"loss": 0.3429,
|
| 2270 |
+
"step": 323
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 2.070287539936102,
|
| 2274 |
+
"grad_norm": 0.5367328609042773,
|
| 2275 |
+
"learning_rate": 5.238799102854941e-06,
|
| 2276 |
+
"loss": 0.3631,
|
| 2277 |
+
"step": 324
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 2.07667731629393,
|
| 2281 |
+
"grad_norm": 0.4753482664474989,
|
| 2282 |
+
"learning_rate": 5.173311024826916e-06,
|
| 2283 |
+
"loss": 0.3164,
|
| 2284 |
+
"step": 325
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 2.083067092651757,
|
| 2288 |
+
"grad_norm": 0.5857488280714297,
|
| 2289 |
+
"learning_rate": 5.108091718074706e-06,
|
| 2290 |
+
"loss": 0.3684,
|
| 2291 |
+
"step": 326
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 2.0894568690095845,
|
| 2295 |
+
"grad_norm": 0.5577030340771072,
|
| 2296 |
+
"learning_rate": 5.043144814296214e-06,
|
| 2297 |
+
"loss": 0.3393,
|
| 2298 |
+
"step": 327
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 2.0958466453674123,
|
| 2302 |
+
"grad_norm": 0.5001282088257198,
|
| 2303 |
+
"learning_rate": 4.9784739300207675e-06,
|
| 2304 |
+
"loss": 0.3289,
|
| 2305 |
+
"step": 328
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 2.1022364217252396,
|
| 2309 |
+
"grad_norm": 0.49155760192395415,
|
| 2310 |
+
"learning_rate": 4.914082666407705e-06,
|
| 2311 |
+
"loss": 0.3126,
|
| 2312 |
+
"step": 329
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 2.108626198083067,
|
| 2316 |
+
"grad_norm": 0.4721435423436379,
|
| 2317 |
+
"learning_rate": 4.849974609045849e-06,
|
| 2318 |
+
"loss": 0.3412,
|
| 2319 |
+
"step": 330
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 2.1150159744408947,
|
| 2323 |
+
"grad_norm": 0.4887160051279591,
|
| 2324 |
+
"learning_rate": 4.786153327753865e-06,
|
| 2325 |
+
"loss": 0.344,
|
| 2326 |
+
"step": 331
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 2.121405750798722,
|
| 2330 |
+
"grad_norm": 0.4325584192349116,
|
| 2331 |
+
"learning_rate": 4.722622376381455e-06,
|
| 2332 |
+
"loss": 0.3316,
|
| 2333 |
+
"step": 332
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 2.1277955271565494,
|
| 2337 |
+
"grad_norm": 0.4294996718579918,
|
| 2338 |
+
"learning_rate": 4.659385292611479e-06,
|
| 2339 |
+
"loss": 0.3339,
|
| 2340 |
+
"step": 333
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 2.134185303514377,
|
| 2344 |
+
"grad_norm": 0.41116978589443015,
|
| 2345 |
+
"learning_rate": 4.59644559776296e-06,
|
| 2346 |
+
"loss": 0.3325,
|
| 2347 |
+
"step": 334
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 2.1405750798722045,
|
| 2351 |
+
"grad_norm": 0.4411913227153377,
|
| 2352 |
+
"learning_rate": 4.533806796594989e-06,
|
| 2353 |
+
"loss": 0.342,
|
| 2354 |
+
"step": 335
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 2.146964856230032,
|
| 2358 |
+
"grad_norm": 0.44530187962960605,
|
| 2359 |
+
"learning_rate": 4.471472377111574e-06,
|
| 2360 |
+
"loss": 0.364,
|
| 2361 |
+
"step": 336
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 2.1533546325878596,
|
| 2365 |
+
"grad_norm": 0.4681980949823063,
|
| 2366 |
+
"learning_rate": 4.409445810367421e-06,
|
| 2367 |
+
"loss": 0.3749,
|
| 2368 |
+
"step": 337
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 2.159744408945687,
|
| 2372 |
+
"grad_norm": 0.4082359456108807,
|
| 2373 |
+
"learning_rate": 4.347730550274628e-06,
|
| 2374 |
+
"loss": 0.3586,
|
| 2375 |
+
"step": 338
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 2.1661341853035143,
|
| 2379 |
+
"grad_norm": 0.41583681737409806,
|
| 2380 |
+
"learning_rate": 4.286330033410384e-06,
|
| 2381 |
+
"loss": 0.3047,
|
| 2382 |
+
"step": 339
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 2.1725239616613417,
|
| 2386 |
+
"grad_norm": 0.4540111795301057,
|
| 2387 |
+
"learning_rate": 4.2252476788255735e-06,
|
| 2388 |
+
"loss": 0.3254,
|
| 2389 |
+
"step": 340
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 2.1789137380191694,
|
| 2393 |
+
"grad_norm": 0.45433063555043707,
|
| 2394 |
+
"learning_rate": 4.164486887854424e-06,
|
| 2395 |
+
"loss": 0.3459,
|
| 2396 |
+
"step": 341
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 2.1853035143769968,
|
| 2400 |
+
"grad_norm": 0.43892759194821435,
|
| 2401 |
+
"learning_rate": 4.104051043925068e-06,
|
| 2402 |
+
"loss": 0.354,
|
| 2403 |
+
"step": 342
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 2.191693290734824,
|
| 2407 |
+
"grad_norm": 0.43626351327017776,
|
| 2408 |
+
"learning_rate": 4.043943512371171e-06,
|
| 2409 |
+
"loss": 0.3484,
|
| 2410 |
+
"step": 343
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 2.198083067092652,
|
| 2414 |
+
"grad_norm": 0.41866320314755173,
|
| 2415 |
+
"learning_rate": 3.984167640244518e-06,
|
| 2416 |
+
"loss": 0.3595,
|
| 2417 |
+
"step": 344
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 2.2044728434504792,
|
| 2421 |
+
"grad_norm": 0.43171890711936267,
|
| 2422 |
+
"learning_rate": 3.924726756128632e-06,
|
| 2423 |
+
"loss": 0.3683,
|
| 2424 |
+
"step": 345
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 2.2108626198083066,
|
| 2428 |
+
"grad_norm": 0.39657734240201464,
|
| 2429 |
+
"learning_rate": 3.8656241699534396e-06,
|
| 2430 |
+
"loss": 0.3319,
|
| 2431 |
+
"step": 346
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 2.2172523961661343,
|
| 2435 |
+
"grad_norm": 0.4390716578058822,
|
| 2436 |
+
"learning_rate": 3.8068631728109364e-06,
|
| 2437 |
+
"loss": 0.3718,
|
| 2438 |
+
"step": 347
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 2.2236421725239617,
|
| 2442 |
+
"grad_norm": 0.43526087538819297,
|
| 2443 |
+
"learning_rate": 3.7484470367719493e-06,
|
| 2444 |
+
"loss": 0.3586,
|
| 2445 |
+
"step": 348
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 2.230031948881789,
|
| 2449 |
+
"grad_norm": 0.41150940940323066,
|
| 2450 |
+
"learning_rate": 3.6903790147039286e-06,
|
| 2451 |
+
"loss": 0.3219,
|
| 2452 |
+
"step": 349
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 2.236421725239617,
|
| 2456 |
+
"grad_norm": 0.4434399201886998,
|
| 2457 |
+
"learning_rate": 3.6326623400897797e-06,
|
| 2458 |
+
"loss": 0.3496,
|
| 2459 |
+
"step": 350
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 2.242811501597444,
|
| 2463 |
+
"grad_norm": 0.4226836887457401,
|
| 2464 |
+
"learning_rate": 3.575300226847863e-06,
|
| 2465 |
+
"loss": 0.3369,
|
| 2466 |
+
"step": 351
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 2.2492012779552715,
|
| 2470 |
+
"grad_norm": 0.449011167578069,
|
| 2471 |
+
"learning_rate": 3.5182958691529945e-06,
|
| 2472 |
+
"loss": 0.3456,
|
| 2473 |
+
"step": 352
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 2.255591054313099,
|
| 2477 |
+
"grad_norm": 0.40337825402760535,
|
| 2478 |
+
"learning_rate": 3.4616524412585797e-06,
|
| 2479 |
+
"loss": 0.3569,
|
| 2480 |
+
"step": 353
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 2.2619808306709266,
|
| 2484 |
+
"grad_norm": 0.4417946658839781,
|
| 2485 |
+
"learning_rate": 3.405373097319875e-06,
|
| 2486 |
+
"loss": 0.2965,
|
| 2487 |
+
"step": 354
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 2.268370607028754,
|
| 2491 |
+
"grad_norm": 0.4226400522886019,
|
| 2492 |
+
"learning_rate": 3.3494609712183323e-06,
|
| 2493 |
+
"loss": 0.3143,
|
| 2494 |
+
"step": 355
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 2.2747603833865817,
|
| 2498 |
+
"grad_norm": 0.42990286288068097,
|
| 2499 |
+
"learning_rate": 3.2939191763871047e-06,
|
| 2500 |
+
"loss": 0.325,
|
| 2501 |
+
"step": 356
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 2.281150159744409,
|
| 2505 |
+
"grad_norm": 0.48668783932063814,
|
| 2506 |
+
"learning_rate": 3.2387508056376726e-06,
|
| 2507 |
+
"loss": 0.3393,
|
| 2508 |
+
"step": 357
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 2.2875399361022364,
|
| 2512 |
+
"grad_norm": 0.45993768274586794,
|
| 2513 |
+
"learning_rate": 3.183958930987612e-06,
|
| 2514 |
+
"loss": 0.3271,
|
| 2515 |
+
"step": 358
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 2.2939297124600637,
|
| 2519 |
+
"grad_norm": 0.3696554039297162,
|
| 2520 |
+
"learning_rate": 3.1295466034895482e-06,
|
| 2521 |
+
"loss": 0.356,
|
| 2522 |
+
"step": 359
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 2.3003194888178915,
|
| 2526 |
+
"grad_norm": 0.41320713175521795,
|
| 2527 |
+
"learning_rate": 3.0755168530612444e-06,
|
| 2528 |
+
"loss": 0.321,
|
| 2529 |
+
"step": 360
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 2.306709265175719,
|
| 2533 |
+
"grad_norm": 0.42742117582586886,
|
| 2534 |
+
"learning_rate": 3.021872688316896e-06,
|
| 2535 |
+
"loss": 0.3161,
|
| 2536 |
+
"step": 361
|
| 2537 |
+
},
|
| 2538 |
+
{
|
| 2539 |
+
"epoch": 2.313099041533546,
|
| 2540 |
+
"grad_norm": 0.41256761998572333,
|
| 2541 |
+
"learning_rate": 2.968617096399592e-06,
|
| 2542 |
+
"loss": 0.3095,
|
| 2543 |
+
"step": 362
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 2.319488817891374,
|
| 2547 |
+
"grad_norm": 0.418828546634445,
|
| 2548 |
+
"learning_rate": 2.9157530428149683e-06,
|
| 2549 |
+
"loss": 0.3434,
|
| 2550 |
+
"step": 363
|
| 2551 |
+
},
|
| 2552 |
+
{
|
| 2553 |
+
"epoch": 2.3258785942492013,
|
| 2554 |
+
"grad_norm": 0.40161025260603606,
|
| 2555 |
+
"learning_rate": 2.8632834712660882e-06,
|
| 2556 |
+
"loss": 0.3203,
|
| 2557 |
+
"step": 364
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 2.3322683706070286,
|
| 2561 |
+
"grad_norm": 0.4182135730630846,
|
| 2562 |
+
"learning_rate": 2.8112113034895273e-06,
|
| 2563 |
+
"loss": 0.3135,
|
| 2564 |
+
"step": 365
|
| 2565 |
+
},
|
| 2566 |
+
{
|
| 2567 |
+
"epoch": 2.3386581469648564,
|
| 2568 |
+
"grad_norm": 0.40613861239190874,
|
| 2569 |
+
"learning_rate": 2.7595394390926557e-06,
|
| 2570 |
+
"loss": 0.3643,
|
| 2571 |
+
"step": 366
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 2.3450479233226837,
|
| 2575 |
+
"grad_norm": 0.41302826534326115,
|
| 2576 |
+
"learning_rate": 2.708270755392207e-06,
|
| 2577 |
+
"loss": 0.3424,
|
| 2578 |
+
"step": 367
|
| 2579 |
+
},
|
| 2580 |
+
{
|
| 2581 |
+
"epoch": 2.351437699680511,
|
| 2582 |
+
"grad_norm": 0.3930172226452873,
|
| 2583 |
+
"learning_rate": 2.657408107254027e-06,
|
| 2584 |
+
"loss": 0.3429,
|
| 2585 |
+
"step": 368
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 2.357827476038339,
|
| 2589 |
+
"grad_norm": 0.41867946397201244,
|
| 2590 |
+
"learning_rate": 2.60695432693412e-06,
|
| 2591 |
+
"loss": 0.3657,
|
| 2592 |
+
"step": 369
|
| 2593 |
+
},
|
| 2594 |
+
{
|
| 2595 |
+
"epoch": 2.364217252396166,
|
| 2596 |
+
"grad_norm": 0.3952956485859315,
|
| 2597 |
+
"learning_rate": 2.5569122239209366e-06,
|
| 2598 |
+
"loss": 0.2999,
|
| 2599 |
+
"step": 370
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 2.3706070287539935,
|
| 2603 |
+
"grad_norm": 0.38547686501477857,
|
| 2604 |
+
"learning_rate": 2.507284584778913e-06,
|
| 2605 |
+
"loss": 0.3229,
|
| 2606 |
+
"step": 371
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 2.376996805111821,
|
| 2610 |
+
"grad_norm": 0.4071024941451391,
|
| 2611 |
+
"learning_rate": 2.4580741729933246e-06,
|
| 2612 |
+
"loss": 0.3398,
|
| 2613 |
+
"step": 372
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 2.3833865814696487,
|
| 2617 |
+
"grad_norm": 0.3975504941590724,
|
| 2618 |
+
"learning_rate": 2.4092837288163807e-06,
|
| 2619 |
+
"loss": 0.3246,
|
| 2620 |
+
"step": 373
|
| 2621 |
+
},
|
| 2622 |
+
{
|
| 2623 |
+
"epoch": 2.389776357827476,
|
| 2624 |
+
"grad_norm": 0.4007814100724813,
|
| 2625 |
+
"learning_rate": 2.3609159691146577e-06,
|
| 2626 |
+
"loss": 0.3834,
|
| 2627 |
+
"step": 374
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 2.3961661341853033,
|
| 2631 |
+
"grad_norm": 0.4132465009460835,
|
| 2632 |
+
"learning_rate": 2.312973587217798e-06,
|
| 2633 |
+
"loss": 0.3552,
|
| 2634 |
+
"step": 375
|
| 2635 |
+
},
|
| 2636 |
+
{
|
| 2637 |
+
"epoch": 2.402555910543131,
|
| 2638 |
+
"grad_norm": 0.38136466401080477,
|
| 2639 |
+
"learning_rate": 2.2654592527685305e-06,
|
| 2640 |
+
"loss": 0.3394,
|
| 2641 |
+
"step": 376
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 2.4089456869009584,
|
| 2645 |
+
"grad_norm": 0.38378352088164336,
|
| 2646 |
+
"learning_rate": 2.2183756115740274e-06,
|
| 2647 |
+
"loss": 0.3417,
|
| 2648 |
+
"step": 377
|
| 2649 |
+
},
|
| 2650 |
+
{
|
| 2651 |
+
"epoch": 2.415335463258786,
|
| 2652 |
+
"grad_norm": 0.42705803790306746,
|
| 2653 |
+
"learning_rate": 2.171725285458559e-06,
|
| 2654 |
+
"loss": 0.3657,
|
| 2655 |
+
"step": 378
|
| 2656 |
+
},
|
| 2657 |
+
{
|
| 2658 |
+
"epoch": 2.4217252396166136,
|
| 2659 |
+
"grad_norm": 0.3893534985584009,
|
| 2660 |
+
"learning_rate": 2.1255108721175066e-06,
|
| 2661 |
+
"loss": 0.3439,
|
| 2662 |
+
"step": 379
|
| 2663 |
+
},
|
| 2664 |
+
{
|
| 2665 |
+
"epoch": 2.428115015974441,
|
| 2666 |
+
"grad_norm": 0.443399810426828,
|
| 2667 |
+
"learning_rate": 2.079734944972717e-06,
|
| 2668 |
+
"loss": 0.3216,
|
| 2669 |
+
"step": 380
|
| 2670 |
+
},
|
| 2671 |
+
{
|
| 2672 |
+
"epoch": 2.4345047923322682,
|
| 2673 |
+
"grad_norm": 0.39874922783339656,
|
| 2674 |
+
"learning_rate": 2.0344000530291875e-06,
|
| 2675 |
+
"loss": 0.3434,
|
| 2676 |
+
"step": 381
|
| 2677 |
+
},
|
| 2678 |
+
{
|
| 2679 |
+
"epoch": 2.440894568690096,
|
| 2680 |
+
"grad_norm": 0.3771297738742276,
|
| 2681 |
+
"learning_rate": 1.9895087207331422e-06,
|
| 2682 |
+
"loss": 0.3409,
|
| 2683 |
+
"step": 382
|
| 2684 |
+
},
|
| 2685 |
+
{
|
| 2686 |
+
"epoch": 2.4472843450479234,
|
| 2687 |
+
"grad_norm": 0.40027082321568275,
|
| 2688 |
+
"learning_rate": 1.945063447831452e-06,
|
| 2689 |
+
"loss": 0.3265,
|
| 2690 |
+
"step": 383
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 2.4536741214057507,
|
| 2694 |
+
"grad_norm": 0.3737581626959035,
|
| 2695 |
+
"learning_rate": 1.9010667092324342e-06,
|
| 2696 |
+
"loss": 0.34,
|
| 2697 |
+
"step": 384
|
| 2698 |
+
},
|
| 2699 |
+
{
|
| 2700 |
+
"epoch": 2.460063897763578,
|
| 2701 |
+
"grad_norm": 0.3841031529537794,
|
| 2702 |
+
"learning_rate": 1.8575209548680472e-06,
|
| 2703 |
+
"loss": 0.3503,
|
| 2704 |
+
"step": 385
|
| 2705 |
+
},
|
| 2706 |
+
{
|
| 2707 |
+
"epoch": 2.466453674121406,
|
| 2708 |
+
"grad_norm": 0.4038855857442773,
|
| 2709 |
+
"learning_rate": 1.814428609557458e-06,
|
| 2710 |
+
"loss": 0.3201,
|
| 2711 |
+
"step": 386
|
| 2712 |
+
},
|
| 2713 |
+
{
|
| 2714 |
+
"epoch": 2.472843450479233,
|
| 2715 |
+
"grad_norm": 0.40823279792933154,
|
| 2716 |
+
"learning_rate": 1.7717920728720284e-06,
|
| 2717 |
+
"loss": 0.3219,
|
| 2718 |
+
"step": 387
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 2.479233226837061,
|
| 2722 |
+
"grad_norm": 0.45571229187170187,
|
| 2723 |
+
"learning_rate": 1.7296137190016916e-06,
|
| 2724 |
+
"loss": 0.3646,
|
| 2725 |
+
"step": 388
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 2.4856230031948883,
|
| 2729 |
+
"grad_norm": 0.3992759518176683,
|
| 2730 |
+
"learning_rate": 1.6878958966227366e-06,
|
| 2731 |
+
"loss": 0.3514,
|
| 2732 |
+
"step": 389
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 2.4920127795527156,
|
| 2736 |
+
"grad_norm": 0.44997582744977993,
|
| 2737 |
+
"learning_rate": 1.646640928767047e-06,
|
| 2738 |
+
"loss": 0.3676,
|
| 2739 |
+
"step": 390
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 2.498402555910543,
|
| 2743 |
+
"grad_norm": 0.4036812441443117,
|
| 2744 |
+
"learning_rate": 1.6058511126927178e-06,
|
| 2745 |
+
"loss": 0.3572,
|
| 2746 |
+
"step": 391
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 2.5047923322683707,
|
| 2750 |
+
"grad_norm": 0.38861999088805715,
|
| 2751 |
+
"learning_rate": 1.5655287197561497e-06,
|
| 2752 |
+
"loss": 0.3176,
|
| 2753 |
+
"step": 392
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 2.511182108626198,
|
| 2757 |
+
"grad_norm": 0.3958987299112533,
|
| 2758 |
+
"learning_rate": 1.5256759952855737e-06,
|
| 2759 |
+
"loss": 0.3411,
|
| 2760 |
+
"step": 393
|
| 2761 |
+
},
|
| 2762 |
+
{
|
| 2763 |
+
"epoch": 2.5175718849840254,
|
| 2764 |
+
"grad_norm": 0.3958900572864119,
|
| 2765 |
+
"learning_rate": 1.4862951584560037e-06,
|
| 2766 |
+
"loss": 0.3391,
|
| 2767 |
+
"step": 394
|
| 2768 |
+
},
|
| 2769 |
+
{
|
| 2770 |
+
"epoch": 2.523961661341853,
|
| 2771 |
+
"grad_norm": 0.3918198479937304,
|
| 2772 |
+
"learning_rate": 1.447388402165686e-06,
|
| 2773 |
+
"loss": 0.3178,
|
| 2774 |
+
"step": 395
|
| 2775 |
+
},
|
| 2776 |
+
{
|
| 2777 |
+
"epoch": 2.5303514376996805,
|
| 2778 |
+
"grad_norm": 0.40756583772176336,
|
| 2779 |
+
"learning_rate": 1.4089578929139635e-06,
|
| 2780 |
+
"loss": 0.3264,
|
| 2781 |
+
"step": 396
|
| 2782 |
+
},
|
| 2783 |
+
{
|
| 2784 |
+
"epoch": 2.536741214057508,
|
| 2785 |
+
"grad_norm": 0.40960058637131896,
|
| 2786 |
+
"learning_rate": 1.371005770680659e-06,
|
| 2787 |
+
"loss": 0.3385,
|
| 2788 |
+
"step": 397
|
| 2789 |
+
},
|
| 2790 |
+
{
|
| 2791 |
+
"epoch": 2.543130990415335,
|
| 2792 |
+
"grad_norm": 0.40903897126869604,
|
| 2793 |
+
"learning_rate": 1.3335341488068997e-06,
|
| 2794 |
+
"loss": 0.3805,
|
| 2795 |
+
"step": 398
|
| 2796 |
+
},
|
| 2797 |
+
{
|
| 2798 |
+
"epoch": 2.549520766773163,
|
| 2799 |
+
"grad_norm": 0.39992597114439177,
|
| 2800 |
+
"learning_rate": 1.2965451138774343e-06,
|
| 2801 |
+
"loss": 0.3196,
|
| 2802 |
+
"step": 399
|
| 2803 |
+
},
|
| 2804 |
+
{
|
| 2805 |
+
"epoch": 2.5559105431309903,
|
| 2806 |
+
"grad_norm": 0.3894861786588525,
|
| 2807 |
+
"learning_rate": 1.2600407256044544e-06,
|
| 2808 |
+
"loss": 0.354,
|
| 2809 |
+
"step": 400
|
| 2810 |
+
},
|
| 2811 |
+
{
|
| 2812 |
+
"epoch": 2.562300319488818,
|
| 2813 |
+
"grad_norm": 0.3773260960595135,
|
| 2814 |
+
"learning_rate": 1.2240230167128863e-06,
|
| 2815 |
+
"loss": 0.3408,
|
| 2816 |
+
"step": 401
|
| 2817 |
+
},
|
| 2818 |
+
{
|
| 2819 |
+
"epoch": 2.5686900958466454,
|
| 2820 |
+
"grad_norm": 0.3916021706010166,
|
| 2821 |
+
"learning_rate": 1.188493992827211e-06,
|
| 2822 |
+
"loss": 0.3141,
|
| 2823 |
+
"step": 402
|
| 2824 |
+
},
|
| 2825 |
+
{
|
| 2826 |
+
"epoch": 2.5750798722044728,
|
| 2827 |
+
"grad_norm": 0.3906836314398566,
|
| 2828 |
+
"learning_rate": 1.1534556323597824e-06,
|
| 2829 |
+
"loss": 0.2924,
|
| 2830 |
+
"step": 403
|
| 2831 |
+
},
|
| 2832 |
+
{
|
| 2833 |
+
"epoch": 2.5814696485623,
|
| 2834 |
+
"grad_norm": 0.4038749879309955,
|
| 2835 |
+
"learning_rate": 1.1189098864006488e-06,
|
| 2836 |
+
"loss": 0.3365,
|
| 2837 |
+
"step": 404
|
| 2838 |
+
},
|
| 2839 |
+
{
|
| 2840 |
+
"epoch": 2.587859424920128,
|
| 2841 |
+
"grad_norm": 0.40279549296487077,
|
| 2842 |
+
"learning_rate": 1.084858678608922e-06,
|
| 2843 |
+
"loss": 0.3239,
|
| 2844 |
+
"step": 405
|
| 2845 |
+
},
|
| 2846 |
+
{
|
| 2847 |
+
"epoch": 2.594249201277955,
|
| 2848 |
+
"grad_norm": 0.36365947820301786,
|
| 2849 |
+
"learning_rate": 1.0513039051056507e-06,
|
| 2850 |
+
"loss": 0.3326,
|
| 2851 |
+
"step": 406
|
| 2852 |
+
},
|
| 2853 |
+
{
|
| 2854 |
+
"epoch": 2.600638977635783,
|
| 2855 |
+
"grad_norm": 0.3696286967249599,
|
| 2856 |
+
"learning_rate": 1.0182474343682346e-06,
|
| 2857 |
+
"loss": 0.3292,
|
| 2858 |
+
"step": 407
|
| 2859 |
+
},
|
| 2860 |
+
{
|
| 2861 |
+
"epoch": 2.6070287539936103,
|
| 2862 |
+
"grad_norm": 0.4175231953214467,
|
| 2863 |
+
"learning_rate": 9.85691107126392e-07,
|
| 2864 |
+
"loss": 0.3744,
|
| 2865 |
+
"step": 408
|
| 2866 |
+
},
|
| 2867 |
+
{
|
| 2868 |
+
"epoch": 2.6134185303514377,
|
| 2869 |
+
"grad_norm": 0.39195370451842787,
|
| 2870 |
+
"learning_rate": 9.536367362596422e-07,
|
| 2871 |
+
"loss": 0.3695,
|
| 2872 |
+
"step": 409
|
| 2873 |
+
},
|
| 2874 |
+
{
|
| 2875 |
+
"epoch": 2.619808306709265,
|
| 2876 |
+
"grad_norm": 0.37605332595306007,
|
| 2877 |
+
"learning_rate": 9.220861066963715e-07,
|
| 2878 |
+
"loss": 0.3418,
|
| 2879 |
+
"step": 410
|
| 2880 |
+
},
|
| 2881 |
+
{
|
| 2882 |
+
"epoch": 2.626198083067093,
|
| 2883 |
+
"grad_norm": 0.3995977702745196,
|
| 2884 |
+
"learning_rate": 8.910409753144344e-07,
|
| 2885 |
+
"loss": 0.3549,
|
| 2886 |
+
"step": 411
|
| 2887 |
+
},
|
| 2888 |
+
{
|
| 2889 |
+
"epoch": 2.63258785942492,
|
| 2890 |
+
"grad_norm": 0.3834229012458761,
|
| 2891 |
+
"learning_rate": 8.605030708433149e-07,
|
| 2892 |
+
"loss": 0.3445,
|
| 2893 |
+
"step": 412
|
| 2894 |
+
},
|
| 2895 |
+
{
|
| 2896 |
+
"epoch": 2.6389776357827475,
|
| 2897 |
+
"grad_norm": 0.37644074285723944,
|
| 2898 |
+
"learning_rate": 8.304740937678835e-07,
|
| 2899 |
+
"loss": 0.3668,
|
| 2900 |
+
"step": 413
|
| 2901 |
+
},
|
| 2902 |
+
{
|
| 2903 |
+
"epoch": 2.6453674121405752,
|
| 2904 |
+
"grad_norm": 0.38149522660404983,
|
| 2905 |
+
"learning_rate": 8.009557162336823e-07,
|
| 2906 |
+
"loss": 0.3286,
|
| 2907 |
+
"step": 414
|
| 2908 |
+
},
|
| 2909 |
+
{
|
| 2910 |
+
"epoch": 2.6517571884984026,
|
| 2911 |
+
"grad_norm": 0.3965348662763524,
|
| 2912 |
+
"learning_rate": 7.719495819538325e-07,
|
| 2913 |
+
"loss": 0.3562,
|
| 2914 |
+
"step": 415
|
| 2915 |
+
},
|
| 2916 |
+
{
|
| 2917 |
+
"epoch": 2.65814696485623,
|
| 2918 |
+
"grad_norm": 0.3740820985387306,
|
| 2919 |
+
"learning_rate": 7.434573061174966e-07,
|
| 2920 |
+
"loss": 0.3171,
|
| 2921 |
+
"step": 416
|
| 2922 |
+
},
|
| 2923 |
+
{
|
| 2924 |
+
"epoch": 2.6645367412140573,
|
| 2925 |
+
"grad_norm": 0.37288133480679564,
|
| 2926 |
+
"learning_rate": 7.154804752999344e-07,
|
| 2927 |
+
"loss": 0.3263,
|
| 2928 |
+
"step": 417
|
| 2929 |
+
},
|
| 2930 |
+
{
|
| 2931 |
+
"epoch": 2.670926517571885,
|
| 2932 |
+
"grad_norm": 0.37023486110236786,
|
| 2933 |
+
"learning_rate": 6.880206473741646e-07,
|
| 2934 |
+
"loss": 0.368,
|
| 2935 |
+
"step": 418
|
| 2936 |
+
},
|
| 2937 |
+
{
|
| 2938 |
+
"epoch": 2.6773162939297124,
|
| 2939 |
+
"grad_norm": 0.3924590139873951,
|
| 2940 |
+
"learning_rate": 6.610793514242075e-07,
|
| 2941 |
+
"loss": 0.3348,
|
| 2942 |
+
"step": 419
|
| 2943 |
+
},
|
| 2944 |
+
{
|
| 2945 |
+
"epoch": 2.68370607028754,
|
| 2946 |
+
"grad_norm": 0.4026773365921225,
|
| 2947 |
+
"learning_rate": 6.346580876599395e-07,
|
| 2948 |
+
"loss": 0.3405,
|
| 2949 |
+
"step": 420
|
| 2950 |
+
},
|
| 2951 |
+
{
|
| 2952 |
+
"epoch": 2.6900958466453675,
|
| 2953 |
+
"grad_norm": 0.3855444929570631,
|
| 2954 |
+
"learning_rate": 6.08758327333564e-07,
|
| 2955 |
+
"loss": 0.3588,
|
| 2956 |
+
"step": 421
|
| 2957 |
+
},
|
| 2958 |
+
{
|
| 2959 |
+
"epoch": 2.696485623003195,
|
| 2960 |
+
"grad_norm": 0.4018291966488895,
|
| 2961 |
+
"learning_rate": 5.833815126576714e-07,
|
| 2962 |
+
"loss": 0.3259,
|
| 2963 |
+
"step": 422
|
| 2964 |
+
},
|
| 2965 |
+
{
|
| 2966 |
+
"epoch": 2.702875399361022,
|
| 2967 |
+
"grad_norm": 0.36389835567175366,
|
| 2968 |
+
"learning_rate": 5.585290567249424e-07,
|
| 2969 |
+
"loss": 0.3514,
|
| 2970 |
+
"step": 423
|
| 2971 |
+
},
|
| 2972 |
+
{
|
| 2973 |
+
"epoch": 2.70926517571885,
|
| 2974 |
+
"grad_norm": 0.40458156951380986,
|
| 2975 |
+
"learning_rate": 5.342023434294552e-07,
|
| 2976 |
+
"loss": 0.337,
|
| 2977 |
+
"step": 424
|
| 2978 |
+
},
|
| 2979 |
+
{
|
| 2980 |
+
"epoch": 2.7156549520766773,
|
| 2981 |
+
"grad_norm": 0.36807317654930927,
|
| 2982 |
+
"learning_rate": 5.104027273896239e-07,
|
| 2983 |
+
"loss": 0.3148,
|
| 2984 |
+
"step": 425
|
| 2985 |
+
},
|
| 2986 |
+
{
|
| 2987 |
+
"epoch": 2.722044728434505,
|
| 2988 |
+
"grad_norm": 0.3689483940462552,
|
| 2989 |
+
"learning_rate": 4.871315338727711e-07,
|
| 2990 |
+
"loss": 0.3181,
|
| 2991 |
+
"step": 426
|
| 2992 |
+
},
|
| 2993 |
+
{
|
| 2994 |
+
"epoch": 2.7284345047923324,
|
| 2995 |
+
"grad_norm": 0.3833457229816993,
|
| 2996 |
+
"learning_rate": 4.6439005872132457e-07,
|
| 2997 |
+
"loss": 0.3368,
|
| 2998 |
+
"step": 427
|
| 2999 |
+
},
|
| 3000 |
+
{
|
| 3001 |
+
"epoch": 2.7348242811501597,
|
| 3002 |
+
"grad_norm": 0.36604943775735366,
|
| 3003 |
+
"learning_rate": 4.421795682806662e-07,
|
| 3004 |
+
"loss": 0.3364,
|
| 3005 |
+
"step": 428
|
| 3006 |
+
},
|
| 3007 |
+
{
|
| 3008 |
+
"epoch": 2.741214057507987,
|
| 3009 |
+
"grad_norm": 0.3773811652537217,
|
| 3010 |
+
"learning_rate": 4.2050129932861394e-07,
|
| 3011 |
+
"loss": 0.3229,
|
| 3012 |
+
"step": 429
|
| 3013 |
+
},
|
| 3014 |
+
{
|
| 3015 |
+
"epoch": 2.747603833865815,
|
| 3016 |
+
"grad_norm": 0.3796116399398149,
|
| 3017 |
+
"learning_rate": 3.9935645900654906e-07,
|
| 3018 |
+
"loss": 0.3633,
|
| 3019 |
+
"step": 430
|
| 3020 |
+
},
|
| 3021 |
+
{
|
| 3022 |
+
"epoch": 2.753993610223642,
|
| 3023 |
+
"grad_norm": 0.37803460451421467,
|
| 3024 |
+
"learning_rate": 3.7874622475220336e-07,
|
| 3025 |
+
"loss": 0.3524,
|
| 3026 |
+
"step": 431
|
| 3027 |
+
},
|
| 3028 |
+
{
|
| 3029 |
+
"epoch": 2.7603833865814695,
|
| 3030 |
+
"grad_norm": 0.36675174735385174,
|
| 3031 |
+
"learning_rate": 3.58671744234087e-07,
|
| 3032 |
+
"loss": 0.365,
|
| 3033 |
+
"step": 432
|
| 3034 |
+
},
|
| 3035 |
+
{
|
| 3036 |
+
"epoch": 2.7667731629392973,
|
| 3037 |
+
"grad_norm": 0.3898919999844523,
|
| 3038 |
+
"learning_rate": 3.3913413528758877e-07,
|
| 3039 |
+
"loss": 0.3323,
|
| 3040 |
+
"step": 433
|
| 3041 |
+
},
|
| 3042 |
+
{
|
| 3043 |
+
"epoch": 2.7731629392971247,
|
| 3044 |
+
"grad_norm": 0.3936657666166714,
|
| 3045 |
+
"learning_rate": 3.2013448585272333e-07,
|
| 3046 |
+
"loss": 0.3337,
|
| 3047 |
+
"step": 434
|
| 3048 |
+
},
|
| 3049 |
+
{
|
| 3050 |
+
"epoch": 2.779552715654952,
|
| 3051 |
+
"grad_norm": 0.38046637386341803,
|
| 3052 |
+
"learning_rate": 3.016738539135566e-07,
|
| 3053 |
+
"loss": 0.344,
|
| 3054 |
+
"step": 435
|
| 3055 |
+
},
|
| 3056 |
+
{
|
| 3057 |
+
"epoch": 2.7859424920127793,
|
| 3058 |
+
"grad_norm": 0.3770525251793597,
|
| 3059 |
+
"learning_rate": 2.837532674392862e-07,
|
| 3060 |
+
"loss": 0.374,
|
| 3061 |
+
"step": 436
|
| 3062 |
+
},
|
| 3063 |
+
{
|
| 3064 |
+
"epoch": 2.792332268370607,
|
| 3065 |
+
"grad_norm": 0.3916319385244186,
|
| 3066 |
+
"learning_rate": 2.6637372432700483e-07,
|
| 3067 |
+
"loss": 0.3492,
|
| 3068 |
+
"step": 437
|
| 3069 |
+
},
|
| 3070 |
+
{
|
| 3071 |
+
"epoch": 2.7987220447284344,
|
| 3072 |
+
"grad_norm": 0.4083221537063404,
|
| 3073 |
+
"learning_rate": 2.4953619234612816e-07,
|
| 3074 |
+
"loss": 0.3056,
|
| 3075 |
+
"step": 438
|
| 3076 |
+
},
|
| 3077 |
+
{
|
| 3078 |
+
"epoch": 2.8051118210862622,
|
| 3079 |
+
"grad_norm": 0.36900391336674243,
|
| 3080 |
+
"learning_rate": 2.332416090845102e-07,
|
| 3081 |
+
"loss": 0.3071,
|
| 3082 |
+
"step": 439
|
| 3083 |
+
},
|
| 3084 |
+
{
|
| 3085 |
+
"epoch": 2.8115015974440896,
|
| 3086 |
+
"grad_norm": 0.4181996987699531,
|
| 3087 |
+
"learning_rate": 2.1749088189622848e-07,
|
| 3088 |
+
"loss": 0.3351,
|
| 3089 |
+
"step": 440
|
| 3090 |
+
},
|
| 3091 |
+
{
|
| 3092 |
+
"epoch": 2.817891373801917,
|
| 3093 |
+
"grad_norm": 0.3547619175700847,
|
| 3094 |
+
"learning_rate": 2.0228488785106636e-07,
|
| 3095 |
+
"loss": 0.3406,
|
| 3096 |
+
"step": 441
|
| 3097 |
+
},
|
| 3098 |
+
{
|
| 3099 |
+
"epoch": 2.8242811501597442,
|
| 3100 |
+
"grad_norm": 0.3977218103469981,
|
| 3101 |
+
"learning_rate": 1.8762447368566582e-07,
|
| 3102 |
+
"loss": 0.3505,
|
| 3103 |
+
"step": 442
|
| 3104 |
+
},
|
| 3105 |
+
{
|
| 3106 |
+
"epoch": 2.830670926517572,
|
| 3107 |
+
"grad_norm": 0.39003543295538634,
|
| 3108 |
+
"learning_rate": 1.7351045575638047e-07,
|
| 3109 |
+
"loss": 0.3753,
|
| 3110 |
+
"step": 443
|
| 3111 |
+
},
|
| 3112 |
+
{
|
| 3113 |
+
"epoch": 2.8370607028753994,
|
| 3114 |
+
"grad_norm": 0.37845868272626343,
|
| 3115 |
+
"learning_rate": 1.5994361999382202e-07,
|
| 3116 |
+
"loss": 0.3278,
|
| 3117 |
+
"step": 444
|
| 3118 |
+
},
|
| 3119 |
+
{
|
| 3120 |
+
"epoch": 2.8434504792332267,
|
| 3121 |
+
"grad_norm": 0.39842394374774287,
|
| 3122 |
+
"learning_rate": 1.4692472185908635e-07,
|
| 3123 |
+
"loss": 0.3682,
|
| 3124 |
+
"step": 445
|
| 3125 |
+
},
|
| 3126 |
+
{
|
| 3127 |
+
"epoch": 2.8498402555910545,
|
| 3128 |
+
"grad_norm": 0.3457049068963664,
|
| 3129 |
+
"learning_rate": 1.344544863016961e-07,
|
| 3130 |
+
"loss": 0.3438,
|
| 3131 |
+
"step": 446
|
| 3132 |
+
},
|
| 3133 |
+
{
|
| 3134 |
+
"epoch": 2.856230031948882,
|
| 3135 |
+
"grad_norm": 0.40463187861502226,
|
| 3136 |
+
"learning_rate": 1.225336077192274e-07,
|
| 3137 |
+
"loss": 0.3356,
|
| 3138 |
+
"step": 447
|
| 3139 |
+
},
|
| 3140 |
+
{
|
| 3141 |
+
"epoch": 2.862619808306709,
|
| 3142 |
+
"grad_norm": 0.5473639905587789,
|
| 3143 |
+
"learning_rate": 1.1116274991864073e-07,
|
| 3144 |
+
"loss": 0.3612,
|
| 3145 |
+
"step": 448
|
| 3146 |
+
},
|
| 3147 |
+
{
|
| 3148 |
+
"epoch": 2.8690095846645365,
|
| 3149 |
+
"grad_norm": 0.36738048359514414,
|
| 3150 |
+
"learning_rate": 1.003425460793217e-07,
|
| 3151 |
+
"loss": 0.3618,
|
| 3152 |
+
"step": 449
|
| 3153 |
+
},
|
| 3154 |
+
{
|
| 3155 |
+
"epoch": 2.8753993610223643,
|
| 3156 |
+
"grad_norm": 0.39397443170606444,
|
| 3157 |
+
"learning_rate": 9.00735987178214e-08,
|
| 3158 |
+
"loss": 0.3325,
|
| 3159 |
+
"step": 450
|
| 3160 |
+
},
|
| 3161 |
+
{
|
| 3162 |
+
"epoch": 2.8817891373801916,
|
| 3163 |
+
"grad_norm": 0.3641877860232395,
|
| 3164 |
+
"learning_rate": 8.035647965430215e-08,
|
| 3165 |
+
"loss": 0.3705,
|
| 3166 |
+
"step": 451
|
| 3167 |
+
},
|
| 3168 |
+
{
|
| 3169 |
+
"epoch": 2.8881789137380194,
|
| 3170 |
+
"grad_norm": 0.3766602850517281,
|
| 3171 |
+
"learning_rate": 7.119172998070412e-08,
|
| 3172 |
+
"loss": 0.3602,
|
| 3173 |
+
"step": 452
|
| 3174 |
+
},
|
| 3175 |
+
{
|
| 3176 |
+
"epoch": 2.8945686900958467,
|
| 3177 |
+
"grad_norm": 0.3504672529434601,
|
| 3178 |
+
"learning_rate": 6.25798600306049e-08,
|
| 3179 |
+
"loss": 0.345,
|
| 3180 |
+
"step": 453
|
| 3181 |
+
},
|
| 3182 |
+
{
|
| 3183 |
+
"epoch": 2.900958466453674,
|
| 3184 |
+
"grad_norm": 0.3689087024207003,
|
| 3185 |
+
"learning_rate": 5.4521349350808996e-08,
|
| 3186 |
+
"loss": 0.3711,
|
| 3187 |
+
"step": 454
|
| 3188 |
+
},
|
| 3189 |
+
{
|
| 3190 |
+
"epoch": 2.9073482428115014,
|
| 3191 |
+
"grad_norm": 0.3816320750179523,
|
| 3192 |
+
"learning_rate": 4.701664667464245e-08,
|
| 3193 |
+
"loss": 0.3646,
|
| 3194 |
+
"step": 455
|
| 3195 |
+
},
|
| 3196 |
+
{
|
| 3197 |
+
"epoch": 2.913738019169329,
|
| 3198 |
+
"grad_norm": 0.3679437431040902,
|
| 3199 |
+
"learning_rate": 4.006616989696621e-08,
|
| 3200 |
+
"loss": 0.3615,
|
| 3201 |
+
"step": 456
|
| 3202 |
+
},
|
| 3203 |
+
{
|
| 3204 |
+
"epoch": 2.9201277955271565,
|
| 3205 |
+
"grad_norm": 0.38571927082544183,
|
| 3206 |
+
"learning_rate": 3.367030605090249e-08,
|
| 3207 |
+
"loss": 0.3222,
|
| 3208 |
+
"step": 457
|
| 3209 |
+
},
|
| 3210 |
+
{
|
| 3211 |
+
"epoch": 2.9265175718849843,
|
| 3212 |
+
"grad_norm": 0.3971237004311223,
|
| 3213 |
+
"learning_rate": 2.7829411286287577e-08,
|
| 3214 |
+
"loss": 0.3485,
|
| 3215 |
+
"step": 458
|
| 3216 |
+
},
|
| 3217 |
+
{
|
| 3218 |
+
"epoch": 2.9329073482428116,
|
| 3219 |
+
"grad_norm": 0.3630064489830963,
|
| 3220 |
+
"learning_rate": 2.254381084983659e-08,
|
| 3221 |
+
"loss": 0.3065,
|
| 3222 |
+
"step": 459
|
| 3223 |
+
},
|
| 3224 |
+
{
|
| 3225 |
+
"epoch": 2.939297124600639,
|
| 3226 |
+
"grad_norm": 0.3754819920105193,
|
| 3227 |
+
"learning_rate": 1.781379906703573e-08,
|
| 3228 |
+
"loss": 0.36,
|
| 3229 |
+
"step": 460
|
| 3230 |
+
},
|
| 3231 |
+
{
|
| 3232 |
+
"epoch": 2.9456869009584663,
|
| 3233 |
+
"grad_norm": 0.37643335933636624,
|
| 3234 |
+
"learning_rate": 1.3639639325748744e-08,
|
| 3235 |
+
"loss": 0.3725,
|
| 3236 |
+
"step": 461
|
| 3237 |
+
},
|
| 3238 |
+
{
|
| 3239 |
+
"epoch": 2.952076677316294,
|
| 3240 |
+
"grad_norm": 0.397354621784988,
|
| 3241 |
+
"learning_rate": 1.0021564061554189e-08,
|
| 3242 |
+
"loss": 0.3378,
|
| 3243 |
+
"step": 462
|
| 3244 |
+
},
|
| 3245 |
+
{
|
| 3246 |
+
"epoch": 2.9584664536741214,
|
| 3247 |
+
"grad_norm": 0.37424179888551773,
|
| 3248 |
+
"learning_rate": 6.959774744796921e-09,
|
| 3249 |
+
"loss": 0.3399,
|
| 3250 |
+
"step": 463
|
| 3251 |
+
},
|
| 3252 |
+
{
|
| 3253 |
+
"epoch": 2.9648562300319488,
|
| 3254 |
+
"grad_norm": 0.37190360281608004,
|
| 3255 |
+
"learning_rate": 4.454441869377047e-09,
|
| 3256 |
+
"loss": 0.3219,
|
| 3257 |
+
"step": 464
|
| 3258 |
+
},
|
| 3259 |
+
{
|
| 3260 |
+
"epoch": 2.9712460063897765,
|
| 3261 |
+
"grad_norm": 0.3657736795626134,
|
| 3262 |
+
"learning_rate": 2.5057049432519744e-09,
|
| 3263 |
+
"loss": 0.3705,
|
| 3264 |
+
"step": 465
|
| 3265 |
+
},
|
| 3266 |
+
{
|
| 3267 |
+
"epoch": 2.977635782747604,
|
| 3268 |
+
"grad_norm": 0.35303669900268125,
|
| 3269 |
+
"learning_rate": 1.1136724806637411e-09,
|
| 3270 |
+
"loss": 0.3318,
|
| 3271 |
+
"step": 466
|
| 3272 |
+
},
|
| 3273 |
+
{
|
| 3274 |
+
"epoch": 2.984025559105431,
|
| 3275 |
+
"grad_norm": 0.36854160936154184,
|
| 3276 |
+
"learning_rate": 2.784219961060597e-10,
|
| 3277 |
+
"loss": 0.3518,
|
| 3278 |
+
"step": 467
|
| 3279 |
+
},
|
| 3280 |
+
{
|
| 3281 |
+
"epoch": 2.9904153354632586,
|
| 3282 |
+
"grad_norm": 0.3989983000303115,
|
| 3283 |
+
"learning_rate": 0.0,
|
| 3284 |
+
"loss": 0.3546,
|
| 3285 |
+
"step": 468
|
| 3286 |
+
},
|
| 3287 |
+
{
|
| 3288 |
+
"epoch": 2.9904153354632586,
|
| 3289 |
+
"step": 468,
|
| 3290 |
+
"total_flos": 3.310734730054861e+17,
|
| 3291 |
+
"train_loss": 0.4434524042229367,
|
| 3292 |
+
"train_runtime": 10205.5973,
|
| 3293 |
+
"train_samples_per_second": 2.939,
|
| 3294 |
+
"train_steps_per_second": 0.046
|
| 3295 |
+
}
|
| 3296 |
+
],
|
| 3297 |
+
"logging_steps": 1.0,
|
| 3298 |
+
"max_steps": 468,
|
| 3299 |
+
"num_input_tokens_seen": 0,
|
| 3300 |
+
"num_train_epochs": 3,
|
| 3301 |
+
"save_steps": 500,
|
| 3302 |
+
"stateful_callbacks": {
|
| 3303 |
+
"TrainerControl": {
|
| 3304 |
+
"args": {
|
| 3305 |
+
"should_epoch_stop": false,
|
| 3306 |
+
"should_evaluate": false,
|
| 3307 |
+
"should_log": false,
|
| 3308 |
+
"should_save": true,
|
| 3309 |
+
"should_training_stop": true
|
| 3310 |
+
},
|
| 3311 |
+
"attributes": {}
|
| 3312 |
+
}
|
| 3313 |
+
},
|
| 3314 |
+
"total_flos": 3.310734730054861e+17,
|
| 3315 |
+
"train_batch_size": 1,
|
| 3316 |
+
"trial_name": null,
|
| 3317 |
+
"trial_params": null
|
| 3318 |
+
}
|
training_loss.png
ADDED
|