End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +1996 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: apache-2.0
|
|
| 4 |
base_model: secmlr/aixcc_DS-Noisy_DS-Clean_QWQ-Noisy_QWQ-Clean_Qwen2.5-7B-Instruct_full_sft_1e-5_aixcc_train
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: aixcc_split_context
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# aixcc_split_context
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [secmlr/aixcc_DS-Noisy_DS-Clean_QWQ-Noisy_QWQ-Clean_Qwen2.5-7B-Instruct_full_sft_1e-5_aixcc_train](https://huggingface.co/secmlr/aixcc_DS-Noisy_DS-Clean_QWQ-Noisy_QWQ-Clean_Qwen2.5-7B-Instruct_full_sft_1e-5_aixcc_train) on
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 4 |
base_model: secmlr/aixcc_DS-Noisy_DS-Clean_QWQ-Noisy_QWQ-Clean_Qwen2.5-7B-Instruct_full_sft_1e-5_aixcc_train
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: aixcc_split_context
|
|
|
|
| 16 |
|
| 17 |
# aixcc_split_context
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [secmlr/aixcc_DS-Noisy_DS-Clean_QWQ-Noisy_QWQ-Clean_Qwen2.5-7B-Instruct_full_sft_1e-5_aixcc_train](https://huggingface.co/secmlr/aixcc_DS-Noisy_DS-Clean_QWQ-Noisy_QWQ-Clean_Qwen2.5-7B-Instruct_full_sft_1e-5_aixcc_train) on the aixcc_split_context dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 2.2819812112387277e+17,
|
| 4 |
+
"train_loss": 0.38972266467027766,
|
| 5 |
+
"train_runtime": 34674.5164,
|
| 6 |
+
"train_samples_per_second": 0.386,
|
| 7 |
+
"train_steps_per_second": 0.008
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 2.2819812112387277e+17,
|
| 4 |
+
"train_loss": 0.38972266467027766,
|
| 5 |
+
"train_runtime": 34674.5164,
|
| 6 |
+
"train_samples_per_second": 0.386,
|
| 7 |
+
"train_steps_per_second": 0.008
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1996 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 279,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.010752688172043012,
|
| 14 |
+
"grad_norm": 5.117406670103657,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 0.8565,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.021505376344086023,
|
| 21 |
+
"grad_norm": 3.932349183270455,
|
| 22 |
+
"learning_rate": 3.5714285714285716e-07,
|
| 23 |
+
"loss": 0.7654,
|
| 24 |
+
"step": 2
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.03225806451612903,
|
| 28 |
+
"grad_norm": 4.430618628715762,
|
| 29 |
+
"learning_rate": 7.142857142857143e-07,
|
| 30 |
+
"loss": 0.8602,
|
| 31 |
+
"step": 3
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.043010752688172046,
|
| 35 |
+
"grad_norm": 4.629935061064256,
|
| 36 |
+
"learning_rate": 1.0714285714285714e-06,
|
| 37 |
+
"loss": 0.8179,
|
| 38 |
+
"step": 4
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.053763440860215055,
|
| 42 |
+
"grad_norm": 4.607689206667246,
|
| 43 |
+
"learning_rate": 1.4285714285714286e-06,
|
| 44 |
+
"loss": 0.7984,
|
| 45 |
+
"step": 5
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.06451612903225806,
|
| 49 |
+
"grad_norm": 4.470859498641417,
|
| 50 |
+
"learning_rate": 1.7857142857142859e-06,
|
| 51 |
+
"loss": 0.8393,
|
| 52 |
+
"step": 6
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.07526881720430108,
|
| 56 |
+
"grad_norm": 3.615495688035928,
|
| 57 |
+
"learning_rate": 2.1428571428571427e-06,
|
| 58 |
+
"loss": 0.7408,
|
| 59 |
+
"step": 7
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.08602150537634409,
|
| 63 |
+
"grad_norm": 3.6184582310708753,
|
| 64 |
+
"learning_rate": 2.5e-06,
|
| 65 |
+
"loss": 0.7991,
|
| 66 |
+
"step": 8
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.0967741935483871,
|
| 70 |
+
"grad_norm": 3.5286647768187804,
|
| 71 |
+
"learning_rate": 2.8571428571428573e-06,
|
| 72 |
+
"loss": 0.7439,
|
| 73 |
+
"step": 9
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.10752688172043011,
|
| 77 |
+
"grad_norm": 3.2631493323575773,
|
| 78 |
+
"learning_rate": 3.2142857142857147e-06,
|
| 79 |
+
"loss": 0.7656,
|
| 80 |
+
"step": 10
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.11827956989247312,
|
| 84 |
+
"grad_norm": 1.9183483696552464,
|
| 85 |
+
"learning_rate": 3.5714285714285718e-06,
|
| 86 |
+
"loss": 0.6424,
|
| 87 |
+
"step": 11
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.12903225806451613,
|
| 91 |
+
"grad_norm": 2.5758188598022036,
|
| 92 |
+
"learning_rate": 3.928571428571429e-06,
|
| 93 |
+
"loss": 0.6746,
|
| 94 |
+
"step": 12
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.13978494623655913,
|
| 98 |
+
"grad_norm": 2.711107640562582,
|
| 99 |
+
"learning_rate": 4.2857142857142855e-06,
|
| 100 |
+
"loss": 0.6786,
|
| 101 |
+
"step": 13
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.15053763440860216,
|
| 105 |
+
"grad_norm": 2.2557127395574335,
|
| 106 |
+
"learning_rate": 4.642857142857144e-06,
|
| 107 |
+
"loss": 0.6464,
|
| 108 |
+
"step": 14
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.16129032258064516,
|
| 112 |
+
"grad_norm": 2.08589822549775,
|
| 113 |
+
"learning_rate": 5e-06,
|
| 114 |
+
"loss": 0.5924,
|
| 115 |
+
"step": 15
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.17204301075268819,
|
| 119 |
+
"grad_norm": 2.442258395861131,
|
| 120 |
+
"learning_rate": 5.357142857142857e-06,
|
| 121 |
+
"loss": 0.6771,
|
| 122 |
+
"step": 16
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.1827956989247312,
|
| 126 |
+
"grad_norm": 2.4088790285819353,
|
| 127 |
+
"learning_rate": 5.7142857142857145e-06,
|
| 128 |
+
"loss": 0.6609,
|
| 129 |
+
"step": 17
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.1935483870967742,
|
| 133 |
+
"grad_norm": 2.599278835350385,
|
| 134 |
+
"learning_rate": 6.071428571428571e-06,
|
| 135 |
+
"loss": 0.665,
|
| 136 |
+
"step": 18
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.20430107526881722,
|
| 140 |
+
"grad_norm": 2.135693738895623,
|
| 141 |
+
"learning_rate": 6.4285714285714295e-06,
|
| 142 |
+
"loss": 0.5946,
|
| 143 |
+
"step": 19
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.21505376344086022,
|
| 147 |
+
"grad_norm": 2.0880720029245343,
|
| 148 |
+
"learning_rate": 6.785714285714287e-06,
|
| 149 |
+
"loss": 0.6027,
|
| 150 |
+
"step": 20
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.22580645161290322,
|
| 154 |
+
"grad_norm": 1.7878249901331582,
|
| 155 |
+
"learning_rate": 7.1428571428571436e-06,
|
| 156 |
+
"loss": 0.6523,
|
| 157 |
+
"step": 21
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.23655913978494625,
|
| 161 |
+
"grad_norm": 1.8499308052576442,
|
| 162 |
+
"learning_rate": 7.500000000000001e-06,
|
| 163 |
+
"loss": 0.5775,
|
| 164 |
+
"step": 22
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.24731182795698925,
|
| 168 |
+
"grad_norm": 1.545055962271408,
|
| 169 |
+
"learning_rate": 7.857142857142858e-06,
|
| 170 |
+
"loss": 0.5343,
|
| 171 |
+
"step": 23
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.25806451612903225,
|
| 175 |
+
"grad_norm": 1.5990557909426337,
|
| 176 |
+
"learning_rate": 8.214285714285714e-06,
|
| 177 |
+
"loss": 0.6303,
|
| 178 |
+
"step": 24
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.26881720430107525,
|
| 182 |
+
"grad_norm": 1.5047883914372557,
|
| 183 |
+
"learning_rate": 8.571428571428571e-06,
|
| 184 |
+
"loss": 0.5673,
|
| 185 |
+
"step": 25
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.27956989247311825,
|
| 189 |
+
"grad_norm": 1.660959104374015,
|
| 190 |
+
"learning_rate": 8.92857142857143e-06,
|
| 191 |
+
"loss": 0.5834,
|
| 192 |
+
"step": 26
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.2903225806451613,
|
| 196 |
+
"grad_norm": 1.4855731115284816,
|
| 197 |
+
"learning_rate": 9.285714285714288e-06,
|
| 198 |
+
"loss": 0.5861,
|
| 199 |
+
"step": 27
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.3010752688172043,
|
| 203 |
+
"grad_norm": 1.5890489850514156,
|
| 204 |
+
"learning_rate": 9.642857142857144e-06,
|
| 205 |
+
"loss": 0.58,
|
| 206 |
+
"step": 28
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.3118279569892473,
|
| 210 |
+
"grad_norm": 1.3375504302217296,
|
| 211 |
+
"learning_rate": 1e-05,
|
| 212 |
+
"loss": 0.5669,
|
| 213 |
+
"step": 29
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.3225806451612903,
|
| 217 |
+
"grad_norm": 1.4010773743864648,
|
| 218 |
+
"learning_rate": 9.999608360361114e-06,
|
| 219 |
+
"loss": 0.551,
|
| 220 |
+
"step": 30
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.3333333333333333,
|
| 224 |
+
"grad_norm": 1.3303386154338483,
|
| 225 |
+
"learning_rate": 9.998433502797097e-06,
|
| 226 |
+
"loss": 0.6109,
|
| 227 |
+
"step": 31
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.34408602150537637,
|
| 231 |
+
"grad_norm": 1.3895786100086411,
|
| 232 |
+
"learning_rate": 9.996475611356265e-06,
|
| 233 |
+
"loss": 0.5155,
|
| 234 |
+
"step": 32
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.3548387096774194,
|
| 238 |
+
"grad_norm": 1.211244402418308,
|
| 239 |
+
"learning_rate": 9.993734992753777e-06,
|
| 240 |
+
"loss": 0.5167,
|
| 241 |
+
"step": 33
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.3655913978494624,
|
| 245 |
+
"grad_norm": 1.205621464067494,
|
| 246 |
+
"learning_rate": 9.990212076323587e-06,
|
| 247 |
+
"loss": 0.626,
|
| 248 |
+
"step": 34
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.3763440860215054,
|
| 252 |
+
"grad_norm": 1.281327619636724,
|
| 253 |
+
"learning_rate": 9.98590741395118e-06,
|
| 254 |
+
"loss": 0.5301,
|
| 255 |
+
"step": 35
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.3870967741935484,
|
| 259 |
+
"grad_norm": 1.4425953234642075,
|
| 260 |
+
"learning_rate": 9.980821679987125e-06,
|
| 261 |
+
"loss": 0.5705,
|
| 262 |
+
"step": 36
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.3978494623655914,
|
| 266 |
+
"grad_norm": 1.3476830260596382,
|
| 267 |
+
"learning_rate": 9.974955671141425e-06,
|
| 268 |
+
"loss": 0.5742,
|
| 269 |
+
"step": 37
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.40860215053763443,
|
| 273 |
+
"grad_norm": 1.3027265736180367,
|
| 274 |
+
"learning_rate": 9.968310306358715e-06,
|
| 275 |
+
"loss": 0.5443,
|
| 276 |
+
"step": 38
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.41935483870967744,
|
| 280 |
+
"grad_norm": 1.3618324591712858,
|
| 281 |
+
"learning_rate": 9.960886626674302e-06,
|
| 282 |
+
"loss": 0.6328,
|
| 283 |
+
"step": 39
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.43010752688172044,
|
| 287 |
+
"grad_norm": 1.3924706399344635,
|
| 288 |
+
"learning_rate": 9.952685795051078e-06,
|
| 289 |
+
"loss": 0.531,
|
| 290 |
+
"step": 40
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.44086021505376344,
|
| 294 |
+
"grad_norm": 1.3681689870094362,
|
| 295 |
+
"learning_rate": 9.943709096197334e-06,
|
| 296 |
+
"loss": 0.5771,
|
| 297 |
+
"step": 41
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.45161290322580644,
|
| 301 |
+
"grad_norm": 1.169520090357751,
|
| 302 |
+
"learning_rate": 9.933957936365515e-06,
|
| 303 |
+
"loss": 0.6155,
|
| 304 |
+
"step": 42
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.46236559139784944,
|
| 308 |
+
"grad_norm": 1.2592535480126792,
|
| 309 |
+
"learning_rate": 9.9234338431319e-06,
|
| 310 |
+
"loss": 0.5614,
|
| 311 |
+
"step": 43
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.4731182795698925,
|
| 315 |
+
"grad_norm": 1.188489938742699,
|
| 316 |
+
"learning_rate": 9.912138465157325e-06,
|
| 317 |
+
"loss": 0.5821,
|
| 318 |
+
"step": 44
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.4838709677419355,
|
| 322 |
+
"grad_norm": 1.1821647113837632,
|
| 323 |
+
"learning_rate": 9.900073571928887e-06,
|
| 324 |
+
"loss": 0.5793,
|
| 325 |
+
"step": 45
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.4946236559139785,
|
| 329 |
+
"grad_norm": 1.363884821931327,
|
| 330 |
+
"learning_rate": 9.887241053482756e-06,
|
| 331 |
+
"loss": 0.5629,
|
| 332 |
+
"step": 46
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.5053763440860215,
|
| 336 |
+
"grad_norm": 1.3092899719841664,
|
| 337 |
+
"learning_rate": 9.87364292010809e-06,
|
| 338 |
+
"loss": 0.5235,
|
| 339 |
+
"step": 47
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.5161290322580645,
|
| 343 |
+
"grad_norm": 1.3352852678722897,
|
| 344 |
+
"learning_rate": 9.859281302032107e-06,
|
| 345 |
+
"loss": 0.5151,
|
| 346 |
+
"step": 48
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.5268817204301075,
|
| 350 |
+
"grad_norm": 1.2505866887814554,
|
| 351 |
+
"learning_rate": 9.844158449086372e-06,
|
| 352 |
+
"loss": 0.5452,
|
| 353 |
+
"step": 49
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.5376344086021505,
|
| 357 |
+
"grad_norm": 1.4936981012829829,
|
| 358 |
+
"learning_rate": 9.828276730354353e-06,
|
| 359 |
+
"loss": 0.5463,
|
| 360 |
+
"step": 50
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.5483870967741935,
|
| 364 |
+
"grad_norm": 1.2994897728299255,
|
| 365 |
+
"learning_rate": 9.811638633800287e-06,
|
| 366 |
+
"loss": 0.524,
|
| 367 |
+
"step": 51
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.5591397849462365,
|
| 371 |
+
"grad_norm": 1.1528734529208322,
|
| 372 |
+
"learning_rate": 9.794246765879421e-06,
|
| 373 |
+
"loss": 0.5134,
|
| 374 |
+
"step": 52
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.5698924731182796,
|
| 378 |
+
"grad_norm": 1.3662191872593852,
|
| 379 |
+
"learning_rate": 9.776103851129706e-06,
|
| 380 |
+
"loss": 0.5074,
|
| 381 |
+
"step": 53
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.5806451612903226,
|
| 385 |
+
"grad_norm": 1.3197245386738852,
|
| 386 |
+
"learning_rate": 9.757212731744973e-06,
|
| 387 |
+
"loss": 0.4936,
|
| 388 |
+
"step": 54
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.5913978494623656,
|
| 392 |
+
"grad_norm": 1.1826061568448532,
|
| 393 |
+
"learning_rate": 9.737576367129694e-06,
|
| 394 |
+
"loss": 0.5291,
|
| 395 |
+
"step": 55
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.6021505376344086,
|
| 399 |
+
"grad_norm": 1.2279962807050635,
|
| 400 |
+
"learning_rate": 9.717197833435367e-06,
|
| 401 |
+
"loss": 0.5401,
|
| 402 |
+
"step": 56
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.6129032258064516,
|
| 406 |
+
"grad_norm": 1.1622891891860894,
|
| 407 |
+
"learning_rate": 9.696080323078621e-06,
|
| 408 |
+
"loss": 0.5341,
|
| 409 |
+
"step": 57
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.6236559139784946,
|
| 413 |
+
"grad_norm": 1.15595461480515,
|
| 414 |
+
"learning_rate": 9.67422714424111e-06,
|
| 415 |
+
"loss": 0.4811,
|
| 416 |
+
"step": 58
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.6344086021505376,
|
| 420 |
+
"grad_norm": 1.1381808394142663,
|
| 421 |
+
"learning_rate": 9.651641720351262e-06,
|
| 422 |
+
"loss": 0.5126,
|
| 423 |
+
"step": 59
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.6451612903225806,
|
| 427 |
+
"grad_norm": 1.2816655929131089,
|
| 428 |
+
"learning_rate": 9.628327589547977e-06,
|
| 429 |
+
"loss": 0.5147,
|
| 430 |
+
"step": 60
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.6559139784946236,
|
| 434 |
+
"grad_norm": 1.176343266853311,
|
| 435 |
+
"learning_rate": 9.604288404126362e-06,
|
| 436 |
+
"loss": 0.533,
|
| 437 |
+
"step": 61
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.6666666666666666,
|
| 441 |
+
"grad_norm": 1.3546093456513846,
|
| 442 |
+
"learning_rate": 9.579527929965581e-06,
|
| 443 |
+
"loss": 0.5972,
|
| 444 |
+
"step": 62
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.6774193548387096,
|
| 448 |
+
"grad_norm": 1.3159036668873394,
|
| 449 |
+
"learning_rate": 9.554050045938893e-06,
|
| 450 |
+
"loss": 0.5211,
|
| 451 |
+
"step": 63
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.6881720430107527,
|
| 455 |
+
"grad_norm": 1.3256416815543717,
|
| 456 |
+
"learning_rate": 9.52785874330602e-06,
|
| 457 |
+
"loss": 0.5664,
|
| 458 |
+
"step": 64
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.6989247311827957,
|
| 462 |
+
"grad_norm": 1.137833912080069,
|
| 463 |
+
"learning_rate": 9.500958125087882e-06,
|
| 464 |
+
"loss": 0.52,
|
| 465 |
+
"step": 65
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.7096774193548387,
|
| 469 |
+
"grad_norm": 1.3219928059082766,
|
| 470 |
+
"learning_rate": 9.473352405423845e-06,
|
| 471 |
+
"loss": 0.5192,
|
| 472 |
+
"step": 66
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.7204301075268817,
|
| 476 |
+
"grad_norm": 1.2000849146820651,
|
| 477 |
+
"learning_rate": 9.445045908911536e-06,
|
| 478 |
+
"loss": 0.5093,
|
| 479 |
+
"step": 67
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.7311827956989247,
|
| 483 |
+
"grad_norm": 1.0948499067842512,
|
| 484 |
+
"learning_rate": 9.416043069929389e-06,
|
| 485 |
+
"loss": 0.4891,
|
| 486 |
+
"step": 68
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.7419354838709677,
|
| 490 |
+
"grad_norm": 1.1326577666179933,
|
| 491 |
+
"learning_rate": 9.386348431941953e-06,
|
| 492 |
+
"loss": 0.4979,
|
| 493 |
+
"step": 69
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.7526881720430108,
|
| 497 |
+
"grad_norm": 1.1971786924652708,
|
| 498 |
+
"learning_rate": 9.355966646788152e-06,
|
| 499 |
+
"loss": 0.4716,
|
| 500 |
+
"step": 70
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.7634408602150538,
|
| 504 |
+
"grad_norm": 1.1712532314666788,
|
| 505 |
+
"learning_rate": 9.324902473952529e-06,
|
| 506 |
+
"loss": 0.4697,
|
| 507 |
+
"step": 71
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.7741935483870968,
|
| 511 |
+
"grad_norm": 1.174242198418526,
|
| 512 |
+
"learning_rate": 9.293160779819658e-06,
|
| 513 |
+
"loss": 0.5306,
|
| 514 |
+
"step": 72
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.7849462365591398,
|
| 518 |
+
"grad_norm": 1.2287418966719115,
|
| 519 |
+
"learning_rate": 9.260746536911792e-06,
|
| 520 |
+
"loss": 0.5267,
|
| 521 |
+
"step": 73
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.7956989247311828,
|
| 525 |
+
"grad_norm": 1.3303630719030897,
|
| 526 |
+
"learning_rate": 9.227664823109884e-06,
|
| 527 |
+
"loss": 0.5243,
|
| 528 |
+
"step": 74
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.8064516129032258,
|
| 532 |
+
"grad_norm": 1.3096448496558815,
|
| 533 |
+
"learning_rate": 9.193920820858113e-06,
|
| 534 |
+
"loss": 0.4986,
|
| 535 |
+
"step": 75
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.8172043010752689,
|
| 539 |
+
"grad_norm": 1.3030805645002468,
|
| 540 |
+
"learning_rate": 9.159519816352021e-06,
|
| 541 |
+
"loss": 0.5732,
|
| 542 |
+
"step": 76
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.8279569892473119,
|
| 546 |
+
"grad_norm": 1.2151108401849033,
|
| 547 |
+
"learning_rate": 9.124467198710401e-06,
|
| 548 |
+
"loss": 0.5374,
|
| 549 |
+
"step": 77
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.8387096774193549,
|
| 553 |
+
"grad_norm": 1.2507532704479085,
|
| 554 |
+
"learning_rate": 9.08876845913106e-06,
|
| 555 |
+
"loss": 0.5251,
|
| 556 |
+
"step": 78
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.8494623655913979,
|
| 560 |
+
"grad_norm": 1.397611316956257,
|
| 561 |
+
"learning_rate": 9.052429190030589e-06,
|
| 562 |
+
"loss": 0.5325,
|
| 563 |
+
"step": 79
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.8602150537634409,
|
| 567 |
+
"grad_norm": 1.2260544279462335,
|
| 568 |
+
"learning_rate": 9.015455084168279e-06,
|
| 569 |
+
"loss": 0.5008,
|
| 570 |
+
"step": 80
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.8709677419354839,
|
| 574 |
+
"grad_norm": 1.219464661892977,
|
| 575 |
+
"learning_rate": 8.977851933754317e-06,
|
| 576 |
+
"loss": 0.5294,
|
| 577 |
+
"step": 81
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.8817204301075269,
|
| 581 |
+
"grad_norm": 1.2576277212991538,
|
| 582 |
+
"learning_rate": 8.939625629542401e-06,
|
| 583 |
+
"loss": 0.5065,
|
| 584 |
+
"step": 82
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.8924731182795699,
|
| 588 |
+
"grad_norm": 1.2231909063495303,
|
| 589 |
+
"learning_rate": 8.900782159906927e-06,
|
| 590 |
+
"loss": 0.5577,
|
| 591 |
+
"step": 83
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.9032258064516129,
|
| 595 |
+
"grad_norm": 1.240487970070817,
|
| 596 |
+
"learning_rate": 8.861327609904859e-06,
|
| 597 |
+
"loss": 0.5607,
|
| 598 |
+
"step": 84
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.9139784946236559,
|
| 602 |
+
"grad_norm": 1.1803222245984772,
|
| 603 |
+
"learning_rate": 8.821268160322482e-06,
|
| 604 |
+
"loss": 0.4559,
|
| 605 |
+
"step": 85
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.9247311827956989,
|
| 609 |
+
"grad_norm": 1.1172971063227777,
|
| 610 |
+
"learning_rate": 8.780610086707149e-06,
|
| 611 |
+
"loss": 0.4524,
|
| 612 |
+
"step": 86
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.9354838709677419,
|
| 616 |
+
"grad_norm": 1.1952992924028192,
|
| 617 |
+
"learning_rate": 8.739359758384162e-06,
|
| 618 |
+
"loss": 0.5183,
|
| 619 |
+
"step": 87
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.946236559139785,
|
| 623 |
+
"grad_norm": 1.2423449341948143,
|
| 624 |
+
"learning_rate": 8.697523637458997e-06,
|
| 625 |
+
"loss": 0.6781,
|
| 626 |
+
"step": 88
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.956989247311828,
|
| 630 |
+
"grad_norm": 1.223456106162861,
|
| 631 |
+
"learning_rate": 8.655108277804975e-06,
|
| 632 |
+
"loss": 0.4719,
|
| 633 |
+
"step": 89
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.967741935483871,
|
| 637 |
+
"grad_norm": 1.2180325223266957,
|
| 638 |
+
"learning_rate": 8.612120324036548e-06,
|
| 639 |
+
"loss": 0.5298,
|
| 640 |
+
"step": 90
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.978494623655914,
|
| 644 |
+
"grad_norm": 1.1908812611967874,
|
| 645 |
+
"learning_rate": 8.568566510468392e-06,
|
| 646 |
+
"loss": 0.4908,
|
| 647 |
+
"step": 91
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.989247311827957,
|
| 651 |
+
"grad_norm": 1.1329246631137397,
|
| 652 |
+
"learning_rate": 8.524453660060434e-06,
|
| 653 |
+
"loss": 0.4884,
|
| 654 |
+
"step": 92
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.0,
|
| 658 |
+
"grad_norm": 1.1739661223625193,
|
| 659 |
+
"learning_rate": 8.479788683348996e-06,
|
| 660 |
+
"loss": 0.5282,
|
| 661 |
+
"step": 93
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.010752688172043,
|
| 665 |
+
"grad_norm": 1.2895603002016933,
|
| 666 |
+
"learning_rate": 8.434578577364218e-06,
|
| 667 |
+
"loss": 0.4053,
|
| 668 |
+
"step": 94
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.021505376344086,
|
| 672 |
+
"grad_norm": 1.2372418394561484,
|
| 673 |
+
"learning_rate": 8.388830424533935e-06,
|
| 674 |
+
"loss": 0.337,
|
| 675 |
+
"step": 95
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.032258064516129,
|
| 679 |
+
"grad_norm": 1.1718375574305269,
|
| 680 |
+
"learning_rate": 8.342551391574165e-06,
|
| 681 |
+
"loss": 0.3569,
|
| 682 |
+
"step": 96
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.043010752688172,
|
| 686 |
+
"grad_norm": 1.2444221432485463,
|
| 687 |
+
"learning_rate": 8.295748728366414e-06,
|
| 688 |
+
"loss": 0.3488,
|
| 689 |
+
"step": 97
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.053763440860215,
|
| 693 |
+
"grad_norm": 1.5344510346454978,
|
| 694 |
+
"learning_rate": 8.248429766821925e-06,
|
| 695 |
+
"loss": 0.387,
|
| 696 |
+
"step": 98
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.064516129032258,
|
| 700 |
+
"grad_norm": 1.83437388566894,
|
| 701 |
+
"learning_rate": 8.200601919733106e-06,
|
| 702 |
+
"loss": 0.3476,
|
| 703 |
+
"step": 99
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.075268817204301,
|
| 707 |
+
"grad_norm": 1.1645823937573538,
|
| 708 |
+
"learning_rate": 8.15227267961226e-06,
|
| 709 |
+
"loss": 0.338,
|
| 710 |
+
"step": 100
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.086021505376344,
|
| 714 |
+
"grad_norm": 1.07943356765298,
|
| 715 |
+
"learning_rate": 8.10344961751785e-06,
|
| 716 |
+
"loss": 0.3756,
|
| 717 |
+
"step": 101
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.096774193548387,
|
| 721 |
+
"grad_norm": 1.136359022672489,
|
| 722 |
+
"learning_rate": 8.054140381868435e-06,
|
| 723 |
+
"loss": 0.3643,
|
| 724 |
+
"step": 102
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.10752688172043,
|
| 728 |
+
"grad_norm": 1.1334256185564782,
|
| 729 |
+
"learning_rate": 8.004352697244516e-06,
|
| 730 |
+
"loss": 0.3537,
|
| 731 |
+
"step": 103
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.118279569892473,
|
| 735 |
+
"grad_norm": 1.272152321916641,
|
| 736 |
+
"learning_rate": 7.954094363178421e-06,
|
| 737 |
+
"loss": 0.3851,
|
| 738 |
+
"step": 104
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.129032258064516,
|
| 742 |
+
"grad_norm": 1.6926984652817842,
|
| 743 |
+
"learning_rate": 7.903373252932474e-06,
|
| 744 |
+
"loss": 0.3236,
|
| 745 |
+
"step": 105
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.139784946236559,
|
| 749 |
+
"grad_norm": 1.1769426909749126,
|
| 750 |
+
"learning_rate": 7.852197312265592e-06,
|
| 751 |
+
"loss": 0.4107,
|
| 752 |
+
"step": 106
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.1505376344086022,
|
| 756 |
+
"grad_norm": 1.2179134329370982,
|
| 757 |
+
"learning_rate": 7.800574558188548e-06,
|
| 758 |
+
"loss": 0.3655,
|
| 759 |
+
"step": 107
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.1612903225806452,
|
| 763 |
+
"grad_norm": 1.1914193859243891,
|
| 764 |
+
"learning_rate": 7.748513077708044e-06,
|
| 765 |
+
"loss": 0.319,
|
| 766 |
+
"step": 108
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.1720430107526882,
|
| 770 |
+
"grad_norm": 1.1623447008406969,
|
| 771 |
+
"learning_rate": 7.69602102655985e-06,
|
| 772 |
+
"loss": 0.3257,
|
| 773 |
+
"step": 109
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.1827956989247312,
|
| 777 |
+
"grad_norm": 1.219276989748195,
|
| 778 |
+
"learning_rate": 7.643106627931148e-06,
|
| 779 |
+
"loss": 0.5513,
|
| 780 |
+
"step": 110
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.1935483870967742,
|
| 784 |
+
"grad_norm": 1.246553411484507,
|
| 785 |
+
"learning_rate": 7.5897781711723215e-06,
|
| 786 |
+
"loss": 0.3581,
|
| 787 |
+
"step": 111
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.2043010752688172,
|
| 791 |
+
"grad_norm": 1.1736474380398347,
|
| 792 |
+
"learning_rate": 7.536044010498396e-06,
|
| 793 |
+
"loss": 0.3513,
|
| 794 |
+
"step": 112
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.2150537634408602,
|
| 798 |
+
"grad_norm": 1.2797115429626638,
|
| 799 |
+
"learning_rate": 7.48191256368028e-06,
|
| 800 |
+
"loss": 0.3443,
|
| 801 |
+
"step": 113
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.2258064516129032,
|
| 805 |
+
"grad_norm": 1.197978350617973,
|
| 806 |
+
"learning_rate": 7.427392310726088e-06,
|
| 807 |
+
"loss": 0.3603,
|
| 808 |
+
"step": 114
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.2365591397849462,
|
| 812 |
+
"grad_norm": 1.1727521029345562,
|
| 813 |
+
"learning_rate": 7.372491792552694e-06,
|
| 814 |
+
"loss": 0.3738,
|
| 815 |
+
"step": 115
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.2473118279569892,
|
| 819 |
+
"grad_norm": 1.1707826597566307,
|
| 820 |
+
"learning_rate": 7.31721960964774e-06,
|
| 821 |
+
"loss": 0.3881,
|
| 822 |
+
"step": 116
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.2580645161290323,
|
| 826 |
+
"grad_norm": 1.2094231500149508,
|
| 827 |
+
"learning_rate": 7.261584420722328e-06,
|
| 828 |
+
"loss": 0.5288,
|
| 829 |
+
"step": 117
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.2688172043010753,
|
| 833 |
+
"grad_norm": 1.1809429787295744,
|
| 834 |
+
"learning_rate": 7.20559494135458e-06,
|
| 835 |
+
"loss": 0.3781,
|
| 836 |
+
"step": 118
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.2795698924731183,
|
| 840 |
+
"grad_norm": 1.1434463967884962,
|
| 841 |
+
"learning_rate": 7.149259942624287e-06,
|
| 842 |
+
"loss": 0.3717,
|
| 843 |
+
"step": 119
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.2903225806451613,
|
| 847 |
+
"grad_norm": 1.1430462929379024,
|
| 848 |
+
"learning_rate": 7.092588249738871e-06,
|
| 849 |
+
"loss": 0.373,
|
| 850 |
+
"step": 120
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.3010752688172043,
|
| 854 |
+
"grad_norm": 1.4627760719280838,
|
| 855 |
+
"learning_rate": 7.03558874065087e-06,
|
| 856 |
+
"loss": 0.3809,
|
| 857 |
+
"step": 121
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.3118279569892473,
|
| 861 |
+
"grad_norm": 1.182317091439007,
|
| 862 |
+
"learning_rate": 6.978270344667143e-06,
|
| 863 |
+
"loss": 0.3583,
|
| 864 |
+
"step": 122
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.3225806451612903,
|
| 868 |
+
"grad_norm": 1.243697527950775,
|
| 869 |
+
"learning_rate": 6.920642041050055e-06,
|
| 870 |
+
"loss": 0.3207,
|
| 871 |
+
"step": 123
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.3333333333333333,
|
| 875 |
+
"grad_norm": 1.2759794387408534,
|
| 876 |
+
"learning_rate": 6.862712857610812e-06,
|
| 877 |
+
"loss": 0.3633,
|
| 878 |
+
"step": 124
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.3440860215053765,
|
| 882 |
+
"grad_norm": 1.1295106977198248,
|
| 883 |
+
"learning_rate": 6.804491869295207e-06,
|
| 884 |
+
"loss": 0.4274,
|
| 885 |
+
"step": 125
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.3548387096774195,
|
| 889 |
+
"grad_norm": 1.1901126832185107,
|
| 890 |
+
"learning_rate": 6.745988196761976e-06,
|
| 891 |
+
"loss": 0.3779,
|
| 892 |
+
"step": 126
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.3655913978494625,
|
| 896 |
+
"grad_norm": 1.3373142316442945,
|
| 897 |
+
"learning_rate": 6.687211004953992e-06,
|
| 898 |
+
"loss": 0.3618,
|
| 899 |
+
"step": 127
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.3763440860215055,
|
| 903 |
+
"grad_norm": 1.116240494926489,
|
| 904 |
+
"learning_rate": 6.628169501662527e-06,
|
| 905 |
+
"loss": 0.3347,
|
| 906 |
+
"step": 128
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.3870967741935485,
|
| 910 |
+
"grad_norm": 1.3073080378383377,
|
| 911 |
+
"learning_rate": 6.568872936084789e-06,
|
| 912 |
+
"loss": 0.3924,
|
| 913 |
+
"step": 129
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.3978494623655915,
|
| 917 |
+
"grad_norm": 1.1658881438715565,
|
| 918 |
+
"learning_rate": 6.509330597374993e-06,
|
| 919 |
+
"loss": 0.3349,
|
| 920 |
+
"step": 130
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.4086021505376345,
|
| 924 |
+
"grad_norm": 1.3285197694874702,
|
| 925 |
+
"learning_rate": 6.44955181318915e-06,
|
| 926 |
+
"loss": 0.383,
|
| 927 |
+
"step": 131
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.4193548387096775,
|
| 931 |
+
"grad_norm": 1.1421963318126769,
|
| 932 |
+
"learning_rate": 6.389545948223841e-06,
|
| 933 |
+
"loss": 0.35,
|
| 934 |
+
"step": 132
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.4301075268817205,
|
| 938 |
+
"grad_norm": 1.1800566601708844,
|
| 939 |
+
"learning_rate": 6.329322402749181e-06,
|
| 940 |
+
"loss": 0.36,
|
| 941 |
+
"step": 133
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.4408602150537635,
|
| 945 |
+
"grad_norm": 1.181427392470128,
|
| 946 |
+
"learning_rate": 6.2688906111362115e-06,
|
| 947 |
+
"loss": 0.366,
|
| 948 |
+
"step": 134
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.4516129032258065,
|
| 952 |
+
"grad_norm": 1.155888875463247,
|
| 953 |
+
"learning_rate": 6.208260040378946e-06,
|
| 954 |
+
"loss": 0.3497,
|
| 955 |
+
"step": 135
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.4623655913978495,
|
| 959 |
+
"grad_norm": 1.1786815694111499,
|
| 960 |
+
"learning_rate": 6.147440188611324e-06,
|
| 961 |
+
"loss": 0.3537,
|
| 962 |
+
"step": 136
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.4731182795698925,
|
| 966 |
+
"grad_norm": 1.2051193700127212,
|
| 967 |
+
"learning_rate": 6.0864405836192575e-06,
|
| 968 |
+
"loss": 0.3527,
|
| 969 |
+
"step": 137
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.4838709677419355,
|
| 973 |
+
"grad_norm": 1.2284826404113511,
|
| 974 |
+
"learning_rate": 6.025270781348055e-06,
|
| 975 |
+
"loss": 0.3378,
|
| 976 |
+
"step": 138
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.4946236559139785,
|
| 980 |
+
"grad_norm": 1.247829453357803,
|
| 981 |
+
"learning_rate": 5.963940364405425e-06,
|
| 982 |
+
"loss": 0.3696,
|
| 983 |
+
"step": 139
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.5053763440860215,
|
| 987 |
+
"grad_norm": 1.201613514704844,
|
| 988 |
+
"learning_rate": 5.902458940560304e-06,
|
| 989 |
+
"loss": 0.3738,
|
| 990 |
+
"step": 140
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.5161290322580645,
|
| 994 |
+
"grad_norm": 1.169777798872826,
|
| 995 |
+
"learning_rate": 5.8408361412377475e-06,
|
| 996 |
+
"loss": 0.3335,
|
| 997 |
+
"step": 141
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.5268817204301075,
|
| 1001 |
+
"grad_norm": 1.122966037731356,
|
| 1002 |
+
"learning_rate": 5.779081620010104e-06,
|
| 1003 |
+
"loss": 0.3232,
|
| 1004 |
+
"step": 142
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.5376344086021505,
|
| 1008 |
+
"grad_norm": 1.194793658559918,
|
| 1009 |
+
"learning_rate": 5.717205051084731e-06,
|
| 1010 |
+
"loss": 0.3392,
|
| 1011 |
+
"step": 143
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.5483870967741935,
|
| 1015 |
+
"grad_norm": 1.2783006705254338,
|
| 1016 |
+
"learning_rate": 5.655216127788472e-06,
|
| 1017 |
+
"loss": 0.3711,
|
| 1018 |
+
"step": 144
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.5591397849462365,
|
| 1022 |
+
"grad_norm": 1.128328576854692,
|
| 1023 |
+
"learning_rate": 5.593124561049141e-06,
|
| 1024 |
+
"loss": 0.3435,
|
| 1025 |
+
"step": 145
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.5698924731182795,
|
| 1029 |
+
"grad_norm": 1.191976250642684,
|
| 1030 |
+
"learning_rate": 5.530940077874248e-06,
|
| 1031 |
+
"loss": 0.3617,
|
| 1032 |
+
"step": 146
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.5806451612903225,
|
| 1036 |
+
"grad_norm": 1.1652853933490293,
|
| 1037 |
+
"learning_rate": 5.468672419827208e-06,
|
| 1038 |
+
"loss": 0.3399,
|
| 1039 |
+
"step": 147
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.5913978494623655,
|
| 1043 |
+
"grad_norm": 1.0915560758197622,
|
| 1044 |
+
"learning_rate": 5.406331341501264e-06,
|
| 1045 |
+
"loss": 0.339,
|
| 1046 |
+
"step": 148
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.6021505376344085,
|
| 1050 |
+
"grad_norm": 1.1053574420353864,
|
| 1051 |
+
"learning_rate": 5.34392660899138e-06,
|
| 1052 |
+
"loss": 0.3207,
|
| 1053 |
+
"step": 149
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.6129032258064515,
|
| 1057 |
+
"grad_norm": 1.1460690041968786,
|
| 1058 |
+
"learning_rate": 5.281467998364314e-06,
|
| 1059 |
+
"loss": 0.3308,
|
| 1060 |
+
"step": 150
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.6236559139784945,
|
| 1064 |
+
"grad_norm": 1.1570813052418365,
|
| 1065 |
+
"learning_rate": 5.218965294127155e-06,
|
| 1066 |
+
"loss": 0.3501,
|
| 1067 |
+
"step": 151
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.6344086021505375,
|
| 1071 |
+
"grad_norm": 1.2691321046241564,
|
| 1072 |
+
"learning_rate": 5.156428287694508e-06,
|
| 1073 |
+
"loss": 0.3542,
|
| 1074 |
+
"step": 152
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.6451612903225805,
|
| 1078 |
+
"grad_norm": 1.1765795742693084,
|
| 1079 |
+
"learning_rate": 5.093866775854618e-06,
|
| 1080 |
+
"loss": 0.334,
|
| 1081 |
+
"step": 153
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.6559139784946235,
|
| 1085 |
+
"grad_norm": 1.114227715473016,
|
| 1086 |
+
"learning_rate": 5.03129055923465e-06,
|
| 1087 |
+
"loss": 0.3124,
|
| 1088 |
+
"step": 154
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.6666666666666665,
|
| 1092 |
+
"grad_norm": 1.2728424503735456,
|
| 1093 |
+
"learning_rate": 4.968709440765352e-06,
|
| 1094 |
+
"loss": 0.3608,
|
| 1095 |
+
"step": 155
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.6774193548387095,
|
| 1099 |
+
"grad_norm": 1.2957106875665612,
|
| 1100 |
+
"learning_rate": 4.906133224145384e-06,
|
| 1101 |
+
"loss": 0.4535,
|
| 1102 |
+
"step": 156
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.6881720430107527,
|
| 1106 |
+
"grad_norm": 1.1832693336037738,
|
| 1107 |
+
"learning_rate": 4.843571712305493e-06,
|
| 1108 |
+
"loss": 0.347,
|
| 1109 |
+
"step": 157
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.6989247311827957,
|
| 1113 |
+
"grad_norm": 1.1976541159478242,
|
| 1114 |
+
"learning_rate": 4.781034705872846e-06,
|
| 1115 |
+
"loss": 0.3429,
|
| 1116 |
+
"step": 158
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.7096774193548387,
|
| 1120 |
+
"grad_norm": 1.1965466685156962,
|
| 1121 |
+
"learning_rate": 4.7185320016356865e-06,
|
| 1122 |
+
"loss": 0.353,
|
| 1123 |
+
"step": 159
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.7204301075268817,
|
| 1127 |
+
"grad_norm": 1.3091493751262704,
|
| 1128 |
+
"learning_rate": 4.656073391008622e-06,
|
| 1129 |
+
"loss": 0.3955,
|
| 1130 |
+
"step": 160
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.7311827956989247,
|
| 1134 |
+
"grad_norm": 1.1853179338764237,
|
| 1135 |
+
"learning_rate": 4.593668658498737e-06,
|
| 1136 |
+
"loss": 0.3522,
|
| 1137 |
+
"step": 161
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.7419354838709677,
|
| 1141 |
+
"grad_norm": 1.0940886869833208,
|
| 1142 |
+
"learning_rate": 4.531327580172794e-06,
|
| 1143 |
+
"loss": 0.3609,
|
| 1144 |
+
"step": 162
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.7526881720430108,
|
| 1148 |
+
"grad_norm": 1.241588019056234,
|
| 1149 |
+
"learning_rate": 4.469059922125753e-06,
|
| 1150 |
+
"loss": 0.3518,
|
| 1151 |
+
"step": 163
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.7634408602150538,
|
| 1155 |
+
"grad_norm": 1.3864224154338305,
|
| 1156 |
+
"learning_rate": 4.4068754389508616e-06,
|
| 1157 |
+
"loss": 0.4151,
|
| 1158 |
+
"step": 164
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.7741935483870968,
|
| 1162 |
+
"grad_norm": 1.2098619933759385,
|
| 1163 |
+
"learning_rate": 4.34478387221153e-06,
|
| 1164 |
+
"loss": 0.348,
|
| 1165 |
+
"step": 165
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 1.7849462365591398,
|
| 1169 |
+
"grad_norm": 1.2016121769392047,
|
| 1170 |
+
"learning_rate": 4.282794948915271e-06,
|
| 1171 |
+
"loss": 0.3336,
|
| 1172 |
+
"step": 166
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.7956989247311828,
|
| 1176 |
+
"grad_norm": 1.2364712139446496,
|
| 1177 |
+
"learning_rate": 4.220918379989898e-06,
|
| 1178 |
+
"loss": 0.3815,
|
| 1179 |
+
"step": 167
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.8064516129032258,
|
| 1183 |
+
"grad_norm": 1.1677279665442852,
|
| 1184 |
+
"learning_rate": 4.159163858762255e-06,
|
| 1185 |
+
"loss": 0.3284,
|
| 1186 |
+
"step": 168
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.817204301075269,
|
| 1190 |
+
"grad_norm": 1.2119363388446562,
|
| 1191 |
+
"learning_rate": 4.097541059439698e-06,
|
| 1192 |
+
"loss": 0.3662,
|
| 1193 |
+
"step": 169
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.827956989247312,
|
| 1197 |
+
"grad_norm": 1.1480161774722477,
|
| 1198 |
+
"learning_rate": 4.036059635594578e-06,
|
| 1199 |
+
"loss": 0.3589,
|
| 1200 |
+
"step": 170
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.838709677419355,
|
| 1204 |
+
"grad_norm": 1.2274813656457675,
|
| 1205 |
+
"learning_rate": 3.974729218651946e-06,
|
| 1206 |
+
"loss": 0.3249,
|
| 1207 |
+
"step": 171
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.849462365591398,
|
| 1211 |
+
"grad_norm": 1.2174884876788425,
|
| 1212 |
+
"learning_rate": 3.913559416380743e-06,
|
| 1213 |
+
"loss": 0.3605,
|
| 1214 |
+
"step": 172
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.860215053763441,
|
| 1218 |
+
"grad_norm": 1.2173044748787643,
|
| 1219 |
+
"learning_rate": 3.852559811388676e-06,
|
| 1220 |
+
"loss": 0.3622,
|
| 1221 |
+
"step": 173
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 1.870967741935484,
|
| 1225 |
+
"grad_norm": 1.0993262002539315,
|
| 1226 |
+
"learning_rate": 3.791739959621054e-06,
|
| 1227 |
+
"loss": 0.3159,
|
| 1228 |
+
"step": 174
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 1.881720430107527,
|
| 1232 |
+
"grad_norm": 1.1781627168157496,
|
| 1233 |
+
"learning_rate": 3.7311093888637906e-06,
|
| 1234 |
+
"loss": 0.37,
|
| 1235 |
+
"step": 175
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 1.89247311827957,
|
| 1239 |
+
"grad_norm": 1.120376466539403,
|
| 1240 |
+
"learning_rate": 3.670677597250819e-06,
|
| 1241 |
+
"loss": 0.3628,
|
| 1242 |
+
"step": 176
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.903225806451613,
|
| 1246 |
+
"grad_norm": 1.1144596517150382,
|
| 1247 |
+
"learning_rate": 3.6104540517761594e-06,
|
| 1248 |
+
"loss": 0.3525,
|
| 1249 |
+
"step": 177
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 1.913978494623656,
|
| 1253 |
+
"grad_norm": 1.1541300654588889,
|
| 1254 |
+
"learning_rate": 3.55044818681085e-06,
|
| 1255 |
+
"loss": 0.3224,
|
| 1256 |
+
"step": 178
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.924731182795699,
|
| 1260 |
+
"grad_norm": 1.2475568699772912,
|
| 1261 |
+
"learning_rate": 3.4906694026250075e-06,
|
| 1262 |
+
"loss": 0.3474,
|
| 1263 |
+
"step": 179
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 1.935483870967742,
|
| 1267 |
+
"grad_norm": 1.1498672361648068,
|
| 1268 |
+
"learning_rate": 3.431127063915213e-06,
|
| 1269 |
+
"loss": 0.3339,
|
| 1270 |
+
"step": 180
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 1.946236559139785,
|
| 1274 |
+
"grad_norm": 1.2308326285216238,
|
| 1275 |
+
"learning_rate": 3.371830498337475e-06,
|
| 1276 |
+
"loss": 0.3123,
|
| 1277 |
+
"step": 181
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 1.956989247311828,
|
| 1281 |
+
"grad_norm": 1.1895143093091571,
|
| 1282 |
+
"learning_rate": 3.3127889950460094e-06,
|
| 1283 |
+
"loss": 0.343,
|
| 1284 |
+
"step": 182
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 1.967741935483871,
|
| 1288 |
+
"grad_norm": 1.1762159546277886,
|
| 1289 |
+
"learning_rate": 3.254011803238026e-06,
|
| 1290 |
+
"loss": 0.3402,
|
| 1291 |
+
"step": 183
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 1.978494623655914,
|
| 1295 |
+
"grad_norm": 1.153653621278308,
|
| 1296 |
+
"learning_rate": 3.195508130704795e-06,
|
| 1297 |
+
"loss": 0.3766,
|
| 1298 |
+
"step": 184
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 1.989247311827957,
|
| 1302 |
+
"grad_norm": 1.2087190097752418,
|
| 1303 |
+
"learning_rate": 3.1372871423891894e-06,
|
| 1304 |
+
"loss": 0.3827,
|
| 1305 |
+
"step": 185
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 2.0,
|
| 1309 |
+
"grad_norm": 1.089032118871395,
|
| 1310 |
+
"learning_rate": 3.079357958949946e-06,
|
| 1311 |
+
"loss": 0.3326,
|
| 1312 |
+
"step": 186
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 2.010752688172043,
|
| 1316 |
+
"grad_norm": 1.2353249862535516,
|
| 1317 |
+
"learning_rate": 3.021729655332858e-06,
|
| 1318 |
+
"loss": 0.2291,
|
| 1319 |
+
"step": 187
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 2.021505376344086,
|
| 1323 |
+
"grad_norm": 1.1205213073958726,
|
| 1324 |
+
"learning_rate": 2.9644112593491315e-06,
|
| 1325 |
+
"loss": 0.2793,
|
| 1326 |
+
"step": 188
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 2.032258064516129,
|
| 1330 |
+
"grad_norm": 1.0679682742372525,
|
| 1331 |
+
"learning_rate": 2.90741175026113e-06,
|
| 1332 |
+
"loss": 0.2318,
|
| 1333 |
+
"step": 189
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 2.043010752688172,
|
| 1337 |
+
"grad_norm": 1.0416057740465434,
|
| 1338 |
+
"learning_rate": 2.850740057375716e-06,
|
| 1339 |
+
"loss": 0.2268,
|
| 1340 |
+
"step": 190
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 2.053763440860215,
|
| 1344 |
+
"grad_norm": 1.1650862570167908,
|
| 1345 |
+
"learning_rate": 2.7944050586454215e-06,
|
| 1346 |
+
"loss": 0.2683,
|
| 1347 |
+
"step": 191
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 2.064516129032258,
|
| 1351 |
+
"grad_norm": 1.0439734734555002,
|
| 1352 |
+
"learning_rate": 2.7384155792776724e-06,
|
| 1353 |
+
"loss": 0.2025,
|
| 1354 |
+
"step": 192
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 2.075268817204301,
|
| 1358 |
+
"grad_norm": 1.0872608821496301,
|
| 1359 |
+
"learning_rate": 2.682780390352262e-06,
|
| 1360 |
+
"loss": 0.2393,
|
| 1361 |
+
"step": 193
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 2.086021505376344,
|
| 1365 |
+
"grad_norm": 1.1996863353483587,
|
| 1366 |
+
"learning_rate": 2.627508207447308e-06,
|
| 1367 |
+
"loss": 0.2294,
|
| 1368 |
+
"step": 194
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 2.096774193548387,
|
| 1372 |
+
"grad_norm": 1.2259184666219345,
|
| 1373 |
+
"learning_rate": 2.5726076892739127e-06,
|
| 1374 |
+
"loss": 0.2282,
|
| 1375 |
+
"step": 195
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 2.10752688172043,
|
| 1379 |
+
"grad_norm": 1.169799186561526,
|
| 1380 |
+
"learning_rate": 2.5180874363197217e-06,
|
| 1381 |
+
"loss": 0.4074,
|
| 1382 |
+
"step": 196
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 2.118279569892473,
|
| 1386 |
+
"grad_norm": 1.2450757774784624,
|
| 1387 |
+
"learning_rate": 2.463955989501607e-06,
|
| 1388 |
+
"loss": 0.2049,
|
| 1389 |
+
"step": 197
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 2.129032258064516,
|
| 1393 |
+
"grad_norm": 1.2928234399217249,
|
| 1394 |
+
"learning_rate": 2.41022182882768e-06,
|
| 1395 |
+
"loss": 0.2867,
|
| 1396 |
+
"step": 198
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 2.139784946236559,
|
| 1400 |
+
"grad_norm": 1.4079638381400967,
|
| 1401 |
+
"learning_rate": 2.356893372068855e-06,
|
| 1402 |
+
"loss": 0.2632,
|
| 1403 |
+
"step": 199
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 2.150537634408602,
|
| 1407 |
+
"grad_norm": 1.2856070305392429,
|
| 1408 |
+
"learning_rate": 2.3039789734401524e-06,
|
| 1409 |
+
"loss": 0.2136,
|
| 1410 |
+
"step": 200
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 2.161290322580645,
|
| 1414 |
+
"grad_norm": 1.257947749337111,
|
| 1415 |
+
"learning_rate": 2.251486922291957e-06,
|
| 1416 |
+
"loss": 0.2032,
|
| 1417 |
+
"step": 201
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 2.172043010752688,
|
| 1421 |
+
"grad_norm": 1.2185848133318558,
|
| 1422 |
+
"learning_rate": 2.1994254418114524e-06,
|
| 1423 |
+
"loss": 0.2516,
|
| 1424 |
+
"step": 202
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 2.182795698924731,
|
| 1428 |
+
"grad_norm": 1.1801170107899257,
|
| 1429 |
+
"learning_rate": 2.147802687734409e-06,
|
| 1430 |
+
"loss": 0.1965,
|
| 1431 |
+
"step": 203
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 2.193548387096774,
|
| 1435 |
+
"grad_norm": 1.0247500981424174,
|
| 1436 |
+
"learning_rate": 2.0966267470675273e-06,
|
| 1437 |
+
"loss": 0.198,
|
| 1438 |
+
"step": 204
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 2.204301075268817,
|
| 1442 |
+
"grad_norm": 1.16238195309318,
|
| 1443 |
+
"learning_rate": 2.0459056368215786e-06,
|
| 1444 |
+
"loss": 0.3509,
|
| 1445 |
+
"step": 205
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 2.21505376344086,
|
| 1449 |
+
"grad_norm": 1.034172470881347,
|
| 1450 |
+
"learning_rate": 1.9956473027554846e-06,
|
| 1451 |
+
"loss": 0.2416,
|
| 1452 |
+
"step": 206
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 2.225806451612903,
|
| 1456 |
+
"grad_norm": 1.2244901538313122,
|
| 1457 |
+
"learning_rate": 1.9458596181315643e-06,
|
| 1458 |
+
"loss": 0.2525,
|
| 1459 |
+
"step": 207
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 2.236559139784946,
|
| 1463 |
+
"grad_norm": 1.0823123036421982,
|
| 1464 |
+
"learning_rate": 1.8965503824821496e-06,
|
| 1465 |
+
"loss": 0.2103,
|
| 1466 |
+
"step": 208
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 2.247311827956989,
|
| 1470 |
+
"grad_norm": 1.1187165499095806,
|
| 1471 |
+
"learning_rate": 1.84772732038774e-06,
|
| 1472 |
+
"loss": 0.2403,
|
| 1473 |
+
"step": 209
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 2.258064516129032,
|
| 1477 |
+
"grad_norm": 1.0442209176999298,
|
| 1478 |
+
"learning_rate": 1.7993980802668947e-06,
|
| 1479 |
+
"loss": 0.2059,
|
| 1480 |
+
"step": 210
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 2.268817204301075,
|
| 1484 |
+
"grad_norm": 1.039636339404873,
|
| 1485 |
+
"learning_rate": 1.7515702331780753e-06,
|
| 1486 |
+
"loss": 0.2106,
|
| 1487 |
+
"step": 211
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 2.279569892473118,
|
| 1491 |
+
"grad_norm": 0.971952637708957,
|
| 1492 |
+
"learning_rate": 1.7042512716335873e-06,
|
| 1493 |
+
"loss": 0.1833,
|
| 1494 |
+
"step": 212
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 2.2903225806451615,
|
| 1498 |
+
"grad_norm": 1.0335059735288603,
|
| 1499 |
+
"learning_rate": 1.6574486084258369e-06,
|
| 1500 |
+
"loss": 0.2071,
|
| 1501 |
+
"step": 213
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 2.3010752688172045,
|
| 1505 |
+
"grad_norm": 1.1712890998348404,
|
| 1506 |
+
"learning_rate": 1.6111695754660667e-06,
|
| 1507 |
+
"loss": 0.2277,
|
| 1508 |
+
"step": 214
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 2.3118279569892475,
|
| 1512 |
+
"grad_norm": 1.0093534018268129,
|
| 1513 |
+
"learning_rate": 1.5654214226357822e-06,
|
| 1514 |
+
"loss": 0.2318,
|
| 1515 |
+
"step": 215
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 2.3225806451612905,
|
| 1519 |
+
"grad_norm": 1.1389615413860168,
|
| 1520 |
+
"learning_rate": 1.5202113166510058e-06,
|
| 1521 |
+
"loss": 0.1953,
|
| 1522 |
+
"step": 216
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 2.3333333333333335,
|
| 1526 |
+
"grad_norm": 1.246098734753724,
|
| 1527 |
+
"learning_rate": 1.475546339939568e-06,
|
| 1528 |
+
"loss": 0.2623,
|
| 1529 |
+
"step": 217
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 2.3440860215053765,
|
| 1533 |
+
"grad_norm": 1.1558696943090916,
|
| 1534 |
+
"learning_rate": 1.4314334895316095e-06,
|
| 1535 |
+
"loss": 0.2445,
|
| 1536 |
+
"step": 218
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 2.3548387096774195,
|
| 1540 |
+
"grad_norm": 1.2104135716011495,
|
| 1541 |
+
"learning_rate": 1.3878796759634544e-06,
|
| 1542 |
+
"loss": 0.2306,
|
| 1543 |
+
"step": 219
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 2.3655913978494625,
|
| 1547 |
+
"grad_norm": 1.2234866527768256,
|
| 1548 |
+
"learning_rate": 1.3448917221950264e-06,
|
| 1549 |
+
"loss": 0.2374,
|
| 1550 |
+
"step": 220
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 2.3763440860215055,
|
| 1554 |
+
"grad_norm": 1.0431434616717088,
|
| 1555 |
+
"learning_rate": 1.3024763625410025e-06,
|
| 1556 |
+
"loss": 0.2015,
|
| 1557 |
+
"step": 221
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 2.3870967741935485,
|
| 1561 |
+
"grad_norm": 1.0687881028758524,
|
| 1562 |
+
"learning_rate": 1.2606402416158391e-06,
|
| 1563 |
+
"loss": 0.2067,
|
| 1564 |
+
"step": 222
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 2.3978494623655915,
|
| 1568 |
+
"grad_norm": 1.134243323797628,
|
| 1569 |
+
"learning_rate": 1.2193899132928539e-06,
|
| 1570 |
+
"loss": 0.2183,
|
| 1571 |
+
"step": 223
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 2.4086021505376345,
|
| 1575 |
+
"grad_norm": 1.0372879190394384,
|
| 1576 |
+
"learning_rate": 1.1787318396775188e-06,
|
| 1577 |
+
"loss": 0.1999,
|
| 1578 |
+
"step": 224
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 2.4193548387096775,
|
| 1582 |
+
"grad_norm": 1.1665054400030295,
|
| 1583 |
+
"learning_rate": 1.138672390095143e-06,
|
| 1584 |
+
"loss": 0.2359,
|
| 1585 |
+
"step": 225
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 2.4301075268817205,
|
| 1589 |
+
"grad_norm": 1.0236202702671575,
|
| 1590 |
+
"learning_rate": 1.0992178400930753e-06,
|
| 1591 |
+
"loss": 0.2212,
|
| 1592 |
+
"step": 226
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 2.4408602150537635,
|
| 1596 |
+
"grad_norm": 1.0558233259176077,
|
| 1597 |
+
"learning_rate": 1.0603743704575992e-06,
|
| 1598 |
+
"loss": 0.2345,
|
| 1599 |
+
"step": 227
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 2.4516129032258065,
|
| 1603 |
+
"grad_norm": 1.0155424223780078,
|
| 1604 |
+
"learning_rate": 1.0221480662456845e-06,
|
| 1605 |
+
"loss": 0.2339,
|
| 1606 |
+
"step": 228
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 2.4623655913978495,
|
| 1610 |
+
"grad_norm": 1.1436634892190285,
|
| 1611 |
+
"learning_rate": 9.845449158317216e-07,
|
| 1612 |
+
"loss": 0.2091,
|
| 1613 |
+
"step": 229
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 2.4731182795698925,
|
| 1617 |
+
"grad_norm": 1.0556139362512549,
|
| 1618 |
+
"learning_rate": 9.475708099694125e-07,
|
| 1619 |
+
"loss": 0.2178,
|
| 1620 |
+
"step": 230
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 2.4838709677419355,
|
| 1624 |
+
"grad_norm": 1.0522117165285618,
|
| 1625 |
+
"learning_rate": 9.112315408689415e-07,
|
| 1626 |
+
"loss": 0.4077,
|
| 1627 |
+
"step": 231
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 2.4946236559139785,
|
| 1631 |
+
"grad_norm": 1.181359684461707,
|
| 1632 |
+
"learning_rate": 8.755328012896002e-07,
|
| 1633 |
+
"loss": 0.2357,
|
| 1634 |
+
"step": 232
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 2.5053763440860215,
|
| 1638 |
+
"grad_norm": 1.0897935630524107,
|
| 1639 |
+
"learning_rate": 8.404801836479809e-07,
|
| 1640 |
+
"loss": 0.2112,
|
| 1641 |
+
"step": 233
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 2.5161290322580645,
|
| 1645 |
+
"grad_norm": 1.2518780229754654,
|
| 1646 |
+
"learning_rate": 8.060791791418887e-07,
|
| 1647 |
+
"loss": 0.2562,
|
| 1648 |
+
"step": 234
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 2.5268817204301075,
|
| 1652 |
+
"grad_norm": 1.1188351065056708,
|
| 1653 |
+
"learning_rate": 7.723351768901172e-07,
|
| 1654 |
+
"loss": 0.2323,
|
| 1655 |
+
"step": 235
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 2.5376344086021505,
|
| 1659 |
+
"grad_norm": 1.065402387910212,
|
| 1660 |
+
"learning_rate": 7.392534630882092e-07,
|
| 1661 |
+
"loss": 0.2481,
|
| 1662 |
+
"step": 236
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 2.5483870967741935,
|
| 1666 |
+
"grad_norm": 1.1032094587545522,
|
| 1667 |
+
"learning_rate": 7.06839220180342e-07,
|
| 1668 |
+
"loss": 0.2124,
|
| 1669 |
+
"step": 237
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 2.5591397849462365,
|
| 1673 |
+
"grad_norm": 1.0607815817961583,
|
| 1674 |
+
"learning_rate": 6.750975260474718e-07,
|
| 1675 |
+
"loss": 0.2528,
|
| 1676 |
+
"step": 238
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 2.5698924731182795,
|
| 1680 |
+
"grad_norm": 1.1102586160747114,
|
| 1681 |
+
"learning_rate": 6.440333532118503e-07,
|
| 1682 |
+
"loss": 0.218,
|
| 1683 |
+
"step": 239
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 2.5806451612903225,
|
| 1687 |
+
"grad_norm": 1.067767516141593,
|
| 1688 |
+
"learning_rate": 6.136515680580479e-07,
|
| 1689 |
+
"loss": 0.2233,
|
| 1690 |
+
"step": 240
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 2.5913978494623655,
|
| 1694 |
+
"grad_norm": 0.998507674449185,
|
| 1695 |
+
"learning_rate": 5.839569300706127e-07,
|
| 1696 |
+
"loss": 0.2116,
|
| 1697 |
+
"step": 241
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 2.6021505376344085,
|
| 1701 |
+
"grad_norm": 1.0336044812206406,
|
| 1702 |
+
"learning_rate": 5.549540910884649e-07,
|
| 1703 |
+
"loss": 0.1977,
|
| 1704 |
+
"step": 242
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 2.6129032258064515,
|
| 1708 |
+
"grad_norm": 1.0581929188450587,
|
| 1709 |
+
"learning_rate": 5.266475945761562e-07,
|
| 1710 |
+
"loss": 0.2062,
|
| 1711 |
+
"step": 243
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 2.6236559139784945,
|
| 1715 |
+
"grad_norm": 1.1943327940895927,
|
| 1716 |
+
"learning_rate": 4.990418749121179e-07,
|
| 1717 |
+
"loss": 0.2217,
|
| 1718 |
+
"step": 244
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 2.6344086021505375,
|
| 1722 |
+
"grad_norm": 1.0573079691578624,
|
| 1723 |
+
"learning_rate": 4.721412566939804e-07,
|
| 1724 |
+
"loss": 0.2265,
|
| 1725 |
+
"step": 245
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 2.6451612903225805,
|
| 1729 |
+
"grad_norm": 1.010938446897227,
|
| 1730 |
+
"learning_rate": 4.4594995406110785e-07,
|
| 1731 |
+
"loss": 0.2379,
|
| 1732 |
+
"step": 246
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 2.6559139784946235,
|
| 1736 |
+
"grad_norm": 1.1607031036965616,
|
| 1737 |
+
"learning_rate": 4.2047207003442003e-07,
|
| 1738 |
+
"loss": 0.2079,
|
| 1739 |
+
"step": 247
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 2.6666666666666665,
|
| 1743 |
+
"grad_norm": 1.0632285683620692,
|
| 1744 |
+
"learning_rate": 3.957115958736374e-07,
|
| 1745 |
+
"loss": 0.2321,
|
| 1746 |
+
"step": 248
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 2.6774193548387095,
|
| 1750 |
+
"grad_norm": 0.9910529748392375,
|
| 1751 |
+
"learning_rate": 3.7167241045202474e-07,
|
| 1752 |
+
"loss": 0.1987,
|
| 1753 |
+
"step": 249
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 2.688172043010753,
|
| 1757 |
+
"grad_norm": 1.0775742035983213,
|
| 1758 |
+
"learning_rate": 3.483582796487395e-07,
|
| 1759 |
+
"loss": 0.2094,
|
| 1760 |
+
"step": 250
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 2.698924731182796,
|
| 1764 |
+
"grad_norm": 0.9984569332006167,
|
| 1765 |
+
"learning_rate": 3.257728557588902e-07,
|
| 1766 |
+
"loss": 0.25,
|
| 1767 |
+
"step": 251
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 2.709677419354839,
|
| 1771 |
+
"grad_norm": 1.206448802708809,
|
| 1772 |
+
"learning_rate": 3.039196769213787e-07,
|
| 1773 |
+
"loss": 0.2763,
|
| 1774 |
+
"step": 252
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 2.720430107526882,
|
| 1778 |
+
"grad_norm": 1.1154480238255622,
|
| 1779 |
+
"learning_rate": 2.828021665646341e-07,
|
| 1780 |
+
"loss": 0.221,
|
| 1781 |
+
"step": 253
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 2.731182795698925,
|
| 1785 |
+
"grad_norm": 1.1493470631886933,
|
| 1786 |
+
"learning_rate": 2.6242363287030617e-07,
|
| 1787 |
+
"loss": 0.3025,
|
| 1788 |
+
"step": 254
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 2.741935483870968,
|
| 1792 |
+
"grad_norm": 1.0349657874746057,
|
| 1793 |
+
"learning_rate": 2.4278726825502696e-07,
|
| 1794 |
+
"loss": 0.2539,
|
| 1795 |
+
"step": 255
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 2.752688172043011,
|
| 1799 |
+
"grad_norm": 1.109346692196228,
|
| 1800 |
+
"learning_rate": 2.2389614887029564e-07,
|
| 1801 |
+
"loss": 0.2281,
|
| 1802 |
+
"step": 256
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 2.763440860215054,
|
| 1806 |
+
"grad_norm": 1.0353141380673936,
|
| 1807 |
+
"learning_rate": 2.0575323412058036e-07,
|
| 1808 |
+
"loss": 0.2141,
|
| 1809 |
+
"step": 257
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 2.774193548387097,
|
| 1813 |
+
"grad_norm": 1.0819606199339722,
|
| 1814 |
+
"learning_rate": 1.8836136619971468e-07,
|
| 1815 |
+
"loss": 0.2195,
|
| 1816 |
+
"step": 258
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 2.78494623655914,
|
| 1820 |
+
"grad_norm": 1.177939271195523,
|
| 1821 |
+
"learning_rate": 1.7172326964564777e-07,
|
| 1822 |
+
"loss": 0.2508,
|
| 1823 |
+
"step": 259
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 2.795698924731183,
|
| 1827 |
+
"grad_norm": 1.1223938711713661,
|
| 1828 |
+
"learning_rate": 1.5584155091362907e-07,
|
| 1829 |
+
"loss": 0.2264,
|
| 1830 |
+
"step": 260
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 2.806451612903226,
|
| 1834 |
+
"grad_norm": 0.9908185773525874,
|
| 1835 |
+
"learning_rate": 1.4071869796789427e-07,
|
| 1836 |
+
"loss": 0.1976,
|
| 1837 |
+
"step": 261
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 2.817204301075269,
|
| 1841 |
+
"grad_norm": 1.002478958639444,
|
| 1842 |
+
"learning_rate": 1.263570798919106e-07,
|
| 1843 |
+
"loss": 0.1927,
|
| 1844 |
+
"step": 262
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 2.827956989247312,
|
| 1848 |
+
"grad_norm": 1.0056557952222767,
|
| 1849 |
+
"learning_rate": 1.1275894651724517e-07,
|
| 1850 |
+
"loss": 0.1868,
|
| 1851 |
+
"step": 263
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 2.838709677419355,
|
| 1855 |
+
"grad_norm": 1.0197297289564395,
|
| 1856 |
+
"learning_rate": 9.992642807111486e-08,
|
| 1857 |
+
"loss": 0.1927,
|
| 1858 |
+
"step": 264
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 2.849462365591398,
|
| 1862 |
+
"grad_norm": 1.0517533923654494,
|
| 1863 |
+
"learning_rate": 8.78615348426759e-08,
|
| 1864 |
+
"loss": 0.2234,
|
| 1865 |
+
"step": 265
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 2.860215053763441,
|
| 1869 |
+
"grad_norm": 0.9940345005525202,
|
| 1870 |
+
"learning_rate": 7.656615686809976e-08,
|
| 1871 |
+
"loss": 0.1817,
|
| 1872 |
+
"step": 266
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 2.870967741935484,
|
| 1876 |
+
"grad_norm": 1.0497686699125726,
|
| 1877 |
+
"learning_rate": 6.604206363448662e-08,
|
| 1878 |
+
"loss": 0.2152,
|
| 1879 |
+
"step": 267
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 2.881720430107527,
|
| 1883 |
+
"grad_norm": 1.0384511431694428,
|
| 1884 |
+
"learning_rate": 5.6290903802665444e-08,
|
| 1885 |
+
"loss": 0.2158,
|
| 1886 |
+
"step": 268
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 2.89247311827957,
|
| 1890 |
+
"grad_norm": 1.3090254246994417,
|
| 1891 |
+
"learning_rate": 4.7314204948923356e-08,
|
| 1892 |
+
"loss": 0.2409,
|
| 1893 |
+
"step": 269
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 2.903225806451613,
|
| 1897 |
+
"grad_norm": 1.0831200870108442,
|
| 1898 |
+
"learning_rate": 3.911337332569876e-08,
|
| 1899 |
+
"loss": 0.215,
|
| 1900 |
+
"step": 270
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 2.913978494623656,
|
| 1904 |
+
"grad_norm": 1.0200774345835755,
|
| 1905 |
+
"learning_rate": 3.168969364128527e-08,
|
| 1906 |
+
"loss": 0.1853,
|
| 1907 |
+
"step": 271
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 2.924731182795699,
|
| 1911 |
+
"grad_norm": 1.0411062374812041,
|
| 1912 |
+
"learning_rate": 2.5044328858576105e-08,
|
| 1913 |
+
"loss": 0.1822,
|
| 1914 |
+
"step": 272
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 2.935483870967742,
|
| 1918 |
+
"grad_norm": 1.0955663825580222,
|
| 1919 |
+
"learning_rate": 1.917832001287645e-08,
|
| 1920 |
+
"loss": 0.2366,
|
| 1921 |
+
"step": 273
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 2.946236559139785,
|
| 1925 |
+
"grad_norm": 1.0058951894911308,
|
| 1926 |
+
"learning_rate": 1.4092586048820578e-08,
|
| 1927 |
+
"loss": 0.2088,
|
| 1928 |
+
"step": 274
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 2.956989247311828,
|
| 1932 |
+
"grad_norm": 1.0534367805397553,
|
| 1933 |
+
"learning_rate": 9.787923676414235e-09,
|
| 1934 |
+
"loss": 0.2006,
|
| 1935 |
+
"step": 275
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 2.967741935483871,
|
| 1939 |
+
"grad_norm": 1.0711677289438932,
|
| 1940 |
+
"learning_rate": 6.265007246223365e-09,
|
| 1941 |
+
"loss": 0.2288,
|
| 1942 |
+
"step": 276
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 2.978494623655914,
|
| 1946 |
+
"grad_norm": 1.1018665243256054,
|
| 1947 |
+
"learning_rate": 3.524388643736387e-09,
|
| 1948 |
+
"loss": 0.2359,
|
| 1949 |
+
"step": 277
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 2.989247311827957,
|
| 1953 |
+
"grad_norm": 0.9977813212471681,
|
| 1954 |
+
"learning_rate": 1.566497202904471e-09,
|
| 1955 |
+
"loss": 0.2032,
|
| 1956 |
+
"step": 278
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 3.0,
|
| 1960 |
+
"grad_norm": 1.121191187403273,
|
| 1961 |
+
"learning_rate": 3.916396388869981e-10,
|
| 1962 |
+
"loss": 0.2414,
|
| 1963 |
+
"step": 279
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 3.0,
|
| 1967 |
+
"step": 279,
|
| 1968 |
+
"total_flos": 2.2819812112387277e+17,
|
| 1969 |
+
"train_loss": 0.38972266467027766,
|
| 1970 |
+
"train_runtime": 34674.5164,
|
| 1971 |
+
"train_samples_per_second": 0.386,
|
| 1972 |
+
"train_steps_per_second": 0.008
|
| 1973 |
+
}
|
| 1974 |
+
],
|
| 1975 |
+
"logging_steps": 1,
|
| 1976 |
+
"max_steps": 279,
|
| 1977 |
+
"num_input_tokens_seen": 0,
|
| 1978 |
+
"num_train_epochs": 3,
|
| 1979 |
+
"save_steps": 200,
|
| 1980 |
+
"stateful_callbacks": {
|
| 1981 |
+
"TrainerControl": {
|
| 1982 |
+
"args": {
|
| 1983 |
+
"should_epoch_stop": false,
|
| 1984 |
+
"should_evaluate": false,
|
| 1985 |
+
"should_log": false,
|
| 1986 |
+
"should_save": true,
|
| 1987 |
+
"should_training_stop": true
|
| 1988 |
+
},
|
| 1989 |
+
"attributes": {}
|
| 1990 |
+
}
|
| 1991 |
+
},
|
| 1992 |
+
"total_flos": 2.2819812112387277e+17,
|
| 1993 |
+
"train_batch_size": 1,
|
| 1994 |
+
"trial_name": null,
|
| 1995 |
+
"trial_params": null
|
| 1996 |
+
}
|
training_loss.png
ADDED
|