End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +1596 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: apache-2.0
|
|
| 4 |
base_model: Qwen/Qwen2.5-7B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: multiple_samples_majority_consensus_numina_aime_llm_verifier
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# multiple_samples_majority_consensus_numina_aime_llm_verifier
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 4 |
base_model: Qwen/Qwen2.5-7B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: multiple_samples_majority_consensus_numina_aime_llm_verifier
|
|
|
|
| 16 |
|
| 17 |
# multiple_samples_majority_consensus_numina_aime_llm_verifier
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/multiple_samples_majority_consensus_numina_aime_llm_verifier dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 209046155558912.0,
|
| 4 |
+
"train_loss": 0.757471783472611,
|
| 5 |
+
"train_runtime": 6900.2048,
|
| 6 |
+
"train_samples_per_second": 3.084,
|
| 7 |
+
"train_steps_per_second": 0.032
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 209046155558912.0,
|
| 4 |
+
"train_loss": 0.757471783472611,
|
| 5 |
+
"train_runtime": 6900.2048,
|
| 6 |
+
"train_samples_per_second": 3.084,
|
| 7 |
+
"train_steps_per_second": 0.032
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1596 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 222,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.013513513513513514,
|
| 13 |
+
"grad_norm": 7.326704502105713,
|
| 14 |
+
"learning_rate": 4.347826086956522e-07,
|
| 15 |
+
"loss": 1.175,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.02702702702702703,
|
| 20 |
+
"grad_norm": 7.073528289794922,
|
| 21 |
+
"learning_rate": 8.695652173913044e-07,
|
| 22 |
+
"loss": 1.1197,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.04054054054054054,
|
| 27 |
+
"grad_norm": 6.842853546142578,
|
| 28 |
+
"learning_rate": 1.3043478260869566e-06,
|
| 29 |
+
"loss": 1.1137,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.05405405405405406,
|
| 34 |
+
"grad_norm": 6.628203868865967,
|
| 35 |
+
"learning_rate": 1.7391304347826088e-06,
|
| 36 |
+
"loss": 1.0553,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.06756756756756757,
|
| 41 |
+
"grad_norm": 6.835032939910889,
|
| 42 |
+
"learning_rate": 2.173913043478261e-06,
|
| 43 |
+
"loss": 1.1348,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.08108108108108109,
|
| 48 |
+
"grad_norm": 5.203673839569092,
|
| 49 |
+
"learning_rate": 2.6086956521739132e-06,
|
| 50 |
+
"loss": 1.0308,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.0945945945945946,
|
| 55 |
+
"grad_norm": 4.976128578186035,
|
| 56 |
+
"learning_rate": 3.043478260869566e-06,
|
| 57 |
+
"loss": 1.0472,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.10810810810810811,
|
| 62 |
+
"grad_norm": 3.2220687866210938,
|
| 63 |
+
"learning_rate": 3.4782608695652175e-06,
|
| 64 |
+
"loss": 1.058,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.12162162162162163,
|
| 69 |
+
"grad_norm": 2.7925970554351807,
|
| 70 |
+
"learning_rate": 3.91304347826087e-06,
|
| 71 |
+
"loss": 1.0007,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.13513513513513514,
|
| 76 |
+
"grad_norm": 2.907792806625366,
|
| 77 |
+
"learning_rate": 4.347826086956522e-06,
|
| 78 |
+
"loss": 0.9742,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.14864864864864866,
|
| 83 |
+
"grad_norm": 4.464594841003418,
|
| 84 |
+
"learning_rate": 4.782608695652174e-06,
|
| 85 |
+
"loss": 1.0229,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.16216216216216217,
|
| 90 |
+
"grad_norm": 4.374394416809082,
|
| 91 |
+
"learning_rate": 5.2173913043478265e-06,
|
| 92 |
+
"loss": 0.9953,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.17567567567567569,
|
| 97 |
+
"grad_norm": 4.183391571044922,
|
| 98 |
+
"learning_rate": 5.652173913043479e-06,
|
| 99 |
+
"loss": 0.9766,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.1891891891891892,
|
| 104 |
+
"grad_norm": 3.3822455406188965,
|
| 105 |
+
"learning_rate": 6.086956521739132e-06,
|
| 106 |
+
"loss": 0.993,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.20270270270270271,
|
| 111 |
+
"grad_norm": 3.2228403091430664,
|
| 112 |
+
"learning_rate": 6.521739130434783e-06,
|
| 113 |
+
"loss": 0.9587,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.21621621621621623,
|
| 118 |
+
"grad_norm": 2.4193832874298096,
|
| 119 |
+
"learning_rate": 6.956521739130435e-06,
|
| 120 |
+
"loss": 0.9076,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.22972972972972974,
|
| 125 |
+
"grad_norm": 1.804916262626648,
|
| 126 |
+
"learning_rate": 7.391304347826087e-06,
|
| 127 |
+
"loss": 0.8446,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.24324324324324326,
|
| 132 |
+
"grad_norm": 2.097240924835205,
|
| 133 |
+
"learning_rate": 7.82608695652174e-06,
|
| 134 |
+
"loss": 0.8502,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.25675675675675674,
|
| 139 |
+
"grad_norm": 1.7936445474624634,
|
| 140 |
+
"learning_rate": 8.260869565217392e-06,
|
| 141 |
+
"loss": 0.8581,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.2702702702702703,
|
| 146 |
+
"grad_norm": 1.5440407991409302,
|
| 147 |
+
"learning_rate": 8.695652173913044e-06,
|
| 148 |
+
"loss": 0.8534,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.28378378378378377,
|
| 153 |
+
"grad_norm": 1.4016180038452148,
|
| 154 |
+
"learning_rate": 9.130434782608697e-06,
|
| 155 |
+
"loss": 0.8604,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.2972972972972973,
|
| 160 |
+
"grad_norm": 1.3873733282089233,
|
| 161 |
+
"learning_rate": 9.565217391304349e-06,
|
| 162 |
+
"loss": 0.8489,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.3108108108108108,
|
| 167 |
+
"grad_norm": 1.1179004907608032,
|
| 168 |
+
"learning_rate": 1e-05,
|
| 169 |
+
"loss": 0.879,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.32432432432432434,
|
| 174 |
+
"grad_norm": 1.0465384721755981,
|
| 175 |
+
"learning_rate": 9.999376947588288e-06,
|
| 176 |
+
"loss": 0.8259,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.33783783783783783,
|
| 181 |
+
"grad_norm": 0.9885022640228271,
|
| 182 |
+
"learning_rate": 9.99750794563087e-06,
|
| 183 |
+
"loss": 0.853,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.35135135135135137,
|
| 188 |
+
"grad_norm": 0.86279296875,
|
| 189 |
+
"learning_rate": 9.994393459922219e-06,
|
| 190 |
+
"loss": 0.792,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.36486486486486486,
|
| 195 |
+
"grad_norm": 0.895187497138977,
|
| 196 |
+
"learning_rate": 9.990034266657468e-06,
|
| 197 |
+
"loss": 0.8566,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.3783783783783784,
|
| 202 |
+
"grad_norm": 0.761161208152771,
|
| 203 |
+
"learning_rate": 9.984431452238968e-06,
|
| 204 |
+
"loss": 0.7679,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.3918918918918919,
|
| 209 |
+
"grad_norm": 0.9026336073875427,
|
| 210 |
+
"learning_rate": 9.97758641300553e-06,
|
| 211 |
+
"loss": 0.8598,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.40540540540540543,
|
| 216 |
+
"grad_norm": 0.9734629392623901,
|
| 217 |
+
"learning_rate": 9.96950085488444e-06,
|
| 218 |
+
"loss": 0.8091,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.4189189189189189,
|
| 223 |
+
"grad_norm": 0.8533677458763123,
|
| 224 |
+
"learning_rate": 9.96017679296629e-06,
|
| 225 |
+
"loss": 0.8095,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.43243243243243246,
|
| 230 |
+
"grad_norm": 0.7178331613540649,
|
| 231 |
+
"learning_rate": 9.949616551002787e-06,
|
| 232 |
+
"loss": 0.8595,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.44594594594594594,
|
| 237 |
+
"grad_norm": 0.6754847168922424,
|
| 238 |
+
"learning_rate": 9.93782276082762e-06,
|
| 239 |
+
"loss": 0.7969,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.4594594594594595,
|
| 244 |
+
"grad_norm": 0.8675635457038879,
|
| 245 |
+
"learning_rate": 9.924798361700554e-06,
|
| 246 |
+
"loss": 0.8794,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.47297297297297297,
|
| 251 |
+
"grad_norm": 0.5807439684867859,
|
| 252 |
+
"learning_rate": 9.910546599574903e-06,
|
| 253 |
+
"loss": 0.7243,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.4864864864864865,
|
| 258 |
+
"grad_norm": 0.6874200105667114,
|
| 259 |
+
"learning_rate": 9.895071026288574e-06,
|
| 260 |
+
"loss": 0.7833,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.5,
|
| 265 |
+
"grad_norm": 0.720252275466919,
|
| 266 |
+
"learning_rate": 9.878375498678869e-06,
|
| 267 |
+
"loss": 0.7887,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.5135135135135135,
|
| 272 |
+
"grad_norm": 0.5706230998039246,
|
| 273 |
+
"learning_rate": 9.860464177621286e-06,
|
| 274 |
+
"loss": 0.8095,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.527027027027027,
|
| 279 |
+
"grad_norm": 0.8039330840110779,
|
| 280 |
+
"learning_rate": 9.841341526992536e-06,
|
| 281 |
+
"loss": 0.7515,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.5405405405405406,
|
| 286 |
+
"grad_norm": 0.6529414653778076,
|
| 287 |
+
"learning_rate": 9.821012312558059e-06,
|
| 288 |
+
"loss": 0.7777,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.5540540540540541,
|
| 293 |
+
"grad_norm": 0.6137668490409851,
|
| 294 |
+
"learning_rate": 9.799481600784286e-06,
|
| 295 |
+
"loss": 0.8174,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.5675675675675675,
|
| 300 |
+
"grad_norm": 0.7379924654960632,
|
| 301 |
+
"learning_rate": 9.776754757575975e-06,
|
| 302 |
+
"loss": 0.7545,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.581081081081081,
|
| 307 |
+
"grad_norm": 0.5984988212585449,
|
| 308 |
+
"learning_rate": 9.752837446938915e-06,
|
| 309 |
+
"loss": 0.7776,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.5945945945945946,
|
| 314 |
+
"grad_norm": 0.5971017479896545,
|
| 315 |
+
"learning_rate": 9.727735629568335e-06,
|
| 316 |
+
"loss": 0.8526,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.6081081081081081,
|
| 321 |
+
"grad_norm": 0.7161526083946228,
|
| 322 |
+
"learning_rate": 9.701455561363378e-06,
|
| 323 |
+
"loss": 0.7635,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.6216216216216216,
|
| 328 |
+
"grad_norm": 0.631260097026825,
|
| 329 |
+
"learning_rate": 9.674003791867993e-06,
|
| 330 |
+
"loss": 0.7661,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.6351351351351351,
|
| 335 |
+
"grad_norm": 0.6133121848106384,
|
| 336 |
+
"learning_rate": 9.645387162638652e-06,
|
| 337 |
+
"loss": 0.7391,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.6486486486486487,
|
| 342 |
+
"grad_norm": 0.7166041135787964,
|
| 343 |
+
"learning_rate": 9.615612805539305e-06,
|
| 344 |
+
"loss": 0.8009,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.6621621621621622,
|
| 349 |
+
"grad_norm": 0.5377827286720276,
|
| 350 |
+
"learning_rate": 9.584688140963945e-06,
|
| 351 |
+
"loss": 0.8176,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.6756756756756757,
|
| 356 |
+
"grad_norm": 0.5944711565971375,
|
| 357 |
+
"learning_rate": 9.552620875987312e-06,
|
| 358 |
+
"loss": 0.8118,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.6891891891891891,
|
| 363 |
+
"grad_norm": 0.6191123127937317,
|
| 364 |
+
"learning_rate": 9.51941900244412e-06,
|
| 365 |
+
"loss": 0.7517,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.7027027027027027,
|
| 370 |
+
"grad_norm": 0.6404368281364441,
|
| 371 |
+
"learning_rate": 9.485090794937319e-06,
|
| 372 |
+
"loss": 0.7027,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.7162162162162162,
|
| 377 |
+
"grad_norm": 0.5731247067451477,
|
| 378 |
+
"learning_rate": 9.449644808775902e-06,
|
| 379 |
+
"loss": 0.8323,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.7297297297297297,
|
| 384 |
+
"grad_norm": 0.5870006680488586,
|
| 385 |
+
"learning_rate": 9.413089877842735e-06,
|
| 386 |
+
"loss": 0.8025,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.7432432432432432,
|
| 391 |
+
"grad_norm": 0.5990195870399475,
|
| 392 |
+
"learning_rate": 9.37543511239297e-06,
|
| 393 |
+
"loss": 0.7901,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.7567567567567568,
|
| 398 |
+
"grad_norm": 0.56047123670578,
|
| 399 |
+
"learning_rate": 9.336689896783575e-06,
|
| 400 |
+
"loss": 0.7497,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.7702702702702703,
|
| 405 |
+
"grad_norm": 0.5658489465713501,
|
| 406 |
+
"learning_rate": 9.296863887134561e-06,
|
| 407 |
+
"loss": 0.7906,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.7837837837837838,
|
| 412 |
+
"grad_norm": 0.5268697738647461,
|
| 413 |
+
"learning_rate": 9.255967008922475e-06,
|
| 414 |
+
"loss": 0.7988,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.7972972972972973,
|
| 419 |
+
"grad_norm": 0.6772133708000183,
|
| 420 |
+
"learning_rate": 9.214009454506754e-06,
|
| 421 |
+
"loss": 0.7905,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.8108108108108109,
|
| 426 |
+
"grad_norm": 0.5280905365943909,
|
| 427 |
+
"learning_rate": 9.17100168058959e-06,
|
| 428 |
+
"loss": 0.7693,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.8243243243243243,
|
| 433 |
+
"grad_norm": 0.6103823781013489,
|
| 434 |
+
"learning_rate": 9.126954405609882e-06,
|
| 435 |
+
"loss": 0.8044,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.8378378378378378,
|
| 440 |
+
"grad_norm": 0.559684157371521,
|
| 441 |
+
"learning_rate": 9.081878607071996e-06,
|
| 442 |
+
"loss": 0.8205,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.8513513513513513,
|
| 447 |
+
"grad_norm": 0.504984974861145,
|
| 448 |
+
"learning_rate": 9.035785518809928e-06,
|
| 449 |
+
"loss": 0.7445,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.8648648648648649,
|
| 454 |
+
"grad_norm": 0.6013747453689575,
|
| 455 |
+
"learning_rate": 8.988686628187597e-06,
|
| 456 |
+
"loss": 0.7848,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.8783783783783784,
|
| 461 |
+
"grad_norm": 0.5867133736610413,
|
| 462 |
+
"learning_rate": 8.940593673235962e-06,
|
| 463 |
+
"loss": 0.8132,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.8918918918918919,
|
| 468 |
+
"grad_norm": 0.5536394119262695,
|
| 469 |
+
"learning_rate": 8.89151863972765e-06,
|
| 470 |
+
"loss": 0.8107,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.9054054054054054,
|
| 475 |
+
"grad_norm": 0.6702824831008911,
|
| 476 |
+
"learning_rate": 8.841473758189853e-06,
|
| 477 |
+
"loss": 0.7629,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.918918918918919,
|
| 482 |
+
"grad_norm": 0.6165092587471008,
|
| 483 |
+
"learning_rate": 8.790471500856229e-06,
|
| 484 |
+
"loss": 0.7454,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.9324324324324325,
|
| 489 |
+
"grad_norm": 0.5387951731681824,
|
| 490 |
+
"learning_rate": 8.738524578558547e-06,
|
| 491 |
+
"loss": 0.8437,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.9459459459459459,
|
| 496 |
+
"grad_norm": 0.5904017090797424,
|
| 497 |
+
"learning_rate": 8.685645937558896e-06,
|
| 498 |
+
"loss": 0.7373,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.9594594594594594,
|
| 503 |
+
"grad_norm": 0.6112914681434631,
|
| 504 |
+
"learning_rate": 8.631848756323198e-06,
|
| 505 |
+
"loss": 0.8012,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.972972972972973,
|
| 510 |
+
"grad_norm": 0.5325087308883667,
|
| 511 |
+
"learning_rate": 8.577146442236856e-06,
|
| 512 |
+
"loss": 0.7613,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.9864864864864865,
|
| 517 |
+
"grad_norm": 0.7188298106193542,
|
| 518 |
+
"learning_rate": 8.521552628263362e-06,
|
| 519 |
+
"loss": 0.7874,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.0,
|
| 524 |
+
"grad_norm": 0.5712509155273438,
|
| 525 |
+
"learning_rate": 8.46508116954666e-06,
|
| 526 |
+
"loss": 0.7701,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.0135135135135136,
|
| 531 |
+
"grad_norm": 0.65369713306427,
|
| 532 |
+
"learning_rate": 8.40774613995817e-06,
|
| 533 |
+
"loss": 0.6942,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.027027027027027,
|
| 538 |
+
"grad_norm": 0.5912752747535706,
|
| 539 |
+
"learning_rate": 8.349561828589276e-06,
|
| 540 |
+
"loss": 0.7572,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.0405405405405406,
|
| 545 |
+
"grad_norm": 0.5766599774360657,
|
| 546 |
+
"learning_rate": 8.29054273619019e-06,
|
| 547 |
+
"loss": 0.7606,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.054054054054054,
|
| 552 |
+
"grad_norm": 0.5183791518211365,
|
| 553 |
+
"learning_rate": 8.23070357155605e-06,
|
| 554 |
+
"loss": 0.7307,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.0675675675675675,
|
| 559 |
+
"grad_norm": 0.47701534628868103,
|
| 560 |
+
"learning_rate": 8.170059247861194e-06,
|
| 561 |
+
"loss": 0.7647,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.0810810810810811,
|
| 566 |
+
"grad_norm": 0.6130340695381165,
|
| 567 |
+
"learning_rate": 8.108624878942477e-06,
|
| 568 |
+
"loss": 0.7751,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.0945945945945945,
|
| 573 |
+
"grad_norm": 0.49725058674812317,
|
| 574 |
+
"learning_rate": 8.046415775532585e-06,
|
| 575 |
+
"loss": 0.7494,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.1081081081081081,
|
| 580 |
+
"grad_norm": 0.540152370929718,
|
| 581 |
+
"learning_rate": 7.98344744144428e-06,
|
| 582 |
+
"loss": 0.7426,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 1.1216216216216217,
|
| 587 |
+
"grad_norm": 0.4972006678581238,
|
| 588 |
+
"learning_rate": 7.919735569706533e-06,
|
| 589 |
+
"loss": 0.7647,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.135135135135135,
|
| 594 |
+
"grad_norm": 0.49149957299232483,
|
| 595 |
+
"learning_rate": 7.855296038653474e-06,
|
| 596 |
+
"loss": 0.7245,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.1486486486486487,
|
| 601 |
+
"grad_norm": 0.5621472001075745,
|
| 602 |
+
"learning_rate": 7.7901449079672e-06,
|
| 603 |
+
"loss": 0.7239,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.1621621621621623,
|
| 608 |
+
"grad_norm": 0.6095807552337646,
|
| 609 |
+
"learning_rate": 7.724298414675353e-06,
|
| 610 |
+
"loss": 0.7654,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.1756756756756757,
|
| 615 |
+
"grad_norm": 0.4576193690299988,
|
| 616 |
+
"learning_rate": 7.657772969104508e-06,
|
| 617 |
+
"loss": 0.7537,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.1891891891891893,
|
| 622 |
+
"grad_norm": 0.6867668628692627,
|
| 623 |
+
"learning_rate": 7.590585150790388e-06,
|
| 624 |
+
"loss": 0.7221,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.2027027027027026,
|
| 629 |
+
"grad_norm": 0.5993993878364563,
|
| 630 |
+
"learning_rate": 7.522751704345888e-06,
|
| 631 |
+
"loss": 0.7081,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.2162162162162162,
|
| 636 |
+
"grad_norm": 0.5961006879806519,
|
| 637 |
+
"learning_rate": 7.454289535287968e-06,
|
| 638 |
+
"loss": 0.7524,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.2297297297297298,
|
| 643 |
+
"grad_norm": 0.6628375053405762,
|
| 644 |
+
"learning_rate": 7.385215705824449e-06,
|
| 645 |
+
"loss": 0.6637,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.2432432432432432,
|
| 650 |
+
"grad_norm": 0.6477952003479004,
|
| 651 |
+
"learning_rate": 7.315547430601739e-06,
|
| 652 |
+
"loss": 0.7065,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.2567567567567568,
|
| 657 |
+
"grad_norm": 0.5361400842666626,
|
| 658 |
+
"learning_rate": 7.245302072414602e-06,
|
| 659 |
+
"loss": 0.723,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.2702702702702702,
|
| 664 |
+
"grad_norm": 0.5660983324050903,
|
| 665 |
+
"learning_rate": 7.174497137878967e-06,
|
| 666 |
+
"loss": 0.7719,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.2837837837837838,
|
| 671 |
+
"grad_norm": 0.5143330693244934,
|
| 672 |
+
"learning_rate": 7.103150273068922e-06,
|
| 673 |
+
"loss": 0.7035,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.2972972972972974,
|
| 678 |
+
"grad_norm": 0.49670517444610596,
|
| 679 |
+
"learning_rate": 7.0312792591189465e-06,
|
| 680 |
+
"loss": 0.7166,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.3108108108108107,
|
| 685 |
+
"grad_norm": 0.5676432251930237,
|
| 686 |
+
"learning_rate": 6.958902007792466e-06,
|
| 687 |
+
"loss": 0.6376,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.3243243243243243,
|
| 692 |
+
"grad_norm": 0.5331136584281921,
|
| 693 |
+
"learning_rate": 6.886036557017881e-06,
|
| 694 |
+
"loss": 0.7584,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 1.3378378378378377,
|
| 699 |
+
"grad_norm": 0.5032922029495239,
|
| 700 |
+
"learning_rate": 6.8127010663931235e-06,
|
| 701 |
+
"loss": 0.7153,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.3513513513513513,
|
| 706 |
+
"grad_norm": 0.5131669044494629,
|
| 707 |
+
"learning_rate": 6.738913812659913e-06,
|
| 708 |
+
"loss": 0.7733,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.364864864864865,
|
| 713 |
+
"grad_norm": 0.5216994285583496,
|
| 714 |
+
"learning_rate": 6.664693185148808e-06,
|
| 715 |
+
"loss": 0.7214,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 1.3783783783783785,
|
| 720 |
+
"grad_norm": 0.4687362611293793,
|
| 721 |
+
"learning_rate": 6.590057681196191e-06,
|
| 722 |
+
"loss": 0.7847,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.3918918918918919,
|
| 727 |
+
"grad_norm": 0.49732452630996704,
|
| 728 |
+
"learning_rate": 6.515025901534364e-06,
|
| 729 |
+
"loss": 0.6675,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.4054054054054055,
|
| 734 |
+
"grad_norm": 0.5848899483680725,
|
| 735 |
+
"learning_rate": 6.439616545655833e-06,
|
| 736 |
+
"loss": 0.7974,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.4189189189189189,
|
| 741 |
+
"grad_norm": 0.5501415729522705,
|
| 742 |
+
"learning_rate": 6.363848407153017e-06,
|
| 743 |
+
"loss": 0.7488,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.4324324324324325,
|
| 748 |
+
"grad_norm": 0.6274934411048889,
|
| 749 |
+
"learning_rate": 6.2877403690344854e-06,
|
| 750 |
+
"loss": 0.7153,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.445945945945946,
|
| 755 |
+
"grad_norm": 0.5663743615150452,
|
| 756 |
+
"learning_rate": 6.2113113990189165e-06,
|
| 757 |
+
"loss": 0.7326,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.4594594594594594,
|
| 762 |
+
"grad_norm": 0.5057617425918579,
|
| 763 |
+
"learning_rate": 6.134580544807951e-06,
|
| 764 |
+
"loss": 0.7548,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.472972972972973,
|
| 769 |
+
"grad_norm": 0.677182674407959,
|
| 770 |
+
"learning_rate": 6.057566929339096e-06,
|
| 771 |
+
"loss": 0.6864,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 1.4864864864864864,
|
| 776 |
+
"grad_norm": 0.4799484312534332,
|
| 777 |
+
"learning_rate": 5.980289746019892e-06,
|
| 778 |
+
"loss": 0.7329,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.5,
|
| 783 |
+
"grad_norm": 0.4800988435745239,
|
| 784 |
+
"learning_rate": 5.902768253944511e-06,
|
| 785 |
+
"loss": 0.656,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.5135135135135136,
|
| 790 |
+
"grad_norm": 0.5524668097496033,
|
| 791 |
+
"learning_rate": 5.825021773093997e-06,
|
| 792 |
+
"loss": 0.7652,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.527027027027027,
|
| 797 |
+
"grad_norm": 0.4573599398136139,
|
| 798 |
+
"learning_rate": 5.747069679521306e-06,
|
| 799 |
+
"loss": 0.7708,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 1.5405405405405406,
|
| 804 |
+
"grad_norm": 0.5032984018325806,
|
| 805 |
+
"learning_rate": 5.668931400522396e-06,
|
| 806 |
+
"loss": 0.7192,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.554054054054054,
|
| 811 |
+
"grad_norm": 0.48436814546585083,
|
| 812 |
+
"learning_rate": 5.5906264097945405e-06,
|
| 813 |
+
"loss": 0.6781,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 1.5675675675675675,
|
| 818 |
+
"grad_norm": 0.5021950006484985,
|
| 819 |
+
"learning_rate": 5.512174222583066e-06,
|
| 820 |
+
"loss": 0.7641,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 1.5810810810810811,
|
| 825 |
+
"grad_norm": 0.47211435437202454,
|
| 826 |
+
"learning_rate": 5.433594390817755e-06,
|
| 827 |
+
"loss": 0.7091,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 1.5945945945945947,
|
| 832 |
+
"grad_norm": 0.5314428210258484,
|
| 833 |
+
"learning_rate": 5.35490649824008e-06,
|
| 834 |
+
"loss": 0.7345,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 1.6081081081081081,
|
| 839 |
+
"grad_norm": 0.46223777532577515,
|
| 840 |
+
"learning_rate": 5.276130155522541e-06,
|
| 841 |
+
"loss": 0.7331,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 1.6216216216216215,
|
| 846 |
+
"grad_norm": 0.4992578327655792,
|
| 847 |
+
"learning_rate": 5.197284995381264e-06,
|
| 848 |
+
"loss": 0.7725,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.635135135135135,
|
| 853 |
+
"grad_norm": 0.4919154644012451,
|
| 854 |
+
"learning_rate": 5.1183906676831195e-06,
|
| 855 |
+
"loss": 0.7716,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 1.6486486486486487,
|
| 860 |
+
"grad_norm": 0.42628881335258484,
|
| 861 |
+
"learning_rate": 5.039466834548568e-06,
|
| 862 |
+
"loss": 0.6676,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 1.6621621621621623,
|
| 867 |
+
"grad_norm": 0.6594741344451904,
|
| 868 |
+
"learning_rate": 4.960533165451435e-06,
|
| 869 |
+
"loss": 0.7117,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 1.6756756756756757,
|
| 874 |
+
"grad_norm": 0.5579748153686523,
|
| 875 |
+
"learning_rate": 4.881609332316881e-06,
|
| 876 |
+
"loss": 0.7336,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 1.689189189189189,
|
| 881 |
+
"grad_norm": 0.504492461681366,
|
| 882 |
+
"learning_rate": 4.802715004618737e-06,
|
| 883 |
+
"loss": 0.7896,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 1.7027027027027026,
|
| 888 |
+
"grad_norm": 0.5601021647453308,
|
| 889 |
+
"learning_rate": 4.72386984447746e-06,
|
| 890 |
+
"loss": 0.7379,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 1.7162162162162162,
|
| 895 |
+
"grad_norm": 0.48954904079437256,
|
| 896 |
+
"learning_rate": 4.6450935017599205e-06,
|
| 897 |
+
"loss": 0.6873,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 1.7297297297297298,
|
| 902 |
+
"grad_norm": 0.5034283995628357,
|
| 903 |
+
"learning_rate": 4.566405609182247e-06,
|
| 904 |
+
"loss": 0.7693,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 1.7432432432432432,
|
| 909 |
+
"grad_norm": 0.5276468992233276,
|
| 910 |
+
"learning_rate": 4.4878257774169345e-06,
|
| 911 |
+
"loss": 0.7212,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 1.7567567567567568,
|
| 916 |
+
"grad_norm": 0.45461001992225647,
|
| 917 |
+
"learning_rate": 4.40937359020546e-06,
|
| 918 |
+
"loss": 0.7144,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 1.7702702702702702,
|
| 923 |
+
"grad_norm": 0.5240442752838135,
|
| 924 |
+
"learning_rate": 4.3310685994776055e-06,
|
| 925 |
+
"loss": 0.6818,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 1.7837837837837838,
|
| 930 |
+
"grad_norm": 0.5194613933563232,
|
| 931 |
+
"learning_rate": 4.252930320478695e-06,
|
| 932 |
+
"loss": 0.6852,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.7972972972972974,
|
| 937 |
+
"grad_norm": 0.4843868911266327,
|
| 938 |
+
"learning_rate": 4.1749782269060045e-06,
|
| 939 |
+
"loss": 0.7232,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.810810810810811,
|
| 944 |
+
"grad_norm": 0.51628577709198,
|
| 945 |
+
"learning_rate": 4.097231746055491e-06,
|
| 946 |
+
"loss": 0.6698,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.8243243243243243,
|
| 951 |
+
"grad_norm": 0.4884800612926483,
|
| 952 |
+
"learning_rate": 4.01971025398011e-06,
|
| 953 |
+
"loss": 0.7136,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 1.8378378378378377,
|
| 958 |
+
"grad_norm": 0.5353890061378479,
|
| 959 |
+
"learning_rate": 3.9424330706609055e-06,
|
| 960 |
+
"loss": 0.7264,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 1.8513513513513513,
|
| 965 |
+
"grad_norm": 0.49839362502098083,
|
| 966 |
+
"learning_rate": 3.865419455192049e-06,
|
| 967 |
+
"loss": 0.7292,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 1.864864864864865,
|
| 972 |
+
"grad_norm": 0.5372514128684998,
|
| 973 |
+
"learning_rate": 3.788688600981085e-06,
|
| 974 |
+
"loss": 0.7389,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 1.8783783783783785,
|
| 979 |
+
"grad_norm": 0.554400622844696,
|
| 980 |
+
"learning_rate": 3.712259630965518e-06,
|
| 981 |
+
"loss": 0.759,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 1.8918918918918919,
|
| 986 |
+
"grad_norm": 0.47880756855010986,
|
| 987 |
+
"learning_rate": 3.636151592846985e-06,
|
| 988 |
+
"loss": 0.6806,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 1.9054054054054053,
|
| 993 |
+
"grad_norm": 0.4559061825275421,
|
| 994 |
+
"learning_rate": 3.5603834543441683e-06,
|
| 995 |
+
"loss": 0.7607,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 1.9189189189189189,
|
| 1000 |
+
"grad_norm": 0.551109790802002,
|
| 1001 |
+
"learning_rate": 3.484974098465636e-06,
|
| 1002 |
+
"loss": 0.7334,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 1.9324324324324325,
|
| 1007 |
+
"grad_norm": 0.4780474305152893,
|
| 1008 |
+
"learning_rate": 3.4099423188038094e-06,
|
| 1009 |
+
"loss": 0.7651,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 1.945945945945946,
|
| 1014 |
+
"grad_norm": 0.45685258507728577,
|
| 1015 |
+
"learning_rate": 3.3353068148511957e-06,
|
| 1016 |
+
"loss": 0.7539,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 1.9594594594594594,
|
| 1021 |
+
"grad_norm": 0.5265383720397949,
|
| 1022 |
+
"learning_rate": 3.2610861873400884e-06,
|
| 1023 |
+
"loss": 0.7079,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 1.972972972972973,
|
| 1028 |
+
"grad_norm": 0.46400219202041626,
|
| 1029 |
+
"learning_rate": 3.187298933606878e-06,
|
| 1030 |
+
"loss": 0.7173,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 1.9864864864864864,
|
| 1035 |
+
"grad_norm": 0.5163304209709167,
|
| 1036 |
+
"learning_rate": 3.1139634429821198e-06,
|
| 1037 |
+
"loss": 0.7489,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 2.0,
|
| 1042 |
+
"grad_norm": 0.527360737323761,
|
| 1043 |
+
"learning_rate": 3.0410979922075344e-06,
|
| 1044 |
+
"loss": 0.7437,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 2.0135135135135136,
|
| 1049 |
+
"grad_norm": 0.6211746335029602,
|
| 1050 |
+
"learning_rate": 2.968720740881056e-06,
|
| 1051 |
+
"loss": 0.7376,
|
| 1052 |
+
"step": 149
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 2.027027027027027,
|
| 1056 |
+
"grad_norm": 0.4409978687763214,
|
| 1057 |
+
"learning_rate": 2.8968497269310803e-06,
|
| 1058 |
+
"loss": 0.6356,
|
| 1059 |
+
"step": 150
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 2.0405405405405403,
|
| 1063 |
+
"grad_norm": 0.4552105665206909,
|
| 1064 |
+
"learning_rate": 2.825502862121036e-06,
|
| 1065 |
+
"loss": 0.6941,
|
| 1066 |
+
"step": 151
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 2.054054054054054,
|
| 1070 |
+
"grad_norm": 0.562812864780426,
|
| 1071 |
+
"learning_rate": 2.754697927585399e-06,
|
| 1072 |
+
"loss": 0.7393,
|
| 1073 |
+
"step": 152
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 2.0675675675675675,
|
| 1077 |
+
"grad_norm": 0.4543214738368988,
|
| 1078 |
+
"learning_rate": 2.6844525693982614e-06,
|
| 1079 |
+
"loss": 0.648,
|
| 1080 |
+
"step": 153
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 2.081081081081081,
|
| 1084 |
+
"grad_norm": 0.4172312617301941,
|
| 1085 |
+
"learning_rate": 2.6147842941755543e-06,
|
| 1086 |
+
"loss": 0.7293,
|
| 1087 |
+
"step": 154
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 2.0945945945945947,
|
| 1091 |
+
"grad_norm": 0.4883958101272583,
|
| 1092 |
+
"learning_rate": 2.5457104647120323e-06,
|
| 1093 |
+
"loss": 0.7275,
|
| 1094 |
+
"step": 155
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 2.108108108108108,
|
| 1098 |
+
"grad_norm": 0.4549468755722046,
|
| 1099 |
+
"learning_rate": 2.4772482956541133e-06,
|
| 1100 |
+
"loss": 0.6401,
|
| 1101 |
+
"step": 156
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 2.1216216216216215,
|
| 1105 |
+
"grad_norm": 0.48548489809036255,
|
| 1106 |
+
"learning_rate": 2.4094148492096124e-06,
|
| 1107 |
+
"loss": 0.6813,
|
| 1108 |
+
"step": 157
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 2.135135135135135,
|
| 1112 |
+
"grad_norm": 0.40865275263786316,
|
| 1113 |
+
"learning_rate": 2.3422270308954936e-06,
|
| 1114 |
+
"loss": 0.7284,
|
| 1115 |
+
"step": 158
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 2.1486486486486487,
|
| 1119 |
+
"grad_norm": 0.4217635691165924,
|
| 1120 |
+
"learning_rate": 2.2757015853246493e-06,
|
| 1121 |
+
"loss": 0.7205,
|
| 1122 |
+
"step": 159
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 2.1621621621621623,
|
| 1126 |
+
"grad_norm": 0.43882879614830017,
|
| 1127 |
+
"learning_rate": 2.2098550920328e-06,
|
| 1128 |
+
"loss": 0.7288,
|
| 1129 |
+
"step": 160
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 2.175675675675676,
|
| 1133 |
+
"grad_norm": 0.474503755569458,
|
| 1134 |
+
"learning_rate": 2.1447039613465265e-06,
|
| 1135 |
+
"loss": 0.7027,
|
| 1136 |
+
"step": 161
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 2.189189189189189,
|
| 1140 |
+
"grad_norm": 0.45140403509140015,
|
| 1141 |
+
"learning_rate": 2.0802644302934683e-06,
|
| 1142 |
+
"loss": 0.7266,
|
| 1143 |
+
"step": 162
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 2.2027027027027026,
|
| 1147 |
+
"grad_norm": 0.46298521757125854,
|
| 1148 |
+
"learning_rate": 2.0165525585557205e-06,
|
| 1149 |
+
"loss": 0.7287,
|
| 1150 |
+
"step": 163
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 2.2162162162162162,
|
| 1154 |
+
"grad_norm": 0.393634557723999,
|
| 1155 |
+
"learning_rate": 1.953584224467418e-06,
|
| 1156 |
+
"loss": 0.6899,
|
| 1157 |
+
"step": 164
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 2.22972972972973,
|
| 1161 |
+
"grad_norm": 0.39404478669166565,
|
| 1162 |
+
"learning_rate": 1.8913751210575248e-06,
|
| 1163 |
+
"loss": 0.6905,
|
| 1164 |
+
"step": 165
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 2.2432432432432434,
|
| 1168 |
+
"grad_norm": 0.43371090292930603,
|
| 1169 |
+
"learning_rate": 1.8299407521388067e-06,
|
| 1170 |
+
"loss": 0.7061,
|
| 1171 |
+
"step": 166
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 2.2567567567567566,
|
| 1175 |
+
"grad_norm": 0.45464712381362915,
|
| 1176 |
+
"learning_rate": 1.7692964284439506e-06,
|
| 1177 |
+
"loss": 0.6592,
|
| 1178 |
+
"step": 167
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 2.27027027027027,
|
| 1182 |
+
"grad_norm": 0.4131033718585968,
|
| 1183 |
+
"learning_rate": 1.7094572638098122e-06,
|
| 1184 |
+
"loss": 0.6191,
|
| 1185 |
+
"step": 168
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 2.2837837837837838,
|
| 1189 |
+
"grad_norm": 0.426092267036438,
|
| 1190 |
+
"learning_rate": 1.6504381714107254e-06,
|
| 1191 |
+
"loss": 0.7861,
|
| 1192 |
+
"step": 169
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 2.2972972972972974,
|
| 1196 |
+
"grad_norm": 0.37817391753196716,
|
| 1197 |
+
"learning_rate": 1.5922538600418319e-06,
|
| 1198 |
+
"loss": 0.6756,
|
| 1199 |
+
"step": 170
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 2.310810810810811,
|
| 1203 |
+
"grad_norm": 0.4261871576309204,
|
| 1204 |
+
"learning_rate": 1.5349188304533414e-06,
|
| 1205 |
+
"loss": 0.6965,
|
| 1206 |
+
"step": 171
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 2.3243243243243246,
|
| 1210 |
+
"grad_norm": 0.4123932421207428,
|
| 1211 |
+
"learning_rate": 1.4784473717366388e-06,
|
| 1212 |
+
"loss": 0.6178,
|
| 1213 |
+
"step": 172
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 2.3378378378378377,
|
| 1217 |
+
"grad_norm": 0.4708331823348999,
|
| 1218 |
+
"learning_rate": 1.4228535577631442e-06,
|
| 1219 |
+
"loss": 0.7379,
|
| 1220 |
+
"step": 173
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 2.3513513513513513,
|
| 1224 |
+
"grad_norm": 0.4335053265094757,
|
| 1225 |
+
"learning_rate": 1.3681512436768047e-06,
|
| 1226 |
+
"loss": 0.6727,
|
| 1227 |
+
"step": 174
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 2.364864864864865,
|
| 1231 |
+
"grad_norm": 0.38014209270477295,
|
| 1232 |
+
"learning_rate": 1.314354062441106e-06,
|
| 1233 |
+
"loss": 0.6992,
|
| 1234 |
+
"step": 175
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 2.3783783783783785,
|
| 1238 |
+
"grad_norm": 0.3943905234336853,
|
| 1239 |
+
"learning_rate": 1.261475421441455e-06,
|
| 1240 |
+
"loss": 0.6942,
|
| 1241 |
+
"step": 176
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 2.391891891891892,
|
| 1245 |
+
"grad_norm": 0.39650100469589233,
|
| 1246 |
+
"learning_rate": 1.2095284991437734e-06,
|
| 1247 |
+
"loss": 0.7095,
|
| 1248 |
+
"step": 177
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 2.4054054054054053,
|
| 1252 |
+
"grad_norm": 0.4110572636127472,
|
| 1253 |
+
"learning_rate": 1.1585262418101468e-06,
|
| 1254 |
+
"loss": 0.7001,
|
| 1255 |
+
"step": 178
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 2.418918918918919,
|
| 1259 |
+
"grad_norm": 0.3708813488483429,
|
| 1260 |
+
"learning_rate": 1.1084813602723516e-06,
|
| 1261 |
+
"loss": 0.6289,
|
| 1262 |
+
"step": 179
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 2.4324324324324325,
|
| 1266 |
+
"grad_norm": 0.3909187912940979,
|
| 1267 |
+
"learning_rate": 1.0594063267640386e-06,
|
| 1268 |
+
"loss": 0.6646,
|
| 1269 |
+
"step": 180
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 2.445945945945946,
|
| 1273 |
+
"grad_norm": 0.4463992118835449,
|
| 1274 |
+
"learning_rate": 1.0113133718124036e-06,
|
| 1275 |
+
"loss": 0.7526,
|
| 1276 |
+
"step": 181
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 2.4594594594594597,
|
| 1280 |
+
"grad_norm": 0.4123649597167969,
|
| 1281 |
+
"learning_rate": 9.64214481190074e-07,
|
| 1282 |
+
"loss": 0.7304,
|
| 1283 |
+
"step": 182
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 2.472972972972973,
|
| 1287 |
+
"grad_norm": 0.4171624779701233,
|
| 1288 |
+
"learning_rate": 9.181213929280047e-07,
|
| 1289 |
+
"loss": 0.7122,
|
| 1290 |
+
"step": 183
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 2.4864864864864864,
|
| 1294 |
+
"grad_norm": 0.4228722155094147,
|
| 1295 |
+
"learning_rate": 8.7304559439012e-07,
|
| 1296 |
+
"loss": 0.6884,
|
| 1297 |
+
"step": 184
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 2.5,
|
| 1301 |
+
"grad_norm": 0.4214862287044525,
|
| 1302 |
+
"learning_rate": 8.289983194104128e-07,
|
| 1303 |
+
"loss": 0.6515,
|
| 1304 |
+
"step": 185
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 2.5135135135135136,
|
| 1308 |
+
"grad_norm": 0.39483752846717834,
|
| 1309 |
+
"learning_rate": 7.859905454932471e-07,
|
| 1310 |
+
"loss": 0.7365,
|
| 1311 |
+
"step": 186
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 2.527027027027027,
|
| 1315 |
+
"grad_norm": 0.4236520230770111,
|
| 1316 |
+
"learning_rate": 7.440329910775274e-07,
|
| 1317 |
+
"loss": 0.7368,
|
| 1318 |
+
"step": 187
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 2.5405405405405403,
|
| 1322 |
+
"grad_norm": 0.4197184443473816,
|
| 1323 |
+
"learning_rate": 7.031361128654402e-07,
|
| 1324 |
+
"loss": 0.7144,
|
| 1325 |
+
"step": 188
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 2.554054054054054,
|
| 1329 |
+
"grad_norm": 0.4189319312572479,
|
| 1330 |
+
"learning_rate": 6.633101032164274e-07,
|
| 1331 |
+
"loss": 0.6884,
|
| 1332 |
+
"step": 189
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 2.5675675675675675,
|
| 1336 |
+
"grad_norm": 0.41916143894195557,
|
| 1337 |
+
"learning_rate": 6.24564887607032e-07,
|
| 1338 |
+
"loss": 0.7383,
|
| 1339 |
+
"step": 190
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 2.581081081081081,
|
| 1343 |
+
"grad_norm": 0.3940398693084717,
|
| 1344 |
+
"learning_rate": 5.869101221572653e-07,
|
| 1345 |
+
"loss": 0.7095,
|
| 1346 |
+
"step": 191
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 2.5945945945945947,
|
| 1350 |
+
"grad_norm": 0.42643100023269653,
|
| 1351 |
+
"learning_rate": 5.50355191224099e-07,
|
| 1352 |
+
"loss": 0.6647,
|
| 1353 |
+
"step": 192
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 2.608108108108108,
|
| 1357 |
+
"grad_norm": 0.4106751084327698,
|
| 1358 |
+
"learning_rate": 5.149092050626825e-07,
|
| 1359 |
+
"loss": 0.7085,
|
| 1360 |
+
"step": 193
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 2.6216216216216215,
|
| 1364 |
+
"grad_norm": 0.35908976197242737,
|
| 1365 |
+
"learning_rate": 4.805809975558828e-07,
|
| 1366 |
+
"loss": 0.6722,
|
| 1367 |
+
"step": 194
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 2.635135135135135,
|
| 1371 |
+
"grad_norm": 0.37956303358078003,
|
| 1372 |
+
"learning_rate": 4.47379124012689e-07,
|
| 1373 |
+
"loss": 0.689,
|
| 1374 |
+
"step": 195
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 2.6486486486486487,
|
| 1378 |
+
"grad_norm": 0.4009411931037903,
|
| 1379 |
+
"learning_rate": 4.1531185903605607e-07,
|
| 1380 |
+
"loss": 0.7396,
|
| 1381 |
+
"step": 196
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 2.6621621621621623,
|
| 1385 |
+
"grad_norm": 0.4129226803779602,
|
| 1386 |
+
"learning_rate": 3.8438719446069693e-07,
|
| 1387 |
+
"loss": 0.6984,
|
| 1388 |
+
"step": 197
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 2.6756756756756754,
|
| 1392 |
+
"grad_norm": 0.3751216530799866,
|
| 1393 |
+
"learning_rate": 3.546128373613472e-07,
|
| 1394 |
+
"loss": 0.676,
|
| 1395 |
+
"step": 198
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 2.689189189189189,
|
| 1399 |
+
"grad_norm": 0.5035135746002197,
|
| 1400 |
+
"learning_rate": 3.259962081320084e-07,
|
| 1401 |
+
"loss": 0.6387,
|
| 1402 |
+
"step": 199
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 2.7027027027027026,
|
| 1406 |
+
"grad_norm": 0.38021719455718994,
|
| 1407 |
+
"learning_rate": 2.9854443863662263e-07,
|
| 1408 |
+
"loss": 0.6955,
|
| 1409 |
+
"step": 200
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 2.7162162162162162,
|
| 1413 |
+
"grad_norm": 0.3587128520011902,
|
| 1414 |
+
"learning_rate": 2.722643704316652e-07,
|
| 1415 |
+
"loss": 0.7018,
|
| 1416 |
+
"step": 201
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 2.72972972972973,
|
| 1420 |
+
"grad_norm": 0.3971840739250183,
|
| 1421 |
+
"learning_rate": 2.4716255306108605e-07,
|
| 1422 |
+
"loss": 0.6882,
|
| 1423 |
+
"step": 202
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 2.743243243243243,
|
| 1427 |
+
"grad_norm": 0.4159408211708069,
|
| 1428 |
+
"learning_rate": 2.232452424240261e-07,
|
| 1429 |
+
"loss": 0.6018,
|
| 1430 |
+
"step": 203
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 2.756756756756757,
|
| 1434 |
+
"grad_norm": 0.40227028727531433,
|
| 1435 |
+
"learning_rate": 2.0051839921571448e-07,
|
| 1436 |
+
"loss": 0.7123,
|
| 1437 |
+
"step": 204
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 2.77027027027027,
|
| 1441 |
+
"grad_norm": 0.3627745509147644,
|
| 1442 |
+
"learning_rate": 1.7898768744194163e-07,
|
| 1443 |
+
"loss": 0.684,
|
| 1444 |
+
"step": 205
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 2.7837837837837838,
|
| 1448 |
+
"grad_norm": 0.4304984211921692,
|
| 1449 |
+
"learning_rate": 1.5865847300746417e-07,
|
| 1450 |
+
"loss": 0.6959,
|
| 1451 |
+
"step": 206
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 2.7972972972972974,
|
| 1455 |
+
"grad_norm": 0.42529451847076416,
|
| 1456 |
+
"learning_rate": 1.395358223787152e-07,
|
| 1457 |
+
"loss": 0.6353,
|
| 1458 |
+
"step": 207
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 2.810810810810811,
|
| 1462 |
+
"grad_norm": 0.41073259711265564,
|
| 1463 |
+
"learning_rate": 1.2162450132113202e-07,
|
| 1464 |
+
"loss": 0.6685,
|
| 1465 |
+
"step": 208
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 2.8243243243243246,
|
| 1469 |
+
"grad_norm": 0.350475013256073,
|
| 1470 |
+
"learning_rate": 1.049289737114273e-07,
|
| 1471 |
+
"loss": 0.6556,
|
| 1472 |
+
"step": 209
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 2.8378378378378377,
|
| 1476 |
+
"grad_norm": 0.44185787439346313,
|
| 1477 |
+
"learning_rate": 8.945340042509799e-08,
|
| 1478 |
+
"loss": 0.6669,
|
| 1479 |
+
"step": 210
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 2.8513513513513513,
|
| 1483 |
+
"grad_norm": 0.36859986186027527,
|
| 1484 |
+
"learning_rate": 7.520163829944805e-08,
|
| 1485 |
+
"loss": 0.6401,
|
| 1486 |
+
"step": 211
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 2.864864864864865,
|
| 1490 |
+
"grad_norm": 0.35210666060447693,
|
| 1491 |
+
"learning_rate": 6.217723917238127e-08,
|
| 1492 |
+
"loss": 0.6644,
|
| 1493 |
+
"step": 212
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 2.8783783783783785,
|
| 1497 |
+
"grad_norm": 0.3914670944213867,
|
| 1498 |
+
"learning_rate": 5.038344899721437e-08,
|
| 1499 |
+
"loss": 0.702,
|
| 1500 |
+
"step": 213
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 2.891891891891892,
|
| 1504 |
+
"grad_norm": 0.37066540122032166,
|
| 1505 |
+
"learning_rate": 3.9823207033710676e-08,
|
| 1506 |
+
"loss": 0.7573,
|
| 1507 |
+
"step": 214
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 2.9054054054054053,
|
| 1511 |
+
"grad_norm": 0.38512107729911804,
|
| 1512 |
+
"learning_rate": 3.049914511556118e-08,
|
| 1513 |
+
"loss": 0.632,
|
| 1514 |
+
"step": 215
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 2.918918918918919,
|
| 1518 |
+
"grad_norm": 0.3650054335594177,
|
| 1519 |
+
"learning_rate": 2.2413586994470826e-08,
|
| 1520 |
+
"loss": 0.673,
|
| 1521 |
+
"step": 216
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 2.9324324324324325,
|
| 1525 |
+
"grad_norm": 0.3610229790210724,
|
| 1526 |
+
"learning_rate": 1.5568547761034003e-08,
|
| 1527 |
+
"loss": 0.666,
|
| 1528 |
+
"step": 217
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 2.945945945945946,
|
| 1532 |
+
"grad_norm": 0.3508203327655792,
|
| 1533 |
+
"learning_rate": 9.965733342532925e-09,
|
| 1534 |
+
"loss": 0.7365,
|
| 1535 |
+
"step": 218
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 2.9594594594594597,
|
| 1539 |
+
"grad_norm": 0.39440926909446716,
|
| 1540 |
+
"learning_rate": 5.606540077782164e-09,
|
| 1541 |
+
"loss": 0.7352,
|
| 1542 |
+
"step": 219
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 2.972972972972973,
|
| 1546 |
+
"grad_norm": 0.40674489736557007,
|
| 1547 |
+
"learning_rate": 2.492054369130914e-09,
|
| 1548 |
+
"loss": 0.6517,
|
| 1549 |
+
"step": 220
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 2.9864864864864864,
|
| 1553 |
+
"grad_norm": 0.41696736216545105,
|
| 1554 |
+
"learning_rate": 6.23052411713454e-10,
|
| 1555 |
+
"loss": 0.6425,
|
| 1556 |
+
"step": 221
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 3.0,
|
| 1560 |
+
"grad_norm": 0.38195478916168213,
|
| 1561 |
+
"learning_rate": 0.0,
|
| 1562 |
+
"loss": 0.6743,
|
| 1563 |
+
"step": 222
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 3.0,
|
| 1567 |
+
"step": 222,
|
| 1568 |
+
"total_flos": 209046155558912.0,
|
| 1569 |
+
"train_loss": 0.757471783472611,
|
| 1570 |
+
"train_runtime": 6900.2048,
|
| 1571 |
+
"train_samples_per_second": 3.084,
|
| 1572 |
+
"train_steps_per_second": 0.032
|
| 1573 |
+
}
|
| 1574 |
+
],
|
| 1575 |
+
"logging_steps": 1.0,
|
| 1576 |
+
"max_steps": 222,
|
| 1577 |
+
"num_input_tokens_seen": 0,
|
| 1578 |
+
"num_train_epochs": 3,
|
| 1579 |
+
"save_steps": 500,
|
| 1580 |
+
"stateful_callbacks": {
|
| 1581 |
+
"TrainerControl": {
|
| 1582 |
+
"args": {
|
| 1583 |
+
"should_epoch_stop": false,
|
| 1584 |
+
"should_evaluate": false,
|
| 1585 |
+
"should_log": false,
|
| 1586 |
+
"should_save": true,
|
| 1587 |
+
"should_training_stop": true
|
| 1588 |
+
},
|
| 1589 |
+
"attributes": {}
|
| 1590 |
+
}
|
| 1591 |
+
},
|
| 1592 |
+
"total_flos": 209046155558912.0,
|
| 1593 |
+
"train_batch_size": 1,
|
| 1594 |
+
"trial_name": null,
|
| 1595 |
+
"trial_params": null
|
| 1596 |
+
}
|
training_loss.png
ADDED
|