End of training
Browse files- README.md +2 -1
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +2108 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: other
|
|
| 4 |
base_model: Qwen/Qwen2.5-Coder-3B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: Qwen2.5-Coder-3B-Instruct-Venus-Cold-Start
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# Qwen2.5-Coder-3B-Instruct-Venus-Cold-Start
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-3B-Instruct) on
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 4 |
base_model: Qwen/Qwen2.5-Coder-3B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: Qwen2.5-Coder-3B-Instruct-Venus-Cold-Start
|
|
|
|
| 16 |
|
| 17 |
# Qwen2.5-Coder-3B-Instruct-Venus-Cold-Start
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-3B-Instruct) on the venus_cold_start dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.9884169884169884,
|
| 3 |
+
"num_input_tokens_seen": 12333744,
|
| 4 |
+
"total_flos": 2.0534009572779622e+17,
|
| 5 |
+
"train_loss": 0.535006606301596,
|
| 6 |
+
"train_runtime": 453.6685,
|
| 7 |
+
"train_samples_per_second": 9.13,
|
| 8 |
+
"train_steps_per_second": 0.569
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.9884169884169884,
|
| 3 |
+
"num_input_tokens_seen": 12333744,
|
| 4 |
+
"total_flos": 2.0534009572779622e+17,
|
| 5 |
+
"train_loss": 0.535006606301596,
|
| 6 |
+
"train_runtime": 453.6685,
|
| 7 |
+
"train_samples_per_second": 9.13,
|
| 8 |
+
"train_steps_per_second": 0.569
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2108 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.9884169884169884,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 258,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.007722007722007722,
|
| 14 |
+
"grad_norm": 3.7684099674224854,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 1.1103,
|
| 17 |
+
"num_input_tokens_seen": 45712,
|
| 18 |
+
"step": 1
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 0.015444015444015444,
|
| 22 |
+
"grad_norm": 3.7689733505249023,
|
| 23 |
+
"learning_rate": 2.5e-06,
|
| 24 |
+
"loss": 1.0548,
|
| 25 |
+
"num_input_tokens_seen": 90856,
|
| 26 |
+
"step": 2
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.023166023166023165,
|
| 30 |
+
"grad_norm": 3.066856622695923,
|
| 31 |
+
"learning_rate": 5e-06,
|
| 32 |
+
"loss": 0.9604,
|
| 33 |
+
"num_input_tokens_seen": 141160,
|
| 34 |
+
"step": 3
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.03088803088803089,
|
| 38 |
+
"grad_norm": 2.7844741344451904,
|
| 39 |
+
"learning_rate": 7.5e-06,
|
| 40 |
+
"loss": 1.0064,
|
| 41 |
+
"num_input_tokens_seen": 191560,
|
| 42 |
+
"step": 4
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.03861003861003861,
|
| 46 |
+
"grad_norm": 1.7969169616699219,
|
| 47 |
+
"learning_rate": 1e-05,
|
| 48 |
+
"loss": 0.935,
|
| 49 |
+
"num_input_tokens_seen": 239792,
|
| 50 |
+
"step": 5
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.04633204633204633,
|
| 54 |
+
"grad_norm": 2.561210870742798,
|
| 55 |
+
"learning_rate": 1.25e-05,
|
| 56 |
+
"loss": 0.9258,
|
| 57 |
+
"num_input_tokens_seen": 286776,
|
| 58 |
+
"step": 6
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.05405405405405406,
|
| 62 |
+
"grad_norm": 2.740765333175659,
|
| 63 |
+
"learning_rate": 1.5e-05,
|
| 64 |
+
"loss": 0.9268,
|
| 65 |
+
"num_input_tokens_seen": 339256,
|
| 66 |
+
"step": 7
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.06177606177606178,
|
| 70 |
+
"grad_norm": 2.7144649028778076,
|
| 71 |
+
"learning_rate": 1.75e-05,
|
| 72 |
+
"loss": 1.023,
|
| 73 |
+
"num_input_tokens_seen": 388616,
|
| 74 |
+
"step": 8
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.0694980694980695,
|
| 78 |
+
"grad_norm": 2.0525765419006348,
|
| 79 |
+
"learning_rate": 2e-05,
|
| 80 |
+
"loss": 0.9466,
|
| 81 |
+
"num_input_tokens_seen": 434136,
|
| 82 |
+
"step": 9
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.07722007722007722,
|
| 86 |
+
"grad_norm": 1.4776036739349365,
|
| 87 |
+
"learning_rate": 2.25e-05,
|
| 88 |
+
"loss": 0.8229,
|
| 89 |
+
"num_input_tokens_seen": 485424,
|
| 90 |
+
"step": 10
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.08494208494208494,
|
| 94 |
+
"grad_norm": 1.4184006452560425,
|
| 95 |
+
"learning_rate": 2.5e-05,
|
| 96 |
+
"loss": 0.8575,
|
| 97 |
+
"num_input_tokens_seen": 532232,
|
| 98 |
+
"step": 11
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.09266409266409266,
|
| 102 |
+
"grad_norm": 1.3195043802261353,
|
| 103 |
+
"learning_rate": 2.7500000000000004e-05,
|
| 104 |
+
"loss": 0.8271,
|
| 105 |
+
"num_input_tokens_seen": 575152,
|
| 106 |
+
"step": 12
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.10038610038610038,
|
| 110 |
+
"grad_norm": 1.1674644947052002,
|
| 111 |
+
"learning_rate": 3e-05,
|
| 112 |
+
"loss": 0.7658,
|
| 113 |
+
"num_input_tokens_seen": 620992,
|
| 114 |
+
"step": 13
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.10810810810810811,
|
| 118 |
+
"grad_norm": 1.2842392921447754,
|
| 119 |
+
"learning_rate": 3.2500000000000004e-05,
|
| 120 |
+
"loss": 0.8372,
|
| 121 |
+
"num_input_tokens_seen": 671288,
|
| 122 |
+
"step": 14
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.11583011583011583,
|
| 126 |
+
"grad_norm": 1.2587034702301025,
|
| 127 |
+
"learning_rate": 3.5e-05,
|
| 128 |
+
"loss": 0.8108,
|
| 129 |
+
"num_input_tokens_seen": 722848,
|
| 130 |
+
"step": 15
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.12355212355212356,
|
| 134 |
+
"grad_norm": 1.1240705251693726,
|
| 135 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 136 |
+
"loss": 0.824,
|
| 137 |
+
"num_input_tokens_seen": 767632,
|
| 138 |
+
"step": 16
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.13127413127413126,
|
| 142 |
+
"grad_norm": 1.2230473756790161,
|
| 143 |
+
"learning_rate": 4e-05,
|
| 144 |
+
"loss": 0.7958,
|
| 145 |
+
"num_input_tokens_seen": 816304,
|
| 146 |
+
"step": 17
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.138996138996139,
|
| 150 |
+
"grad_norm": 1.0638173818588257,
|
| 151 |
+
"learning_rate": 4.25e-05,
|
| 152 |
+
"loss": 0.7784,
|
| 153 |
+
"num_input_tokens_seen": 865360,
|
| 154 |
+
"step": 18
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.14671814671814673,
|
| 158 |
+
"grad_norm": 0.9111860394477844,
|
| 159 |
+
"learning_rate": 4.5e-05,
|
| 160 |
+
"loss": 0.7205,
|
| 161 |
+
"num_input_tokens_seen": 919800,
|
| 162 |
+
"step": 19
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.15444015444015444,
|
| 166 |
+
"grad_norm": 1.1077393293380737,
|
| 167 |
+
"learning_rate": 4.75e-05,
|
| 168 |
+
"loss": 0.7929,
|
| 169 |
+
"num_input_tokens_seen": 965736,
|
| 170 |
+
"step": 20
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.16216216216216217,
|
| 174 |
+
"grad_norm": 0.9261448383331299,
|
| 175 |
+
"learning_rate": 5e-05,
|
| 176 |
+
"loss": 0.7326,
|
| 177 |
+
"num_input_tokens_seen": 1017352,
|
| 178 |
+
"step": 21
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.16988416988416988,
|
| 182 |
+
"grad_norm": 1.0034143924713135,
|
| 183 |
+
"learning_rate": 4.999782204181027e-05,
|
| 184 |
+
"loss": 0.749,
|
| 185 |
+
"num_input_tokens_seen": 1061344,
|
| 186 |
+
"step": 22
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.1776061776061776,
|
| 190 |
+
"grad_norm": 0.9668173789978027,
|
| 191 |
+
"learning_rate": 4.999128854672123e-05,
|
| 192 |
+
"loss": 0.7499,
|
| 193 |
+
"num_input_tokens_seen": 1109672,
|
| 194 |
+
"step": 23
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.18532818532818532,
|
| 198 |
+
"grad_norm": 0.8699672818183899,
|
| 199 |
+
"learning_rate": 4.9980400653107194e-05,
|
| 200 |
+
"loss": 0.6966,
|
| 201 |
+
"num_input_tokens_seen": 1159832,
|
| 202 |
+
"step": 24
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.19305019305019305,
|
| 206 |
+
"grad_norm": 0.863695502281189,
|
| 207 |
+
"learning_rate": 4.9965160258038346e-05,
|
| 208 |
+
"loss": 0.7161,
|
| 209 |
+
"num_input_tokens_seen": 1209240,
|
| 210 |
+
"step": 25
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.20077220077220076,
|
| 214 |
+
"grad_norm": 0.9278308749198914,
|
| 215 |
+
"learning_rate": 4.9945570016950135e-05,
|
| 216 |
+
"loss": 0.7119,
|
| 217 |
+
"num_input_tokens_seen": 1259568,
|
| 218 |
+
"step": 26
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.2084942084942085,
|
| 222 |
+
"grad_norm": 1.0021332502365112,
|
| 223 |
+
"learning_rate": 4.9921633343180654e-05,
|
| 224 |
+
"loss": 0.8077,
|
| 225 |
+
"num_input_tokens_seen": 1308136,
|
| 226 |
+
"step": 27
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.21621621621621623,
|
| 230 |
+
"grad_norm": 0.9220330715179443,
|
| 231 |
+
"learning_rate": 4.989335440737586e-05,
|
| 232 |
+
"loss": 0.7465,
|
| 233 |
+
"num_input_tokens_seen": 1356408,
|
| 234 |
+
"step": 28
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.22393822393822393,
|
| 238 |
+
"grad_norm": 0.9325352907180786,
|
| 239 |
+
"learning_rate": 4.986073813676296e-05,
|
| 240 |
+
"loss": 0.7342,
|
| 241 |
+
"num_input_tokens_seen": 1402072,
|
| 242 |
+
"step": 29
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.23166023166023167,
|
| 246 |
+
"grad_norm": 0.9855431914329529,
|
| 247 |
+
"learning_rate": 4.9823790214291836e-05,
|
| 248 |
+
"loss": 0.7492,
|
| 249 |
+
"num_input_tokens_seen": 1454592,
|
| 250 |
+
"step": 30
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.23938223938223938,
|
| 254 |
+
"grad_norm": 0.9169183373451233,
|
| 255 |
+
"learning_rate": 4.978251707764492e-05,
|
| 256 |
+
"loss": 0.7423,
|
| 257 |
+
"num_input_tokens_seen": 1500560,
|
| 258 |
+
"step": 31
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.2471042471042471,
|
| 262 |
+
"grad_norm": 0.9389194846153259,
|
| 263 |
+
"learning_rate": 4.973692591811549e-05,
|
| 264 |
+
"loss": 0.7463,
|
| 265 |
+
"num_input_tokens_seen": 1546960,
|
| 266 |
+
"step": 32
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.2548262548262548,
|
| 270 |
+
"grad_norm": 0.9559301733970642,
|
| 271 |
+
"learning_rate": 4.968702467935469e-05,
|
| 272 |
+
"loss": 0.7673,
|
| 273 |
+
"num_input_tokens_seen": 1598424,
|
| 274 |
+
"step": 33
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.2625482625482625,
|
| 278 |
+
"grad_norm": 0.9239445328712463,
|
| 279 |
+
"learning_rate": 4.963282205598744e-05,
|
| 280 |
+
"loss": 0.6737,
|
| 281 |
+
"num_input_tokens_seen": 1643656,
|
| 282 |
+
"step": 34
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.2702702702702703,
|
| 286 |
+
"grad_norm": 0.8067498803138733,
|
| 287 |
+
"learning_rate": 4.957432749209755e-05,
|
| 288 |
+
"loss": 0.68,
|
| 289 |
+
"num_input_tokens_seen": 1698008,
|
| 290 |
+
"step": 35
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.277992277992278,
|
| 294 |
+
"grad_norm": 0.8876193761825562,
|
| 295 |
+
"learning_rate": 4.9511551179582174e-05,
|
| 296 |
+
"loss": 0.7391,
|
| 297 |
+
"num_input_tokens_seen": 1743856,
|
| 298 |
+
"step": 36
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.2857142857142857,
|
| 302 |
+
"grad_norm": 0.8399716019630432,
|
| 303 |
+
"learning_rate": 4.944450405637602e-05,
|
| 304 |
+
"loss": 0.7076,
|
| 305 |
+
"num_input_tokens_seen": 1797032,
|
| 306 |
+
"step": 37
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.29343629343629346,
|
| 310 |
+
"grad_norm": 0.8189979791641235,
|
| 311 |
+
"learning_rate": 4.937319780454559e-05,
|
| 312 |
+
"loss": 0.6502,
|
| 313 |
+
"num_input_tokens_seen": 1847632,
|
| 314 |
+
"step": 38
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.30115830115830117,
|
| 318 |
+
"grad_norm": 0.8758053183555603,
|
| 319 |
+
"learning_rate": 4.929764484825369e-05,
|
| 320 |
+
"loss": 0.7052,
|
| 321 |
+
"num_input_tokens_seen": 1895000,
|
| 322 |
+
"step": 39
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.3088803088803089,
|
| 326 |
+
"grad_norm": 0.9134597778320312,
|
| 327 |
+
"learning_rate": 4.921785835159472e-05,
|
| 328 |
+
"loss": 0.7224,
|
| 329 |
+
"num_input_tokens_seen": 1936384,
|
| 330 |
+
"step": 40
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.3166023166023166,
|
| 334 |
+
"grad_norm": 0.8602584600448608,
|
| 335 |
+
"learning_rate": 4.9133852216300965e-05,
|
| 336 |
+
"loss": 0.7023,
|
| 337 |
+
"num_input_tokens_seen": 1984248,
|
| 338 |
+
"step": 41
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.32432432432432434,
|
| 342 |
+
"grad_norm": 0.8215887546539307,
|
| 343 |
+
"learning_rate": 4.9045641079320484e-05,
|
| 344 |
+
"loss": 0.7099,
|
| 345 |
+
"num_input_tokens_seen": 2029000,
|
| 346 |
+
"step": 42
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.33204633204633205,
|
| 350 |
+
"grad_norm": 0.8211591243743896,
|
| 351 |
+
"learning_rate": 4.89532403102667e-05,
|
| 352 |
+
"loss": 0.7397,
|
| 353 |
+
"num_input_tokens_seen": 2078944,
|
| 354 |
+
"step": 43
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.33976833976833976,
|
| 358 |
+
"grad_norm": 0.8224607110023499,
|
| 359 |
+
"learning_rate": 4.8856666008740583e-05,
|
| 360 |
+
"loss": 0.6995,
|
| 361 |
+
"num_input_tokens_seen": 2126352,
|
| 362 |
+
"step": 44
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.3474903474903475,
|
| 366 |
+
"grad_norm": 0.913007915019989,
|
| 367 |
+
"learning_rate": 4.875593500152538e-05,
|
| 368 |
+
"loss": 0.6849,
|
| 369 |
+
"num_input_tokens_seen": 2172368,
|
| 370 |
+
"step": 45
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.3552123552123552,
|
| 374 |
+
"grad_norm": 0.8476090431213379,
|
| 375 |
+
"learning_rate": 4.865106483965487e-05,
|
| 376 |
+
"loss": 0.7019,
|
| 377 |
+
"num_input_tokens_seen": 2217024,
|
| 378 |
+
"step": 46
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.36293436293436293,
|
| 382 |
+
"grad_norm": 0.7849616408348083,
|
| 383 |
+
"learning_rate": 4.8542073795355294e-05,
|
| 384 |
+
"loss": 0.6447,
|
| 385 |
+
"num_input_tokens_seen": 2266472,
|
| 386 |
+
"step": 47
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.37065637065637064,
|
| 390 |
+
"grad_norm": 0.8142545819282532,
|
| 391 |
+
"learning_rate": 4.842898085886164e-05,
|
| 392 |
+
"loss": 0.6961,
|
| 393 |
+
"num_input_tokens_seen": 2318480,
|
| 394 |
+
"step": 48
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.3783783783783784,
|
| 398 |
+
"grad_norm": 0.8318261504173279,
|
| 399 |
+
"learning_rate": 4.8311805735108894e-05,
|
| 400 |
+
"loss": 0.6864,
|
| 401 |
+
"num_input_tokens_seen": 2368432,
|
| 402 |
+
"step": 49
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.3861003861003861,
|
| 406 |
+
"grad_norm": 0.8627023696899414,
|
| 407 |
+
"learning_rate": 4.81905688402987e-05,
|
| 408 |
+
"loss": 0.6599,
|
| 409 |
+
"num_input_tokens_seen": 2413104,
|
| 410 |
+
"step": 50
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.3938223938223938,
|
| 414 |
+
"grad_norm": 0.8817498087882996,
|
| 415 |
+
"learning_rate": 4.806529129834208e-05,
|
| 416 |
+
"loss": 0.7159,
|
| 417 |
+
"num_input_tokens_seen": 2458232,
|
| 418 |
+
"step": 51
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.4015444015444015,
|
| 422 |
+
"grad_norm": 0.8289158940315247,
|
| 423 |
+
"learning_rate": 4.793599493717891e-05,
|
| 424 |
+
"loss": 0.6649,
|
| 425 |
+
"num_input_tokens_seen": 2501480,
|
| 426 |
+
"step": 52
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.4092664092664093,
|
| 430 |
+
"grad_norm": 0.794998824596405,
|
| 431 |
+
"learning_rate": 4.78027022849747e-05,
|
| 432 |
+
"loss": 0.6671,
|
| 433 |
+
"num_input_tokens_seen": 2548328,
|
| 434 |
+
"step": 53
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.416988416988417,
|
| 438 |
+
"grad_norm": 0.8775593638420105,
|
| 439 |
+
"learning_rate": 4.766543656619532e-05,
|
| 440 |
+
"loss": 0.6504,
|
| 441 |
+
"num_input_tokens_seen": 2592744,
|
| 442 |
+
"step": 54
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.4247104247104247,
|
| 446 |
+
"grad_norm": 0.7581058740615845,
|
| 447 |
+
"learning_rate": 4.752422169756048e-05,
|
| 448 |
+
"loss": 0.611,
|
| 449 |
+
"num_input_tokens_seen": 2648832,
|
| 450 |
+
"step": 55
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.43243243243243246,
|
| 454 |
+
"grad_norm": 0.8995907306671143,
|
| 455 |
+
"learning_rate": 4.7379082283876566e-05,
|
| 456 |
+
"loss": 0.6815,
|
| 457 |
+
"num_input_tokens_seen": 2695656,
|
| 458 |
+
"step": 56
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.44015444015444016,
|
| 462 |
+
"grad_norm": 0.8074026703834534,
|
| 463 |
+
"learning_rate": 4.723004361374953e-05,
|
| 464 |
+
"loss": 0.6714,
|
| 465 |
+
"num_input_tokens_seen": 2748024,
|
| 466 |
+
"step": 57
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.44787644787644787,
|
| 470 |
+
"grad_norm": 0.817803680896759,
|
| 471 |
+
"learning_rate": 4.707713165517877e-05,
|
| 472 |
+
"loss": 0.6611,
|
| 473 |
+
"num_input_tokens_seen": 2797448,
|
| 474 |
+
"step": 58
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.4555984555984556,
|
| 478 |
+
"grad_norm": 0.8251329660415649,
|
| 479 |
+
"learning_rate": 4.692037305103247e-05,
|
| 480 |
+
"loss": 0.638,
|
| 481 |
+
"num_input_tokens_seen": 2843456,
|
| 482 |
+
"step": 59
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.46332046332046334,
|
| 486 |
+
"grad_norm": 0.9807698130607605,
|
| 487 |
+
"learning_rate": 4.675979511440549e-05,
|
| 488 |
+
"loss": 0.7447,
|
| 489 |
+
"num_input_tokens_seen": 2888008,
|
| 490 |
+
"step": 60
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.47104247104247104,
|
| 494 |
+
"grad_norm": 0.8173831701278687,
|
| 495 |
+
"learning_rate": 4.659542582386041e-05,
|
| 496 |
+
"loss": 0.6413,
|
| 497 |
+
"num_input_tokens_seen": 2930816,
|
| 498 |
+
"step": 61
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.47876447876447875,
|
| 502 |
+
"grad_norm": 0.9126039147377014,
|
| 503 |
+
"learning_rate": 4.642729381855262e-05,
|
| 504 |
+
"loss": 0.6495,
|
| 505 |
+
"num_input_tokens_seen": 2976920,
|
| 506 |
+
"step": 62
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.4864864864864865,
|
| 510 |
+
"grad_norm": 0.9136143326759338,
|
| 511 |
+
"learning_rate": 4.625542839324036e-05,
|
| 512 |
+
"loss": 0.6735,
|
| 513 |
+
"num_input_tokens_seen": 3022496,
|
| 514 |
+
"step": 63
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.4942084942084942,
|
| 518 |
+
"grad_norm": 0.8095064759254456,
|
| 519 |
+
"learning_rate": 4.607985949318047e-05,
|
| 520 |
+
"loss": 0.6856,
|
| 521 |
+
"num_input_tokens_seen": 3071824,
|
| 522 |
+
"step": 64
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.5019305019305019,
|
| 526 |
+
"grad_norm": 0.868986189365387,
|
| 527 |
+
"learning_rate": 4.5900617708910854e-05,
|
| 528 |
+
"loss": 0.689,
|
| 529 |
+
"num_input_tokens_seen": 3119136,
|
| 530 |
+
"step": 65
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.5096525096525096,
|
| 534 |
+
"grad_norm": 0.8730259537696838,
|
| 535 |
+
"learning_rate": 4.571773427092047e-05,
|
| 536 |
+
"loss": 0.685,
|
| 537 |
+
"num_input_tokens_seen": 3160840,
|
| 538 |
+
"step": 66
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 0.5173745173745173,
|
| 542 |
+
"grad_norm": 0.7655907869338989,
|
| 543 |
+
"learning_rate": 4.553124104420784e-05,
|
| 544 |
+
"loss": 0.6211,
|
| 545 |
+
"num_input_tokens_seen": 3205472,
|
| 546 |
+
"step": 67
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.525096525096525,
|
| 550 |
+
"grad_norm": 0.8272292613983154,
|
| 551 |
+
"learning_rate": 4.5341170522729006e-05,
|
| 552 |
+
"loss": 0.6785,
|
| 553 |
+
"num_input_tokens_seen": 3255480,
|
| 554 |
+
"step": 68
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.5328185328185329,
|
| 558 |
+
"grad_norm": 0.7634907960891724,
|
| 559 |
+
"learning_rate": 4.514755582373587e-05,
|
| 560 |
+
"loss": 0.6477,
|
| 561 |
+
"num_input_tokens_seen": 3306024,
|
| 562 |
+
"step": 69
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.5405405405405406,
|
| 566 |
+
"grad_norm": 0.8490803241729736,
|
| 567 |
+
"learning_rate": 4.4950430682006e-05,
|
| 568 |
+
"loss": 0.7086,
|
| 569 |
+
"num_input_tokens_seen": 3350976,
|
| 570 |
+
"step": 70
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.5482625482625483,
|
| 574 |
+
"grad_norm": 0.7535845637321472,
|
| 575 |
+
"learning_rate": 4.4749829443964705e-05,
|
| 576 |
+
"loss": 0.6436,
|
| 577 |
+
"num_input_tokens_seen": 3400376,
|
| 578 |
+
"step": 71
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.555984555984556,
|
| 582 |
+
"grad_norm": 0.8641594052314758,
|
| 583 |
+
"learning_rate": 4.454578706170075e-05,
|
| 584 |
+
"loss": 0.6926,
|
| 585 |
+
"num_input_tokens_seen": 3446016,
|
| 586 |
+
"step": 72
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.5637065637065637,
|
| 590 |
+
"grad_norm": 0.8073216080665588,
|
| 591 |
+
"learning_rate": 4.433833908687633e-05,
|
| 592 |
+
"loss": 0.6917,
|
| 593 |
+
"num_input_tokens_seen": 3497296,
|
| 594 |
+
"step": 73
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.5714285714285714,
|
| 598 |
+
"grad_norm": 0.8128077387809753,
|
| 599 |
+
"learning_rate": 4.4127521664532704e-05,
|
| 600 |
+
"loss": 0.6608,
|
| 601 |
+
"num_input_tokens_seen": 3543456,
|
| 602 |
+
"step": 74
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 0.5791505791505791,
|
| 606 |
+
"grad_norm": 0.8153249621391296,
|
| 607 |
+
"learning_rate": 4.39133715267924e-05,
|
| 608 |
+
"loss": 0.6712,
|
| 609 |
+
"num_input_tokens_seen": 3587352,
|
| 610 |
+
"step": 75
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 0.5868725868725869,
|
| 614 |
+
"grad_norm": 0.748672604560852,
|
| 615 |
+
"learning_rate": 4.3695925986459115e-05,
|
| 616 |
+
"loss": 0.6644,
|
| 617 |
+
"num_input_tokens_seen": 3635888,
|
| 618 |
+
"step": 76
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.5945945945945946,
|
| 622 |
+
"grad_norm": 0.8283869028091431,
|
| 623 |
+
"learning_rate": 4.347522293051648e-05,
|
| 624 |
+
"loss": 0.6168,
|
| 625 |
+
"num_input_tokens_seen": 3684128,
|
| 626 |
+
"step": 77
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.6023166023166023,
|
| 630 |
+
"grad_norm": 0.8540968894958496,
|
| 631 |
+
"learning_rate": 4.3251300813526754e-05,
|
| 632 |
+
"loss": 0.687,
|
| 633 |
+
"num_input_tokens_seen": 3733704,
|
| 634 |
+
"step": 78
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.61003861003861,
|
| 638 |
+
"grad_norm": 0.7499772906303406,
|
| 639 |
+
"learning_rate": 4.3024198650930625e-05,
|
| 640 |
+
"loss": 0.6009,
|
| 641 |
+
"num_input_tokens_seen": 3777744,
|
| 642 |
+
"step": 79
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 0.6177606177606177,
|
| 646 |
+
"grad_norm": 0.7799640893936157,
|
| 647 |
+
"learning_rate": 4.279395601224928e-05,
|
| 648 |
+
"loss": 0.6559,
|
| 649 |
+
"num_input_tokens_seen": 3828288,
|
| 650 |
+
"step": 80
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.6254826254826255,
|
| 654 |
+
"grad_norm": 0.7528457045555115,
|
| 655 |
+
"learning_rate": 4.2560613014189966e-05,
|
| 656 |
+
"loss": 0.6037,
|
| 657 |
+
"num_input_tokens_seen": 3875936,
|
| 658 |
+
"step": 81
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 0.6332046332046332,
|
| 662 |
+
"grad_norm": 0.8638529181480408,
|
| 663 |
+
"learning_rate": 4.2324210313656176e-05,
|
| 664 |
+
"loss": 0.6906,
|
| 665 |
+
"num_input_tokens_seen": 3921376,
|
| 666 |
+
"step": 82
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 0.640926640926641,
|
| 670 |
+
"grad_norm": 0.8515468835830688,
|
| 671 |
+
"learning_rate": 4.208478910066371e-05,
|
| 672 |
+
"loss": 0.6672,
|
| 673 |
+
"num_input_tokens_seen": 3968400,
|
| 674 |
+
"step": 83
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.6486486486486487,
|
| 678 |
+
"grad_norm": 0.7536445260047913,
|
| 679 |
+
"learning_rate": 4.184239109116393e-05,
|
| 680 |
+
"loss": 0.6584,
|
| 681 |
+
"num_input_tokens_seen": 4016608,
|
| 682 |
+
"step": 84
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.6563706563706564,
|
| 686 |
+
"grad_norm": 0.8643118739128113,
|
| 687 |
+
"learning_rate": 4.159705851977521e-05,
|
| 688 |
+
"loss": 0.6464,
|
| 689 |
+
"num_input_tokens_seen": 4064472,
|
| 690 |
+
"step": 85
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.6640926640926641,
|
| 694 |
+
"grad_norm": 0.8485602140426636,
|
| 695 |
+
"learning_rate": 4.134883413242421e-05,
|
| 696 |
+
"loss": 0.6592,
|
| 697 |
+
"num_input_tokens_seen": 4114672,
|
| 698 |
+
"step": 86
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.6718146718146718,
|
| 702 |
+
"grad_norm": 0.8153643012046814,
|
| 703 |
+
"learning_rate": 4.109776117889789e-05,
|
| 704 |
+
"loss": 0.5927,
|
| 705 |
+
"num_input_tokens_seen": 4158376,
|
| 706 |
+
"step": 87
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.6795366795366795,
|
| 710 |
+
"grad_norm": 0.7843388915061951,
|
| 711 |
+
"learning_rate": 4.084388340530791e-05,
|
| 712 |
+
"loss": 0.6028,
|
| 713 |
+
"num_input_tokens_seen": 4207504,
|
| 714 |
+
"step": 88
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 0.6872586872586872,
|
| 718 |
+
"grad_norm": 0.8065616488456726,
|
| 719 |
+
"learning_rate": 4.058724504646834e-05,
|
| 720 |
+
"loss": 0.6888,
|
| 721 |
+
"num_input_tokens_seen": 4259504,
|
| 722 |
+
"step": 89
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 0.694980694980695,
|
| 726 |
+
"grad_norm": 0.8020586371421814,
|
| 727 |
+
"learning_rate": 4.032789081818843e-05,
|
| 728 |
+
"loss": 0.6555,
|
| 729 |
+
"num_input_tokens_seen": 4303104,
|
| 730 |
+
"step": 90
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.7027027027027027,
|
| 734 |
+
"grad_norm": 0.7873929738998413,
|
| 735 |
+
"learning_rate": 4.0065865909481417e-05,
|
| 736 |
+
"loss": 0.6481,
|
| 737 |
+
"num_input_tokens_seen": 4352824,
|
| 738 |
+
"step": 91
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.7104247104247104,
|
| 742 |
+
"grad_norm": 0.8812729716300964,
|
| 743 |
+
"learning_rate": 3.980121597469096e-05,
|
| 744 |
+
"loss": 0.631,
|
| 745 |
+
"num_input_tokens_seen": 4398424,
|
| 746 |
+
"step": 92
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.7181467181467182,
|
| 750 |
+
"grad_norm": 0.748152494430542,
|
| 751 |
+
"learning_rate": 3.95339871255365e-05,
|
| 752 |
+
"loss": 0.6168,
|
| 753 |
+
"num_input_tokens_seen": 4446624,
|
| 754 |
+
"step": 93
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.7258687258687259,
|
| 758 |
+
"grad_norm": 0.7249035239219666,
|
| 759 |
+
"learning_rate": 3.926422592307888e-05,
|
| 760 |
+
"loss": 0.6152,
|
| 761 |
+
"num_input_tokens_seen": 4493880,
|
| 762 |
+
"step": 94
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 0.7335907335907336,
|
| 766 |
+
"grad_norm": 0.8587039113044739,
|
| 767 |
+
"learning_rate": 3.89919793696077e-05,
|
| 768 |
+
"loss": 0.6533,
|
| 769 |
+
"num_input_tokens_seen": 4541640,
|
| 770 |
+
"step": 95
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.7413127413127413,
|
| 774 |
+
"grad_norm": 0.7924438118934631,
|
| 775 |
+
"learning_rate": 3.871729490045185e-05,
|
| 776 |
+
"loss": 0.6414,
|
| 777 |
+
"num_input_tokens_seen": 4589296,
|
| 778 |
+
"step": 96
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 0.749034749034749,
|
| 782 |
+
"grad_norm": 0.8338213562965393,
|
| 783 |
+
"learning_rate": 3.844022037571443e-05,
|
| 784 |
+
"loss": 0.71,
|
| 785 |
+
"num_input_tokens_seen": 4639848,
|
| 786 |
+
"step": 97
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.7567567567567568,
|
| 790 |
+
"grad_norm": 0.7877117991447449,
|
| 791 |
+
"learning_rate": 3.81608040719339e-05,
|
| 792 |
+
"loss": 0.6575,
|
| 793 |
+
"num_input_tokens_seen": 4683808,
|
| 794 |
+
"step": 98
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.7644787644787645,
|
| 798 |
+
"grad_norm": 0.7668321132659912,
|
| 799 |
+
"learning_rate": 3.78790946736724e-05,
|
| 800 |
+
"loss": 0.6277,
|
| 801 |
+
"num_input_tokens_seen": 4733296,
|
| 802 |
+
"step": 99
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 0.7722007722007722,
|
| 806 |
+
"grad_norm": 0.8455983996391296,
|
| 807 |
+
"learning_rate": 3.759514126503324e-05,
|
| 808 |
+
"loss": 0.6586,
|
| 809 |
+
"num_input_tokens_seen": 4778416,
|
| 810 |
+
"step": 100
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.7799227799227799,
|
| 814 |
+
"grad_norm": 0.757305383682251,
|
| 815 |
+
"learning_rate": 3.7308993321108556e-05,
|
| 816 |
+
"loss": 0.6535,
|
| 817 |
+
"num_input_tokens_seen": 4828584,
|
| 818 |
+
"step": 101
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.7876447876447876,
|
| 822 |
+
"grad_norm": 0.7417029142379761,
|
| 823 |
+
"learning_rate": 3.702070069935898e-05,
|
| 824 |
+
"loss": 0.6324,
|
| 825 |
+
"num_input_tokens_seen": 4877424,
|
| 826 |
+
"step": 102
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.7953667953667953,
|
| 830 |
+
"grad_norm": 0.7691876292228699,
|
| 831 |
+
"learning_rate": 3.673031363092666e-05,
|
| 832 |
+
"loss": 0.607,
|
| 833 |
+
"num_input_tokens_seen": 4922312,
|
| 834 |
+
"step": 103
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 0.803088803088803,
|
| 838 |
+
"grad_norm": 0.8705837726593018,
|
| 839 |
+
"learning_rate": 3.6437882711883084e-05,
|
| 840 |
+
"loss": 0.6511,
|
| 841 |
+
"num_input_tokens_seen": 4968208,
|
| 842 |
+
"step": 104
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.8108108108108109,
|
| 846 |
+
"grad_norm": 0.7560796141624451,
|
| 847 |
+
"learning_rate": 3.6143458894413465e-05,
|
| 848 |
+
"loss": 0.6331,
|
| 849 |
+
"num_input_tokens_seen": 5018880,
|
| 850 |
+
"step": 105
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.8185328185328186,
|
| 854 |
+
"grad_norm": 0.7419978380203247,
|
| 855 |
+
"learning_rate": 3.5847093477938956e-05,
|
| 856 |
+
"loss": 0.6489,
|
| 857 |
+
"num_input_tokens_seen": 5069312,
|
| 858 |
+
"step": 106
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 0.8262548262548263,
|
| 862 |
+
"grad_norm": 0.7836557626724243,
|
| 863 |
+
"learning_rate": 3.554883810017844e-05,
|
| 864 |
+
"loss": 0.6151,
|
| 865 |
+
"num_input_tokens_seen": 5113280,
|
| 866 |
+
"step": 107
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.833976833976834,
|
| 870 |
+
"grad_norm": 0.8063251376152039,
|
| 871 |
+
"learning_rate": 3.5248744728151345e-05,
|
| 872 |
+
"loss": 0.6362,
|
| 873 |
+
"num_input_tokens_seen": 5158416,
|
| 874 |
+
"step": 108
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 0.8416988416988417,
|
| 878 |
+
"grad_norm": 0.7751627564430237,
|
| 879 |
+
"learning_rate": 3.494686564912302e-05,
|
| 880 |
+
"loss": 0.6611,
|
| 881 |
+
"num_input_tokens_seen": 5209288,
|
| 882 |
+
"step": 109
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 0.8494208494208494,
|
| 886 |
+
"grad_norm": 0.7138671278953552,
|
| 887 |
+
"learning_rate": 3.464325346149449e-05,
|
| 888 |
+
"loss": 0.6323,
|
| 889 |
+
"num_input_tokens_seen": 5264480,
|
| 890 |
+
"step": 110
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 0.8571428571428571,
|
| 894 |
+
"grad_norm": 0.806349515914917,
|
| 895 |
+
"learning_rate": 3.433796106563779e-05,
|
| 896 |
+
"loss": 0.6324,
|
| 897 |
+
"num_input_tokens_seen": 5308480,
|
| 898 |
+
"step": 111
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.8648648648648649,
|
| 902 |
+
"grad_norm": 0.7439104914665222,
|
| 903 |
+
"learning_rate": 3.403104165467883e-05,
|
| 904 |
+
"loss": 0.62,
|
| 905 |
+
"num_input_tokens_seen": 5355096,
|
| 906 |
+
"step": 112
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.8725868725868726,
|
| 910 |
+
"grad_norm": 0.7520055770874023,
|
| 911 |
+
"learning_rate": 3.3722548705229175e-05,
|
| 912 |
+
"loss": 0.6024,
|
| 913 |
+
"num_input_tokens_seen": 5401288,
|
| 914 |
+
"step": 113
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 0.8803088803088803,
|
| 918 |
+
"grad_norm": 0.7431480884552002,
|
| 919 |
+
"learning_rate": 3.341253596806848e-05,
|
| 920 |
+
"loss": 0.6548,
|
| 921 |
+
"num_input_tokens_seen": 5453648,
|
| 922 |
+
"step": 114
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.888030888030888,
|
| 926 |
+
"grad_norm": 0.7664536833763123,
|
| 927 |
+
"learning_rate": 3.310105745877915e-05,
|
| 928 |
+
"loss": 0.626,
|
| 929 |
+
"num_input_tokens_seen": 5502248,
|
| 930 |
+
"step": 115
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 0.8957528957528957,
|
| 934 |
+
"grad_norm": 0.8179628849029541,
|
| 935 |
+
"learning_rate": 3.278816744833479e-05,
|
| 936 |
+
"loss": 0.6515,
|
| 937 |
+
"num_input_tokens_seen": 5550512,
|
| 938 |
+
"step": 116
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 0.9034749034749034,
|
| 942 |
+
"grad_norm": 0.7596731185913086,
|
| 943 |
+
"learning_rate": 3.247392045364426e-05,
|
| 944 |
+
"loss": 0.6619,
|
| 945 |
+
"num_input_tokens_seen": 5603224,
|
| 946 |
+
"step": 117
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 0.9111969111969112,
|
| 950 |
+
"grad_norm": 0.7250100374221802,
|
| 951 |
+
"learning_rate": 3.215837122805282e-05,
|
| 952 |
+
"loss": 0.6463,
|
| 953 |
+
"num_input_tokens_seen": 5653152,
|
| 954 |
+
"step": 118
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.918918918918919,
|
| 958 |
+
"grad_norm": 0.7781504988670349,
|
| 959 |
+
"learning_rate": 3.1841574751802076e-05,
|
| 960 |
+
"loss": 0.6135,
|
| 961 |
+
"num_input_tokens_seen": 5699968,
|
| 962 |
+
"step": 119
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.9266409266409267,
|
| 966 |
+
"grad_norm": 0.7662553191184998,
|
| 967 |
+
"learning_rate": 3.152358622245042e-05,
|
| 968 |
+
"loss": 0.6147,
|
| 969 |
+
"num_input_tokens_seen": 5750360,
|
| 970 |
+
"step": 120
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 0.9343629343629344,
|
| 974 |
+
"grad_norm": 0.7741676568984985,
|
| 975 |
+
"learning_rate": 3.1204461045255604e-05,
|
| 976 |
+
"loss": 0.6018,
|
| 977 |
+
"num_input_tokens_seen": 5793216,
|
| 978 |
+
"step": 121
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.9420849420849421,
|
| 982 |
+
"grad_norm": 0.7969425916671753,
|
| 983 |
+
"learning_rate": 3.088425482352107e-05,
|
| 984 |
+
"loss": 0.6716,
|
| 985 |
+
"num_input_tokens_seen": 5838920,
|
| 986 |
+
"step": 122
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 0.9498069498069498,
|
| 990 |
+
"grad_norm": 0.7865390181541443,
|
| 991 |
+
"learning_rate": 3.056302334890786e-05,
|
| 992 |
+
"loss": 0.6123,
|
| 993 |
+
"num_input_tokens_seen": 5885064,
|
| 994 |
+
"step": 123
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 0.9575289575289575,
|
| 998 |
+
"grad_norm": 0.7254599332809448,
|
| 999 |
+
"learning_rate": 3.024082259171367e-05,
|
| 1000 |
+
"loss": 0.5959,
|
| 1001 |
+
"num_input_tokens_seen": 5934624,
|
| 1002 |
+
"step": 124
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 0.9652509652509652,
|
| 1006 |
+
"grad_norm": 0.7473117709159851,
|
| 1007 |
+
"learning_rate": 2.9917708691120706e-05,
|
| 1008 |
+
"loss": 0.6206,
|
| 1009 |
+
"num_input_tokens_seen": 5987336,
|
| 1010 |
+
"step": 125
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.972972972972973,
|
| 1014 |
+
"grad_norm": 0.7521440982818604,
|
| 1015 |
+
"learning_rate": 2.9593737945414264e-05,
|
| 1016 |
+
"loss": 0.6213,
|
| 1017 |
+
"num_input_tokens_seen": 6035896,
|
| 1018 |
+
"step": 126
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.9806949806949807,
|
| 1022 |
+
"grad_norm": 0.8182458281517029,
|
| 1023 |
+
"learning_rate": 2.9268966802173436e-05,
|
| 1024 |
+
"loss": 0.6743,
|
| 1025 |
+
"num_input_tokens_seen": 6080816,
|
| 1026 |
+
"step": 127
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 0.9884169884169884,
|
| 1030 |
+
"grad_norm": 0.6886686086654663,
|
| 1031 |
+
"learning_rate": 2.8943451848435936e-05,
|
| 1032 |
+
"loss": 0.5528,
|
| 1033 |
+
"num_input_tokens_seen": 6126984,
|
| 1034 |
+
"step": 128
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.9961389961389961,
|
| 1038 |
+
"grad_norm": 0.764229953289032,
|
| 1039 |
+
"learning_rate": 2.8617249800838513e-05,
|
| 1040 |
+
"loss": 0.6412,
|
| 1041 |
+
"num_input_tokens_seen": 6178704,
|
| 1042 |
+
"step": 129
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 1.0,
|
| 1046 |
+
"grad_norm": 1.057747483253479,
|
| 1047 |
+
"learning_rate": 2.8290417495734837e-05,
|
| 1048 |
+
"loss": 0.6122,
|
| 1049 |
+
"num_input_tokens_seen": 6201760,
|
| 1050 |
+
"step": 130
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 1.0077220077220077,
|
| 1054 |
+
"grad_norm": 0.9056001901626587,
|
| 1055 |
+
"learning_rate": 2.7963011879292573e-05,
|
| 1056 |
+
"loss": 0.412,
|
| 1057 |
+
"num_input_tokens_seen": 6246264,
|
| 1058 |
+
"step": 131
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 1.0154440154440154,
|
| 1062 |
+
"grad_norm": 0.8688384890556335,
|
| 1063 |
+
"learning_rate": 2.7635089997571196e-05,
|
| 1064 |
+
"loss": 0.4194,
|
| 1065 |
+
"num_input_tokens_seen": 6293720,
|
| 1066 |
+
"step": 132
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 1.0231660231660231,
|
| 1070 |
+
"grad_norm": 0.7179760336875916,
|
| 1071 |
+
"learning_rate": 2.7306708986582553e-05,
|
| 1072 |
+
"loss": 0.3895,
|
| 1073 |
+
"num_input_tokens_seen": 6348992,
|
| 1074 |
+
"step": 133
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.0308880308880308,
|
| 1078 |
+
"grad_norm": 0.7055646181106567,
|
| 1079 |
+
"learning_rate": 2.6977926062335617e-05,
|
| 1080 |
+
"loss": 0.3801,
|
| 1081 |
+
"num_input_tokens_seen": 6396000,
|
| 1082 |
+
"step": 134
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 1.0386100386100385,
|
| 1086 |
+
"grad_norm": 0.7302276492118835,
|
| 1087 |
+
"learning_rate": 2.6648798510867386e-05,
|
| 1088 |
+
"loss": 0.3523,
|
| 1089 |
+
"num_input_tokens_seen": 6439376,
|
| 1090 |
+
"step": 135
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 1.0463320463320462,
|
| 1094 |
+
"grad_norm": 0.8147051930427551,
|
| 1095 |
+
"learning_rate": 2.6319383678261562e-05,
|
| 1096 |
+
"loss": 0.3759,
|
| 1097 |
+
"num_input_tokens_seen": 6484320,
|
| 1098 |
+
"step": 136
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 1.054054054054054,
|
| 1102 |
+
"grad_norm": 1.063301682472229,
|
| 1103 |
+
"learning_rate": 2.598973896065674e-05,
|
| 1104 |
+
"loss": 0.3866,
|
| 1105 |
+
"num_input_tokens_seen": 6531032,
|
| 1106 |
+
"step": 137
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 1.0617760617760619,
|
| 1110 |
+
"grad_norm": 0.9116234183311462,
|
| 1111 |
+
"learning_rate": 2.565992179424591e-05,
|
| 1112 |
+
"loss": 0.3943,
|
| 1113 |
+
"num_input_tokens_seen": 6581096,
|
| 1114 |
+
"step": 138
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 1.0694980694980696,
|
| 1118 |
+
"grad_norm": 0.8477054834365845,
|
| 1119 |
+
"learning_rate": 2.5329989645268977e-05,
|
| 1120 |
+
"loss": 0.3617,
|
| 1121 |
+
"num_input_tokens_seen": 6632824,
|
| 1122 |
+
"step": 139
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 1.0772200772200773,
|
| 1126 |
+
"grad_norm": 0.8234580755233765,
|
| 1127 |
+
"learning_rate": 2.5e-05,
|
| 1128 |
+
"loss": 0.3467,
|
| 1129 |
+
"num_input_tokens_seen": 6681960,
|
| 1130 |
+
"step": 140
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.084942084942085,
|
| 1134 |
+
"grad_norm": 0.8218559622764587,
|
| 1135 |
+
"learning_rate": 2.467001035473103e-05,
|
| 1136 |
+
"loss": 0.3829,
|
| 1137 |
+
"num_input_tokens_seen": 6731624,
|
| 1138 |
+
"step": 141
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 1.0926640926640927,
|
| 1142 |
+
"grad_norm": 0.8188300132751465,
|
| 1143 |
+
"learning_rate": 2.43400782057541e-05,
|
| 1144 |
+
"loss": 0.3873,
|
| 1145 |
+
"num_input_tokens_seen": 6778008,
|
| 1146 |
+
"step": 142
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 1.1003861003861004,
|
| 1150 |
+
"grad_norm": 0.734234094619751,
|
| 1151 |
+
"learning_rate": 2.401026103934327e-05,
|
| 1152 |
+
"loss": 0.3874,
|
| 1153 |
+
"num_input_tokens_seen": 6834336,
|
| 1154 |
+
"step": 143
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 1.1081081081081081,
|
| 1158 |
+
"grad_norm": 0.7244148254394531,
|
| 1159 |
+
"learning_rate": 2.368061632173844e-05,
|
| 1160 |
+
"loss": 0.3628,
|
| 1161 |
+
"num_input_tokens_seen": 6885472,
|
| 1162 |
+
"step": 144
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 1.1158301158301158,
|
| 1166 |
+
"grad_norm": 0.7350901365280151,
|
| 1167 |
+
"learning_rate": 2.3351201489132616e-05,
|
| 1168 |
+
"loss": 0.3552,
|
| 1169 |
+
"num_input_tokens_seen": 6935216,
|
| 1170 |
+
"step": 145
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 1.1235521235521235,
|
| 1174 |
+
"grad_norm": 0.7877046465873718,
|
| 1175 |
+
"learning_rate": 2.3022073937664386e-05,
|
| 1176 |
+
"loss": 0.3953,
|
| 1177 |
+
"num_input_tokens_seen": 6981112,
|
| 1178 |
+
"step": 146
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 1.1312741312741312,
|
| 1182 |
+
"grad_norm": 0.82071453332901,
|
| 1183 |
+
"learning_rate": 2.2693291013417453e-05,
|
| 1184 |
+
"loss": 0.425,
|
| 1185 |
+
"num_input_tokens_seen": 7027848,
|
| 1186 |
+
"step": 147
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.138996138996139,
|
| 1190 |
+
"grad_norm": 0.718041181564331,
|
| 1191 |
+
"learning_rate": 2.236491000242881e-05,
|
| 1192 |
+
"loss": 0.3766,
|
| 1193 |
+
"num_input_tokens_seen": 7079048,
|
| 1194 |
+
"step": 148
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 1.1467181467181466,
|
| 1198 |
+
"grad_norm": 0.7367174029350281,
|
| 1199 |
+
"learning_rate": 2.2036988120707436e-05,
|
| 1200 |
+
"loss": 0.3661,
|
| 1201 |
+
"num_input_tokens_seen": 7125096,
|
| 1202 |
+
"step": 149
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 1.1544401544401544,
|
| 1206 |
+
"grad_norm": 0.7686619758605957,
|
| 1207 |
+
"learning_rate": 2.170958250426517e-05,
|
| 1208 |
+
"loss": 0.3583,
|
| 1209 |
+
"num_input_tokens_seen": 7169448,
|
| 1210 |
+
"step": 150
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 1.1621621621621623,
|
| 1214 |
+
"grad_norm": 0.763224184513092,
|
| 1215 |
+
"learning_rate": 2.1382750199161496e-05,
|
| 1216 |
+
"loss": 0.3806,
|
| 1217 |
+
"num_input_tokens_seen": 7218200,
|
| 1218 |
+
"step": 151
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 1.16988416988417,
|
| 1222 |
+
"grad_norm": 0.7307192087173462,
|
| 1223 |
+
"learning_rate": 2.1056548151564063e-05,
|
| 1224 |
+
"loss": 0.3813,
|
| 1225 |
+
"num_input_tokens_seen": 7273032,
|
| 1226 |
+
"step": 152
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 1.1776061776061777,
|
| 1230 |
+
"grad_norm": 0.7209292650222778,
|
| 1231 |
+
"learning_rate": 2.073103319782656e-05,
|
| 1232 |
+
"loss": 0.3738,
|
| 1233 |
+
"num_input_tokens_seen": 7327712,
|
| 1234 |
+
"step": 153
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 1.1853281853281854,
|
| 1238 |
+
"grad_norm": 0.8867378830909729,
|
| 1239 |
+
"learning_rate": 2.0406262054585738e-05,
|
| 1240 |
+
"loss": 0.3732,
|
| 1241 |
+
"num_input_tokens_seen": 7370416,
|
| 1242 |
+
"step": 154
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.193050193050193,
|
| 1246 |
+
"grad_norm": 0.7197648286819458,
|
| 1247 |
+
"learning_rate": 2.00822913088793e-05,
|
| 1248 |
+
"loss": 0.3354,
|
| 1249 |
+
"num_input_tokens_seen": 7419056,
|
| 1250 |
+
"step": 155
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 1.2007722007722008,
|
| 1254 |
+
"grad_norm": 0.7414352297782898,
|
| 1255 |
+
"learning_rate": 1.975917740828634e-05,
|
| 1256 |
+
"loss": 0.3303,
|
| 1257 |
+
"num_input_tokens_seen": 7464800,
|
| 1258 |
+
"step": 156
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 1.2084942084942085,
|
| 1262 |
+
"grad_norm": 0.716848611831665,
|
| 1263 |
+
"learning_rate": 1.9436976651092144e-05,
|
| 1264 |
+
"loss": 0.336,
|
| 1265 |
+
"num_input_tokens_seen": 7512016,
|
| 1266 |
+
"step": 157
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 1.2162162162162162,
|
| 1270 |
+
"grad_norm": 0.7576581835746765,
|
| 1271 |
+
"learning_rate": 1.9115745176478946e-05,
|
| 1272 |
+
"loss": 0.3835,
|
| 1273 |
+
"num_input_tokens_seen": 7558192,
|
| 1274 |
+
"step": 158
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 1.223938223938224,
|
| 1278 |
+
"grad_norm": 0.7724153399467468,
|
| 1279 |
+
"learning_rate": 1.879553895474441e-05,
|
| 1280 |
+
"loss": 0.3977,
|
| 1281 |
+
"num_input_tokens_seen": 7606360,
|
| 1282 |
+
"step": 159
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"epoch": 1.2316602316602316,
|
| 1286 |
+
"grad_norm": 0.7829853892326355,
|
| 1287 |
+
"learning_rate": 1.8476413777549585e-05,
|
| 1288 |
+
"loss": 0.3973,
|
| 1289 |
+
"num_input_tokens_seen": 7658256,
|
| 1290 |
+
"step": 160
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 1.2393822393822393,
|
| 1294 |
+
"grad_norm": 0.73533695936203,
|
| 1295 |
+
"learning_rate": 1.815842524819793e-05,
|
| 1296 |
+
"loss": 0.3545,
|
| 1297 |
+
"num_input_tokens_seen": 7705928,
|
| 1298 |
+
"step": 161
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 1.247104247104247,
|
| 1302 |
+
"grad_norm": 0.731606662273407,
|
| 1303 |
+
"learning_rate": 1.784162877194719e-05,
|
| 1304 |
+
"loss": 0.3374,
|
| 1305 |
+
"num_input_tokens_seen": 7754904,
|
| 1306 |
+
"step": 162
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 1.2548262548262548,
|
| 1310 |
+
"grad_norm": 0.7551190257072449,
|
| 1311 |
+
"learning_rate": 1.7526079546355744e-05,
|
| 1312 |
+
"loss": 0.3622,
|
| 1313 |
+
"num_input_tokens_seen": 7801208,
|
| 1314 |
+
"step": 163
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 1.2625482625482625,
|
| 1318 |
+
"grad_norm": 0.8263510465621948,
|
| 1319 |
+
"learning_rate": 1.7211832551665214e-05,
|
| 1320 |
+
"loss": 0.3612,
|
| 1321 |
+
"num_input_tokens_seen": 7846632,
|
| 1322 |
+
"step": 164
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 1.2702702702702702,
|
| 1326 |
+
"grad_norm": 0.7753041982650757,
|
| 1327 |
+
"learning_rate": 1.6898942541220856e-05,
|
| 1328 |
+
"loss": 0.3578,
|
| 1329 |
+
"num_input_tokens_seen": 7893448,
|
| 1330 |
+
"step": 165
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 1.2779922779922779,
|
| 1334 |
+
"grad_norm": 0.7862949967384338,
|
| 1335 |
+
"learning_rate": 1.6587464031931528e-05,
|
| 1336 |
+
"loss": 0.3916,
|
| 1337 |
+
"num_input_tokens_seen": 7941168,
|
| 1338 |
+
"step": 166
|
| 1339 |
+
},
|
| 1340 |
+
{
|
| 1341 |
+
"epoch": 1.2857142857142856,
|
| 1342 |
+
"grad_norm": 0.7567591667175293,
|
| 1343 |
+
"learning_rate": 1.6277451294770834e-05,
|
| 1344 |
+
"loss": 0.3759,
|
| 1345 |
+
"num_input_tokens_seen": 7994968,
|
| 1346 |
+
"step": 167
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 1.2934362934362935,
|
| 1350 |
+
"grad_norm": 0.7898448705673218,
|
| 1351 |
+
"learning_rate": 1.5968958345321178e-05,
|
| 1352 |
+
"loss": 0.3732,
|
| 1353 |
+
"num_input_tokens_seen": 8040744,
|
| 1354 |
+
"step": 168
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 1.3011583011583012,
|
| 1358 |
+
"grad_norm": 0.7488287687301636,
|
| 1359 |
+
"learning_rate": 1.566203893436221e-05,
|
| 1360 |
+
"loss": 0.3854,
|
| 1361 |
+
"num_input_tokens_seen": 8090992,
|
| 1362 |
+
"step": 169
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 1.308880308880309,
|
| 1366 |
+
"grad_norm": 0.7275019884109497,
|
| 1367 |
+
"learning_rate": 1.5356746538505513e-05,
|
| 1368 |
+
"loss": 0.3519,
|
| 1369 |
+
"num_input_tokens_seen": 8138688,
|
| 1370 |
+
"step": 170
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 1.3166023166023166,
|
| 1374 |
+
"grad_norm": 0.8107270002365112,
|
| 1375 |
+
"learning_rate": 1.5053134350876983e-05,
|
| 1376 |
+
"loss": 0.4125,
|
| 1377 |
+
"num_input_tokens_seen": 8188200,
|
| 1378 |
+
"step": 171
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 1.3243243243243243,
|
| 1382 |
+
"grad_norm": 0.748126208782196,
|
| 1383 |
+
"learning_rate": 1.4751255271848662e-05,
|
| 1384 |
+
"loss": 0.3839,
|
| 1385 |
+
"num_input_tokens_seen": 8238184,
|
| 1386 |
+
"step": 172
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 1.332046332046332,
|
| 1390 |
+
"grad_norm": 0.7602939605712891,
|
| 1391 |
+
"learning_rate": 1.4451161899821558e-05,
|
| 1392 |
+
"loss": 0.3998,
|
| 1393 |
+
"num_input_tokens_seen": 8287400,
|
| 1394 |
+
"step": 173
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 1.3397683397683398,
|
| 1398 |
+
"grad_norm": 0.7316227555274963,
|
| 1399 |
+
"learning_rate": 1.4152906522061048e-05,
|
| 1400 |
+
"loss": 0.363,
|
| 1401 |
+
"num_input_tokens_seen": 8332240,
|
| 1402 |
+
"step": 174
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 1.3474903474903475,
|
| 1406 |
+
"grad_norm": 0.6714322566986084,
|
| 1407 |
+
"learning_rate": 1.3856541105586545e-05,
|
| 1408 |
+
"loss": 0.3426,
|
| 1409 |
+
"num_input_tokens_seen": 8383952,
|
| 1410 |
+
"step": 175
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 1.3552123552123552,
|
| 1414 |
+
"grad_norm": 0.8157584071159363,
|
| 1415 |
+
"learning_rate": 1.3562117288116924e-05,
|
| 1416 |
+
"loss": 0.4047,
|
| 1417 |
+
"num_input_tokens_seen": 8430544,
|
| 1418 |
+
"step": 176
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 1.3629343629343629,
|
| 1422 |
+
"grad_norm": 0.7479146122932434,
|
| 1423 |
+
"learning_rate": 1.3269686369073347e-05,
|
| 1424 |
+
"loss": 0.3402,
|
| 1425 |
+
"num_input_tokens_seen": 8471896,
|
| 1426 |
+
"step": 177
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 1.3706563706563706,
|
| 1430 |
+
"grad_norm": 0.7816237807273865,
|
| 1431 |
+
"learning_rate": 1.2979299300641018e-05,
|
| 1432 |
+
"loss": 0.4113,
|
| 1433 |
+
"num_input_tokens_seen": 8517400,
|
| 1434 |
+
"step": 178
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 1.3783783783783785,
|
| 1438 |
+
"grad_norm": 0.7359681725502014,
|
| 1439 |
+
"learning_rate": 1.2691006678891446e-05,
|
| 1440 |
+
"loss": 0.3818,
|
| 1441 |
+
"num_input_tokens_seen": 8563608,
|
| 1442 |
+
"step": 179
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 1.3861003861003862,
|
| 1446 |
+
"grad_norm": 0.7472447156906128,
|
| 1447 |
+
"learning_rate": 1.240485873496677e-05,
|
| 1448 |
+
"loss": 0.3753,
|
| 1449 |
+
"num_input_tokens_seen": 8609832,
|
| 1450 |
+
"step": 180
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"epoch": 1.393822393822394,
|
| 1454 |
+
"grad_norm": 0.7036008834838867,
|
| 1455 |
+
"learning_rate": 1.2120905326327598e-05,
|
| 1456 |
+
"loss": 0.3512,
|
| 1457 |
+
"num_input_tokens_seen": 8656152,
|
| 1458 |
+
"step": 181
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 1.4015444015444016,
|
| 1462 |
+
"grad_norm": 0.7634910345077515,
|
| 1463 |
+
"learning_rate": 1.1839195928066102e-05,
|
| 1464 |
+
"loss": 0.4048,
|
| 1465 |
+
"num_input_tokens_seen": 8704416,
|
| 1466 |
+
"step": 182
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 1.4092664092664093,
|
| 1470 |
+
"grad_norm": 0.7366232872009277,
|
| 1471 |
+
"learning_rate": 1.1559779624285564e-05,
|
| 1472 |
+
"loss": 0.3488,
|
| 1473 |
+
"num_input_tokens_seen": 8748368,
|
| 1474 |
+
"step": 183
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 1.416988416988417,
|
| 1478 |
+
"grad_norm": 0.6778586506843567,
|
| 1479 |
+
"learning_rate": 1.128270509954816e-05,
|
| 1480 |
+
"loss": 0.3416,
|
| 1481 |
+
"num_input_tokens_seen": 8798392,
|
| 1482 |
+
"step": 184
|
| 1483 |
+
},
|
| 1484 |
+
{
|
| 1485 |
+
"epoch": 1.4247104247104247,
|
| 1486 |
+
"grad_norm": 0.727095365524292,
|
| 1487 |
+
"learning_rate": 1.1008020630392302e-05,
|
| 1488 |
+
"loss": 0.3747,
|
| 1489 |
+
"num_input_tokens_seen": 8848240,
|
| 1490 |
+
"step": 185
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 1.4324324324324325,
|
| 1494 |
+
"grad_norm": 0.7619035243988037,
|
| 1495 |
+
"learning_rate": 1.0735774076921129e-05,
|
| 1496 |
+
"loss": 0.3734,
|
| 1497 |
+
"num_input_tokens_seen": 8896008,
|
| 1498 |
+
"step": 186
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 1.4401544401544402,
|
| 1502 |
+
"grad_norm": 0.7539617419242859,
|
| 1503 |
+
"learning_rate": 1.0466012874463507e-05,
|
| 1504 |
+
"loss": 0.3563,
|
| 1505 |
+
"num_input_tokens_seen": 8943224,
|
| 1506 |
+
"step": 187
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 1.4478764478764479,
|
| 1510 |
+
"grad_norm": 0.7609190940856934,
|
| 1511 |
+
"learning_rate": 1.0198784025309047e-05,
|
| 1512 |
+
"loss": 0.3821,
|
| 1513 |
+
"num_input_tokens_seen": 8989312,
|
| 1514 |
+
"step": 188
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 1.4555984555984556,
|
| 1518 |
+
"grad_norm": 0.7501497864723206,
|
| 1519 |
+
"learning_rate": 9.934134090518593e-06,
|
| 1520 |
+
"loss": 0.378,
|
| 1521 |
+
"num_input_tokens_seen": 9042424,
|
| 1522 |
+
"step": 189
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 1.4633204633204633,
|
| 1526 |
+
"grad_norm": 0.804295539855957,
|
| 1527 |
+
"learning_rate": 9.672109181811575e-06,
|
| 1528 |
+
"loss": 0.3665,
|
| 1529 |
+
"num_input_tokens_seen": 9086072,
|
| 1530 |
+
"step": 190
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 1.471042471042471,
|
| 1534 |
+
"grad_norm": 0.7334874868392944,
|
| 1535 |
+
"learning_rate": 9.412754953531663e-06,
|
| 1536 |
+
"loss": 0.3523,
|
| 1537 |
+
"num_input_tokens_seen": 9133240,
|
| 1538 |
+
"step": 191
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 1.4787644787644787,
|
| 1542 |
+
"grad_norm": 0.7709252238273621,
|
| 1543 |
+
"learning_rate": 9.156116594692096e-06,
|
| 1544 |
+
"loss": 0.3338,
|
| 1545 |
+
"num_input_tokens_seen": 9178152,
|
| 1546 |
+
"step": 192
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 1.4864864864864864,
|
| 1550 |
+
"grad_norm": 0.7570241093635559,
|
| 1551 |
+
"learning_rate": 8.902238821102111e-06,
|
| 1552 |
+
"loss": 0.3877,
|
| 1553 |
+
"num_input_tokens_seen": 9226432,
|
| 1554 |
+
"step": 193
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 1.494208494208494,
|
| 1558 |
+
"grad_norm": 0.7098576426506042,
|
| 1559 |
+
"learning_rate": 8.651165867575797e-06,
|
| 1560 |
+
"loss": 0.3696,
|
| 1561 |
+
"num_input_tokens_seen": 9278656,
|
| 1562 |
+
"step": 194
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 1.5019305019305018,
|
| 1566 |
+
"grad_norm": 0.7327427864074707,
|
| 1567 |
+
"learning_rate": 8.402941480224797e-06,
|
| 1568 |
+
"loss": 0.3387,
|
| 1569 |
+
"num_input_tokens_seen": 9323040,
|
| 1570 |
+
"step": 195
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 1.5096525096525095,
|
| 1574 |
+
"grad_norm": 0.7151550054550171,
|
| 1575 |
+
"learning_rate": 8.15760890883607e-06,
|
| 1576 |
+
"loss": 0.3617,
|
| 1577 |
+
"num_input_tokens_seen": 9373024,
|
| 1578 |
+
"step": 196
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 1.5173745173745172,
|
| 1582 |
+
"grad_norm": 0.7485451102256775,
|
| 1583 |
+
"learning_rate": 7.915210899336284e-06,
|
| 1584 |
+
"loss": 0.3717,
|
| 1585 |
+
"num_input_tokens_seen": 9421792,
|
| 1586 |
+
"step": 197
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 1.525096525096525,
|
| 1590 |
+
"grad_norm": 0.7549355030059814,
|
| 1591 |
+
"learning_rate": 7.67578968634383e-06,
|
| 1592 |
+
"loss": 0.3815,
|
| 1593 |
+
"num_input_tokens_seen": 9470992,
|
| 1594 |
+
"step": 198
|
| 1595 |
+
},
|
| 1596 |
+
{
|
| 1597 |
+
"epoch": 1.5328185328185329,
|
| 1598 |
+
"grad_norm": 0.759557843208313,
|
| 1599 |
+
"learning_rate": 7.439386985810037e-06,
|
| 1600 |
+
"loss": 0.373,
|
| 1601 |
+
"num_input_tokens_seen": 9518240,
|
| 1602 |
+
"step": 199
|
| 1603 |
+
},
|
| 1604 |
+
{
|
| 1605 |
+
"epoch": 1.5405405405405406,
|
| 1606 |
+
"grad_norm": 0.6981601119041443,
|
| 1607 |
+
"learning_rate": 7.206043987750729e-06,
|
| 1608 |
+
"loss": 0.3398,
|
| 1609 |
+
"num_input_tokens_seen": 9565296,
|
| 1610 |
+
"step": 200
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 1.5482625482625483,
|
| 1614 |
+
"grad_norm": 0.7525540590286255,
|
| 1615 |
+
"learning_rate": 6.9758013490693855e-06,
|
| 1616 |
+
"loss": 0.3703,
|
| 1617 |
+
"num_input_tokens_seen": 9614328,
|
| 1618 |
+
"step": 201
|
| 1619 |
+
},
|
| 1620 |
+
{
|
| 1621 |
+
"epoch": 1.555984555984556,
|
| 1622 |
+
"grad_norm": 0.732926607131958,
|
| 1623 |
+
"learning_rate": 6.7486991864732505e-06,
|
| 1624 |
+
"loss": 0.3406,
|
| 1625 |
+
"num_input_tokens_seen": 9660560,
|
| 1626 |
+
"step": 202
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 1.5637065637065637,
|
| 1630 |
+
"grad_norm": 0.7453652024269104,
|
| 1631 |
+
"learning_rate": 6.524777069483526e-06,
|
| 1632 |
+
"loss": 0.385,
|
| 1633 |
+
"num_input_tokens_seen": 9711688,
|
| 1634 |
+
"step": 203
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 1.5714285714285714,
|
| 1638 |
+
"grad_norm": 0.7156092524528503,
|
| 1639 |
+
"learning_rate": 6.3040740135408864e-06,
|
| 1640 |
+
"loss": 0.3335,
|
| 1641 |
+
"num_input_tokens_seen": 9758240,
|
| 1642 |
+
"step": 204
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"epoch": 1.579150579150579,
|
| 1646 |
+
"grad_norm": 0.723884642124176,
|
| 1647 |
+
"learning_rate": 6.086628473207606e-06,
|
| 1648 |
+
"loss": 0.3542,
|
| 1649 |
+
"num_input_tokens_seen": 9806832,
|
| 1650 |
+
"step": 205
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 1.586872586872587,
|
| 1654 |
+
"grad_norm": 0.750363290309906,
|
| 1655 |
+
"learning_rate": 5.872478335467299e-06,
|
| 1656 |
+
"loss": 0.349,
|
| 1657 |
+
"num_input_tokens_seen": 9852096,
|
| 1658 |
+
"step": 206
|
| 1659 |
+
},
|
| 1660 |
+
{
|
| 1661 |
+
"epoch": 1.5945945945945947,
|
| 1662 |
+
"grad_norm": 0.7412139773368835,
|
| 1663 |
+
"learning_rate": 5.661660913123673e-06,
|
| 1664 |
+
"loss": 0.351,
|
| 1665 |
+
"num_input_tokens_seen": 9899240,
|
| 1666 |
+
"step": 207
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 1.6023166023166024,
|
| 1670 |
+
"grad_norm": 0.6961778402328491,
|
| 1671 |
+
"learning_rate": 5.454212938299255e-06,
|
| 1672 |
+
"loss": 0.3343,
|
| 1673 |
+
"num_input_tokens_seen": 9947712,
|
| 1674 |
+
"step": 208
|
| 1675 |
+
},
|
| 1676 |
+
{
|
| 1677 |
+
"epoch": 1.6100386100386102,
|
| 1678 |
+
"grad_norm": 0.7364585995674133,
|
| 1679 |
+
"learning_rate": 5.250170556035302e-06,
|
| 1680 |
+
"loss": 0.3283,
|
| 1681 |
+
"num_input_tokens_seen": 9991232,
|
| 1682 |
+
"step": 209
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 1.6177606177606179,
|
| 1686 |
+
"grad_norm": 0.7384213805198669,
|
| 1687 |
+
"learning_rate": 5.049569317994013e-06,
|
| 1688 |
+
"loss": 0.3525,
|
| 1689 |
+
"num_input_tokens_seen": 10038696,
|
| 1690 |
+
"step": 210
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 1.6254826254826256,
|
| 1694 |
+
"grad_norm": 0.8023526668548584,
|
| 1695 |
+
"learning_rate": 4.852444176264129e-06,
|
| 1696 |
+
"loss": 0.4056,
|
| 1697 |
+
"num_input_tokens_seen": 10090976,
|
| 1698 |
+
"step": 211
|
| 1699 |
+
},
|
| 1700 |
+
{
|
| 1701 |
+
"epoch": 1.6332046332046333,
|
| 1702 |
+
"grad_norm": 0.7126312851905823,
|
| 1703 |
+
"learning_rate": 4.658829477270996e-06,
|
| 1704 |
+
"loss": 0.3567,
|
| 1705 |
+
"num_input_tokens_seen": 10140048,
|
| 1706 |
+
"step": 212
|
| 1707 |
+
},
|
| 1708 |
+
{
|
| 1709 |
+
"epoch": 1.640926640926641,
|
| 1710 |
+
"grad_norm": 0.7448667883872986,
|
| 1711 |
+
"learning_rate": 4.46875895579216e-06,
|
| 1712 |
+
"loss": 0.3507,
|
| 1713 |
+
"num_input_tokens_seen": 10187872,
|
| 1714 |
+
"step": 213
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 1.6486486486486487,
|
| 1718 |
+
"grad_norm": 0.7644662261009216,
|
| 1719 |
+
"learning_rate": 4.282265729079535e-06,
|
| 1720 |
+
"loss": 0.3818,
|
| 1721 |
+
"num_input_tokens_seen": 10234368,
|
| 1722 |
+
"step": 214
|
| 1723 |
+
},
|
| 1724 |
+
{
|
| 1725 |
+
"epoch": 1.6563706563706564,
|
| 1726 |
+
"grad_norm": 0.8175966739654541,
|
| 1727 |
+
"learning_rate": 4.099382291089151e-06,
|
| 1728 |
+
"loss": 0.407,
|
| 1729 |
+
"num_input_tokens_seen": 10284208,
|
| 1730 |
+
"step": 215
|
| 1731 |
+
},
|
| 1732 |
+
{
|
| 1733 |
+
"epoch": 1.664092664092664,
|
| 1734 |
+
"grad_norm": 0.8007215261459351,
|
| 1735 |
+
"learning_rate": 3.920140506819539e-06,
|
| 1736 |
+
"loss": 0.4055,
|
| 1737 |
+
"num_input_tokens_seen": 10331624,
|
| 1738 |
+
"step": 216
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 1.6718146718146718,
|
| 1742 |
+
"grad_norm": 0.7793760895729065,
|
| 1743 |
+
"learning_rate": 3.7445716067596503e-06,
|
| 1744 |
+
"loss": 0.37,
|
| 1745 |
+
"num_input_tokens_seen": 10377720,
|
| 1746 |
+
"step": 217
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 1.6795366795366795,
|
| 1750 |
+
"grad_norm": 0.6971163749694824,
|
| 1751 |
+
"learning_rate": 3.5727061814473854e-06,
|
| 1752 |
+
"loss": 0.3521,
|
| 1753 |
+
"num_input_tokens_seen": 10430784,
|
| 1754 |
+
"step": 218
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 1.6872586872586872,
|
| 1758 |
+
"grad_norm": 0.7408994436264038,
|
| 1759 |
+
"learning_rate": 3.404574176139591e-06,
|
| 1760 |
+
"loss": 0.3667,
|
| 1761 |
+
"num_input_tokens_seen": 10477896,
|
| 1762 |
+
"step": 219
|
| 1763 |
+
},
|
| 1764 |
+
{
|
| 1765 |
+
"epoch": 1.694980694980695,
|
| 1766 |
+
"grad_norm": 0.7539640665054321,
|
| 1767 |
+
"learning_rate": 3.240204885594514e-06,
|
| 1768 |
+
"loss": 0.3438,
|
| 1769 |
+
"num_input_tokens_seen": 10524432,
|
| 1770 |
+
"step": 220
|
| 1771 |
+
},
|
| 1772 |
+
{
|
| 1773 |
+
"epoch": 1.7027027027027026,
|
| 1774 |
+
"grad_norm": 0.6838665008544922,
|
| 1775 |
+
"learning_rate": 3.0796269489675344e-06,
|
| 1776 |
+
"loss": 0.3155,
|
| 1777 |
+
"num_input_tokens_seen": 10571912,
|
| 1778 |
+
"step": 221
|
| 1779 |
+
},
|
| 1780 |
+
{
|
| 1781 |
+
"epoch": 1.7104247104247103,
|
| 1782 |
+
"grad_norm": 0.7157579660415649,
|
| 1783 |
+
"learning_rate": 2.922868344821236e-06,
|
| 1784 |
+
"loss": 0.3812,
|
| 1785 |
+
"num_input_tokens_seen": 10622048,
|
| 1786 |
+
"step": 222
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 1.718146718146718,
|
| 1790 |
+
"grad_norm": 0.7010034918785095,
|
| 1791 |
+
"learning_rate": 2.769956386250472e-06,
|
| 1792 |
+
"loss": 0.351,
|
| 1793 |
+
"num_input_tokens_seen": 10673328,
|
| 1794 |
+
"step": 223
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 1.7258687258687258,
|
| 1798 |
+
"grad_norm": 0.7771580219268799,
|
| 1799 |
+
"learning_rate": 2.6209177161234445e-06,
|
| 1800 |
+
"loss": 0.3879,
|
| 1801 |
+
"num_input_tokens_seen": 10721704,
|
| 1802 |
+
"step": 224
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 1.7335907335907335,
|
| 1806 |
+
"grad_norm": 0.7555801868438721,
|
| 1807 |
+
"learning_rate": 2.475778302439524e-06,
|
| 1808 |
+
"loss": 0.3903,
|
| 1809 |
+
"num_input_tokens_seen": 10769240,
|
| 1810 |
+
"step": 225
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 1.7413127413127412,
|
| 1814 |
+
"grad_norm": 0.7153806686401367,
|
| 1815 |
+
"learning_rate": 2.3345634338046875e-06,
|
| 1816 |
+
"loss": 0.3437,
|
| 1817 |
+
"num_input_tokens_seen": 10814464,
|
| 1818 |
+
"step": 226
|
| 1819 |
+
},
|
| 1820 |
+
{
|
| 1821 |
+
"epoch": 1.7490347490347489,
|
| 1822 |
+
"grad_norm": 0.7552188038825989,
|
| 1823 |
+
"learning_rate": 2.1972977150253064e-06,
|
| 1824 |
+
"loss": 0.3612,
|
| 1825 |
+
"num_input_tokens_seen": 10859000,
|
| 1826 |
+
"step": 227
|
| 1827 |
+
},
|
| 1828 |
+
{
|
| 1829 |
+
"epoch": 1.7567567567567568,
|
| 1830 |
+
"grad_norm": 0.6911195516586304,
|
| 1831 |
+
"learning_rate": 2.064005062821095e-06,
|
| 1832 |
+
"loss": 0.32,
|
| 1833 |
+
"num_input_tokens_seen": 10906008,
|
| 1834 |
+
"step": 228
|
| 1835 |
+
},
|
| 1836 |
+
{
|
| 1837 |
+
"epoch": 1.7644787644787645,
|
| 1838 |
+
"grad_norm": 0.7437323927879333,
|
| 1839 |
+
"learning_rate": 1.9347087016579278e-06,
|
| 1840 |
+
"loss": 0.3504,
|
| 1841 |
+
"num_input_tokens_seen": 10952840,
|
| 1842 |
+
"step": 229
|
| 1843 |
+
},
|
| 1844 |
+
{
|
| 1845 |
+
"epoch": 1.7722007722007722,
|
| 1846 |
+
"grad_norm": 0.8080976605415344,
|
| 1847 |
+
"learning_rate": 1.8094311597013052e-06,
|
| 1848 |
+
"loss": 0.3971,
|
| 1849 |
+
"num_input_tokens_seen": 11001384,
|
| 1850 |
+
"step": 230
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 1.77992277992278,
|
| 1854 |
+
"grad_norm": 0.7577563524246216,
|
| 1855 |
+
"learning_rate": 1.6881942648911076e-06,
|
| 1856 |
+
"loss": 0.3904,
|
| 1857 |
+
"num_input_tokens_seen": 11049440,
|
| 1858 |
+
"step": 231
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 1.7876447876447876,
|
| 1862 |
+
"grad_norm": 0.732723593711853,
|
| 1863 |
+
"learning_rate": 1.5710191411383662e-06,
|
| 1864 |
+
"loss": 0.3325,
|
| 1865 |
+
"num_input_tokens_seen": 11093928,
|
| 1866 |
+
"step": 232
|
| 1867 |
+
},
|
| 1868 |
+
{
|
| 1869 |
+
"epoch": 1.7953667953667953,
|
| 1870 |
+
"grad_norm": 0.7599166035652161,
|
| 1871 |
+
"learning_rate": 1.4579262046447107e-06,
|
| 1872 |
+
"loss": 0.393,
|
| 1873 |
+
"num_input_tokens_seen": 11140832,
|
| 1874 |
+
"step": 233
|
| 1875 |
+
},
|
| 1876 |
+
{
|
| 1877 |
+
"epoch": 1.803088803088803,
|
| 1878 |
+
"grad_norm": 0.8044569492340088,
|
| 1879 |
+
"learning_rate": 1.3489351603451329e-06,
|
| 1880 |
+
"loss": 0.4306,
|
| 1881 |
+
"num_input_tokens_seen": 11191600,
|
| 1882 |
+
"step": 234
|
| 1883 |
+
},
|
| 1884 |
+
{
|
| 1885 |
+
"epoch": 1.810810810810811,
|
| 1886 |
+
"grad_norm": 0.795045793056488,
|
| 1887 |
+
"learning_rate": 1.2440649984746256e-06,
|
| 1888 |
+
"loss": 0.3767,
|
| 1889 |
+
"num_input_tokens_seen": 11235984,
|
| 1890 |
+
"step": 235
|
| 1891 |
+
},
|
| 1892 |
+
{
|
| 1893 |
+
"epoch": 1.8185328185328187,
|
| 1894 |
+
"grad_norm": 0.7915075421333313,
|
| 1895 |
+
"learning_rate": 1.1433339912594266e-06,
|
| 1896 |
+
"loss": 0.3552,
|
| 1897 |
+
"num_input_tokens_seen": 11276416,
|
| 1898 |
+
"step": 236
|
| 1899 |
+
},
|
| 1900 |
+
{
|
| 1901 |
+
"epoch": 1.8262548262548264,
|
| 1902 |
+
"grad_norm": 0.7200133204460144,
|
| 1903 |
+
"learning_rate": 1.046759689733301e-06,
|
| 1904 |
+
"loss": 0.3686,
|
| 1905 |
+
"num_input_tokens_seen": 11328536,
|
| 1906 |
+
"step": 237
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 1.833976833976834,
|
| 1910 |
+
"grad_norm": 0.7975424528121948,
|
| 1911 |
+
"learning_rate": 9.54358920679524e-07,
|
| 1912 |
+
"loss": 0.3981,
|
| 1913 |
+
"num_input_tokens_seen": 11374664,
|
| 1914 |
+
"step": 238
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 1.8416988416988418,
|
| 1918 |
+
"grad_norm": 0.7360520958900452,
|
| 1919 |
+
"learning_rate": 8.661477836990339e-07,
|
| 1920 |
+
"loss": 0.3678,
|
| 1921 |
+
"num_input_tokens_seen": 11424256,
|
| 1922 |
+
"step": 239
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 1.8494208494208495,
|
| 1926 |
+
"grad_norm": 0.713374674320221,
|
| 1927 |
+
"learning_rate": 7.821416484052879e-07,
|
| 1928 |
+
"loss": 0.3443,
|
| 1929 |
+
"num_input_tokens_seen": 11469272,
|
| 1930 |
+
"step": 240
|
| 1931 |
+
},
|
| 1932 |
+
{
|
| 1933 |
+
"epoch": 1.8571428571428572,
|
| 1934 |
+
"grad_norm": 0.7081705331802368,
|
| 1935 |
+
"learning_rate": 7.02355151746309e-07,
|
| 1936 |
+
"loss": 0.3333,
|
| 1937 |
+
"num_input_tokens_seen": 11514592,
|
| 1938 |
+
"step": 241
|
| 1939 |
+
},
|
| 1940 |
+
{
|
| 1941 |
+
"epoch": 1.864864864864865,
|
| 1942 |
+
"grad_norm": 0.7440131902694702,
|
| 1943 |
+
"learning_rate": 6.268021954544096e-07,
|
| 1944 |
+
"loss": 0.3661,
|
| 1945 |
+
"num_input_tokens_seen": 11559064,
|
| 1946 |
+
"step": 242
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 1.8725868725868726,
|
| 1950 |
+
"grad_norm": 0.6954824328422546,
|
| 1951 |
+
"learning_rate": 5.554959436239821e-07,
|
| 1952 |
+
"loss": 0.3499,
|
| 1953 |
+
"num_input_tokens_seen": 11609720,
|
| 1954 |
+
"step": 243
|
| 1955 |
+
},
|
| 1956 |
+
{
|
| 1957 |
+
"epoch": 1.8803088803088803,
|
| 1958 |
+
"grad_norm": 0.7557532787322998,
|
| 1959 |
+
"learning_rate": 4.884488204178333e-07,
|
| 1960 |
+
"loss": 0.3657,
|
| 1961 |
+
"num_input_tokens_seen": 11657256,
|
| 1962 |
+
"step": 244
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 1.888030888030888,
|
| 1966 |
+
"grad_norm": 0.7957518100738525,
|
| 1967 |
+
"learning_rate": 4.256725079024554e-07,
|
| 1968 |
+
"loss": 0.3827,
|
| 1969 |
+
"num_input_tokens_seen": 11704528,
|
| 1970 |
+
"step": 245
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 1.8957528957528957,
|
| 1974 |
+
"grad_norm": 0.7069993019104004,
|
| 1975 |
+
"learning_rate": 3.6717794401256445e-07,
|
| 1976 |
+
"loss": 0.34,
|
| 1977 |
+
"num_input_tokens_seen": 11752560,
|
| 1978 |
+
"step": 246
|
| 1979 |
+
},
|
| 1980 |
+
{
|
| 1981 |
+
"epoch": 1.9034749034749034,
|
| 1982 |
+
"grad_norm": 0.7414040565490723,
|
| 1983 |
+
"learning_rate": 3.129753206453201e-07,
|
| 1984 |
+
"loss": 0.3512,
|
| 1985 |
+
"num_input_tokens_seen": 11798928,
|
| 1986 |
+
"step": 247
|
| 1987 |
+
},
|
| 1988 |
+
{
|
| 1989 |
+
"epoch": 1.9111969111969112,
|
| 1990 |
+
"grad_norm": 0.6941518187522888,
|
| 1991 |
+
"learning_rate": 2.630740818845123e-07,
|
| 1992 |
+
"loss": 0.3566,
|
| 1993 |
+
"num_input_tokens_seen": 11848456,
|
| 1994 |
+
"step": 248
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 1.9189189189189189,
|
| 1998 |
+
"grad_norm": 0.6867352724075317,
|
| 1999 |
+
"learning_rate": 2.174829223550806e-07,
|
| 2000 |
+
"loss": 0.3551,
|
| 2001 |
+
"num_input_tokens_seen": 11899192,
|
| 2002 |
+
"step": 249
|
| 2003 |
+
},
|
| 2004 |
+
{
|
| 2005 |
+
"epoch": 1.9266409266409266,
|
| 2006 |
+
"grad_norm": 0.6801990270614624,
|
| 2007 |
+
"learning_rate": 1.762097857081646e-07,
|
| 2008 |
+
"loss": 0.3205,
|
| 2009 |
+
"num_input_tokens_seen": 11947904,
|
| 2010 |
+
"step": 250
|
| 2011 |
+
},
|
| 2012 |
+
{
|
| 2013 |
+
"epoch": 1.9343629343629343,
|
| 2014 |
+
"grad_norm": 0.682864248752594,
|
| 2015 |
+
"learning_rate": 1.3926186323703905e-07,
|
| 2016 |
+
"loss": 0.3455,
|
| 2017 |
+
"num_input_tokens_seen": 11997104,
|
| 2018 |
+
"step": 251
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 1.942084942084942,
|
| 2022 |
+
"grad_norm": 0.7804450988769531,
|
| 2023 |
+
"learning_rate": 1.0664559262413831e-07,
|
| 2024 |
+
"loss": 0.4022,
|
| 2025 |
+
"num_input_tokens_seen": 12045824,
|
| 2026 |
+
"step": 252
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 1.9498069498069497,
|
| 2030 |
+
"grad_norm": 0.7370994687080383,
|
| 2031 |
+
"learning_rate": 7.836665681935085e-08,
|
| 2032 |
+
"loss": 0.3797,
|
| 2033 |
+
"num_input_tokens_seen": 12096360,
|
| 2034 |
+
"step": 253
|
| 2035 |
+
},
|
| 2036 |
+
{
|
| 2037 |
+
"epoch": 1.9575289575289574,
|
| 2038 |
+
"grad_norm": 0.7060906291007996,
|
| 2039 |
+
"learning_rate": 5.44299830498668e-08,
|
| 2040 |
+
"loss": 0.3234,
|
| 2041 |
+
"num_input_tokens_seen": 12141952,
|
| 2042 |
+
"step": 254
|
| 2043 |
+
},
|
| 2044 |
+
{
|
| 2045 |
+
"epoch": 1.965250965250965,
|
| 2046 |
+
"grad_norm": 0.7281149625778198,
|
| 2047 |
+
"learning_rate": 3.4839741961659176e-08,
|
| 2048 |
+
"loss": 0.3741,
|
| 2049 |
+
"num_input_tokens_seen": 12193160,
|
| 2050 |
+
"step": 255
|
| 2051 |
+
},
|
| 2052 |
+
{
|
| 2053 |
+
"epoch": 1.972972972972973,
|
| 2054 |
+
"grad_norm": 0.7566375136375427,
|
| 2055 |
+
"learning_rate": 1.9599346892809622e-08,
|
| 2056 |
+
"loss": 0.3475,
|
| 2057 |
+
"num_input_tokens_seen": 12237616,
|
| 2058 |
+
"step": 256
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 1.9806949806949807,
|
| 2062 |
+
"grad_norm": 0.7222142815589905,
|
| 2063 |
+
"learning_rate": 8.711453278778536e-09,
|
| 2064 |
+
"loss": 0.3699,
|
| 2065 |
+
"num_input_tokens_seen": 12283352,
|
| 2066 |
+
"step": 257
|
| 2067 |
+
},
|
| 2068 |
+
{
|
| 2069 |
+
"epoch": 1.9884169884169884,
|
| 2070 |
+
"grad_norm": 0.7003583908081055,
|
| 2071 |
+
"learning_rate": 2.177958189733542e-09,
|
| 2072 |
+
"loss": 0.3471,
|
| 2073 |
+
"num_input_tokens_seen": 12333744,
|
| 2074 |
+
"step": 258
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 1.9884169884169884,
|
| 2078 |
+
"num_input_tokens_seen": 12333744,
|
| 2079 |
+
"step": 258,
|
| 2080 |
+
"total_flos": 2.0534009572779622e+17,
|
| 2081 |
+
"train_loss": 0.535006606301596,
|
| 2082 |
+
"train_runtime": 453.6685,
|
| 2083 |
+
"train_samples_per_second": 9.13,
|
| 2084 |
+
"train_steps_per_second": 0.569
|
| 2085 |
+
}
|
| 2086 |
+
],
|
| 2087 |
+
"logging_steps": 1.0,
|
| 2088 |
+
"max_steps": 258,
|
| 2089 |
+
"num_input_tokens_seen": 12333744,
|
| 2090 |
+
"num_train_epochs": 2,
|
| 2091 |
+
"save_steps": 500,
|
| 2092 |
+
"stateful_callbacks": {
|
| 2093 |
+
"TrainerControl": {
|
| 2094 |
+
"args": {
|
| 2095 |
+
"should_epoch_stop": false,
|
| 2096 |
+
"should_evaluate": false,
|
| 2097 |
+
"should_log": false,
|
| 2098 |
+
"should_save": true,
|
| 2099 |
+
"should_training_stop": true
|
| 2100 |
+
},
|
| 2101 |
+
"attributes": {}
|
| 2102 |
+
}
|
| 2103 |
+
},
|
| 2104 |
+
"total_flos": 2.0534009572779622e+17,
|
| 2105 |
+
"train_batch_size": 1,
|
| 2106 |
+
"trial_name": null,
|
| 2107 |
+
"trial_params": null
|
| 2108 |
+
}
|
training_loss.png
ADDED
|