End of training
Browse files- README.md +3 -2
- all_results.json +13 -0
- eval_results.json +8 -0
- train_results.json +9 -0
- trainer_state.json +1313 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: apache-2.0
|
|
| 4 |
base_model: AdaptLLM/biomed-Qwen2-VL-2B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: qwenvl-2B-cadica-stenosis-classify-lora
|
|
@@ -15,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# qwenvl-2B-cadica-stenosis-classify-lora
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [AdaptLLM/biomed-Qwen2-VL-2B-Instruct](https://huggingface.co/AdaptLLM/biomed-Qwen2-VL-2B-Instruct) on
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 0.7947
|
| 21 |
-
- Num Input Tokens Seen:
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 4 |
base_model: AdaptLLM/biomed-Qwen2-VL-2B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- lora
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: qwenvl-2B-cadica-stenosis-classify-lora
|
|
|
|
| 16 |
|
| 17 |
# qwenvl-2B-cadica-stenosis-classify-lora
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [AdaptLLM/biomed-Qwen2-VL-2B-Instruct](https://huggingface.co/AdaptLLM/biomed-Qwen2-VL-2B-Instruct) on the CADICA狹窄分析選擇題(TRAIN) dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.7947
|
| 22 |
+
- Num Input Tokens Seen: 11152104
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.9968586387434555,
|
| 3 |
+
"eval_loss": 0.794740617275238,
|
| 4 |
+
"eval_runtime": 46.549,
|
| 5 |
+
"eval_samples_per_second": 3.136,
|
| 6 |
+
"eval_steps_per_second": 0.795,
|
| 7 |
+
"num_input_tokens_seen": 11152104,
|
| 8 |
+
"total_flos": 754095660204032.0,
|
| 9 |
+
"train_loss": 0.9049516569136241,
|
| 10 |
+
"train_runtime": 17154.0309,
|
| 11 |
+
"train_samples_per_second": 1.336,
|
| 12 |
+
"train_steps_per_second": 0.042
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.9968586387434555,
|
| 3 |
+
"eval_loss": 0.794740617275238,
|
| 4 |
+
"eval_runtime": 46.549,
|
| 5 |
+
"eval_samples_per_second": 3.136,
|
| 6 |
+
"eval_steps_per_second": 0.795,
|
| 7 |
+
"num_input_tokens_seen": 11152104
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.9968586387434555,
|
| 3 |
+
"num_input_tokens_seen": 11152104,
|
| 4 |
+
"total_flos": 754095660204032.0,
|
| 5 |
+
"train_loss": 0.9049516569136241,
|
| 6 |
+
"train_runtime": 17154.0309,
|
| 7 |
+
"train_samples_per_second": 1.336,
|
| 8 |
+
"train_steps_per_second": 0.042
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1313 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.794740617275238,
|
| 3 |
+
"best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_classily/lora/sft/checkpoint-700",
|
| 4 |
+
"epoch": 1.9968586387434555,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 716,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.013961605584642234,
|
| 13 |
+
"grad_norm": 21.25276507868793,
|
| 14 |
+
"learning_rate": 6.944444444444445e-06,
|
| 15 |
+
"loss": 2.9908,
|
| 16 |
+
"num_input_tokens_seen": 77944,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.027923211169284468,
|
| 21 |
+
"grad_norm": 21.89043285054519,
|
| 22 |
+
"learning_rate": 1.388888888888889e-05,
|
| 23 |
+
"loss": 3.0071,
|
| 24 |
+
"num_input_tokens_seen": 155896,
|
| 25 |
+
"step": 10
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.041884816753926704,
|
| 29 |
+
"grad_norm": 16.65776874449816,
|
| 30 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 31 |
+
"loss": 2.354,
|
| 32 |
+
"num_input_tokens_seen": 233896,
|
| 33 |
+
"step": 15
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.055846422338568937,
|
| 37 |
+
"grad_norm": 3.772799389266845,
|
| 38 |
+
"learning_rate": 2.777777777777778e-05,
|
| 39 |
+
"loss": 1.2959,
|
| 40 |
+
"num_input_tokens_seen": 311840,
|
| 41 |
+
"step": 20
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.06980802792321117,
|
| 45 |
+
"grad_norm": 2.5936011954385334,
|
| 46 |
+
"learning_rate": 3.472222222222222e-05,
|
| 47 |
+
"loss": 1.0206,
|
| 48 |
+
"num_input_tokens_seen": 389816,
|
| 49 |
+
"step": 25
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.08376963350785341,
|
| 53 |
+
"grad_norm": 1.380523901017673,
|
| 54 |
+
"learning_rate": 4.166666666666667e-05,
|
| 55 |
+
"loss": 0.9285,
|
| 56 |
+
"num_input_tokens_seen": 467808,
|
| 57 |
+
"step": 30
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.09773123909249563,
|
| 61 |
+
"grad_norm": 0.9535971270874376,
|
| 62 |
+
"learning_rate": 4.8611111111111115e-05,
|
| 63 |
+
"loss": 0.9052,
|
| 64 |
+
"num_input_tokens_seen": 545776,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.11169284467713787,
|
| 69 |
+
"grad_norm": 0.7487685762175865,
|
| 70 |
+
"learning_rate": 5.555555555555556e-05,
|
| 71 |
+
"loss": 0.929,
|
| 72 |
+
"num_input_tokens_seen": 623744,
|
| 73 |
+
"step": 40
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.1256544502617801,
|
| 77 |
+
"grad_norm": 0.9517829869317949,
|
| 78 |
+
"learning_rate": 6.25e-05,
|
| 79 |
+
"loss": 0.9076,
|
| 80 |
+
"num_input_tokens_seen": 701720,
|
| 81 |
+
"step": 45
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.13961605584642234,
|
| 85 |
+
"grad_norm": 0.5105376471286923,
|
| 86 |
+
"learning_rate": 6.944444444444444e-05,
|
| 87 |
+
"loss": 0.9039,
|
| 88 |
+
"num_input_tokens_seen": 779728,
|
| 89 |
+
"step": 50
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.13961605584642234,
|
| 93 |
+
"eval_loss": 0.9039102792739868,
|
| 94 |
+
"eval_runtime": 74.9579,
|
| 95 |
+
"eval_samples_per_second": 1.948,
|
| 96 |
+
"eval_steps_per_second": 0.494,
|
| 97 |
+
"num_input_tokens_seen": 779728,
|
| 98 |
+
"step": 50
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.15357766143106458,
|
| 102 |
+
"grad_norm": 0.6125311992064874,
|
| 103 |
+
"learning_rate": 7.638888888888889e-05,
|
| 104 |
+
"loss": 0.8983,
|
| 105 |
+
"num_input_tokens_seen": 857728,
|
| 106 |
+
"step": 55
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.16753926701570682,
|
| 110 |
+
"grad_norm": 0.8799068808838695,
|
| 111 |
+
"learning_rate": 8.333333333333334e-05,
|
| 112 |
+
"loss": 0.9115,
|
| 113 |
+
"num_input_tokens_seen": 935680,
|
| 114 |
+
"step": 60
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.18150087260034903,
|
| 118 |
+
"grad_norm": 0.7270711909487898,
|
| 119 |
+
"learning_rate": 9.027777777777779e-05,
|
| 120 |
+
"loss": 0.9022,
|
| 121 |
+
"num_input_tokens_seen": 1013664,
|
| 122 |
+
"step": 65
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.19546247818499127,
|
| 126 |
+
"grad_norm": 0.6023654770278246,
|
| 127 |
+
"learning_rate": 9.722222222222223e-05,
|
| 128 |
+
"loss": 0.8981,
|
| 129 |
+
"num_input_tokens_seen": 1091656,
|
| 130 |
+
"step": 70
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.2094240837696335,
|
| 134 |
+
"grad_norm": 0.5698794386547648,
|
| 135 |
+
"learning_rate": 9.999464569905628e-05,
|
| 136 |
+
"loss": 0.9067,
|
| 137 |
+
"num_input_tokens_seen": 1169664,
|
| 138 |
+
"step": 75
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.22338568935427575,
|
| 142 |
+
"grad_norm": 0.32260644881875,
|
| 143 |
+
"learning_rate": 9.99619291237835e-05,
|
| 144 |
+
"loss": 0.9075,
|
| 145 |
+
"num_input_tokens_seen": 1247672,
|
| 146 |
+
"step": 80
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.23734729493891799,
|
| 150 |
+
"grad_norm": 0.41708039368778405,
|
| 151 |
+
"learning_rate": 9.989949002448076e-05,
|
| 152 |
+
"loss": 0.8964,
|
| 153 |
+
"num_input_tokens_seen": 1325640,
|
| 154 |
+
"step": 85
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.2513089005235602,
|
| 158 |
+
"grad_norm": 0.6145758907120942,
|
| 159 |
+
"learning_rate": 9.980736554638366e-05,
|
| 160 |
+
"loss": 0.9128,
|
| 161 |
+
"num_input_tokens_seen": 1403688,
|
| 162 |
+
"step": 90
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.26527050610820246,
|
| 166 |
+
"grad_norm": 0.30302247663937915,
|
| 167 |
+
"learning_rate": 9.968561049466214e-05,
|
| 168 |
+
"loss": 0.8991,
|
| 169 |
+
"num_input_tokens_seen": 1481664,
|
| 170 |
+
"step": 95
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.2792321116928447,
|
| 174 |
+
"grad_norm": 0.32920212256475023,
|
| 175 |
+
"learning_rate": 9.953429730181653e-05,
|
| 176 |
+
"loss": 0.9033,
|
| 177 |
+
"num_input_tokens_seen": 1559632,
|
| 178 |
+
"step": 100
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.2792321116928447,
|
| 182 |
+
"eval_loss": 0.9009457230567932,
|
| 183 |
+
"eval_runtime": 47.3577,
|
| 184 |
+
"eval_samples_per_second": 3.083,
|
| 185 |
+
"eval_steps_per_second": 0.781,
|
| 186 |
+
"num_input_tokens_seen": 1559632,
|
| 187 |
+
"step": 100
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 0.2931937172774869,
|
| 191 |
+
"grad_norm": 0.3748068082841054,
|
| 192 |
+
"learning_rate": 9.935351598458742e-05,
|
| 193 |
+
"loss": 0.902,
|
| 194 |
+
"num_input_tokens_seen": 1637592,
|
| 195 |
+
"step": 105
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.30715532286212915,
|
| 199 |
+
"grad_norm": 0.367692204424778,
|
| 200 |
+
"learning_rate": 9.914337409040418e-05,
|
| 201 |
+
"loss": 0.903,
|
| 202 |
+
"num_input_tokens_seen": 1715592,
|
| 203 |
+
"step": 110
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.32111692844677137,
|
| 207 |
+
"grad_norm": 0.523389228578757,
|
| 208 |
+
"learning_rate": 9.890399663340478e-05,
|
| 209 |
+
"loss": 0.9014,
|
| 210 |
+
"num_input_tokens_seen": 1793544,
|
| 211 |
+
"step": 115
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.33507853403141363,
|
| 215 |
+
"grad_norm": 0.7666885810234405,
|
| 216 |
+
"learning_rate": 9.863552602006435e-05,
|
| 217 |
+
"loss": 0.8966,
|
| 218 |
+
"num_input_tokens_seen": 1871520,
|
| 219 |
+
"step": 120
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.34904013961605584,
|
| 223 |
+
"grad_norm": 0.45411297588089927,
|
| 224 |
+
"learning_rate": 9.83381219644771e-05,
|
| 225 |
+
"loss": 0.9032,
|
| 226 |
+
"num_input_tokens_seen": 1949488,
|
| 227 |
+
"step": 125
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.36300174520069806,
|
| 231 |
+
"grad_norm": 0.34304009173464395,
|
| 232 |
+
"learning_rate": 9.801196139334195e-05,
|
| 233 |
+
"loss": 0.8919,
|
| 234 |
+
"num_input_tokens_seen": 2027488,
|
| 235 |
+
"step": 130
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 0.3769633507853403,
|
| 239 |
+
"grad_norm": 0.46756876437741973,
|
| 240 |
+
"learning_rate": 9.765723834070804e-05,
|
| 241 |
+
"loss": 0.9025,
|
| 242 |
+
"num_input_tokens_seen": 2105424,
|
| 243 |
+
"step": 135
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.39092495636998253,
|
| 247 |
+
"grad_norm": 0.5067842714503226,
|
| 248 |
+
"learning_rate": 9.72741638325434e-05,
|
| 249 |
+
"loss": 0.9001,
|
| 250 |
+
"num_input_tokens_seen": 2183432,
|
| 251 |
+
"step": 140
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.4048865619546248,
|
| 255 |
+
"grad_norm": 0.45330848125911494,
|
| 256 |
+
"learning_rate": 9.686296576119471e-05,
|
| 257 |
+
"loss": 0.9007,
|
| 258 |
+
"num_input_tokens_seen": 2261408,
|
| 259 |
+
"step": 145
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 0.418848167539267,
|
| 263 |
+
"grad_norm": 0.3379495380306588,
|
| 264 |
+
"learning_rate": 9.642388874981347e-05,
|
| 265 |
+
"loss": 0.9001,
|
| 266 |
+
"num_input_tokens_seen": 2339368,
|
| 267 |
+
"step": 150
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.418848167539267,
|
| 271 |
+
"eval_loss": 0.8987511396408081,
|
| 272 |
+
"eval_runtime": 46.4204,
|
| 273 |
+
"eval_samples_per_second": 3.145,
|
| 274 |
+
"eval_steps_per_second": 0.797,
|
| 275 |
+
"num_input_tokens_seen": 2339368,
|
| 276 |
+
"step": 150
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.4328097731239092,
|
| 280 |
+
"grad_norm": 0.4705971769713144,
|
| 281 |
+
"learning_rate": 9.595719400682881e-05,
|
| 282 |
+
"loss": 0.8974,
|
| 283 |
+
"num_input_tokens_seen": 2417328,
|
| 284 |
+
"step": 155
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.4467713787085515,
|
| 288 |
+
"grad_norm": 0.2877245912486978,
|
| 289 |
+
"learning_rate": 9.546315917055361e-05,
|
| 290 |
+
"loss": 0.895,
|
| 291 |
+
"num_input_tokens_seen": 2495328,
|
| 292 |
+
"step": 160
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 0.4607329842931937,
|
| 296 |
+
"grad_norm": 0.3089085786477158,
|
| 297 |
+
"learning_rate": 9.494207814401672e-05,
|
| 298 |
+
"loss": 0.8993,
|
| 299 |
+
"num_input_tokens_seen": 2573264,
|
| 300 |
+
"step": 165
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 0.47469458987783597,
|
| 304 |
+
"grad_norm": 0.23434151328428765,
|
| 305 |
+
"learning_rate": 9.439426092011875e-05,
|
| 306 |
+
"loss": 0.9011,
|
| 307 |
+
"num_input_tokens_seen": 2651200,
|
| 308 |
+
"step": 170
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.4886561954624782,
|
| 312 |
+
"grad_norm": 0.3895079869752368,
|
| 313 |
+
"learning_rate": 9.382003339721652e-05,
|
| 314 |
+
"loss": 0.8943,
|
| 315 |
+
"num_input_tokens_seen": 2729208,
|
| 316 |
+
"step": 175
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.5026178010471204,
|
| 320 |
+
"grad_norm": 0.21859941380068879,
|
| 321 |
+
"learning_rate": 9.321973718524472e-05,
|
| 322 |
+
"loss": 0.9074,
|
| 323 |
+
"num_input_tokens_seen": 2807176,
|
| 324 |
+
"step": 180
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.5165794066317626,
|
| 328 |
+
"grad_norm": 0.3026569089827376,
|
| 329 |
+
"learning_rate": 9.25937294024912e-05,
|
| 330 |
+
"loss": 0.8979,
|
| 331 |
+
"num_input_tokens_seen": 2885136,
|
| 332 |
+
"step": 185
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.5305410122164049,
|
| 336 |
+
"grad_norm": 0.24552828812005026,
|
| 337 |
+
"learning_rate": 9.194238246314599e-05,
|
| 338 |
+
"loss": 0.8908,
|
| 339 |
+
"num_input_tokens_seen": 2963120,
|
| 340 |
+
"step": 190
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.5445026178010471,
|
| 344 |
+
"grad_norm": 0.31370225105827704,
|
| 345 |
+
"learning_rate": 9.126608385575076e-05,
|
| 346 |
+
"loss": 0.8922,
|
| 347 |
+
"num_input_tokens_seen": 3041096,
|
| 348 |
+
"step": 195
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 0.5584642233856894,
|
| 352 |
+
"grad_norm": 0.19991243424614802,
|
| 353 |
+
"learning_rate": 9.056523591268064e-05,
|
| 354 |
+
"loss": 0.902,
|
| 355 |
+
"num_input_tokens_seen": 3119064,
|
| 356 |
+
"step": 200
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.5584642233856894,
|
| 360 |
+
"eval_loss": 0.9003660678863525,
|
| 361 |
+
"eval_runtime": 46.4656,
|
| 362 |
+
"eval_samples_per_second": 3.142,
|
| 363 |
+
"eval_steps_per_second": 0.796,
|
| 364 |
+
"num_input_tokens_seen": 3119064,
|
| 365 |
+
"step": 200
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 0.5724258289703316,
|
| 369 |
+
"grad_norm": 0.29215232660029566,
|
| 370 |
+
"learning_rate": 8.984025557079523e-05,
|
| 371 |
+
"loss": 0.9016,
|
| 372 |
+
"num_input_tokens_seen": 3197048,
|
| 373 |
+
"step": 205
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.5863874345549738,
|
| 377 |
+
"grad_norm": 0.4850357234182881,
|
| 378 |
+
"learning_rate": 8.90915741234015e-05,
|
| 379 |
+
"loss": 0.907,
|
| 380 |
+
"num_input_tokens_seen": 3275024,
|
| 381 |
+
"step": 210
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.6003490401396161,
|
| 385 |
+
"grad_norm": 0.3567000129034729,
|
| 386 |
+
"learning_rate": 8.831963696367581e-05,
|
| 387 |
+
"loss": 0.8966,
|
| 388 |
+
"num_input_tokens_seen": 3353024,
|
| 389 |
+
"step": 215
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.6143106457242583,
|
| 393 |
+
"grad_norm": 0.26853087654006846,
|
| 394 |
+
"learning_rate": 8.752490331969807e-05,
|
| 395 |
+
"loss": 0.9031,
|
| 396 |
+
"num_input_tokens_seen": 3430936,
|
| 397 |
+
"step": 220
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.6282722513089005,
|
| 401 |
+
"grad_norm": 0.20742364801678845,
|
| 402 |
+
"learning_rate": 8.670784598125533e-05,
|
| 403 |
+
"loss": 0.9012,
|
| 404 |
+
"num_input_tokens_seen": 3508920,
|
| 405 |
+
"step": 225
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.6422338568935427,
|
| 409 |
+
"grad_norm": 0.2838565453202246,
|
| 410 |
+
"learning_rate": 8.586895101857747e-05,
|
| 411 |
+
"loss": 0.8936,
|
| 412 |
+
"num_input_tokens_seen": 3586920,
|
| 413 |
+
"step": 230
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 0.6561954624781849,
|
| 417 |
+
"grad_norm": 0.4892803498442385,
|
| 418 |
+
"learning_rate": 8.500871749317243e-05,
|
| 419 |
+
"loss": 0.9042,
|
| 420 |
+
"num_input_tokens_seen": 3664896,
|
| 421 |
+
"step": 235
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.6701570680628273,
|
| 425 |
+
"grad_norm": 0.37976656488421395,
|
| 426 |
+
"learning_rate": 8.412765716093272e-05,
|
| 427 |
+
"loss": 0.9034,
|
| 428 |
+
"num_input_tokens_seen": 3742832,
|
| 429 |
+
"step": 240
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.6841186736474695,
|
| 433 |
+
"grad_norm": 0.291645150101734,
|
| 434 |
+
"learning_rate": 8.322629416769006e-05,
|
| 435 |
+
"loss": 0.8969,
|
| 436 |
+
"num_input_tokens_seen": 3820792,
|
| 437 |
+
"step": 245
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.6980802792321117,
|
| 441 |
+
"grad_norm": 0.30837187813275513,
|
| 442 |
+
"learning_rate": 8.230516473739935e-05,
|
| 443 |
+
"loss": 0.8933,
|
| 444 |
+
"num_input_tokens_seen": 3898784,
|
| 445 |
+
"step": 250
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.6980802792321117,
|
| 449 |
+
"eval_loss": 0.9052047729492188,
|
| 450 |
+
"eval_runtime": 46.4894,
|
| 451 |
+
"eval_samples_per_second": 3.141,
|
| 452 |
+
"eval_steps_per_second": 0.796,
|
| 453 |
+
"num_input_tokens_seen": 3898784,
|
| 454 |
+
"step": 250
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 0.7120418848167539,
|
| 458 |
+
"grad_norm": 0.30727171157251326,
|
| 459 |
+
"learning_rate": 8.1364816853137e-05,
|
| 460 |
+
"loss": 0.9079,
|
| 461 |
+
"num_input_tokens_seen": 3976824,
|
| 462 |
+
"step": 255
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 0.7260034904013961,
|
| 466 |
+
"grad_norm": 0.24728667308223853,
|
| 467 |
+
"learning_rate": 8.040580993110404e-05,
|
| 468 |
+
"loss": 0.9044,
|
| 469 |
+
"num_input_tokens_seen": 4054752,
|
| 470 |
+
"step": 260
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.7399650959860384,
|
| 474 |
+
"grad_norm": 0.154782478333375,
|
| 475 |
+
"learning_rate": 7.942871448782748e-05,
|
| 476 |
+
"loss": 0.895,
|
| 477 |
+
"num_input_tokens_seen": 4132664,
|
| 478 |
+
"step": 265
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.7539267015706806,
|
| 482 |
+
"grad_norm": 0.21937062747939326,
|
| 483 |
+
"learning_rate": 7.843411180075794e-05,
|
| 484 |
+
"loss": 0.8984,
|
| 485 |
+
"num_input_tokens_seen": 4210656,
|
| 486 |
+
"step": 270
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.7678883071553229,
|
| 490 |
+
"grad_norm": 0.28854882430140594,
|
| 491 |
+
"learning_rate": 7.742259356246593e-05,
|
| 492 |
+
"loss": 0.904,
|
| 493 |
+
"num_input_tokens_seen": 4288664,
|
| 494 |
+
"step": 275
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.7818499127399651,
|
| 498 |
+
"grad_norm": 0.23726372374470991,
|
| 499 |
+
"learning_rate": 7.639476152864162e-05,
|
| 500 |
+
"loss": 0.8973,
|
| 501 |
+
"num_input_tokens_seen": 4366608,
|
| 502 |
+
"step": 280
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 0.7958115183246073,
|
| 506 |
+
"grad_norm": 0.34106252388262337,
|
| 507 |
+
"learning_rate": 7.535122716010849e-05,
|
| 508 |
+
"loss": 0.9018,
|
| 509 |
+
"num_input_tokens_seen": 4444568,
|
| 510 |
+
"step": 285
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 0.8097731239092496,
|
| 514 |
+
"grad_norm": 0.37561723629929783,
|
| 515 |
+
"learning_rate": 7.42926112590631e-05,
|
| 516 |
+
"loss": 0.8886,
|
| 517 |
+
"num_input_tokens_seen": 4522512,
|
| 518 |
+
"step": 290
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.8237347294938918,
|
| 522 |
+
"grad_norm": 0.26053439132207656,
|
| 523 |
+
"learning_rate": 7.321954359975776e-05,
|
| 524 |
+
"loss": 0.9002,
|
| 525 |
+
"num_input_tokens_seen": 4600504,
|
| 526 |
+
"step": 295
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 0.837696335078534,
|
| 530 |
+
"grad_norm": 0.248855595995717,
|
| 531 |
+
"learning_rate": 7.21326625538456e-05,
|
| 532 |
+
"loss": 0.897,
|
| 533 |
+
"num_input_tokens_seen": 4678472,
|
| 534 |
+
"step": 300
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.837696335078534,
|
| 538 |
+
"eval_loss": 0.9003945589065552,
|
| 539 |
+
"eval_runtime": 46.3308,
|
| 540 |
+
"eval_samples_per_second": 3.151,
|
| 541 |
+
"eval_steps_per_second": 0.799,
|
| 542 |
+
"num_input_tokens_seen": 4678472,
|
| 543 |
+
"step": 300
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.8516579406631762,
|
| 547 |
+
"grad_norm": 0.18200381843269203,
|
| 548 |
+
"learning_rate": 7.103261471061116e-05,
|
| 549 |
+
"loss": 0.9088,
|
| 550 |
+
"num_input_tokens_seen": 4756440,
|
| 551 |
+
"step": 305
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.8656195462478184,
|
| 555 |
+
"grad_norm": 0.19255528640902111,
|
| 556 |
+
"learning_rate": 6.992005449231208e-05,
|
| 557 |
+
"loss": 0.899,
|
| 558 |
+
"num_input_tokens_seen": 4834424,
|
| 559 |
+
"step": 310
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 0.8795811518324608,
|
| 563 |
+
"grad_norm": 0.3960850388870267,
|
| 564 |
+
"learning_rate": 6.879564376486114e-05,
|
| 565 |
+
"loss": 0.905,
|
| 566 |
+
"num_input_tokens_seen": 4912376,
|
| 567 |
+
"step": 315
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.893542757417103,
|
| 571 |
+
"grad_norm": 0.3472454916197344,
|
| 572 |
+
"learning_rate": 6.76600514440799e-05,
|
| 573 |
+
"loss": 0.8968,
|
| 574 |
+
"num_input_tokens_seen": 4990328,
|
| 575 |
+
"step": 320
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.9075043630017452,
|
| 579 |
+
"grad_norm": 0.42131468150264795,
|
| 580 |
+
"learning_rate": 6.651395309775837e-05,
|
| 581 |
+
"loss": 0.8916,
|
| 582 |
+
"num_input_tokens_seen": 5068304,
|
| 583 |
+
"step": 325
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.9214659685863874,
|
| 587 |
+
"grad_norm": 0.7373865772840422,
|
| 588 |
+
"learning_rate": 6.535803054375738e-05,
|
| 589 |
+
"loss": 0.8937,
|
| 590 |
+
"num_input_tokens_seen": 5146272,
|
| 591 |
+
"step": 330
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.9354275741710296,
|
| 595 |
+
"grad_norm": 0.6075085371236206,
|
| 596 |
+
"learning_rate": 6.419297144439283e-05,
|
| 597 |
+
"loss": 0.8965,
|
| 598 |
+
"num_input_tokens_seen": 5224232,
|
| 599 |
+
"step": 335
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.9493891797556719,
|
| 603 |
+
"grad_norm": 0.5336896324950464,
|
| 604 |
+
"learning_rate": 6.301946889734302e-05,
|
| 605 |
+
"loss": 0.8957,
|
| 606 |
+
"num_input_tokens_seen": 5302200,
|
| 607 |
+
"step": 340
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 0.9633507853403142,
|
| 611 |
+
"grad_norm": 0.7535717304812762,
|
| 612 |
+
"learning_rate": 6.183822102332234e-05,
|
| 613 |
+
"loss": 0.9025,
|
| 614 |
+
"num_input_tokens_seen": 5380168,
|
| 615 |
+
"step": 345
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.9773123909249564,
|
| 619 |
+
"grad_norm": 1.9146693047973427,
|
| 620 |
+
"learning_rate": 6.064993055076698e-05,
|
| 621 |
+
"loss": 0.8997,
|
| 622 |
+
"num_input_tokens_seen": 5458104,
|
| 623 |
+
"step": 350
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 0.9773123909249564,
|
| 627 |
+
"eval_loss": 0.9016226530075073,
|
| 628 |
+
"eval_runtime": 46.29,
|
| 629 |
+
"eval_samples_per_second": 3.154,
|
| 630 |
+
"eval_steps_per_second": 0.799,
|
| 631 |
+
"num_input_tokens_seen": 5458104,
|
| 632 |
+
"step": 350
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.9912739965095986,
|
| 636 |
+
"grad_norm": 0.4275320872134287,
|
| 637 |
+
"learning_rate": 5.945530439777923e-05,
|
| 638 |
+
"loss": 0.902,
|
| 639 |
+
"num_input_tokens_seen": 5536072,
|
| 640 |
+
"step": 355
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.0027923211169285,
|
| 644 |
+
"grad_norm": 1.5609644797837416,
|
| 645 |
+
"learning_rate": 5.8255053251579616e-05,
|
| 646 |
+
"loss": 0.7347,
|
| 647 |
+
"num_input_tokens_seen": 5600392,
|
| 648 |
+
"step": 360
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 1.0167539267015706,
|
| 652 |
+
"grad_norm": 0.4880192687307677,
|
| 653 |
+
"learning_rate": 5.704989114571648e-05,
|
| 654 |
+
"loss": 0.8899,
|
| 655 |
+
"num_input_tokens_seen": 5678424,
|
| 656 |
+
"step": 365
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 1.030715532286213,
|
| 660 |
+
"grad_norm": 0.37744049750587216,
|
| 661 |
+
"learning_rate": 5.5840535035285025e-05,
|
| 662 |
+
"loss": 0.8929,
|
| 663 |
+
"num_input_tokens_seen": 5756400,
|
| 664 |
+
"step": 370
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 1.0446771378708553,
|
| 668 |
+
"grad_norm": 0.9395658719072697,
|
| 669 |
+
"learning_rate": 5.4627704370408236e-05,
|
| 670 |
+
"loss": 0.8904,
|
| 671 |
+
"num_input_tokens_seen": 5834352,
|
| 672 |
+
"step": 375
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 1.0586387434554974,
|
| 676 |
+
"grad_norm": 0.5490353927737941,
|
| 677 |
+
"learning_rate": 5.341212066823355e-05,
|
| 678 |
+
"loss": 0.8964,
|
| 679 |
+
"num_input_tokens_seen": 5912320,
|
| 680 |
+
"step": 380
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 1.0726003490401397,
|
| 684 |
+
"grad_norm": 1.1114978460946199,
|
| 685 |
+
"learning_rate": 5.219450708369977e-05,
|
| 686 |
+
"loss": 0.8843,
|
| 687 |
+
"num_input_tokens_seen": 5990312,
|
| 688 |
+
"step": 385
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.0865619546247818,
|
| 692 |
+
"grad_norm": 1.1913979980069938,
|
| 693 |
+
"learning_rate": 5.0975587979329734e-05,
|
| 694 |
+
"loss": 0.8879,
|
| 695 |
+
"num_input_tokens_seen": 6068280,
|
| 696 |
+
"step": 390
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.100523560209424,
|
| 700 |
+
"grad_norm": 2.222951083897475,
|
| 701 |
+
"learning_rate": 4.9756088494304504e-05,
|
| 702 |
+
"loss": 0.8816,
|
| 703 |
+
"num_input_tokens_seen": 6146288,
|
| 704 |
+
"step": 395
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 1.1144851657940662,
|
| 708 |
+
"grad_norm": 1.5657191660795382,
|
| 709 |
+
"learning_rate": 4.853673411307564e-05,
|
| 710 |
+
"loss": 0.9109,
|
| 711 |
+
"num_input_tokens_seen": 6224248,
|
| 712 |
+
"step": 400
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 1.1144851657940662,
|
| 716 |
+
"eval_loss": 0.8960007429122925,
|
| 717 |
+
"eval_runtime": 46.5432,
|
| 718 |
+
"eval_samples_per_second": 3.137,
|
| 719 |
+
"eval_steps_per_second": 0.795,
|
| 720 |
+
"num_input_tokens_seen": 6224248,
|
| 721 |
+
"step": 400
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 1.1284467713787085,
|
| 725 |
+
"grad_norm": 2.66254478509122,
|
| 726 |
+
"learning_rate": 4.731825023377192e-05,
|
| 727 |
+
"loss": 0.8631,
|
| 728 |
+
"num_input_tokens_seen": 6302208,
|
| 729 |
+
"step": 405
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 1.1424083769633508,
|
| 733 |
+
"grad_norm": 1.7871963773512198,
|
| 734 |
+
"learning_rate": 4.610136173665751e-05,
|
| 735 |
+
"loss": 0.8722,
|
| 736 |
+
"num_input_tokens_seen": 6380096,
|
| 737 |
+
"step": 410
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.156369982547993,
|
| 741 |
+
"grad_norm": 2.511479150461674,
|
| 742 |
+
"learning_rate": 4.4886792552898286e-05,
|
| 743 |
+
"loss": 0.864,
|
| 744 |
+
"num_input_tokens_seen": 6458096,
|
| 745 |
+
"step": 415
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.1703315881326353,
|
| 749 |
+
"grad_norm": 2.9185608745372837,
|
| 750 |
+
"learning_rate": 4.367526523389253e-05,
|
| 751 |
+
"loss": 0.8446,
|
| 752 |
+
"num_input_tokens_seen": 6536064,
|
| 753 |
+
"step": 420
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 1.1842931937172776,
|
| 757 |
+
"grad_norm": 3.7053458609530403,
|
| 758 |
+
"learning_rate": 4.24675005214227e-05,
|
| 759 |
+
"loss": 0.8576,
|
| 760 |
+
"num_input_tokens_seen": 6614048,
|
| 761 |
+
"step": 425
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 1.1982547993019197,
|
| 765 |
+
"grad_norm": 2.3073667949552124,
|
| 766 |
+
"learning_rate": 4.1264216918883656e-05,
|
| 767 |
+
"loss": 0.8715,
|
| 768 |
+
"num_input_tokens_seen": 6691984,
|
| 769 |
+
"step": 430
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 1.212216404886562,
|
| 773 |
+
"grad_norm": 2.597389084730036,
|
| 774 |
+
"learning_rate": 4.006613026384249e-05,
|
| 775 |
+
"loss": 0.8708,
|
| 776 |
+
"num_input_tokens_seen": 6769984,
|
| 777 |
+
"step": 435
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 1.2261780104712041,
|
| 781 |
+
"grad_norm": 1.889225145403208,
|
| 782 |
+
"learning_rate": 3.887395330218429e-05,
|
| 783 |
+
"loss": 0.8546,
|
| 784 |
+
"num_input_tokens_seen": 6847976,
|
| 785 |
+
"step": 440
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 1.2401396160558464,
|
| 789 |
+
"grad_norm": 2.61428130233799,
|
| 790 |
+
"learning_rate": 3.768839526409718e-05,
|
| 791 |
+
"loss": 0.8592,
|
| 792 |
+
"num_input_tokens_seen": 6925944,
|
| 793 |
+
"step": 445
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.2541012216404885,
|
| 797 |
+
"grad_norm": 5.825082846471074,
|
| 798 |
+
"learning_rate": 3.651016144214878e-05,
|
| 799 |
+
"loss": 0.8127,
|
| 800 |
+
"num_input_tokens_seen": 7003904,
|
| 801 |
+
"step": 450
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.2541012216404885,
|
| 805 |
+
"eval_loss": 0.8821887373924255,
|
| 806 |
+
"eval_runtime": 46.527,
|
| 807 |
+
"eval_samples_per_second": 3.138,
|
| 808 |
+
"eval_steps_per_second": 0.795,
|
| 809 |
+
"num_input_tokens_seen": 7003904,
|
| 810 |
+
"step": 450
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 1.2680628272251309,
|
| 814 |
+
"grad_norm": 3.745385127572465,
|
| 815 |
+
"learning_rate": 3.533995277170532e-05,
|
| 816 |
+
"loss": 0.837,
|
| 817 |
+
"num_input_tokens_seen": 7081856,
|
| 818 |
+
"step": 455
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 1.2820244328097732,
|
| 822 |
+
"grad_norm": 3.1595331481084896,
|
| 823 |
+
"learning_rate": 3.4178465413942625e-05,
|
| 824 |
+
"loss": 0.8631,
|
| 825 |
+
"num_input_tokens_seen": 7159776,
|
| 826 |
+
"step": 460
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 1.2959860383944153,
|
| 830 |
+
"grad_norm": 3.241335528071935,
|
| 831 |
+
"learning_rate": 3.3026390341697576e-05,
|
| 832 |
+
"loss": 0.8511,
|
| 833 |
+
"num_input_tokens_seen": 7237720,
|
| 834 |
+
"step": 465
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 1.3099476439790576,
|
| 838 |
+
"grad_norm": 2.065109380918334,
|
| 839 |
+
"learning_rate": 3.188441292840587e-05,
|
| 840 |
+
"loss": 0.8439,
|
| 841 |
+
"num_input_tokens_seen": 7315704,
|
| 842 |
+
"step": 470
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 1.3239092495637,
|
| 846 |
+
"grad_norm": 3.25037907997737,
|
| 847 |
+
"learning_rate": 3.075321254037112e-05,
|
| 848 |
+
"loss": 0.872,
|
| 849 |
+
"num_input_tokens_seen": 7393672,
|
| 850 |
+
"step": 475
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.337870855148342,
|
| 854 |
+
"grad_norm": 4.772644937407586,
|
| 855 |
+
"learning_rate": 2.963346213260737e-05,
|
| 856 |
+
"loss": 0.8397,
|
| 857 |
+
"num_input_tokens_seen": 7471632,
|
| 858 |
+
"step": 480
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 1.3518324607329844,
|
| 862 |
+
"grad_norm": 4.371699254241009,
|
| 863 |
+
"learning_rate": 2.8525827848495913e-05,
|
| 864 |
+
"loss": 0.8254,
|
| 865 |
+
"num_input_tokens_seen": 7549624,
|
| 866 |
+
"step": 485
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 1.3657940663176265,
|
| 870 |
+
"grad_norm": 3.1620853722419797,
|
| 871 |
+
"learning_rate": 2.743096862349427e-05,
|
| 872 |
+
"loss": 0.8236,
|
| 873 |
+
"num_input_tokens_seen": 7627568,
|
| 874 |
+
"step": 490
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 1.3797556719022688,
|
| 878 |
+
"grad_norm": 5.330846549870451,
|
| 879 |
+
"learning_rate": 2.6349535793133196e-05,
|
| 880 |
+
"loss": 0.8561,
|
| 881 |
+
"num_input_tokens_seen": 7705512,
|
| 882 |
+
"step": 495
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 1.3937172774869109,
|
| 886 |
+
"grad_norm": 6.723230790293138,
|
| 887 |
+
"learning_rate": 2.5282172705535013e-05,
|
| 888 |
+
"loss": 0.8198,
|
| 889 |
+
"num_input_tokens_seen": 7783528,
|
| 890 |
+
"step": 500
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 1.3937172774869109,
|
| 894 |
+
"eval_loss": 0.846021294593811,
|
| 895 |
+
"eval_runtime": 46.2996,
|
| 896 |
+
"eval_samples_per_second": 3.153,
|
| 897 |
+
"eval_steps_per_second": 0.799,
|
| 898 |
+
"num_input_tokens_seen": 7783528,
|
| 899 |
+
"step": 500
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.4076788830715532,
|
| 903 |
+
"grad_norm": 3.08479773422221,
|
| 904 |
+
"learning_rate": 2.4229514338683458e-05,
|
| 905 |
+
"loss": 0.8498,
|
| 906 |
+
"num_input_tokens_seen": 7861512,
|
| 907 |
+
"step": 505
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 1.4216404886561955,
|
| 911 |
+
"grad_norm": 6.6639723675246385,
|
| 912 |
+
"learning_rate": 2.3192186922673186e-05,
|
| 913 |
+
"loss": 0.8195,
|
| 914 |
+
"num_input_tokens_seen": 7939480,
|
| 915 |
+
"step": 510
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 1.4356020942408376,
|
| 919 |
+
"grad_norm": 5.041383098958532,
|
| 920 |
+
"learning_rate": 2.2170807567163294e-05,
|
| 921 |
+
"loss": 0.8428,
|
| 922 |
+
"num_input_tokens_seen": 8017496,
|
| 923 |
+
"step": 515
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 1.44956369982548,
|
| 927 |
+
"grad_norm": 6.547003709523484,
|
| 928 |
+
"learning_rate": 2.1165983894256647e-05,
|
| 929 |
+
"loss": 0.8534,
|
| 930 |
+
"num_input_tokens_seen": 8095504,
|
| 931 |
+
"step": 520
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 1.4635253054101223,
|
| 935 |
+
"grad_norm": 6.396371201229991,
|
| 936 |
+
"learning_rate": 2.0178313677023425e-05,
|
| 937 |
+
"loss": 0.8113,
|
| 938 |
+
"num_input_tokens_seen": 8173440,
|
| 939 |
+
"step": 525
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 1.4774869109947644,
|
| 943 |
+
"grad_norm": 3.194803428296668,
|
| 944 |
+
"learning_rate": 1.9208384483883817e-05,
|
| 945 |
+
"loss": 0.8325,
|
| 946 |
+
"num_input_tokens_seen": 8251400,
|
| 947 |
+
"step": 530
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.4914485165794067,
|
| 951 |
+
"grad_norm": 3.8201513107026552,
|
| 952 |
+
"learning_rate": 1.8256773329061567e-05,
|
| 953 |
+
"loss": 0.8158,
|
| 954 |
+
"num_input_tokens_seen": 8329384,
|
| 955 |
+
"step": 535
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.505410122164049,
|
| 959 |
+
"grad_norm": 7.081372136918514,
|
| 960 |
+
"learning_rate": 1.732404632931625e-05,
|
| 961 |
+
"loss": 0.8183,
|
| 962 |
+
"num_input_tokens_seen": 8407384,
|
| 963 |
+
"step": 540
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 1.5193717277486911,
|
| 967 |
+
"grad_norm": 5.594321718168384,
|
| 968 |
+
"learning_rate": 1.6410758367158385e-05,
|
| 969 |
+
"loss": 0.8364,
|
| 970 |
+
"num_input_tokens_seen": 8485328,
|
| 971 |
+
"step": 545
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 1.5333333333333332,
|
| 975 |
+
"grad_norm": 6.74399246622262,
|
| 976 |
+
"learning_rate": 1.5517452760747975e-05,
|
| 977 |
+
"loss": 0.832,
|
| 978 |
+
"num_input_tokens_seen": 8563264,
|
| 979 |
+
"step": 550
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"epoch": 1.5333333333333332,
|
| 983 |
+
"eval_loss": 0.8187811374664307,
|
| 984 |
+
"eval_runtime": 46.4274,
|
| 985 |
+
"eval_samples_per_second": 3.145,
|
| 986 |
+
"eval_steps_per_second": 0.797,
|
| 987 |
+
"num_input_tokens_seen": 8563264,
|
| 988 |
+
"step": 550
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 1.5472949389179755,
|
| 992 |
+
"grad_norm": 3.6364413823808968,
|
| 993 |
+
"learning_rate": 1.4644660940672627e-05,
|
| 994 |
+
"loss": 0.8445,
|
| 995 |
+
"num_input_tokens_seen": 8641240,
|
| 996 |
+
"step": 555
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 1.5612565445026179,
|
| 1000 |
+
"grad_norm": 4.8432505694035495,
|
| 1001 |
+
"learning_rate": 1.3792902133797692e-05,
|
| 1002 |
+
"loss": 0.8372,
|
| 1003 |
+
"num_input_tokens_seen": 8719256,
|
| 1004 |
+
"step": 560
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.57521815008726,
|
| 1008 |
+
"grad_norm": 3.5469277881436545,
|
| 1009 |
+
"learning_rate": 1.2962683054376373e-05,
|
| 1010 |
+
"loss": 0.8107,
|
| 1011 |
+
"num_input_tokens_seen": 8797240,
|
| 1012 |
+
"step": 565
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 1.5891797556719023,
|
| 1016 |
+
"grad_norm": 3.916756694748693,
|
| 1017 |
+
"learning_rate": 1.2154497602603703e-05,
|
| 1018 |
+
"loss": 0.8472,
|
| 1019 |
+
"num_input_tokens_seen": 8875208,
|
| 1020 |
+
"step": 570
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 1.6031413612565446,
|
| 1024 |
+
"grad_norm": 5.159527110013197,
|
| 1025 |
+
"learning_rate": 1.13688265707936e-05,
|
| 1026 |
+
"loss": 0.8221,
|
| 1027 |
+
"num_input_tokens_seen": 8953176,
|
| 1028 |
+
"step": 575
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 1.6171029668411867,
|
| 1032 |
+
"grad_norm": 3.9357730966522637,
|
| 1033 |
+
"learning_rate": 1.060613735735384e-05,
|
| 1034 |
+
"loss": 0.8076,
|
| 1035 |
+
"num_input_tokens_seen": 9031192,
|
| 1036 |
+
"step": 580
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 1.6310645724258288,
|
| 1040 |
+
"grad_norm": 4.296138435306084,
|
| 1041 |
+
"learning_rate": 9.86688368872919e-06,
|
| 1042 |
+
"loss": 0.7987,
|
| 1043 |
+
"num_input_tokens_seen": 9109184,
|
| 1044 |
+
"step": 585
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 1.6450261780104714,
|
| 1048 |
+
"grad_norm": 5.917164796099687,
|
| 1049 |
+
"learning_rate": 9.151505349477902e-06,
|
| 1050 |
+
"loss": 0.7814,
|
| 1051 |
+
"num_input_tokens_seen": 9187136,
|
| 1052 |
+
"step": 590
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 1.6589877835951135,
|
| 1056 |
+
"grad_norm": 6.642916615289702,
|
| 1057 |
+
"learning_rate": 8.460427920642423e-06,
|
| 1058 |
+
"loss": 0.7907,
|
| 1059 |
+
"num_input_tokens_seen": 9265112,
|
| 1060 |
+
"step": 595
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.6729493891797556,
|
| 1064 |
+
"grad_norm": 6.455529863705343,
|
| 1065 |
+
"learning_rate": 7.794062526569734e-06,
|
| 1066 |
+
"loss": 0.786,
|
| 1067 |
+
"num_input_tokens_seen": 9343120,
|
| 1068 |
+
"step": 600
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 1.6729493891797556,
|
| 1072 |
+
"eval_loss": 0.8021153211593628,
|
| 1073 |
+
"eval_runtime": 46.5141,
|
| 1074 |
+
"eval_samples_per_second": 3.139,
|
| 1075 |
+
"eval_steps_per_second": 0.795,
|
| 1076 |
+
"num_input_tokens_seen": 9343120,
|
| 1077 |
+
"step": 600
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 1.6869109947643979,
|
| 1081 |
+
"grad_norm": 18.00061211274046,
|
| 1082 |
+
"learning_rate": 7.152805590332079e-06,
|
| 1083 |
+
"loss": 0.7702,
|
| 1084 |
+
"num_input_tokens_seen": 9421080,
|
| 1085 |
+
"step": 605
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 1.7008726003490402,
|
| 1089 |
+
"grad_norm": 6.515893934614007,
|
| 1090 |
+
"learning_rate": 6.53703859789348e-06,
|
| 1091 |
+
"loss": 0.7447,
|
| 1092 |
+
"num_input_tokens_seen": 9499048,
|
| 1093 |
+
"step": 610
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 1.7148342059336823,
|
| 1097 |
+
"grad_norm": 8.393536107737633,
|
| 1098 |
+
"learning_rate": 5.947127871162456e-06,
|
| 1099 |
+
"loss": 0.7943,
|
| 1100 |
+
"num_input_tokens_seen": 9577048,
|
| 1101 |
+
"step": 615
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 1.7287958115183246,
|
| 1105 |
+
"grad_norm": 10.522936719634327,
|
| 1106 |
+
"learning_rate": 5.383424350065824e-06,
|
| 1107 |
+
"loss": 0.7784,
|
| 1108 |
+
"num_input_tokens_seen": 9655032,
|
| 1109 |
+
"step": 620
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.742757417102967,
|
| 1113 |
+
"grad_norm": 4.303878340242376,
|
| 1114 |
+
"learning_rate": 4.846263383773364e-06,
|
| 1115 |
+
"loss": 0.8188,
|
| 1116 |
+
"num_input_tokens_seen": 9733000,
|
| 1117 |
+
"step": 625
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 1.756719022687609,
|
| 1121 |
+
"grad_norm": 7.6073494826846035,
|
| 1122 |
+
"learning_rate": 4.335964531197401e-06,
|
| 1123 |
+
"loss": 0.7514,
|
| 1124 |
+
"num_input_tokens_seen": 9810984,
|
| 1125 |
+
"step": 630
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 1.7706806282722511,
|
| 1129 |
+
"grad_norm": 4.962378312676078,
|
| 1130 |
+
"learning_rate": 3.8528313708861174e-06,
|
| 1131 |
+
"loss": 0.8165,
|
| 1132 |
+
"num_input_tokens_seen": 9888984,
|
| 1133 |
+
"step": 635
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 1.7846422338568937,
|
| 1137 |
+
"grad_norm": 5.475236961963435,
|
| 1138 |
+
"learning_rate": 3.397151320423647e-06,
|
| 1139 |
+
"loss": 0.7778,
|
| 1140 |
+
"num_input_tokens_seen": 9966984,
|
| 1141 |
+
"step": 640
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 1.7986038394415358,
|
| 1145 |
+
"grad_norm": 7.658362208235343,
|
| 1146 |
+
"learning_rate": 2.9691954654443355e-06,
|
| 1147 |
+
"loss": 0.7745,
|
| 1148 |
+
"num_input_tokens_seen": 10044928,
|
| 1149 |
+
"step": 645
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 1.812565445026178,
|
| 1153 |
+
"grad_norm": 6.541910443575109,
|
| 1154 |
+
"learning_rate": 2.5692183983629713e-06,
|
| 1155 |
+
"loss": 0.8312,
|
| 1156 |
+
"num_input_tokens_seen": 10122936,
|
| 1157 |
+
"step": 650
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.812565445026178,
|
| 1161 |
+
"eval_loss": 0.7986289858818054,
|
| 1162 |
+
"eval_runtime": 46.4273,
|
| 1163 |
+
"eval_samples_per_second": 3.145,
|
| 1164 |
+
"eval_steps_per_second": 0.797,
|
| 1165 |
+
"num_input_tokens_seen": 10122936,
|
| 1166 |
+
"step": 650
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 1.8265270506108202,
|
| 1170 |
+
"grad_norm": 9.39953604203485,
|
| 1171 |
+
"learning_rate": 2.197458066916891e-06,
|
| 1172 |
+
"loss": 0.794,
|
| 1173 |
+
"num_input_tokens_seen": 10200848,
|
| 1174 |
+
"step": 655
|
| 1175 |
+
},
|
| 1176 |
+
{
|
| 1177 |
+
"epoch": 1.8404886561954625,
|
| 1178 |
+
"grad_norm": 5.45740552150688,
|
| 1179 |
+
"learning_rate": 1.8541356326100433e-06,
|
| 1180 |
+
"loss": 0.8129,
|
| 1181 |
+
"num_input_tokens_seen": 10278848,
|
| 1182 |
+
"step": 660
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 1.8544502617801046,
|
| 1186 |
+
"grad_norm": 5.2960185422888575,
|
| 1187 |
+
"learning_rate": 1.5394553391432143e-06,
|
| 1188 |
+
"loss": 0.8057,
|
| 1189 |
+
"num_input_tokens_seen": 10356800,
|
| 1190 |
+
"step": 665
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 1.868411867364747,
|
| 1194 |
+
"grad_norm": 4.792059943516234,
|
| 1195 |
+
"learning_rate": 1.2536043909088191e-06,
|
| 1196 |
+
"loss": 0.7678,
|
| 1197 |
+
"num_input_tokens_seen": 10434768,
|
| 1198 |
+
"step": 670
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 1.8823734729493893,
|
| 1202 |
+
"grad_norm": 4.924682676533088,
|
| 1203 |
+
"learning_rate": 9.967528416222838e-07,
|
| 1204 |
+
"loss": 0.7851,
|
| 1205 |
+
"num_input_tokens_seen": 10512752,
|
| 1206 |
+
"step": 675
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 1.8963350785340314,
|
| 1210 |
+
"grad_norm": 7.6405932797853096,
|
| 1211 |
+
"learning_rate": 7.690534931565518e-07,
|
| 1212 |
+
"loss": 0.7381,
|
| 1213 |
+
"num_input_tokens_seen": 10590760,
|
| 1214 |
+
"step": 680
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.9102966841186735,
|
| 1218 |
+
"grad_norm": 4.326706788996488,
|
| 1219 |
+
"learning_rate": 5.706418046396989e-07,
|
| 1220 |
+
"loss": 0.7495,
|
| 1221 |
+
"num_input_tokens_seen": 10668752,
|
| 1222 |
+
"step": 685
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 1.924258289703316,
|
| 1226 |
+
"grad_norm": 5.0004961580783815,
|
| 1227 |
+
"learning_rate": 4.0163581186984935e-07,
|
| 1228 |
+
"loss": 0.7406,
|
| 1229 |
+
"num_input_tokens_seen": 10746696,
|
| 1230 |
+
"step": 690
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 1.9382198952879581,
|
| 1234 |
+
"grad_norm": 7.870737498179825,
|
| 1235 |
+
"learning_rate": 2.62136057095258e-07,
|
| 1236 |
+
"loss": 0.7823,
|
| 1237 |
+
"num_input_tokens_seen": 10824664,
|
| 1238 |
+
"step": 695
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 1.9521815008726002,
|
| 1242 |
+
"grad_norm": 6.748561230572036,
|
| 1243 |
+
"learning_rate": 1.5222552920138856e-07,
|
| 1244 |
+
"loss": 0.7797,
|
| 1245 |
+
"num_input_tokens_seen": 10902632,
|
| 1246 |
+
"step": 700
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 1.9521815008726002,
|
| 1250 |
+
"eval_loss": 0.794740617275238,
|
| 1251 |
+
"eval_runtime": 46.5422,
|
| 1252 |
+
"eval_samples_per_second": 3.137,
|
| 1253 |
+
"eval_steps_per_second": 0.795,
|
| 1254 |
+
"num_input_tokens_seen": 10902632,
|
| 1255 |
+
"step": 700
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 1.9661431064572426,
|
| 1259 |
+
"grad_norm": 23.84213538429929,
|
| 1260 |
+
"learning_rate": 7.196961434052796e-08,
|
| 1261 |
+
"loss": 0.8029,
|
| 1262 |
+
"num_input_tokens_seen": 10980576,
|
| 1263 |
+
"step": 705
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 1.9801047120418849,
|
| 1267 |
+
"grad_norm": 7.4190814811781145,
|
| 1268 |
+
"learning_rate": 2.1416057033352144e-08,
|
| 1269 |
+
"loss": 0.7942,
|
| 1270 |
+
"num_input_tokens_seen": 11058552,
|
| 1271 |
+
"step": 710
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 1.994066317626527,
|
| 1275 |
+
"grad_norm": 6.100028794501354,
|
| 1276 |
+
"learning_rate": 5.949317655462583e-10,
|
| 1277 |
+
"loss": 0.7964,
|
| 1278 |
+
"num_input_tokens_seen": 11136520,
|
| 1279 |
+
"step": 715
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 1.9968586387434555,
|
| 1283 |
+
"num_input_tokens_seen": 11152104,
|
| 1284 |
+
"step": 716,
|
| 1285 |
+
"total_flos": 754095660204032.0,
|
| 1286 |
+
"train_loss": 0.9049516569136241,
|
| 1287 |
+
"train_runtime": 17154.0309,
|
| 1288 |
+
"train_samples_per_second": 1.336,
|
| 1289 |
+
"train_steps_per_second": 0.042
|
| 1290 |
+
}
|
| 1291 |
+
],
|
| 1292 |
+
"logging_steps": 5,
|
| 1293 |
+
"max_steps": 716,
|
| 1294 |
+
"num_input_tokens_seen": 11152104,
|
| 1295 |
+
"num_train_epochs": 2,
|
| 1296 |
+
"save_steps": 50,
|
| 1297 |
+
"stateful_callbacks": {
|
| 1298 |
+
"TrainerControl": {
|
| 1299 |
+
"args": {
|
| 1300 |
+
"should_epoch_stop": false,
|
| 1301 |
+
"should_evaluate": false,
|
| 1302 |
+
"should_log": false,
|
| 1303 |
+
"should_save": true,
|
| 1304 |
+
"should_training_stop": true
|
| 1305 |
+
},
|
| 1306 |
+
"attributes": {}
|
| 1307 |
+
}
|
| 1308 |
+
},
|
| 1309 |
+
"total_flos": 754095660204032.0,
|
| 1310 |
+
"train_batch_size": 1,
|
| 1311 |
+
"trial_name": null,
|
| 1312 |
+
"trial_params": null
|
| 1313 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|