End of training
Browse files- README.md +3 -2
- all_results.json +12 -0
- eval_results.json +7 -0
- runs/May31_22-40-32_t9onywctr1717164743911-xnk6s/events.out.tfevents.1717232705.t9onywctr1717164743911-xnk6s.11369.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +1045 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -2,6 +2,7 @@
|
|
| 2 |
base_model: liswei/OpenELM-1_1B-zh-cp
|
| 3 |
tags:
|
| 4 |
- llama-factory
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
model-index:
|
| 7 |
- name: OpenELM-1_1B-zh-sft
|
|
@@ -13,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
# OpenELM-1_1B-zh-sft
|
| 15 |
|
| 16 |
-
This model is a fine-tuned version of [liswei/OpenELM-1_1B-zh-cp](https://huggingface.co/liswei/OpenELM-1_1B-zh-cp) on the
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
- Loss: 1.
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 2 |
base_model: liswei/OpenELM-1_1B-zh-cp
|
| 3 |
tags:
|
| 4 |
- llama-factory
|
| 5 |
+
- full
|
| 6 |
- generated_from_trainer
|
| 7 |
model-index:
|
| 8 |
- name: OpenELM-1_1B-zh-sft
|
|
|
|
| 14 |
|
| 15 |
# OpenELM-1_1B-zh-sft
|
| 16 |
|
| 17 |
+
This model is a fine-tuned version of [liswei/OpenELM-1_1B-zh-cp](https://huggingface.co/liswei/OpenELM-1_1B-zh-cp) on the en2tw-alignment-sft and the TaiwanChat datasets.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.3355
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9994709927702345,
|
| 3 |
+
"eval_loss": 1.3354638814926147,
|
| 4 |
+
"eval_runtime": 1576.9499,
|
| 5 |
+
"eval_samples_per_second": 38.356,
|
| 6 |
+
"eval_steps_per_second": 0.4,
|
| 7 |
+
"total_flos": 3.7897423231228314e+17,
|
| 8 |
+
"train_loss": 1.4671159325642071,
|
| 9 |
+
"train_runtime": 64163.8855,
|
| 10 |
+
"train_samples_per_second": 8.484,
|
| 11 |
+
"train_steps_per_second": 0.022
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9994709927702345,
|
| 3 |
+
"eval_loss": 1.3354638814926147,
|
| 4 |
+
"eval_runtime": 1576.9499,
|
| 5 |
+
"eval_samples_per_second": 38.356,
|
| 6 |
+
"eval_steps_per_second": 0.4
|
| 7 |
+
}
|
runs/May31_22-40-32_t9onywctr1717164743911-xnk6s/events.out.tfevents.1717232705.t9onywctr1717164743911-xnk6s.11369.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e97b95183e4b3130295361d76c5d9dd2c5f73bf8bff7afe0c8f1b655f62ce87
|
| 3 |
+
size 359
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9994709927702345,
|
| 3 |
+
"total_flos": 3.7897423231228314e+17,
|
| 4 |
+
"train_loss": 1.4671159325642071,
|
| 5 |
+
"train_runtime": 64163.8855,
|
| 6 |
+
"train_samples_per_second": 8.484,
|
| 7 |
+
"train_steps_per_second": 0.022
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1045 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9994709927702345,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1417,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.007053429730206313,
|
| 13 |
+
"grad_norm": 1.3042659759521484,
|
| 14 |
+
"learning_rate": 7.042253521126762e-06,
|
| 15 |
+
"loss": 2.258,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.014106859460412626,
|
| 20 |
+
"grad_norm": 0.738134503364563,
|
| 21 |
+
"learning_rate": 1.4084507042253523e-05,
|
| 22 |
+
"loss": 2.0805,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.02116028919061894,
|
| 27 |
+
"grad_norm": 0.5946909785270691,
|
| 28 |
+
"learning_rate": 2.112676056338028e-05,
|
| 29 |
+
"loss": 1.9582,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.02821371892082525,
|
| 34 |
+
"grad_norm": 0.5485147833824158,
|
| 35 |
+
"learning_rate": 2.8169014084507046e-05,
|
| 36 |
+
"loss": 1.9138,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.03526714865103157,
|
| 41 |
+
"grad_norm": 0.5394290089607239,
|
| 42 |
+
"learning_rate": 3.5211267605633805e-05,
|
| 43 |
+
"loss": 1.8736,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.04232057838123788,
|
| 48 |
+
"grad_norm": 0.49499747157096863,
|
| 49 |
+
"learning_rate": 4.225352112676056e-05,
|
| 50 |
+
"loss": 1.7826,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.04937400811144419,
|
| 55 |
+
"grad_norm": 0.48521119356155396,
|
| 56 |
+
"learning_rate": 4.929577464788733e-05,
|
| 57 |
+
"loss": 1.7868,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.0564274378416505,
|
| 62 |
+
"grad_norm": 0.5505830645561218,
|
| 63 |
+
"learning_rate": 5.633802816901409e-05,
|
| 64 |
+
"loss": 1.754,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.06348086757185682,
|
| 69 |
+
"grad_norm": 0.512299656867981,
|
| 70 |
+
"learning_rate": 6.338028169014085e-05,
|
| 71 |
+
"loss": 1.7356,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.07053429730206313,
|
| 76 |
+
"grad_norm": 0.47940096259117126,
|
| 77 |
+
"learning_rate": 7.042253521126761e-05,
|
| 78 |
+
"loss": 1.6952,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.07758772703226945,
|
| 83 |
+
"grad_norm": 0.48518213629722595,
|
| 84 |
+
"learning_rate": 7.746478873239437e-05,
|
| 85 |
+
"loss": 1.6853,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.08464115676247576,
|
| 90 |
+
"grad_norm": 0.5208117961883545,
|
| 91 |
+
"learning_rate": 8.450704225352113e-05,
|
| 92 |
+
"loss": 1.7022,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.09169458649268207,
|
| 97 |
+
"grad_norm": 0.5312570333480835,
|
| 98 |
+
"learning_rate": 9.15492957746479e-05,
|
| 99 |
+
"loss": 1.6371,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.09874801622288838,
|
| 104 |
+
"grad_norm": 0.5060498118400574,
|
| 105 |
+
"learning_rate": 9.859154929577466e-05,
|
| 106 |
+
"loss": 1.665,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.1058014459530947,
|
| 111 |
+
"grad_norm": 0.482503205537796,
|
| 112 |
+
"learning_rate": 9.999028628636837e-05,
|
| 113 |
+
"loss": 1.6445,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.112854875683301,
|
| 118 |
+
"grad_norm": 0.5026859045028687,
|
| 119 |
+
"learning_rate": 9.99508307932129e-05,
|
| 120 |
+
"loss": 1.6505,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.11990830541350732,
|
| 125 |
+
"grad_norm": 0.508380651473999,
|
| 126 |
+
"learning_rate": 9.988105034827552e-05,
|
| 127 |
+
"loss": 1.6513,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.12696173514371364,
|
| 132 |
+
"grad_norm": 0.4797461926937103,
|
| 133 |
+
"learning_rate": 9.978098731498833e-05,
|
| 134 |
+
"loss": 1.6382,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.13401516487391996,
|
| 139 |
+
"grad_norm": 0.5087615847587585,
|
| 140 |
+
"learning_rate": 9.965070244122301e-05,
|
| 141 |
+
"loss": 1.6464,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.14106859460412627,
|
| 146 |
+
"grad_norm": 0.4981568455696106,
|
| 147 |
+
"learning_rate": 9.949027482241107e-05,
|
| 148 |
+
"loss": 1.6105,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.14812202433433258,
|
| 153 |
+
"grad_norm": 0.4438849091529846,
|
| 154 |
+
"learning_rate": 9.929980185352526e-05,
|
| 155 |
+
"loss": 1.6194,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.1551754540645389,
|
| 160 |
+
"grad_norm": 0.5086779594421387,
|
| 161 |
+
"learning_rate": 9.907939916995152e-05,
|
| 162 |
+
"loss": 1.6073,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.1622288837947452,
|
| 167 |
+
"grad_norm": 0.5140203833580017,
|
| 168 |
+
"learning_rate": 9.88292005772872e-05,
|
| 169 |
+
"loss": 1.6031,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.16928231352495152,
|
| 174 |
+
"grad_norm": 0.5097965002059937,
|
| 175 |
+
"learning_rate": 9.854935797010821e-05,
|
| 176 |
+
"loss": 1.6216,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.17633574325515783,
|
| 181 |
+
"grad_norm": 0.5518028140068054,
|
| 182 |
+
"learning_rate": 9.824004123975435e-05,
|
| 183 |
+
"loss": 1.5585,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.18338917298536414,
|
| 188 |
+
"grad_norm": 0.48416197299957275,
|
| 189 |
+
"learning_rate": 9.790143817118904e-05,
|
| 190 |
+
"loss": 1.5739,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.19044260271557045,
|
| 195 |
+
"grad_norm": 0.4688737690448761,
|
| 196 |
+
"learning_rate": 9.753375432899581e-05,
|
| 197 |
+
"loss": 1.571,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.19749603244577676,
|
| 202 |
+
"grad_norm": 0.4657231569290161,
|
| 203 |
+
"learning_rate": 9.713721293258078e-05,
|
| 204 |
+
"loss": 1.5614,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.20454946217598308,
|
| 209 |
+
"grad_norm": 0.47847288846969604,
|
| 210 |
+
"learning_rate": 9.671205472065707e-05,
|
| 211 |
+
"loss": 1.5474,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.2116028919061894,
|
| 216 |
+
"grad_norm": 0.5418571829795837,
|
| 217 |
+
"learning_rate": 9.625853780509335e-05,
|
| 218 |
+
"loss": 1.5562,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.2186563216363957,
|
| 223 |
+
"grad_norm": 0.5494666695594788,
|
| 224 |
+
"learning_rate": 9.577693751421506e-05,
|
| 225 |
+
"loss": 1.5585,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.225709751366602,
|
| 230 |
+
"grad_norm": 0.5272155404090881,
|
| 231 |
+
"learning_rate": 9.52675462256537e-05,
|
| 232 |
+
"loss": 1.546,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.23276318109680832,
|
| 237 |
+
"grad_norm": 0.5072800517082214,
|
| 238 |
+
"learning_rate": 9.473067318884552e-05,
|
| 239 |
+
"loss": 1.5395,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.23981661082701464,
|
| 244 |
+
"grad_norm": 0.48417559266090393,
|
| 245 |
+
"learning_rate": 9.416664433728748e-05,
|
| 246 |
+
"loss": 1.5342,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.24687004055722095,
|
| 251 |
+
"grad_norm": 0.49016687273979187,
|
| 252 |
+
"learning_rate": 9.357580209066416e-05,
|
| 253 |
+
"loss": 1.5155,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.2539234702874273,
|
| 258 |
+
"grad_norm": 0.48039939999580383,
|
| 259 |
+
"learning_rate": 9.295850514696628e-05,
|
| 260 |
+
"loss": 1.5194,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.2609769000176336,
|
| 265 |
+
"grad_norm": 0.4710429906845093,
|
| 266 |
+
"learning_rate": 9.23151282647265e-05,
|
| 267 |
+
"loss": 1.4984,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.2680303297478399,
|
| 272 |
+
"grad_norm": 0.46802473068237305,
|
| 273 |
+
"learning_rate": 9.164606203550497e-05,
|
| 274 |
+
"loss": 1.5316,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.2750837594780462,
|
| 279 |
+
"grad_norm": 0.46727123856544495,
|
| 280 |
+
"learning_rate": 9.095171264676283e-05,
|
| 281 |
+
"loss": 1.5478,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.28213718920825254,
|
| 286 |
+
"grad_norm": 0.4999746084213257,
|
| 287 |
+
"learning_rate": 9.023250163526731e-05,
|
| 288 |
+
"loss": 1.5335,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.2891906189384588,
|
| 293 |
+
"grad_norm": 0.4812432825565338,
|
| 294 |
+
"learning_rate": 8.948886563117844e-05,
|
| 295 |
+
"loss": 1.5063,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.29624404866866516,
|
| 300 |
+
"grad_norm": 0.48060664534568787,
|
| 301 |
+
"learning_rate": 8.872125609297271e-05,
|
| 302 |
+
"loss": 1.5039,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.30329747839887145,
|
| 307 |
+
"grad_norm": 0.4972708523273468,
|
| 308 |
+
"learning_rate": 8.793013903336428e-05,
|
| 309 |
+
"loss": 1.5414,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.3103509081290778,
|
| 314 |
+
"grad_norm": 0.4610942006111145,
|
| 315 |
+
"learning_rate": 8.711599473639058e-05,
|
| 316 |
+
"loss": 1.4808,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.31740433785928407,
|
| 321 |
+
"grad_norm": 0.45125675201416016,
|
| 322 |
+
"learning_rate": 8.627931746583378e-05,
|
| 323 |
+
"loss": 1.5097,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.3244577675894904,
|
| 328 |
+
"grad_norm": 0.46617043018341064,
|
| 329 |
+
"learning_rate": 8.542061516515512e-05,
|
| 330 |
+
"loss": 1.4708,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.3315111973196967,
|
| 335 |
+
"grad_norm": 0.5127195119857788,
|
| 336 |
+
"learning_rate": 8.454040914912456e-05,
|
| 337 |
+
"loss": 1.4894,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.33856462704990303,
|
| 342 |
+
"grad_norm": 0.45094090700149536,
|
| 343 |
+
"learning_rate": 8.363923378733255e-05,
|
| 344 |
+
"loss": 1.4554,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.3456180567801093,
|
| 349 |
+
"grad_norm": 0.48269587755203247,
|
| 350 |
+
"learning_rate": 8.271763617977641e-05,
|
| 351 |
+
"loss": 1.4732,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.35267148651031566,
|
| 356 |
+
"grad_norm": 0.4571676552295685,
|
| 357 |
+
"learning_rate": 8.177617582471813e-05,
|
| 358 |
+
"loss": 1.4543,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.35267148651031566,
|
| 363 |
+
"eval_loss": 1.4671958684921265,
|
| 364 |
+
"eval_runtime": 1577.1702,
|
| 365 |
+
"eval_samples_per_second": 38.35,
|
| 366 |
+
"eval_steps_per_second": 0.4,
|
| 367 |
+
"step": 500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.35972491624052194,
|
| 371 |
+
"grad_norm": 0.4831838011741638,
|
| 372 |
+
"learning_rate": 8.081542427901503e-05,
|
| 373 |
+
"loss": 1.4805,
|
| 374 |
+
"step": 510
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.3667783459707283,
|
| 378 |
+
"grad_norm": 0.47973912954330444,
|
| 379 |
+
"learning_rate": 7.983596481113005e-05,
|
| 380 |
+
"loss": 1.4767,
|
| 381 |
+
"step": 520
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.37383177570093457,
|
| 385 |
+
"grad_norm": 0.4587724208831787,
|
| 386 |
+
"learning_rate": 7.883839204703165e-05,
|
| 387 |
+
"loss": 1.4783,
|
| 388 |
+
"step": 530
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.3808852054311409,
|
| 392 |
+
"grad_norm": 0.48470768332481384,
|
| 393 |
+
"learning_rate": 7.782331160919877e-05,
|
| 394 |
+
"loss": 1.4691,
|
| 395 |
+
"step": 540
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.3879386351613472,
|
| 399 |
+
"grad_norm": 0.4692317247390747,
|
| 400 |
+
"learning_rate": 7.679133974894983e-05,
|
| 401 |
+
"loss": 1.4651,
|
| 402 |
+
"step": 550
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.39499206489155353,
|
| 406 |
+
"grad_norm": 0.5106418132781982,
|
| 407 |
+
"learning_rate": 7.574310297231897e-05,
|
| 408 |
+
"loss": 1.4651,
|
| 409 |
+
"step": 560
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.4020454946217598,
|
| 413 |
+
"grad_norm": 0.4444584250450134,
|
| 414 |
+
"learning_rate": 7.46792376597067e-05,
|
| 415 |
+
"loss": 1.459,
|
| 416 |
+
"step": 570
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.40909892435196615,
|
| 420 |
+
"grad_norm": 0.44441869854927063,
|
| 421 |
+
"learning_rate": 7.360038967953598e-05,
|
| 422 |
+
"loss": 1.466,
|
| 423 |
+
"step": 580
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.41615235408217244,
|
| 427 |
+
"grad_norm": 0.4592408537864685,
|
| 428 |
+
"learning_rate": 7.250721399614786e-05,
|
| 429 |
+
"loss": 1.4527,
|
| 430 |
+
"step": 590
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.4232057838123788,
|
| 434 |
+
"grad_norm": 0.48659372329711914,
|
| 435 |
+
"learning_rate": 7.140037427217545e-05,
|
| 436 |
+
"loss": 1.4409,
|
| 437 |
+
"step": 600
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.43025921354258506,
|
| 441 |
+
"grad_norm": 0.49556177854537964,
|
| 442 |
+
"learning_rate": 7.02805424656368e-05,
|
| 443 |
+
"loss": 1.4378,
|
| 444 |
+
"step": 610
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.4373126432727914,
|
| 448 |
+
"grad_norm": 0.4970695674419403,
|
| 449 |
+
"learning_rate": 6.914839842199187e-05,
|
| 450 |
+
"loss": 1.4209,
|
| 451 |
+
"step": 620
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.4443660730029977,
|
| 455 |
+
"grad_norm": 0.4574239253997803,
|
| 456 |
+
"learning_rate": 6.800462946141109e-05,
|
| 457 |
+
"loss": 1.4215,
|
| 458 |
+
"step": 630
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.451419502733204,
|
| 462 |
+
"grad_norm": 0.44600942730903625,
|
| 463 |
+
"learning_rate": 6.684992996150599e-05,
|
| 464 |
+
"loss": 1.4481,
|
| 465 |
+
"step": 640
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.4584729324634103,
|
| 469 |
+
"grad_norm": 0.4874365031719208,
|
| 470 |
+
"learning_rate": 6.568500093577525e-05,
|
| 471 |
+
"loss": 1.4357,
|
| 472 |
+
"step": 650
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.46552636219361665,
|
| 476 |
+
"grad_norm": 0.44276514649391174,
|
| 477 |
+
"learning_rate": 6.451054960802224e-05,
|
| 478 |
+
"loss": 1.4229,
|
| 479 |
+
"step": 660
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.47257979192382293,
|
| 483 |
+
"grad_norm": 0.4567689895629883,
|
| 484 |
+
"learning_rate": 6.332728898300221e-05,
|
| 485 |
+
"loss": 1.3891,
|
| 486 |
+
"step": 670
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.4796332216540293,
|
| 490 |
+
"grad_norm": 0.4700818359851837,
|
| 491 |
+
"learning_rate": 6.213593741355993e-05,
|
| 492 |
+
"loss": 1.3942,
|
| 493 |
+
"step": 680
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.48668665138423556,
|
| 497 |
+
"grad_norm": 0.510308027267456,
|
| 498 |
+
"learning_rate": 6.093721816452052e-05,
|
| 499 |
+
"loss": 1.4321,
|
| 500 |
+
"step": 690
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.4937400811144419,
|
| 504 |
+
"grad_norm": 0.4537096321582794,
|
| 505 |
+
"learning_rate": 5.973185897359828e-05,
|
| 506 |
+
"loss": 1.4058,
|
| 507 |
+
"step": 700
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.5007935108446482,
|
| 511 |
+
"grad_norm": 0.46621763706207275,
|
| 512 |
+
"learning_rate": 5.852059160958988e-05,
|
| 513 |
+
"loss": 1.4264,
|
| 514 |
+
"step": 710
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.5078469405748546,
|
| 518 |
+
"grad_norm": 0.4476553201675415,
|
| 519 |
+
"learning_rate": 5.730415142812059e-05,
|
| 520 |
+
"loss": 1.3943,
|
| 521 |
+
"step": 720
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.5149003703050609,
|
| 525 |
+
"grad_norm": 0.4877742528915405,
|
| 526 |
+
"learning_rate": 5.6083276925212624e-05,
|
| 527 |
+
"loss": 1.4114,
|
| 528 |
+
"step": 730
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.5219538000352671,
|
| 532 |
+
"grad_norm": 0.4259643256664276,
|
| 533 |
+
"learning_rate": 5.485870928894725e-05,
|
| 534 |
+
"loss": 1.3905,
|
| 535 |
+
"step": 740
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.5290072297654734,
|
| 539 |
+
"grad_norm": 0.4499744772911072,
|
| 540 |
+
"learning_rate": 5.3631191949492354e-05,
|
| 541 |
+
"loss": 1.3973,
|
| 542 |
+
"step": 750
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.5360606594956798,
|
| 546 |
+
"grad_norm": 0.45207515358924866,
|
| 547 |
+
"learning_rate": 5.240147012776899e-05,
|
| 548 |
+
"loss": 1.3957,
|
| 549 |
+
"step": 760
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.5431140892258861,
|
| 553 |
+
"grad_norm": 0.4296036958694458,
|
| 554 |
+
"learning_rate": 5.117029038303065e-05,
|
| 555 |
+
"loss": 1.4023,
|
| 556 |
+
"step": 770
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.5501675189560924,
|
| 560 |
+
"grad_norm": 0.4590493142604828,
|
| 561 |
+
"learning_rate": 4.993840015963016e-05,
|
| 562 |
+
"loss": 1.414,
|
| 563 |
+
"step": 780
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.5572209486862987,
|
| 567 |
+
"grad_norm": 0.4364815652370453,
|
| 568 |
+
"learning_rate": 4.870654733324907e-05,
|
| 569 |
+
"loss": 1.3939,
|
| 570 |
+
"step": 790
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.5642743784165051,
|
| 574 |
+
"grad_norm": 0.4730934798717499,
|
| 575 |
+
"learning_rate": 4.747547975686538e-05,
|
| 576 |
+
"loss": 1.3951,
|
| 577 |
+
"step": 800
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.5713278081467114,
|
| 581 |
+
"grad_norm": 0.4653618037700653,
|
| 582 |
+
"learning_rate": 4.6245944806734966e-05,
|
| 583 |
+
"loss": 1.3919,
|
| 584 |
+
"step": 810
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.5783812378769176,
|
| 588 |
+
"grad_norm": 0.44776442646980286,
|
| 589 |
+
"learning_rate": 4.50186889286623e-05,
|
| 590 |
+
"loss": 1.401,
|
| 591 |
+
"step": 820
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.5854346676071239,
|
| 595 |
+
"grad_norm": 0.47814151644706726,
|
| 596 |
+
"learning_rate": 4.379445718483626e-05,
|
| 597 |
+
"loss": 1.4014,
|
| 598 |
+
"step": 830
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.5924880973373303,
|
| 602 |
+
"grad_norm": 0.4623441994190216,
|
| 603 |
+
"learning_rate": 4.257399280150576e-05,
|
| 604 |
+
"loss": 1.4101,
|
| 605 |
+
"step": 840
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.5995415270675366,
|
| 609 |
+
"grad_norm": 0.47123944759368896,
|
| 610 |
+
"learning_rate": 4.135803671777011e-05,
|
| 611 |
+
"loss": 1.3687,
|
| 612 |
+
"step": 850
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.6065949567977429,
|
| 616 |
+
"grad_norm": 0.4534803628921509,
|
| 617 |
+
"learning_rate": 4.014732713575769e-05,
|
| 618 |
+
"loss": 1.3675,
|
| 619 |
+
"step": 860
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.6136483865279492,
|
| 623 |
+
"grad_norm": 0.4451278746128082,
|
| 624 |
+
"learning_rate": 3.894259907246652e-05,
|
| 625 |
+
"loss": 1.3705,
|
| 626 |
+
"step": 870
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.6207018162581556,
|
| 630 |
+
"grad_norm": 0.40993040800094604,
|
| 631 |
+
"learning_rate": 3.774458391353821e-05,
|
| 632 |
+
"loss": 1.3944,
|
| 633 |
+
"step": 880
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.6277552459883619,
|
| 637 |
+
"grad_norm": 0.43390119075775146,
|
| 638 |
+
"learning_rate": 3.655400896923672e-05,
|
| 639 |
+
"loss": 1.3898,
|
| 640 |
+
"step": 890
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.6348086757185681,
|
| 644 |
+
"grad_norm": 0.469901442527771,
|
| 645 |
+
"learning_rate": 3.537159703290112e-05,
|
| 646 |
+
"loss": 1.3975,
|
| 647 |
+
"step": 900
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.6418621054487744,
|
| 651 |
+
"grad_norm": 0.4519672989845276,
|
| 652 |
+
"learning_rate": 3.419806594214063e-05,
|
| 653 |
+
"loss": 1.3705,
|
| 654 |
+
"step": 910
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.6489155351789808,
|
| 658 |
+
"grad_norm": 0.44010812044143677,
|
| 659 |
+
"learning_rate": 3.303412814303827e-05,
|
| 660 |
+
"loss": 1.3673,
|
| 661 |
+
"step": 920
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.6559689649091871,
|
| 665 |
+
"grad_norm": 0.45562589168548584,
|
| 666 |
+
"learning_rate": 3.1880490257627646e-05,
|
| 667 |
+
"loss": 1.3754,
|
| 668 |
+
"step": 930
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.6630223946393934,
|
| 672 |
+
"grad_norm": 0.4654683768749237,
|
| 673 |
+
"learning_rate": 3.0737852654905497e-05,
|
| 674 |
+
"loss": 1.3809,
|
| 675 |
+
"step": 940
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.6700758243695997,
|
| 679 |
+
"grad_norm": 0.40361422300338745,
|
| 680 |
+
"learning_rate": 2.960690902564044e-05,
|
| 681 |
+
"loss": 1.3432,
|
| 682 |
+
"step": 950
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.6771292540998061,
|
| 686 |
+
"grad_norm": 0.45382988452911377,
|
| 687 |
+
"learning_rate": 2.8488345961236075e-05,
|
| 688 |
+
"loss": 1.3686,
|
| 689 |
+
"step": 960
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.6841826838300124,
|
| 693 |
+
"grad_norm": 0.4258984327316284,
|
| 694 |
+
"learning_rate": 2.7382842536904075e-05,
|
| 695 |
+
"loss": 1.3755,
|
| 696 |
+
"step": 970
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.6912361135602186,
|
| 700 |
+
"grad_norm": 0.5345839858055115,
|
| 701 |
+
"learning_rate": 2.629106989940025e-05,
|
| 702 |
+
"loss": 1.3793,
|
| 703 |
+
"step": 980
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.6982895432904249,
|
| 707 |
+
"grad_norm": 0.42425984144210815,
|
| 708 |
+
"learning_rate": 2.5213690859574058e-05,
|
| 709 |
+
"loss": 1.3385,
|
| 710 |
+
"step": 990
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.7053429730206313,
|
| 714 |
+
"grad_norm": 0.43758624792099,
|
| 715 |
+
"learning_rate": 2.4151359489978733e-05,
|
| 716 |
+
"loss": 1.3683,
|
| 717 |
+
"step": 1000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.7053429730206313,
|
| 721 |
+
"eval_loss": 1.3570424318313599,
|
| 722 |
+
"eval_runtime": 1575.8807,
|
| 723 |
+
"eval_samples_per_second": 38.382,
|
| 724 |
+
"eval_steps_per_second": 0.4,
|
| 725 |
+
"step": 1000
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.7123964027508376,
|
| 729 |
+
"grad_norm": 0.4325385093688965,
|
| 730 |
+
"learning_rate": 2.3104720727786467e-05,
|
| 731 |
+
"loss": 1.3411,
|
| 732 |
+
"step": 1010
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.7194498324810439,
|
| 736 |
+
"grad_norm": 0.41445136070251465,
|
| 737 |
+
"learning_rate": 2.2074409983249545e-05,
|
| 738 |
+
"loss": 1.3495,
|
| 739 |
+
"step": 1020
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 0.7265032622112502,
|
| 743 |
+
"grad_norm": 0.4271891415119171,
|
| 744 |
+
"learning_rate": 2.106105275394533e-05,
|
| 745 |
+
"loss": 1.3505,
|
| 746 |
+
"step": 1030
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.7335566919414566,
|
| 750 |
+
"grad_norm": 0.4772493243217468,
|
| 751 |
+
"learning_rate": 2.0065264245039128e-05,
|
| 752 |
+
"loss": 1.317,
|
| 753 |
+
"step": 1040
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.7406101216716628,
|
| 757 |
+
"grad_norm": 0.43762919306755066,
|
| 758 |
+
"learning_rate": 1.9087648995795658e-05,
|
| 759 |
+
"loss": 1.349,
|
| 760 |
+
"step": 1050
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 0.7476635514018691,
|
| 764 |
+
"grad_norm": 0.4569909870624542,
|
| 765 |
+
"learning_rate": 1.8128800512565513e-05,
|
| 766 |
+
"loss": 1.3473,
|
| 767 |
+
"step": 1060
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 0.7547169811320755,
|
| 771 |
+
"grad_norm": 0.4433094561100006,
|
| 772 |
+
"learning_rate": 1.7189300908469912e-05,
|
| 773 |
+
"loss": 1.3386,
|
| 774 |
+
"step": 1070
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.7617704108622818,
|
| 778 |
+
"grad_norm": 0.48191553354263306,
|
| 779 |
+
"learning_rate": 1.6269720550002077e-05,
|
| 780 |
+
"loss": 1.3765,
|
| 781 |
+
"step": 1080
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 0.7688238405924881,
|
| 785 |
+
"grad_norm": 0.40601858496665955,
|
| 786 |
+
"learning_rate": 1.5370617710760004e-05,
|
| 787 |
+
"loss": 1.3354,
|
| 788 |
+
"step": 1090
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.7758772703226944,
|
| 792 |
+
"grad_norm": 0.43439218401908875,
|
| 793 |
+
"learning_rate": 1.4492538232520791e-05,
|
| 794 |
+
"loss": 1.3404,
|
| 795 |
+
"step": 1100
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.7829307000529008,
|
| 799 |
+
"grad_norm": 0.47002339363098145,
|
| 800 |
+
"learning_rate": 1.3636015193862212e-05,
|
| 801 |
+
"loss": 1.3562,
|
| 802 |
+
"step": 1110
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 0.7899841297831071,
|
| 806 |
+
"grad_norm": 0.44879859685897827,
|
| 807 |
+
"learning_rate": 1.2801568586532837e-05,
|
| 808 |
+
"loss": 1.3652,
|
| 809 |
+
"step": 1120
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 0.7970375595133133,
|
| 813 |
+
"grad_norm": 0.44707298278808594,
|
| 814 |
+
"learning_rate": 1.1989704999767149e-05,
|
| 815 |
+
"loss": 1.3332,
|
| 816 |
+
"step": 1130
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 0.8040909892435196,
|
| 820 |
+
"grad_norm": 0.45202744007110596,
|
| 821 |
+
"learning_rate": 1.1200917312737135e-05,
|
| 822 |
+
"loss": 1.3488,
|
| 823 |
+
"step": 1140
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 0.811144418973726,
|
| 827 |
+
"grad_norm": 0.4314928650856018,
|
| 828 |
+
"learning_rate": 1.043568439532735e-05,
|
| 829 |
+
"loss": 1.3592,
|
| 830 |
+
"step": 1150
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.8181978487039323,
|
| 834 |
+
"grad_norm": 0.47974613308906555,
|
| 835 |
+
"learning_rate": 9.69447081741487e-06,
|
| 836 |
+
"loss": 1.3273,
|
| 837 |
+
"step": 1160
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.8252512784341386,
|
| 841 |
+
"grad_norm": 0.49341320991516113,
|
| 842 |
+
"learning_rate": 8.97772656683083e-06,
|
| 843 |
+
"loss": 1.3495,
|
| 844 |
+
"step": 1170
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 0.8323047081643449,
|
| 848 |
+
"grad_norm": 0.45349812507629395,
|
| 849 |
+
"learning_rate": 8.2858867761745e-06,
|
| 850 |
+
"loss": 1.3349,
|
| 851 |
+
"step": 1180
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 0.8393581378945513,
|
| 855 |
+
"grad_norm": 0.4800957143306732,
|
| 856 |
+
"learning_rate": 7.619371458646007e-06,
|
| 857 |
+
"loss": 1.3282,
|
| 858 |
+
"step": 1190
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 0.8464115676247576,
|
| 862 |
+
"grad_norm": 0.41283947229385376,
|
| 863 |
+
"learning_rate": 6.978585253058101e-06,
|
| 864 |
+
"loss": 1.3289,
|
| 865 |
+
"step": 1200
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 0.8534649973549638,
|
| 869 |
+
"grad_norm": 0.3885229825973511,
|
| 870 |
+
"learning_rate": 6.363917178181389e-06,
|
| 871 |
+
"loss": 1.3251,
|
| 872 |
+
"step": 1210
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 0.8605184270851701,
|
| 876 |
+
"grad_norm": 0.3919270634651184,
|
| 877 |
+
"learning_rate": 5.7757403965726655e-06,
|
| 878 |
+
"loss": 1.3552,
|
| 879 |
+
"step": 1220
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.8675718568153765,
|
| 883 |
+
"grad_norm": 0.4169398546218872,
|
| 884 |
+
"learning_rate": 5.214411988029355e-06,
|
| 885 |
+
"loss": 1.332,
|
| 886 |
+
"step": 1230
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 0.8746252865455828,
|
| 890 |
+
"grad_norm": 0.4624149799346924,
|
| 891 |
+
"learning_rate": 4.680272732807834e-06,
|
| 892 |
+
"loss": 1.3261,
|
| 893 |
+
"step": 1240
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 0.8816787162757891,
|
| 897 |
+
"grad_norm": 0.404799222946167,
|
| 898 |
+
"learning_rate": 4.173646904737027e-06,
|
| 899 |
+
"loss": 1.3352,
|
| 900 |
+
"step": 1250
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 0.8887321460059954,
|
| 904 |
+
"grad_norm": 0.45688724517822266,
|
| 905 |
+
"learning_rate": 3.694842074353061e-06,
|
| 906 |
+
"loss": 1.3586,
|
| 907 |
+
"step": 1260
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 0.8957855757362018,
|
| 911 |
+
"grad_norm": 0.42276087403297424,
|
| 912 |
+
"learning_rate": 3.244148922174445e-06,
|
| 913 |
+
"loss": 1.3653,
|
| 914 |
+
"step": 1270
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 0.902839005466408,
|
| 918 |
+
"grad_norm": 0.446267306804657,
|
| 919 |
+
"learning_rate": 2.8218410622310286e-06,
|
| 920 |
+
"loss": 1.3674,
|
| 921 |
+
"step": 1280
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.9098924351966143,
|
| 925 |
+
"grad_norm": 0.48505640029907227,
|
| 926 |
+
"learning_rate": 2.4281748759540534e-06,
|
| 927 |
+
"loss": 1.3289,
|
| 928 |
+
"step": 1290
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 0.9169458649268206,
|
| 932 |
+
"grad_norm": 0.43678343296051025,
|
| 933 |
+
"learning_rate": 2.0633893565279615e-06,
|
| 934 |
+
"loss": 1.3405,
|
| 935 |
+
"step": 1300
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 0.923999294657027,
|
| 939 |
+
"grad_norm": 0.4217219650745392,
|
| 940 |
+
"learning_rate": 1.7277059637985925e-06,
|
| 941 |
+
"loss": 1.3356,
|
| 942 |
+
"step": 1310
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 0.9310527243872333,
|
| 946 |
+
"grad_norm": 0.40834924578666687,
|
| 947 |
+
"learning_rate": 1.4213284898258073e-06,
|
| 948 |
+
"loss": 1.3514,
|
| 949 |
+
"step": 1320
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 0.9381061541174396,
|
| 953 |
+
"grad_norm": 0.43623679876327515,
|
| 954 |
+
"learning_rate": 1.1444429351620933e-06,
|
| 955 |
+
"loss": 1.3239,
|
| 956 |
+
"step": 1330
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 0.9451595838476459,
|
| 960 |
+
"grad_norm": 0.3971399664878845,
|
| 961 |
+
"learning_rate": 8.972173959324093e-07,
|
| 962 |
+
"loss": 1.3358,
|
| 963 |
+
"step": 1340
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 0.9522130135778523,
|
| 967 |
+
"grad_norm": 0.42954108119010925,
|
| 968 |
+
"learning_rate": 6.798019617836437e-07,
|
| 969 |
+
"loss": 1.336,
|
| 970 |
+
"step": 1350
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 0.9592664433080585,
|
| 974 |
+
"grad_norm": 0.43156835436820984,
|
| 975 |
+
"learning_rate": 4.923286247658476e-07,
|
| 976 |
+
"loss": 1.3414,
|
| 977 |
+
"step": 1360
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 0.9663198730382648,
|
| 981 |
+
"grad_norm": 0.43554648756980896,
|
| 982 |
+
"learning_rate": 3.349111992003218e-07,
|
| 983 |
+
"loss": 1.3395,
|
| 984 |
+
"step": 1370
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 0.9733733027684711,
|
| 988 |
+
"grad_norm": 0.44990482926368713,
|
| 989 |
+
"learning_rate": 2.0764525258341606e-07,
|
| 990 |
+
"loss": 1.3522,
|
| 991 |
+
"step": 1380
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 0.9804267324986775,
|
| 995 |
+
"grad_norm": 0.46251362562179565,
|
| 996 |
+
"learning_rate": 1.1060804756790055e-07,
|
| 997 |
+
"loss": 1.3422,
|
| 998 |
+
"step": 1390
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 0.9874801622288838,
|
| 1002 |
+
"grad_norm": 0.4148382842540741,
|
| 1003 |
+
"learning_rate": 4.385849505708084e-08,
|
| 1004 |
+
"loss": 1.336,
|
| 1005 |
+
"step": 1400
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 0.9945335919590901,
|
| 1009 |
+
"grad_norm": 0.39327695965766907,
|
| 1010 |
+
"learning_rate": 7.437118440245528e-09,
|
| 1011 |
+
"loss": 1.367,
|
| 1012 |
+
"step": 1410
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 0.9994709927702345,
|
| 1016 |
+
"step": 1417,
|
| 1017 |
+
"total_flos": 3.7897423231228314e+17,
|
| 1018 |
+
"train_loss": 1.4671159325642071,
|
| 1019 |
+
"train_runtime": 64163.8855,
|
| 1020 |
+
"train_samples_per_second": 8.484,
|
| 1021 |
+
"train_steps_per_second": 0.022
|
| 1022 |
+
}
|
| 1023 |
+
],
|
| 1024 |
+
"logging_steps": 10,
|
| 1025 |
+
"max_steps": 1417,
|
| 1026 |
+
"num_input_tokens_seen": 0,
|
| 1027 |
+
"num_train_epochs": 1,
|
| 1028 |
+
"save_steps": 4000,
|
| 1029 |
+
"stateful_callbacks": {
|
| 1030 |
+
"TrainerControl": {
|
| 1031 |
+
"args": {
|
| 1032 |
+
"should_epoch_stop": false,
|
| 1033 |
+
"should_evaluate": false,
|
| 1034 |
+
"should_log": false,
|
| 1035 |
+
"should_save": false,
|
| 1036 |
+
"should_training_stop": false
|
| 1037 |
+
},
|
| 1038 |
+
"attributes": {}
|
| 1039 |
+
}
|
| 1040 |
+
},
|
| 1041 |
+
"total_flos": 3.7897423231228314e+17,
|
| 1042 |
+
"train_batch_size": 12,
|
| 1043 |
+
"trial_name": null,
|
| 1044 |
+
"trial_params": null
|
| 1045 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|