End of training
Browse files- README.md +3 -3
- all_results.json +13 -0
- eval_results.json +8 -0
- runs/Dec11_13-06-33_c3e1296b588a/events.out.tfevents.1733924630.c3e1296b588a.292864.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +1071 -0
README.md
CHANGED
|
@@ -23,7 +23,7 @@ model-index:
|
|
| 23 |
metrics:
|
| 24 |
- name: Accuracy
|
| 25 |
type: accuracy
|
| 26 |
-
value: 0.
|
| 27 |
---
|
| 28 |
|
| 29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -33,8 +33,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 33 |
|
| 34 |
This model is a fine-tuned version of [facebook/vit-msn-base](https://huggingface.co/facebook/vit-msn-base) on the imagefolder dataset.
|
| 35 |
It achieves the following results on the evaluation set:
|
| 36 |
-
- Loss: 0.
|
| 37 |
-
- Accuracy: 0.
|
| 38 |
|
| 39 |
## Model description
|
| 40 |
|
|
|
|
| 23 |
metrics:
|
| 24 |
- name: Accuracy
|
| 25 |
type: accuracy
|
| 26 |
+
value: 0.9234042553191489
|
| 27 |
---
|
| 28 |
|
| 29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 33 |
|
| 34 |
This model is a fine-tuned version of [facebook/vit-msn-base](https://huggingface.co/facebook/vit-msn-base) on the imagefolder dataset.
|
| 35 |
It achieves the following results on the evaluation set:
|
| 36 |
+
- Loss: 0.2414
|
| 37 |
+
- Accuracy: 0.9234
|
| 38 |
|
| 39 |
## Model description
|
| 40 |
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 76.8,
|
| 3 |
+
"eval_accuracy": 0.9234042553191489,
|
| 4 |
+
"eval_loss": 0.24138842523097992,
|
| 5 |
+
"eval_runtime": 4.1974,
|
| 6 |
+
"eval_samples_per_second": 111.975,
|
| 7 |
+
"eval_steps_per_second": 3.574,
|
| 8 |
+
"total_flos": 4.5903154968099717e+18,
|
| 9 |
+
"train_loss": 0.19423907659947873,
|
| 10 |
+
"train_runtime": 1687.359,
|
| 11 |
+
"train_samples_per_second": 36.554,
|
| 12 |
+
"train_steps_per_second": 0.284
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 76.8,
|
| 3 |
+
"eval_accuracy": 0.9234042553191489,
|
| 4 |
+
"eval_loss": 0.24138842523097992,
|
| 5 |
+
"eval_runtime": 4.1974,
|
| 6 |
+
"eval_samples_per_second": 111.975,
|
| 7 |
+
"eval_steps_per_second": 3.574
|
| 8 |
+
}
|
runs/Dec11_13-06-33_c3e1296b588a/events.out.tfevents.1733924630.c3e1296b588a.292864.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:374fd6200b40c7636a17200d0aa24cba92819919e5243b7045e0b084f8c73f82
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 76.8,
|
| 3 |
+
"total_flos": 4.5903154968099717e+18,
|
| 4 |
+
"train_loss": 0.19423907659947873,
|
| 5 |
+
"train_runtime": 1687.359,
|
| 6 |
+
"train_samples_per_second": 36.554,
|
| 7 |
+
"train_steps_per_second": 0.284
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1071 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9234042553191489,
|
| 3 |
+
"best_model_checkpoint": "vit-msn-base-finetuned-lf-invalidation/checkpoint-62",
|
| 4 |
+
"epoch": 76.8,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 480,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.96,
|
| 13 |
+
"eval_accuracy": 0.6957446808510638,
|
| 14 |
+
"eval_loss": 0.6511951088905334,
|
| 15 |
+
"eval_runtime": 4.1128,
|
| 16 |
+
"eval_samples_per_second": 114.277,
|
| 17 |
+
"eval_steps_per_second": 3.647,
|
| 18 |
+
"step": 6
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 1.6,
|
| 22 |
+
"grad_norm": 100.99421691894531,
|
| 23 |
+
"learning_rate": 1.0416666666666668e-05,
|
| 24 |
+
"loss": 0.7053,
|
| 25 |
+
"step": 10
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 1.92,
|
| 29 |
+
"eval_accuracy": 0.6808510638297872,
|
| 30 |
+
"eval_loss": 0.6310930848121643,
|
| 31 |
+
"eval_runtime": 4.1662,
|
| 32 |
+
"eval_samples_per_second": 112.813,
|
| 33 |
+
"eval_steps_per_second": 3.6,
|
| 34 |
+
"step": 12
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 2.88,
|
| 38 |
+
"eval_accuracy": 0.7276595744680852,
|
| 39 |
+
"eval_loss": 0.5360996127128601,
|
| 40 |
+
"eval_runtime": 4.0581,
|
| 41 |
+
"eval_samples_per_second": 115.819,
|
| 42 |
+
"eval_steps_per_second": 3.696,
|
| 43 |
+
"step": 18
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 3.2,
|
| 47 |
+
"grad_norm": 14.486075401306152,
|
| 48 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 49 |
+
"loss": 0.5163,
|
| 50 |
+
"step": 20
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 4.0,
|
| 54 |
+
"eval_accuracy": 0.8680851063829788,
|
| 55 |
+
"eval_loss": 0.3341110050678253,
|
| 56 |
+
"eval_runtime": 3.919,
|
| 57 |
+
"eval_samples_per_second": 119.928,
|
| 58 |
+
"eval_steps_per_second": 3.827,
|
| 59 |
+
"step": 25
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 4.8,
|
| 63 |
+
"grad_norm": 19.806690216064453,
|
| 64 |
+
"learning_rate": 3.125e-05,
|
| 65 |
+
"loss": 0.3242,
|
| 66 |
+
"step": 30
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 4.96,
|
| 70 |
+
"eval_accuracy": 0.8808510638297873,
|
| 71 |
+
"eval_loss": 0.3167176842689514,
|
| 72 |
+
"eval_runtime": 3.8854,
|
| 73 |
+
"eval_samples_per_second": 120.965,
|
| 74 |
+
"eval_steps_per_second": 3.861,
|
| 75 |
+
"step": 31
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 5.92,
|
| 79 |
+
"eval_accuracy": 0.8191489361702128,
|
| 80 |
+
"eval_loss": 0.39598795771598816,
|
| 81 |
+
"eval_runtime": 4.17,
|
| 82 |
+
"eval_samples_per_second": 112.71,
|
| 83 |
+
"eval_steps_per_second": 3.597,
|
| 84 |
+
"step": 37
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 6.4,
|
| 88 |
+
"grad_norm": 18.975563049316406,
|
| 89 |
+
"learning_rate": 4.166666666666667e-05,
|
| 90 |
+
"loss": 0.2779,
|
| 91 |
+
"step": 40
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 6.88,
|
| 95 |
+
"eval_accuracy": 0.825531914893617,
|
| 96 |
+
"eval_loss": 0.3817645013332367,
|
| 97 |
+
"eval_runtime": 3.9864,
|
| 98 |
+
"eval_samples_per_second": 117.9,
|
| 99 |
+
"eval_steps_per_second": 3.763,
|
| 100 |
+
"step": 43
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 8.0,
|
| 104 |
+
"grad_norm": 50.12718963623047,
|
| 105 |
+
"learning_rate": 4.976851851851852e-05,
|
| 106 |
+
"loss": 0.2348,
|
| 107 |
+
"step": 50
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 8.0,
|
| 111 |
+
"eval_accuracy": 0.7361702127659574,
|
| 112 |
+
"eval_loss": 0.5018748641014099,
|
| 113 |
+
"eval_runtime": 4.0244,
|
| 114 |
+
"eval_samples_per_second": 116.789,
|
| 115 |
+
"eval_steps_per_second": 3.727,
|
| 116 |
+
"step": 50
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 8.96,
|
| 120 |
+
"eval_accuracy": 0.8851063829787233,
|
| 121 |
+
"eval_loss": 0.29437732696533203,
|
| 122 |
+
"eval_runtime": 3.863,
|
| 123 |
+
"eval_samples_per_second": 121.668,
|
| 124 |
+
"eval_steps_per_second": 3.883,
|
| 125 |
+
"step": 56
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 9.6,
|
| 129 |
+
"grad_norm": 87.47682189941406,
|
| 130 |
+
"learning_rate": 4.8611111111111115e-05,
|
| 131 |
+
"loss": 0.26,
|
| 132 |
+
"step": 60
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 9.92,
|
| 136 |
+
"eval_accuracy": 0.9234042553191489,
|
| 137 |
+
"eval_loss": 0.24138842523097992,
|
| 138 |
+
"eval_runtime": 3.9931,
|
| 139 |
+
"eval_samples_per_second": 117.702,
|
| 140 |
+
"eval_steps_per_second": 3.756,
|
| 141 |
+
"step": 62
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 10.88,
|
| 145 |
+
"eval_accuracy": 0.8297872340425532,
|
| 146 |
+
"eval_loss": 0.36644989252090454,
|
| 147 |
+
"eval_runtime": 3.8761,
|
| 148 |
+
"eval_samples_per_second": 121.257,
|
| 149 |
+
"eval_steps_per_second": 3.87,
|
| 150 |
+
"step": 68
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 11.2,
|
| 154 |
+
"grad_norm": 37.262699127197266,
|
| 155 |
+
"learning_rate": 4.745370370370371e-05,
|
| 156 |
+
"loss": 0.2778,
|
| 157 |
+
"step": 70
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 12.0,
|
| 161 |
+
"eval_accuracy": 0.9042553191489362,
|
| 162 |
+
"eval_loss": 0.2505495548248291,
|
| 163 |
+
"eval_runtime": 3.8837,
|
| 164 |
+
"eval_samples_per_second": 121.018,
|
| 165 |
+
"eval_steps_per_second": 3.862,
|
| 166 |
+
"step": 75
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 12.8,
|
| 170 |
+
"grad_norm": 39.793601989746094,
|
| 171 |
+
"learning_rate": 4.62962962962963e-05,
|
| 172 |
+
"loss": 0.2271,
|
| 173 |
+
"step": 80
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 12.96,
|
| 177 |
+
"eval_accuracy": 0.6297872340425532,
|
| 178 |
+
"eval_loss": 0.6277480721473694,
|
| 179 |
+
"eval_runtime": 3.9373,
|
| 180 |
+
"eval_samples_per_second": 119.372,
|
| 181 |
+
"eval_steps_per_second": 3.81,
|
| 182 |
+
"step": 81
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 13.92,
|
| 186 |
+
"eval_accuracy": 0.874468085106383,
|
| 187 |
+
"eval_loss": 0.275258332490921,
|
| 188 |
+
"eval_runtime": 3.9907,
|
| 189 |
+
"eval_samples_per_second": 117.773,
|
| 190 |
+
"eval_steps_per_second": 3.759,
|
| 191 |
+
"step": 87
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 14.4,
|
| 195 |
+
"grad_norm": 45.56210708618164,
|
| 196 |
+
"learning_rate": 4.5138888888888894e-05,
|
| 197 |
+
"loss": 0.2488,
|
| 198 |
+
"step": 90
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 14.88,
|
| 202 |
+
"eval_accuracy": 0.6957446808510638,
|
| 203 |
+
"eval_loss": 0.6249393820762634,
|
| 204 |
+
"eval_runtime": 4.032,
|
| 205 |
+
"eval_samples_per_second": 116.567,
|
| 206 |
+
"eval_steps_per_second": 3.72,
|
| 207 |
+
"step": 93
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 16.0,
|
| 211 |
+
"grad_norm": 39.393192291259766,
|
| 212 |
+
"learning_rate": 4.3981481481481486e-05,
|
| 213 |
+
"loss": 0.2729,
|
| 214 |
+
"step": 100
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 16.0,
|
| 218 |
+
"eval_accuracy": 0.7148936170212766,
|
| 219 |
+
"eval_loss": 0.519493043422699,
|
| 220 |
+
"eval_runtime": 4.1537,
|
| 221 |
+
"eval_samples_per_second": 113.151,
|
| 222 |
+
"eval_steps_per_second": 3.611,
|
| 223 |
+
"step": 100
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 16.96,
|
| 227 |
+
"eval_accuracy": 0.574468085106383,
|
| 228 |
+
"eval_loss": 0.7983953952789307,
|
| 229 |
+
"eval_runtime": 4.0505,
|
| 230 |
+
"eval_samples_per_second": 116.036,
|
| 231 |
+
"eval_steps_per_second": 3.703,
|
| 232 |
+
"step": 106
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 17.6,
|
| 236 |
+
"grad_norm": 52.11545944213867,
|
| 237 |
+
"learning_rate": 4.282407407407408e-05,
|
| 238 |
+
"loss": 0.3261,
|
| 239 |
+
"step": 110
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 17.92,
|
| 243 |
+
"eval_accuracy": 0.7723404255319148,
|
| 244 |
+
"eval_loss": 0.4630971848964691,
|
| 245 |
+
"eval_runtime": 4.0296,
|
| 246 |
+
"eval_samples_per_second": 116.636,
|
| 247 |
+
"eval_steps_per_second": 3.722,
|
| 248 |
+
"step": 112
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 18.88,
|
| 252 |
+
"eval_accuracy": 0.5148936170212766,
|
| 253 |
+
"eval_loss": 1.100958228111267,
|
| 254 |
+
"eval_runtime": 4.0952,
|
| 255 |
+
"eval_samples_per_second": 114.768,
|
| 256 |
+
"eval_steps_per_second": 3.663,
|
| 257 |
+
"step": 118
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 19.2,
|
| 261 |
+
"grad_norm": 80.0373764038086,
|
| 262 |
+
"learning_rate": 4.166666666666667e-05,
|
| 263 |
+
"loss": 0.2212,
|
| 264 |
+
"step": 120
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 20.0,
|
| 268 |
+
"eval_accuracy": 0.9170212765957447,
|
| 269 |
+
"eval_loss": 0.23374585807323456,
|
| 270 |
+
"eval_runtime": 4.0961,
|
| 271 |
+
"eval_samples_per_second": 114.744,
|
| 272 |
+
"eval_steps_per_second": 3.662,
|
| 273 |
+
"step": 125
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 20.8,
|
| 277 |
+
"grad_norm": 2.179731607437134,
|
| 278 |
+
"learning_rate": 4.0509259259259265e-05,
|
| 279 |
+
"loss": 0.2802,
|
| 280 |
+
"step": 130
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 20.96,
|
| 284 |
+
"eval_accuracy": 0.7574468085106383,
|
| 285 |
+
"eval_loss": 0.46376925706863403,
|
| 286 |
+
"eval_runtime": 4.1103,
|
| 287 |
+
"eval_samples_per_second": 114.347,
|
| 288 |
+
"eval_steps_per_second": 3.649,
|
| 289 |
+
"step": 131
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 21.92,
|
| 293 |
+
"eval_accuracy": 0.8361702127659575,
|
| 294 |
+
"eval_loss": 0.38592880964279175,
|
| 295 |
+
"eval_runtime": 4.1405,
|
| 296 |
+
"eval_samples_per_second": 113.513,
|
| 297 |
+
"eval_steps_per_second": 3.623,
|
| 298 |
+
"step": 137
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 22.4,
|
| 302 |
+
"grad_norm": 4.62510871887207,
|
| 303 |
+
"learning_rate": 3.935185185185186e-05,
|
| 304 |
+
"loss": 0.2112,
|
| 305 |
+
"step": 140
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 22.88,
|
| 309 |
+
"eval_accuracy": 0.6893617021276596,
|
| 310 |
+
"eval_loss": 0.6708246469497681,
|
| 311 |
+
"eval_runtime": 4.1195,
|
| 312 |
+
"eval_samples_per_second": 114.091,
|
| 313 |
+
"eval_steps_per_second": 3.641,
|
| 314 |
+
"step": 143
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 24.0,
|
| 318 |
+
"grad_norm": 5.395915508270264,
|
| 319 |
+
"learning_rate": 3.8194444444444444e-05,
|
| 320 |
+
"loss": 0.2231,
|
| 321 |
+
"step": 150
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 24.0,
|
| 325 |
+
"eval_accuracy": 0.8680851063829788,
|
| 326 |
+
"eval_loss": 0.3386794626712799,
|
| 327 |
+
"eval_runtime": 4.0237,
|
| 328 |
+
"eval_samples_per_second": 116.808,
|
| 329 |
+
"eval_steps_per_second": 3.728,
|
| 330 |
+
"step": 150
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 24.96,
|
| 334 |
+
"eval_accuracy": 0.6553191489361702,
|
| 335 |
+
"eval_loss": 0.7044735550880432,
|
| 336 |
+
"eval_runtime": 4.1207,
|
| 337 |
+
"eval_samples_per_second": 114.059,
|
| 338 |
+
"eval_steps_per_second": 3.64,
|
| 339 |
+
"step": 156
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 25.6,
|
| 343 |
+
"grad_norm": 12.411273002624512,
|
| 344 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 345 |
+
"loss": 0.2037,
|
| 346 |
+
"step": 160
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 25.92,
|
| 350 |
+
"eval_accuracy": 0.8276595744680851,
|
| 351 |
+
"eval_loss": 0.3957701325416565,
|
| 352 |
+
"eval_runtime": 4.0677,
|
| 353 |
+
"eval_samples_per_second": 115.543,
|
| 354 |
+
"eval_steps_per_second": 3.688,
|
| 355 |
+
"step": 162
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 26.88,
|
| 359 |
+
"eval_accuracy": 0.7702127659574468,
|
| 360 |
+
"eval_loss": 0.5082454681396484,
|
| 361 |
+
"eval_runtime": 4.0429,
|
| 362 |
+
"eval_samples_per_second": 116.254,
|
| 363 |
+
"eval_steps_per_second": 3.71,
|
| 364 |
+
"step": 168
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 27.2,
|
| 368 |
+
"grad_norm": 13.522443771362305,
|
| 369 |
+
"learning_rate": 3.587962962962963e-05,
|
| 370 |
+
"loss": 0.1845,
|
| 371 |
+
"step": 170
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 28.0,
|
| 375 |
+
"eval_accuracy": 0.723404255319149,
|
| 376 |
+
"eval_loss": 0.5990515351295471,
|
| 377 |
+
"eval_runtime": 4.0619,
|
| 378 |
+
"eval_samples_per_second": 115.71,
|
| 379 |
+
"eval_steps_per_second": 3.693,
|
| 380 |
+
"step": 175
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 28.8,
|
| 384 |
+
"grad_norm": 40.79707336425781,
|
| 385 |
+
"learning_rate": 3.472222222222222e-05,
|
| 386 |
+
"loss": 0.1898,
|
| 387 |
+
"step": 180
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 28.96,
|
| 391 |
+
"eval_accuracy": 0.7617021276595745,
|
| 392 |
+
"eval_loss": 0.510837197303772,
|
| 393 |
+
"eval_runtime": 4.1139,
|
| 394 |
+
"eval_samples_per_second": 114.248,
|
| 395 |
+
"eval_steps_per_second": 3.646,
|
| 396 |
+
"step": 181
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 29.92,
|
| 400 |
+
"eval_accuracy": 0.9085106382978724,
|
| 401 |
+
"eval_loss": 0.27203500270843506,
|
| 402 |
+
"eval_runtime": 4.1071,
|
| 403 |
+
"eval_samples_per_second": 114.435,
|
| 404 |
+
"eval_steps_per_second": 3.652,
|
| 405 |
+
"step": 187
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 30.4,
|
| 409 |
+
"grad_norm": 34.6284065246582,
|
| 410 |
+
"learning_rate": 3.3564814814814815e-05,
|
| 411 |
+
"loss": 0.2118,
|
| 412 |
+
"step": 190
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 30.88,
|
| 416 |
+
"eval_accuracy": 0.7851063829787234,
|
| 417 |
+
"eval_loss": 0.4935612976551056,
|
| 418 |
+
"eval_runtime": 4.1447,
|
| 419 |
+
"eval_samples_per_second": 113.398,
|
| 420 |
+
"eval_steps_per_second": 3.619,
|
| 421 |
+
"step": 193
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 32.0,
|
| 425 |
+
"grad_norm": 5.604860782623291,
|
| 426 |
+
"learning_rate": 3.240740740740741e-05,
|
| 427 |
+
"loss": 0.2097,
|
| 428 |
+
"step": 200
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 32.0,
|
| 432 |
+
"eval_accuracy": 0.8404255319148937,
|
| 433 |
+
"eval_loss": 0.37482374906539917,
|
| 434 |
+
"eval_runtime": 4.0858,
|
| 435 |
+
"eval_samples_per_second": 115.032,
|
| 436 |
+
"eval_steps_per_second": 3.671,
|
| 437 |
+
"step": 200
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 32.96,
|
| 441 |
+
"eval_accuracy": 0.776595744680851,
|
| 442 |
+
"eval_loss": 0.5048179626464844,
|
| 443 |
+
"eval_runtime": 4.0089,
|
| 444 |
+
"eval_samples_per_second": 117.24,
|
| 445 |
+
"eval_steps_per_second": 3.742,
|
| 446 |
+
"step": 206
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 33.6,
|
| 450 |
+
"grad_norm": 7.735608100891113,
|
| 451 |
+
"learning_rate": 3.125e-05,
|
| 452 |
+
"loss": 0.1704,
|
| 453 |
+
"step": 210
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 33.92,
|
| 457 |
+
"eval_accuracy": 0.7957446808510639,
|
| 458 |
+
"eval_loss": 0.43682861328125,
|
| 459 |
+
"eval_runtime": 4.0913,
|
| 460 |
+
"eval_samples_per_second": 114.879,
|
| 461 |
+
"eval_steps_per_second": 3.666,
|
| 462 |
+
"step": 212
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 34.88,
|
| 466 |
+
"eval_accuracy": 0.6829787234042554,
|
| 467 |
+
"eval_loss": 0.6958675384521484,
|
| 468 |
+
"eval_runtime": 4.1104,
|
| 469 |
+
"eval_samples_per_second": 114.345,
|
| 470 |
+
"eval_steps_per_second": 3.649,
|
| 471 |
+
"step": 218
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 35.2,
|
| 475 |
+
"grad_norm": 25.477895736694336,
|
| 476 |
+
"learning_rate": 3.0092592592592593e-05,
|
| 477 |
+
"loss": 0.1962,
|
| 478 |
+
"step": 220
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 36.0,
|
| 482 |
+
"eval_accuracy": 0.5957446808510638,
|
| 483 |
+
"eval_loss": 1.009740948677063,
|
| 484 |
+
"eval_runtime": 4.0288,
|
| 485 |
+
"eval_samples_per_second": 116.66,
|
| 486 |
+
"eval_steps_per_second": 3.723,
|
| 487 |
+
"step": 225
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 36.8,
|
| 491 |
+
"grad_norm": 7.080097198486328,
|
| 492 |
+
"learning_rate": 2.8935185185185186e-05,
|
| 493 |
+
"loss": 0.1686,
|
| 494 |
+
"step": 230
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 36.96,
|
| 498 |
+
"eval_accuracy": 0.7914893617021277,
|
| 499 |
+
"eval_loss": 0.4992178976535797,
|
| 500 |
+
"eval_runtime": 4.0814,
|
| 501 |
+
"eval_samples_per_second": 115.157,
|
| 502 |
+
"eval_steps_per_second": 3.675,
|
| 503 |
+
"step": 231
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 37.92,
|
| 507 |
+
"eval_accuracy": 0.7574468085106383,
|
| 508 |
+
"eval_loss": 0.5373654365539551,
|
| 509 |
+
"eval_runtime": 4.2322,
|
| 510 |
+
"eval_samples_per_second": 111.052,
|
| 511 |
+
"eval_steps_per_second": 3.544,
|
| 512 |
+
"step": 237
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 38.4,
|
| 516 |
+
"grad_norm": 39.29030227661133,
|
| 517 |
+
"learning_rate": 2.777777777777778e-05,
|
| 518 |
+
"loss": 0.1855,
|
| 519 |
+
"step": 240
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 38.88,
|
| 523 |
+
"eval_accuracy": 0.8340425531914893,
|
| 524 |
+
"eval_loss": 0.371025025844574,
|
| 525 |
+
"eval_runtime": 4.1514,
|
| 526 |
+
"eval_samples_per_second": 113.216,
|
| 527 |
+
"eval_steps_per_second": 3.613,
|
| 528 |
+
"step": 243
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 40.0,
|
| 532 |
+
"grad_norm": 21.52515983581543,
|
| 533 |
+
"learning_rate": 2.6620370370370372e-05,
|
| 534 |
+
"loss": 0.1528,
|
| 535 |
+
"step": 250
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 40.0,
|
| 539 |
+
"eval_accuracy": 0.8446808510638298,
|
| 540 |
+
"eval_loss": 0.3630984425544739,
|
| 541 |
+
"eval_runtime": 4.1723,
|
| 542 |
+
"eval_samples_per_second": 112.647,
|
| 543 |
+
"eval_steps_per_second": 3.595,
|
| 544 |
+
"step": 250
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 40.96,
|
| 548 |
+
"eval_accuracy": 0.7680851063829788,
|
| 549 |
+
"eval_loss": 0.5588864088058472,
|
| 550 |
+
"eval_runtime": 4.2314,
|
| 551 |
+
"eval_samples_per_second": 111.075,
|
| 552 |
+
"eval_steps_per_second": 3.545,
|
| 553 |
+
"step": 256
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 41.6,
|
| 557 |
+
"grad_norm": 2.9336180686950684,
|
| 558 |
+
"learning_rate": 2.5462962962962965e-05,
|
| 559 |
+
"loss": 0.1523,
|
| 560 |
+
"step": 260
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 41.92,
|
| 564 |
+
"eval_accuracy": 0.7808510638297872,
|
| 565 |
+
"eval_loss": 0.5147323608398438,
|
| 566 |
+
"eval_runtime": 4.1942,
|
| 567 |
+
"eval_samples_per_second": 112.059,
|
| 568 |
+
"eval_steps_per_second": 3.576,
|
| 569 |
+
"step": 262
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 42.88,
|
| 573 |
+
"eval_accuracy": 0.7638297872340426,
|
| 574 |
+
"eval_loss": 0.5298714637756348,
|
| 575 |
+
"eval_runtime": 4.0956,
|
| 576 |
+
"eval_samples_per_second": 114.756,
|
| 577 |
+
"eval_steps_per_second": 3.662,
|
| 578 |
+
"step": 268
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 43.2,
|
| 582 |
+
"grad_norm": 20.56193733215332,
|
| 583 |
+
"learning_rate": 2.4305555555555558e-05,
|
| 584 |
+
"loss": 0.1709,
|
| 585 |
+
"step": 270
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 44.0,
|
| 589 |
+
"eval_accuracy": 0.7446808510638298,
|
| 590 |
+
"eval_loss": 0.5937234163284302,
|
| 591 |
+
"eval_runtime": 4.0352,
|
| 592 |
+
"eval_samples_per_second": 116.474,
|
| 593 |
+
"eval_steps_per_second": 3.717,
|
| 594 |
+
"step": 275
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 44.8,
|
| 598 |
+
"grad_norm": 17.483304977416992,
|
| 599 |
+
"learning_rate": 2.314814814814815e-05,
|
| 600 |
+
"loss": 0.1527,
|
| 601 |
+
"step": 280
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 44.96,
|
| 605 |
+
"eval_accuracy": 0.7382978723404255,
|
| 606 |
+
"eval_loss": 0.5969159603118896,
|
| 607 |
+
"eval_runtime": 4.1383,
|
| 608 |
+
"eval_samples_per_second": 113.574,
|
| 609 |
+
"eval_steps_per_second": 3.625,
|
| 610 |
+
"step": 281
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 45.92,
|
| 614 |
+
"eval_accuracy": 0.725531914893617,
|
| 615 |
+
"eval_loss": 0.6439131498336792,
|
| 616 |
+
"eval_runtime": 4.1256,
|
| 617 |
+
"eval_samples_per_second": 113.922,
|
| 618 |
+
"eval_steps_per_second": 3.636,
|
| 619 |
+
"step": 287
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 46.4,
|
| 623 |
+
"grad_norm": 13.123701095581055,
|
| 624 |
+
"learning_rate": 2.1990740740740743e-05,
|
| 625 |
+
"loss": 0.1397,
|
| 626 |
+
"step": 290
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 46.88,
|
| 630 |
+
"eval_accuracy": 0.6723404255319149,
|
| 631 |
+
"eval_loss": 0.7720506191253662,
|
| 632 |
+
"eval_runtime": 4.0907,
|
| 633 |
+
"eval_samples_per_second": 114.894,
|
| 634 |
+
"eval_steps_per_second": 3.667,
|
| 635 |
+
"step": 293
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 48.0,
|
| 639 |
+
"grad_norm": 15.003984451293945,
|
| 640 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 641 |
+
"loss": 0.1538,
|
| 642 |
+
"step": 300
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 48.0,
|
| 646 |
+
"eval_accuracy": 0.7702127659574468,
|
| 647 |
+
"eval_loss": 0.5767794251441956,
|
| 648 |
+
"eval_runtime": 4.0083,
|
| 649 |
+
"eval_samples_per_second": 117.257,
|
| 650 |
+
"eval_steps_per_second": 3.742,
|
| 651 |
+
"step": 300
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 48.96,
|
| 655 |
+
"eval_accuracy": 0.7595744680851064,
|
| 656 |
+
"eval_loss": 0.5801470875740051,
|
| 657 |
+
"eval_runtime": 3.9427,
|
| 658 |
+
"eval_samples_per_second": 119.209,
|
| 659 |
+
"eval_steps_per_second": 3.805,
|
| 660 |
+
"step": 306
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 49.6,
|
| 664 |
+
"grad_norm": 2.649744987487793,
|
| 665 |
+
"learning_rate": 1.967592592592593e-05,
|
| 666 |
+
"loss": 0.1466,
|
| 667 |
+
"step": 310
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 49.92,
|
| 671 |
+
"eval_accuracy": 0.7574468085106383,
|
| 672 |
+
"eval_loss": 0.5672721266746521,
|
| 673 |
+
"eval_runtime": 4.0569,
|
| 674 |
+
"eval_samples_per_second": 115.852,
|
| 675 |
+
"eval_steps_per_second": 3.697,
|
| 676 |
+
"step": 312
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 50.88,
|
| 680 |
+
"eval_accuracy": 0.7085106382978723,
|
| 681 |
+
"eval_loss": 0.6468719244003296,
|
| 682 |
+
"eval_runtime": 4.0234,
|
| 683 |
+
"eval_samples_per_second": 116.818,
|
| 684 |
+
"eval_steps_per_second": 3.728,
|
| 685 |
+
"step": 318
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 51.2,
|
| 689 |
+
"grad_norm": 12.5094633102417,
|
| 690 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 691 |
+
"loss": 0.1302,
|
| 692 |
+
"step": 320
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 52.0,
|
| 696 |
+
"eval_accuracy": 0.6957446808510638,
|
| 697 |
+
"eval_loss": 0.7276235222816467,
|
| 698 |
+
"eval_runtime": 4.0008,
|
| 699 |
+
"eval_samples_per_second": 117.475,
|
| 700 |
+
"eval_steps_per_second": 3.749,
|
| 701 |
+
"step": 325
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 52.8,
|
| 705 |
+
"grad_norm": 6.599560737609863,
|
| 706 |
+
"learning_rate": 1.736111111111111e-05,
|
| 707 |
+
"loss": 0.1565,
|
| 708 |
+
"step": 330
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 52.96,
|
| 712 |
+
"eval_accuracy": 0.6723404255319149,
|
| 713 |
+
"eval_loss": 0.8247136473655701,
|
| 714 |
+
"eval_runtime": 4.0526,
|
| 715 |
+
"eval_samples_per_second": 115.976,
|
| 716 |
+
"eval_steps_per_second": 3.701,
|
| 717 |
+
"step": 331
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 53.92,
|
| 721 |
+
"eval_accuracy": 0.7978723404255319,
|
| 722 |
+
"eval_loss": 0.4810582399368286,
|
| 723 |
+
"eval_runtime": 4.0005,
|
| 724 |
+
"eval_samples_per_second": 117.486,
|
| 725 |
+
"eval_steps_per_second": 3.75,
|
| 726 |
+
"step": 337
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 54.4,
|
| 730 |
+
"grad_norm": 12.574357986450195,
|
| 731 |
+
"learning_rate": 1.6203703703703704e-05,
|
| 732 |
+
"loss": 0.1267,
|
| 733 |
+
"step": 340
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 54.88,
|
| 737 |
+
"eval_accuracy": 0.7021276595744681,
|
| 738 |
+
"eval_loss": 0.6372675895690918,
|
| 739 |
+
"eval_runtime": 4.047,
|
| 740 |
+
"eval_samples_per_second": 116.135,
|
| 741 |
+
"eval_steps_per_second": 3.706,
|
| 742 |
+
"step": 343
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 56.0,
|
| 746 |
+
"grad_norm": 29.667768478393555,
|
| 747 |
+
"learning_rate": 1.5046296296296297e-05,
|
| 748 |
+
"loss": 0.1424,
|
| 749 |
+
"step": 350
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 56.0,
|
| 753 |
+
"eval_accuracy": 0.6723404255319149,
|
| 754 |
+
"eval_loss": 0.7251705527305603,
|
| 755 |
+
"eval_runtime": 4.0519,
|
| 756 |
+
"eval_samples_per_second": 115.995,
|
| 757 |
+
"eval_steps_per_second": 3.702,
|
| 758 |
+
"step": 350
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 56.96,
|
| 762 |
+
"eval_accuracy": 0.7489361702127659,
|
| 763 |
+
"eval_loss": 0.5696622729301453,
|
| 764 |
+
"eval_runtime": 4.0808,
|
| 765 |
+
"eval_samples_per_second": 115.174,
|
| 766 |
+
"eval_steps_per_second": 3.676,
|
| 767 |
+
"step": 356
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 57.6,
|
| 771 |
+
"grad_norm": 3.276287317276001,
|
| 772 |
+
"learning_rate": 1.388888888888889e-05,
|
| 773 |
+
"loss": 0.1053,
|
| 774 |
+
"step": 360
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 57.92,
|
| 778 |
+
"eval_accuracy": 0.6957446808510638,
|
| 779 |
+
"eval_loss": 0.7066917419433594,
|
| 780 |
+
"eval_runtime": 4.0845,
|
| 781 |
+
"eval_samples_per_second": 115.07,
|
| 782 |
+
"eval_steps_per_second": 3.672,
|
| 783 |
+
"step": 362
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 58.88,
|
| 787 |
+
"eval_accuracy": 0.7063829787234043,
|
| 788 |
+
"eval_loss": 0.6576955318450928,
|
| 789 |
+
"eval_runtime": 4.1852,
|
| 790 |
+
"eval_samples_per_second": 112.301,
|
| 791 |
+
"eval_steps_per_second": 3.584,
|
| 792 |
+
"step": 368
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 59.2,
|
| 796 |
+
"grad_norm": 7.9189982414245605,
|
| 797 |
+
"learning_rate": 1.2731481481481482e-05,
|
| 798 |
+
"loss": 0.1301,
|
| 799 |
+
"step": 370
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 60.0,
|
| 803 |
+
"eval_accuracy": 0.774468085106383,
|
| 804 |
+
"eval_loss": 0.5325801372528076,
|
| 805 |
+
"eval_runtime": 4.0787,
|
| 806 |
+
"eval_samples_per_second": 115.233,
|
| 807 |
+
"eval_steps_per_second": 3.678,
|
| 808 |
+
"step": 375
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 60.8,
|
| 812 |
+
"grad_norm": 14.686637878417969,
|
| 813 |
+
"learning_rate": 1.1574074074074075e-05,
|
| 814 |
+
"loss": 0.0906,
|
| 815 |
+
"step": 380
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 60.96,
|
| 819 |
+
"eval_accuracy": 0.7851063829787234,
|
| 820 |
+
"eval_loss": 0.546753466129303,
|
| 821 |
+
"eval_runtime": 4.0812,
|
| 822 |
+
"eval_samples_per_second": 115.163,
|
| 823 |
+
"eval_steps_per_second": 3.675,
|
| 824 |
+
"step": 381
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 61.92,
|
| 828 |
+
"eval_accuracy": 0.8276595744680851,
|
| 829 |
+
"eval_loss": 0.4413163959980011,
|
| 830 |
+
"eval_runtime": 4.1408,
|
| 831 |
+
"eval_samples_per_second": 113.504,
|
| 832 |
+
"eval_steps_per_second": 3.622,
|
| 833 |
+
"step": 387
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 62.4,
|
| 837 |
+
"grad_norm": 9.14445686340332,
|
| 838 |
+
"learning_rate": 1.0416666666666668e-05,
|
| 839 |
+
"loss": 0.0974,
|
| 840 |
+
"step": 390
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 62.88,
|
| 844 |
+
"eval_accuracy": 0.7659574468085106,
|
| 845 |
+
"eval_loss": 0.5478885173797607,
|
| 846 |
+
"eval_runtime": 4.1286,
|
| 847 |
+
"eval_samples_per_second": 113.839,
|
| 848 |
+
"eval_steps_per_second": 3.633,
|
| 849 |
+
"step": 393
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 64.0,
|
| 853 |
+
"grad_norm": 4.1058526039123535,
|
| 854 |
+
"learning_rate": 9.259259259259259e-06,
|
| 855 |
+
"loss": 0.1133,
|
| 856 |
+
"step": 400
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 64.0,
|
| 860 |
+
"eval_accuracy": 0.7042553191489361,
|
| 861 |
+
"eval_loss": 0.7109193801879883,
|
| 862 |
+
"eval_runtime": 4.2149,
|
| 863 |
+
"eval_samples_per_second": 111.508,
|
| 864 |
+
"eval_steps_per_second": 3.559,
|
| 865 |
+
"step": 400
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 64.96,
|
| 869 |
+
"eval_accuracy": 0.7617021276595745,
|
| 870 |
+
"eval_loss": 0.5734679102897644,
|
| 871 |
+
"eval_runtime": 4.1133,
|
| 872 |
+
"eval_samples_per_second": 114.265,
|
| 873 |
+
"eval_steps_per_second": 3.647,
|
| 874 |
+
"step": 406
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 65.6,
|
| 878 |
+
"grad_norm": 5.876250267028809,
|
| 879 |
+
"learning_rate": 8.101851851851852e-06,
|
| 880 |
+
"loss": 0.1189,
|
| 881 |
+
"step": 410
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 65.92,
|
| 885 |
+
"eval_accuracy": 0.8297872340425532,
|
| 886 |
+
"eval_loss": 0.4084050953388214,
|
| 887 |
+
"eval_runtime": 4.1883,
|
| 888 |
+
"eval_samples_per_second": 112.218,
|
| 889 |
+
"eval_steps_per_second": 3.581,
|
| 890 |
+
"step": 412
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 66.88,
|
| 894 |
+
"eval_accuracy": 0.7489361702127659,
|
| 895 |
+
"eval_loss": 0.5716192722320557,
|
| 896 |
+
"eval_runtime": 4.1124,
|
| 897 |
+
"eval_samples_per_second": 114.289,
|
| 898 |
+
"eval_steps_per_second": 3.648,
|
| 899 |
+
"step": 418
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 67.2,
|
| 903 |
+
"grad_norm": 2.931035280227661,
|
| 904 |
+
"learning_rate": 6.944444444444445e-06,
|
| 905 |
+
"loss": 0.1064,
|
| 906 |
+
"step": 420
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 68.0,
|
| 910 |
+
"eval_accuracy": 0.7553191489361702,
|
| 911 |
+
"eval_loss": 0.5537174940109253,
|
| 912 |
+
"eval_runtime": 4.0965,
|
| 913 |
+
"eval_samples_per_second": 114.731,
|
| 914 |
+
"eval_steps_per_second": 3.662,
|
| 915 |
+
"step": 425
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 68.8,
|
| 919 |
+
"grad_norm": 4.387136936187744,
|
| 920 |
+
"learning_rate": 5.787037037037038e-06,
|
| 921 |
+
"loss": 0.1084,
|
| 922 |
+
"step": 430
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 68.96,
|
| 926 |
+
"eval_accuracy": 0.8021276595744681,
|
| 927 |
+
"eval_loss": 0.456912100315094,
|
| 928 |
+
"eval_runtime": 4.1477,
|
| 929 |
+
"eval_samples_per_second": 113.315,
|
| 930 |
+
"eval_steps_per_second": 3.616,
|
| 931 |
+
"step": 431
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 69.92,
|
| 935 |
+
"eval_accuracy": 0.7617021276595745,
|
| 936 |
+
"eval_loss": 0.5227068066596985,
|
| 937 |
+
"eval_runtime": 4.1656,
|
| 938 |
+
"eval_samples_per_second": 112.828,
|
| 939 |
+
"eval_steps_per_second": 3.601,
|
| 940 |
+
"step": 437
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 70.4,
|
| 944 |
+
"grad_norm": 6.693394184112549,
|
| 945 |
+
"learning_rate": 4.6296296296296296e-06,
|
| 946 |
+
"loss": 0.1054,
|
| 947 |
+
"step": 440
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 70.88,
|
| 951 |
+
"eval_accuracy": 0.7276595744680852,
|
| 952 |
+
"eval_loss": 0.5995042324066162,
|
| 953 |
+
"eval_runtime": 4.1654,
|
| 954 |
+
"eval_samples_per_second": 112.834,
|
| 955 |
+
"eval_steps_per_second": 3.601,
|
| 956 |
+
"step": 443
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 72.0,
|
| 960 |
+
"grad_norm": 8.600502014160156,
|
| 961 |
+
"learning_rate": 3.4722222222222224e-06,
|
| 962 |
+
"loss": 0.1005,
|
| 963 |
+
"step": 450
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 72.0,
|
| 967 |
+
"eval_accuracy": 0.7638297872340426,
|
| 968 |
+
"eval_loss": 0.5560170412063599,
|
| 969 |
+
"eval_runtime": 4.1827,
|
| 970 |
+
"eval_samples_per_second": 112.367,
|
| 971 |
+
"eval_steps_per_second": 3.586,
|
| 972 |
+
"step": 450
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 72.96,
|
| 976 |
+
"eval_accuracy": 0.8063829787234043,
|
| 977 |
+
"eval_loss": 0.45502665638923645,
|
| 978 |
+
"eval_runtime": 4.2071,
|
| 979 |
+
"eval_samples_per_second": 111.715,
|
| 980 |
+
"eval_steps_per_second": 3.565,
|
| 981 |
+
"step": 456
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 73.6,
|
| 985 |
+
"grad_norm": 10.198132514953613,
|
| 986 |
+
"learning_rate": 2.3148148148148148e-06,
|
| 987 |
+
"loss": 0.1028,
|
| 988 |
+
"step": 460
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 73.92,
|
| 992 |
+
"eval_accuracy": 0.823404255319149,
|
| 993 |
+
"eval_loss": 0.4404470920562744,
|
| 994 |
+
"eval_runtime": 4.1806,
|
| 995 |
+
"eval_samples_per_second": 112.425,
|
| 996 |
+
"eval_steps_per_second": 3.588,
|
| 997 |
+
"step": 462
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 74.88,
|
| 1001 |
+
"eval_accuracy": 0.7957446808510639,
|
| 1002 |
+
"eval_loss": 0.4761447310447693,
|
| 1003 |
+
"eval_runtime": 4.1871,
|
| 1004 |
+
"eval_samples_per_second": 112.251,
|
| 1005 |
+
"eval_steps_per_second": 3.582,
|
| 1006 |
+
"step": 468
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 75.2,
|
| 1010 |
+
"grad_norm": 7.506448268890381,
|
| 1011 |
+
"learning_rate": 1.1574074074074074e-06,
|
| 1012 |
+
"loss": 0.0917,
|
| 1013 |
+
"step": 470
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 76.0,
|
| 1017 |
+
"eval_accuracy": 0.7680851063829788,
|
| 1018 |
+
"eval_loss": 0.5278272032737732,
|
| 1019 |
+
"eval_runtime": 4.1615,
|
| 1020 |
+
"eval_samples_per_second": 112.939,
|
| 1021 |
+
"eval_steps_per_second": 3.604,
|
| 1022 |
+
"step": 475
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 76.8,
|
| 1026 |
+
"grad_norm": 5.474030494689941,
|
| 1027 |
+
"learning_rate": 0.0,
|
| 1028 |
+
"loss": 0.1009,
|
| 1029 |
+
"step": 480
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 76.8,
|
| 1033 |
+
"eval_accuracy": 0.7617021276595745,
|
| 1034 |
+
"eval_loss": 0.5345979332923889,
|
| 1035 |
+
"eval_runtime": 4.1813,
|
| 1036 |
+
"eval_samples_per_second": 112.405,
|
| 1037 |
+
"eval_steps_per_second": 3.587,
|
| 1038 |
+
"step": 480
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 76.8,
|
| 1042 |
+
"step": 480,
|
| 1043 |
+
"total_flos": 4.5903154968099717e+18,
|
| 1044 |
+
"train_loss": 0.19423907659947873,
|
| 1045 |
+
"train_runtime": 1687.359,
|
| 1046 |
+
"train_samples_per_second": 36.554,
|
| 1047 |
+
"train_steps_per_second": 0.284
|
| 1048 |
+
}
|
| 1049 |
+
],
|
| 1050 |
+
"logging_steps": 10,
|
| 1051 |
+
"max_steps": 480,
|
| 1052 |
+
"num_input_tokens_seen": 0,
|
| 1053 |
+
"num_train_epochs": 80,
|
| 1054 |
+
"save_steps": 500,
|
| 1055 |
+
"stateful_callbacks": {
|
| 1056 |
+
"TrainerControl": {
|
| 1057 |
+
"args": {
|
| 1058 |
+
"should_epoch_stop": false,
|
| 1059 |
+
"should_evaluate": false,
|
| 1060 |
+
"should_log": false,
|
| 1061 |
+
"should_save": true,
|
| 1062 |
+
"should_training_stop": true
|
| 1063 |
+
},
|
| 1064 |
+
"attributes": {}
|
| 1065 |
+
}
|
| 1066 |
+
},
|
| 1067 |
+
"total_flos": 4.5903154968099717e+18,
|
| 1068 |
+
"train_batch_size": 32,
|
| 1069 |
+
"trial_name": null,
|
| 1070 |
+
"trial_params": null
|
| 1071 |
+
}
|