Commit
•
b726223
1
Parent(s):
3d5547f
End of training
Browse files- README.md +3 -3
- all_results.json +12 -0
- eval_results.json +8 -0
- runs/May23_07-59-52_DESKTOP-SKBE9FB/events.out.tfevents.1716475133.DESKTOP-SKBE9FB.17360.1 +3 -0
- train_results.json +7 -0
- trainer_state.json +870 -0
README.md
CHANGED
|
@@ -22,7 +22,7 @@ model-index:
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
-
value: 0.
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss: 0.
|
| 36 |
-
- Accuracy: 0.
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
+
value: 0.8666666666666667
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.5495
|
| 36 |
+
- Accuracy: 0.8667
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 40.0,
|
| 3 |
+
"eval_accuracy": 0.8666666666666667,
|
| 4 |
+
"eval_loss": 0.5495395660400391,
|
| 5 |
+
"eval_runtime": 1.1232,
|
| 6 |
+
"eval_samples_per_second": 53.418,
|
| 7 |
+
"eval_steps_per_second": 1.781,
|
| 8 |
+
"train_loss": 0.1800640467181802,
|
| 9 |
+
"train_runtime": 1621.1538,
|
| 10 |
+
"train_samples_per_second": 62.671,
|
| 11 |
+
"train_steps_per_second": 0.493
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 40.0,
|
| 3 |
+
"eval_accuracy": 0.8666666666666667,
|
| 4 |
+
"eval_loss": 0.5495395660400391,
|
| 5 |
+
"eval_runtime": 1.1232,
|
| 6 |
+
"eval_samples_per_second": 53.418,
|
| 7 |
+
"eval_steps_per_second": 1.781
|
| 8 |
+
}
|
runs/May23_07-59-52_DESKTOP-SKBE9FB/events.out.tfevents.1716475133.DESKTOP-SKBE9FB.17360.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ed67502d7fe64b141bb80b4dfaaa161266ee7c3bbec3a56cf18342ce6c69c82
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 40.0,
|
| 3 |
+
"train_loss": 0.1800640467181802,
|
| 4 |
+
"train_runtime": 1621.1538,
|
| 5 |
+
"train_samples_per_second": 62.671,
|
| 6 |
+
"train_steps_per_second": 0.493
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,870 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8666666666666667,
|
| 3 |
+
"best_model_checkpoint": "vit-base-patch16-224-U8-40\\checkpoint-100",
|
| 4 |
+
"epoch": 40.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 800,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.5,
|
| 13 |
+
"learning_rate": 1.375e-05,
|
| 14 |
+
"loss": 1.3823,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 1.0,
|
| 19 |
+
"learning_rate": 2.75e-05,
|
| 20 |
+
"loss": 1.3457,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 1.0,
|
| 25 |
+
"eval_accuracy": 0.45,
|
| 26 |
+
"eval_loss": 1.312751054763794,
|
| 27 |
+
"eval_runtime": 1.0907,
|
| 28 |
+
"eval_samples_per_second": 55.012,
|
| 29 |
+
"eval_steps_per_second": 1.834,
|
| 30 |
+
"step": 20
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 1.5,
|
| 34 |
+
"learning_rate": 4.125e-05,
|
| 35 |
+
"loss": 1.2727,
|
| 36 |
+
"step": 30
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 2.0,
|
| 40 |
+
"learning_rate": 5.5e-05,
|
| 41 |
+
"loss": 1.1498,
|
| 42 |
+
"step": 40
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 2.0,
|
| 46 |
+
"eval_accuracy": 0.5666666666666667,
|
| 47 |
+
"eval_loss": 1.10469388961792,
|
| 48 |
+
"eval_runtime": 1.0087,
|
| 49 |
+
"eval_samples_per_second": 59.483,
|
| 50 |
+
"eval_steps_per_second": 1.983,
|
| 51 |
+
"step": 40
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 2.5,
|
| 55 |
+
"learning_rate": 5.4276315789473686e-05,
|
| 56 |
+
"loss": 1.0035,
|
| 57 |
+
"step": 50
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 3.0,
|
| 61 |
+
"learning_rate": 5.355263157894737e-05,
|
| 62 |
+
"loss": 0.8312,
|
| 63 |
+
"step": 60
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 3.0,
|
| 67 |
+
"eval_accuracy": 0.65,
|
| 68 |
+
"eval_loss": 0.8231016397476196,
|
| 69 |
+
"eval_runtime": 0.959,
|
| 70 |
+
"eval_samples_per_second": 62.565,
|
| 71 |
+
"eval_steps_per_second": 2.086,
|
| 72 |
+
"step": 60
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 3.5,
|
| 76 |
+
"learning_rate": 5.282894736842105e-05,
|
| 77 |
+
"loss": 0.6784,
|
| 78 |
+
"step": 70
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 4.0,
|
| 82 |
+
"learning_rate": 5.210526315789474e-05,
|
| 83 |
+
"loss": 0.5334,
|
| 84 |
+
"step": 80
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 4.0,
|
| 88 |
+
"eval_accuracy": 0.8166666666666667,
|
| 89 |
+
"eval_loss": 0.5718551278114319,
|
| 90 |
+
"eval_runtime": 0.9624,
|
| 91 |
+
"eval_samples_per_second": 62.346,
|
| 92 |
+
"eval_steps_per_second": 2.078,
|
| 93 |
+
"step": 80
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 4.5,
|
| 97 |
+
"learning_rate": 5.138157894736842e-05,
|
| 98 |
+
"loss": 0.4291,
|
| 99 |
+
"step": 90
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 5.0,
|
| 103 |
+
"learning_rate": 5.0657894736842104e-05,
|
| 104 |
+
"loss": 0.3582,
|
| 105 |
+
"step": 100
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 5.0,
|
| 109 |
+
"eval_accuracy": 0.8666666666666667,
|
| 110 |
+
"eval_loss": 0.5495395660400391,
|
| 111 |
+
"eval_runtime": 0.9691,
|
| 112 |
+
"eval_samples_per_second": 61.916,
|
| 113 |
+
"eval_steps_per_second": 2.064,
|
| 114 |
+
"step": 100
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 5.5,
|
| 118 |
+
"learning_rate": 4.9934210526315795e-05,
|
| 119 |
+
"loss": 0.3013,
|
| 120 |
+
"step": 110
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 6.0,
|
| 124 |
+
"learning_rate": 4.921052631578948e-05,
|
| 125 |
+
"loss": 0.2389,
|
| 126 |
+
"step": 120
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 6.0,
|
| 130 |
+
"eval_accuracy": 0.8333333333333334,
|
| 131 |
+
"eval_loss": 0.5800701975822449,
|
| 132 |
+
"eval_runtime": 0.9832,
|
| 133 |
+
"eval_samples_per_second": 61.028,
|
| 134 |
+
"eval_steps_per_second": 2.034,
|
| 135 |
+
"step": 120
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 6.5,
|
| 139 |
+
"learning_rate": 4.8486842105263156e-05,
|
| 140 |
+
"loss": 0.2008,
|
| 141 |
+
"step": 130
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 7.0,
|
| 145 |
+
"learning_rate": 4.7763157894736846e-05,
|
| 146 |
+
"loss": 0.2055,
|
| 147 |
+
"step": 140
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 7.0,
|
| 151 |
+
"eval_accuracy": 0.8166666666666667,
|
| 152 |
+
"eval_loss": 0.6727150678634644,
|
| 153 |
+
"eval_runtime": 0.9731,
|
| 154 |
+
"eval_samples_per_second": 61.656,
|
| 155 |
+
"eval_steps_per_second": 2.055,
|
| 156 |
+
"step": 140
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 7.5,
|
| 160 |
+
"learning_rate": 4.703947368421053e-05,
|
| 161 |
+
"loss": 0.2019,
|
| 162 |
+
"step": 150
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 8.0,
|
| 166 |
+
"learning_rate": 4.631578947368421e-05,
|
| 167 |
+
"loss": 0.1738,
|
| 168 |
+
"step": 160
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 8.0,
|
| 172 |
+
"eval_accuracy": 0.8,
|
| 173 |
+
"eval_loss": 0.7237645983695984,
|
| 174 |
+
"eval_runtime": 0.9886,
|
| 175 |
+
"eval_samples_per_second": 60.69,
|
| 176 |
+
"eval_steps_per_second": 2.023,
|
| 177 |
+
"step": 160
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 8.5,
|
| 181 |
+
"learning_rate": 4.55921052631579e-05,
|
| 182 |
+
"loss": 0.1508,
|
| 183 |
+
"step": 170
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 9.0,
|
| 187 |
+
"learning_rate": 4.486842105263158e-05,
|
| 188 |
+
"loss": 0.1556,
|
| 189 |
+
"step": 180
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 9.0,
|
| 193 |
+
"eval_accuracy": 0.75,
|
| 194 |
+
"eval_loss": 0.7665268778800964,
|
| 195 |
+
"eval_runtime": 0.9669,
|
| 196 |
+
"eval_samples_per_second": 62.054,
|
| 197 |
+
"eval_steps_per_second": 2.068,
|
| 198 |
+
"step": 180
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 9.5,
|
| 202 |
+
"learning_rate": 4.4144736842105265e-05,
|
| 203 |
+
"loss": 0.1414,
|
| 204 |
+
"step": 190
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 10.0,
|
| 208 |
+
"learning_rate": 4.342105263157895e-05,
|
| 209 |
+
"loss": 0.1461,
|
| 210 |
+
"step": 200
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 10.0,
|
| 214 |
+
"eval_accuracy": 0.7666666666666667,
|
| 215 |
+
"eval_loss": 0.822857677936554,
|
| 216 |
+
"eval_runtime": 1.0828,
|
| 217 |
+
"eval_samples_per_second": 55.411,
|
| 218 |
+
"eval_steps_per_second": 1.847,
|
| 219 |
+
"step": 200
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 10.5,
|
| 223 |
+
"learning_rate": 4.269736842105263e-05,
|
| 224 |
+
"loss": 0.1309,
|
| 225 |
+
"step": 210
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 11.0,
|
| 229 |
+
"learning_rate": 4.197368421052632e-05,
|
| 230 |
+
"loss": 0.1401,
|
| 231 |
+
"step": 220
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 11.0,
|
| 235 |
+
"eval_accuracy": 0.75,
|
| 236 |
+
"eval_loss": 0.8102101683616638,
|
| 237 |
+
"eval_runtime": 0.9793,
|
| 238 |
+
"eval_samples_per_second": 61.265,
|
| 239 |
+
"eval_steps_per_second": 2.042,
|
| 240 |
+
"step": 220
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 11.5,
|
| 244 |
+
"learning_rate": 4.125e-05,
|
| 245 |
+
"loss": 0.1161,
|
| 246 |
+
"step": 230
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 12.0,
|
| 250 |
+
"learning_rate": 4.0526315789473684e-05,
|
| 251 |
+
"loss": 0.08,
|
| 252 |
+
"step": 240
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 12.0,
|
| 256 |
+
"eval_accuracy": 0.8333333333333334,
|
| 257 |
+
"eval_loss": 0.6608515977859497,
|
| 258 |
+
"eval_runtime": 1.0247,
|
| 259 |
+
"eval_samples_per_second": 58.555,
|
| 260 |
+
"eval_steps_per_second": 1.952,
|
| 261 |
+
"step": 240
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 12.5,
|
| 265 |
+
"learning_rate": 3.9802631578947374e-05,
|
| 266 |
+
"loss": 0.1089,
|
| 267 |
+
"step": 250
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 13.0,
|
| 271 |
+
"learning_rate": 3.907894736842105e-05,
|
| 272 |
+
"loss": 0.0989,
|
| 273 |
+
"step": 260
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 13.0,
|
| 277 |
+
"eval_accuracy": 0.8333333333333334,
|
| 278 |
+
"eval_loss": 0.6703253388404846,
|
| 279 |
+
"eval_runtime": 1.0441,
|
| 280 |
+
"eval_samples_per_second": 57.465,
|
| 281 |
+
"eval_steps_per_second": 1.915,
|
| 282 |
+
"step": 260
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 13.5,
|
| 286 |
+
"learning_rate": 3.8355263157894735e-05,
|
| 287 |
+
"loss": 0.1044,
|
| 288 |
+
"step": 270
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 14.0,
|
| 292 |
+
"learning_rate": 3.7631578947368425e-05,
|
| 293 |
+
"loss": 0.0773,
|
| 294 |
+
"step": 280
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 14.0,
|
| 298 |
+
"eval_accuracy": 0.8166666666666667,
|
| 299 |
+
"eval_loss": 0.7303264141082764,
|
| 300 |
+
"eval_runtime": 1.0099,
|
| 301 |
+
"eval_samples_per_second": 59.412,
|
| 302 |
+
"eval_steps_per_second": 1.98,
|
| 303 |
+
"step": 280
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 14.5,
|
| 307 |
+
"learning_rate": 3.69078947368421e-05,
|
| 308 |
+
"loss": 0.0816,
|
| 309 |
+
"step": 290
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 15.0,
|
| 313 |
+
"learning_rate": 3.618421052631579e-05,
|
| 314 |
+
"loss": 0.089,
|
| 315 |
+
"step": 300
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 15.0,
|
| 319 |
+
"eval_accuracy": 0.7833333333333333,
|
| 320 |
+
"eval_loss": 0.7757053971290588,
|
| 321 |
+
"eval_runtime": 1.0238,
|
| 322 |
+
"eval_samples_per_second": 58.605,
|
| 323 |
+
"eval_steps_per_second": 1.953,
|
| 324 |
+
"step": 300
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 15.5,
|
| 328 |
+
"learning_rate": 3.5460526315789476e-05,
|
| 329 |
+
"loss": 0.0591,
|
| 330 |
+
"step": 310
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 16.0,
|
| 334 |
+
"learning_rate": 3.473684210526316e-05,
|
| 335 |
+
"loss": 0.11,
|
| 336 |
+
"step": 320
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 16.0,
|
| 340 |
+
"eval_accuracy": 0.8,
|
| 341 |
+
"eval_loss": 0.7278648614883423,
|
| 342 |
+
"eval_runtime": 1.0068,
|
| 343 |
+
"eval_samples_per_second": 59.595,
|
| 344 |
+
"eval_steps_per_second": 1.987,
|
| 345 |
+
"step": 320
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 16.5,
|
| 349 |
+
"learning_rate": 3.4013157894736844e-05,
|
| 350 |
+
"loss": 0.0749,
|
| 351 |
+
"step": 330
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 17.0,
|
| 355 |
+
"learning_rate": 3.328947368421053e-05,
|
| 356 |
+
"loss": 0.086,
|
| 357 |
+
"step": 340
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 17.0,
|
| 361 |
+
"eval_accuracy": 0.7833333333333333,
|
| 362 |
+
"eval_loss": 0.849124014377594,
|
| 363 |
+
"eval_runtime": 0.9755,
|
| 364 |
+
"eval_samples_per_second": 61.509,
|
| 365 |
+
"eval_steps_per_second": 2.05,
|
| 366 |
+
"step": 340
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 17.5,
|
| 370 |
+
"learning_rate": 3.256578947368421e-05,
|
| 371 |
+
"loss": 0.0875,
|
| 372 |
+
"step": 350
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 18.0,
|
| 376 |
+
"learning_rate": 3.1842105263157895e-05,
|
| 377 |
+
"loss": 0.0671,
|
| 378 |
+
"step": 360
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 18.0,
|
| 382 |
+
"eval_accuracy": 0.8,
|
| 383 |
+
"eval_loss": 0.7949829697608948,
|
| 384 |
+
"eval_runtime": 1.0555,
|
| 385 |
+
"eval_samples_per_second": 56.847,
|
| 386 |
+
"eval_steps_per_second": 1.895,
|
| 387 |
+
"step": 360
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 18.5,
|
| 391 |
+
"learning_rate": 3.111842105263158e-05,
|
| 392 |
+
"loss": 0.0828,
|
| 393 |
+
"step": 370
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 19.0,
|
| 397 |
+
"learning_rate": 3.0394736842105266e-05,
|
| 398 |
+
"loss": 0.0775,
|
| 399 |
+
"step": 380
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 19.0,
|
| 403 |
+
"eval_accuracy": 0.85,
|
| 404 |
+
"eval_loss": 0.6752822995185852,
|
| 405 |
+
"eval_runtime": 1.0074,
|
| 406 |
+
"eval_samples_per_second": 59.558,
|
| 407 |
+
"eval_steps_per_second": 1.985,
|
| 408 |
+
"step": 380
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 19.5,
|
| 412 |
+
"learning_rate": 2.967105263157895e-05,
|
| 413 |
+
"loss": 0.0816,
|
| 414 |
+
"step": 390
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 20.0,
|
| 418 |
+
"learning_rate": 2.894736842105263e-05,
|
| 419 |
+
"loss": 0.0636,
|
| 420 |
+
"step": 400
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 20.0,
|
| 424 |
+
"eval_accuracy": 0.8333333333333334,
|
| 425 |
+
"eval_loss": 0.7880961298942566,
|
| 426 |
+
"eval_runtime": 1.036,
|
| 427 |
+
"eval_samples_per_second": 57.915,
|
| 428 |
+
"eval_steps_per_second": 1.93,
|
| 429 |
+
"step": 400
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 20.5,
|
| 433 |
+
"learning_rate": 2.822368421052632e-05,
|
| 434 |
+
"loss": 0.0592,
|
| 435 |
+
"step": 410
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 21.0,
|
| 439 |
+
"learning_rate": 2.75e-05,
|
| 440 |
+
"loss": 0.0737,
|
| 441 |
+
"step": 420
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 21.0,
|
| 445 |
+
"eval_accuracy": 0.8333333333333334,
|
| 446 |
+
"eval_loss": 0.7449613809585571,
|
| 447 |
+
"eval_runtime": 0.996,
|
| 448 |
+
"eval_samples_per_second": 60.243,
|
| 449 |
+
"eval_steps_per_second": 2.008,
|
| 450 |
+
"step": 420
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 21.5,
|
| 454 |
+
"learning_rate": 2.6776315789473685e-05,
|
| 455 |
+
"loss": 0.0616,
|
| 456 |
+
"step": 430
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 22.0,
|
| 460 |
+
"learning_rate": 2.605263157894737e-05,
|
| 461 |
+
"loss": 0.0583,
|
| 462 |
+
"step": 440
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 22.0,
|
| 466 |
+
"eval_accuracy": 0.8,
|
| 467 |
+
"eval_loss": 0.8295071125030518,
|
| 468 |
+
"eval_runtime": 0.9869,
|
| 469 |
+
"eval_samples_per_second": 60.794,
|
| 470 |
+
"eval_steps_per_second": 2.026,
|
| 471 |
+
"step": 440
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 22.5,
|
| 475 |
+
"learning_rate": 2.5328947368421052e-05,
|
| 476 |
+
"loss": 0.0546,
|
| 477 |
+
"step": 450
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 23.0,
|
| 481 |
+
"learning_rate": 2.460526315789474e-05,
|
| 482 |
+
"loss": 0.0646,
|
| 483 |
+
"step": 460
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 23.0,
|
| 487 |
+
"eval_accuracy": 0.8333333333333334,
|
| 488 |
+
"eval_loss": 0.8226525187492371,
|
| 489 |
+
"eval_runtime": 1.0606,
|
| 490 |
+
"eval_samples_per_second": 56.57,
|
| 491 |
+
"eval_steps_per_second": 1.886,
|
| 492 |
+
"step": 460
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 23.5,
|
| 496 |
+
"learning_rate": 2.3881578947368423e-05,
|
| 497 |
+
"loss": 0.0703,
|
| 498 |
+
"step": 470
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 24.0,
|
| 502 |
+
"learning_rate": 2.3157894736842103e-05,
|
| 503 |
+
"loss": 0.0637,
|
| 504 |
+
"step": 480
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 24.0,
|
| 508 |
+
"eval_accuracy": 0.7833333333333333,
|
| 509 |
+
"eval_loss": 0.9029874205589294,
|
| 510 |
+
"eval_runtime": 0.9829,
|
| 511 |
+
"eval_samples_per_second": 61.045,
|
| 512 |
+
"eval_steps_per_second": 2.035,
|
| 513 |
+
"step": 480
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 24.5,
|
| 517 |
+
"learning_rate": 2.243421052631579e-05,
|
| 518 |
+
"loss": 0.0375,
|
| 519 |
+
"step": 490
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 25.0,
|
| 523 |
+
"learning_rate": 2.1710526315789474e-05,
|
| 524 |
+
"loss": 0.0647,
|
| 525 |
+
"step": 500
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 25.0,
|
| 529 |
+
"eval_accuracy": 0.8,
|
| 530 |
+
"eval_loss": 0.8656226992607117,
|
| 531 |
+
"eval_runtime": 1.0209,
|
| 532 |
+
"eval_samples_per_second": 58.772,
|
| 533 |
+
"eval_steps_per_second": 1.959,
|
| 534 |
+
"step": 500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 25.5,
|
| 538 |
+
"learning_rate": 2.098684210526316e-05,
|
| 539 |
+
"loss": 0.0578,
|
| 540 |
+
"step": 510
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 26.0,
|
| 544 |
+
"learning_rate": 2.0263157894736842e-05,
|
| 545 |
+
"loss": 0.0477,
|
| 546 |
+
"step": 520
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 26.0,
|
| 550 |
+
"eval_accuracy": 0.8,
|
| 551 |
+
"eval_loss": 0.836243748664856,
|
| 552 |
+
"eval_runtime": 1.0029,
|
| 553 |
+
"eval_samples_per_second": 59.824,
|
| 554 |
+
"eval_steps_per_second": 1.994,
|
| 555 |
+
"step": 520
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 26.5,
|
| 559 |
+
"learning_rate": 1.9539473684210525e-05,
|
| 560 |
+
"loss": 0.0532,
|
| 561 |
+
"step": 530
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 27.0,
|
| 565 |
+
"learning_rate": 1.8815789473684213e-05,
|
| 566 |
+
"loss": 0.0481,
|
| 567 |
+
"step": 540
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 27.0,
|
| 571 |
+
"eval_accuracy": 0.8,
|
| 572 |
+
"eval_loss": 0.8388897180557251,
|
| 573 |
+
"eval_runtime": 1.0189,
|
| 574 |
+
"eval_samples_per_second": 58.885,
|
| 575 |
+
"eval_steps_per_second": 1.963,
|
| 576 |
+
"step": 540
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 27.5,
|
| 580 |
+
"learning_rate": 1.8092105263157896e-05,
|
| 581 |
+
"loss": 0.0426,
|
| 582 |
+
"step": 550
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 28.0,
|
| 586 |
+
"learning_rate": 1.736842105263158e-05,
|
| 587 |
+
"loss": 0.0355,
|
| 588 |
+
"step": 560
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 28.0,
|
| 592 |
+
"eval_accuracy": 0.8,
|
| 593 |
+
"eval_loss": 0.9424023032188416,
|
| 594 |
+
"eval_runtime": 1.0258,
|
| 595 |
+
"eval_samples_per_second": 58.493,
|
| 596 |
+
"eval_steps_per_second": 1.95,
|
| 597 |
+
"step": 560
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 28.5,
|
| 601 |
+
"learning_rate": 1.6644736842105264e-05,
|
| 602 |
+
"loss": 0.0298,
|
| 603 |
+
"step": 570
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 29.0,
|
| 607 |
+
"learning_rate": 1.5921052631578948e-05,
|
| 608 |
+
"loss": 0.0352,
|
| 609 |
+
"step": 580
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 29.0,
|
| 613 |
+
"eval_accuracy": 0.8,
|
| 614 |
+
"eval_loss": 0.8962697386741638,
|
| 615 |
+
"eval_runtime": 1.0413,
|
| 616 |
+
"eval_samples_per_second": 57.622,
|
| 617 |
+
"eval_steps_per_second": 1.921,
|
| 618 |
+
"step": 580
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 29.5,
|
| 622 |
+
"learning_rate": 1.5197368421052633e-05,
|
| 623 |
+
"loss": 0.0516,
|
| 624 |
+
"step": 590
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 30.0,
|
| 628 |
+
"learning_rate": 1.4473684210526315e-05,
|
| 629 |
+
"loss": 0.0335,
|
| 630 |
+
"step": 600
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 30.0,
|
| 634 |
+
"eval_accuracy": 0.8333333333333334,
|
| 635 |
+
"eval_loss": 0.8559876680374146,
|
| 636 |
+
"eval_runtime": 1.042,
|
| 637 |
+
"eval_samples_per_second": 57.582,
|
| 638 |
+
"eval_steps_per_second": 1.919,
|
| 639 |
+
"step": 600
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 30.5,
|
| 643 |
+
"learning_rate": 1.375e-05,
|
| 644 |
+
"loss": 0.0535,
|
| 645 |
+
"step": 610
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 31.0,
|
| 649 |
+
"learning_rate": 1.3026315789473684e-05,
|
| 650 |
+
"loss": 0.0372,
|
| 651 |
+
"step": 620
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 31.0,
|
| 655 |
+
"eval_accuracy": 0.8333333333333334,
|
| 656 |
+
"eval_loss": 0.7249892950057983,
|
| 657 |
+
"eval_runtime": 1.024,
|
| 658 |
+
"eval_samples_per_second": 58.596,
|
| 659 |
+
"eval_steps_per_second": 1.953,
|
| 660 |
+
"step": 620
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 31.5,
|
| 664 |
+
"learning_rate": 1.230263157894737e-05,
|
| 665 |
+
"loss": 0.037,
|
| 666 |
+
"step": 630
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 32.0,
|
| 670 |
+
"learning_rate": 1.1578947368421052e-05,
|
| 671 |
+
"loss": 0.0389,
|
| 672 |
+
"step": 640
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 32.0,
|
| 676 |
+
"eval_accuracy": 0.8166666666666667,
|
| 677 |
+
"eval_loss": 0.7846233248710632,
|
| 678 |
+
"eval_runtime": 1.0305,
|
| 679 |
+
"eval_samples_per_second": 58.227,
|
| 680 |
+
"eval_steps_per_second": 1.941,
|
| 681 |
+
"step": 640
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 32.5,
|
| 685 |
+
"learning_rate": 1.0855263157894737e-05,
|
| 686 |
+
"loss": 0.0281,
|
| 687 |
+
"step": 650
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 33.0,
|
| 691 |
+
"learning_rate": 1.0131578947368421e-05,
|
| 692 |
+
"loss": 0.0425,
|
| 693 |
+
"step": 660
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 33.0,
|
| 697 |
+
"eval_accuracy": 0.8333333333333334,
|
| 698 |
+
"eval_loss": 0.8532330989837646,
|
| 699 |
+
"eval_runtime": 1.0292,
|
| 700 |
+
"eval_samples_per_second": 58.296,
|
| 701 |
+
"eval_steps_per_second": 1.943,
|
| 702 |
+
"step": 660
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 33.5,
|
| 706 |
+
"learning_rate": 9.407894736842106e-06,
|
| 707 |
+
"loss": 0.0398,
|
| 708 |
+
"step": 670
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 34.0,
|
| 712 |
+
"learning_rate": 8.68421052631579e-06,
|
| 713 |
+
"loss": 0.0404,
|
| 714 |
+
"step": 680
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 34.0,
|
| 718 |
+
"eval_accuracy": 0.8333333333333334,
|
| 719 |
+
"eval_loss": 0.8169179558753967,
|
| 720 |
+
"eval_runtime": 0.9963,
|
| 721 |
+
"eval_samples_per_second": 60.225,
|
| 722 |
+
"eval_steps_per_second": 2.007,
|
| 723 |
+
"step": 680
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 34.5,
|
| 727 |
+
"learning_rate": 7.960526315789474e-06,
|
| 728 |
+
"loss": 0.0282,
|
| 729 |
+
"step": 690
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 35.0,
|
| 733 |
+
"learning_rate": 7.2368421052631575e-06,
|
| 734 |
+
"loss": 0.0359,
|
| 735 |
+
"step": 700
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 35.0,
|
| 739 |
+
"eval_accuracy": 0.8166666666666667,
|
| 740 |
+
"eval_loss": 0.868202269077301,
|
| 741 |
+
"eval_runtime": 1.0467,
|
| 742 |
+
"eval_samples_per_second": 57.325,
|
| 743 |
+
"eval_steps_per_second": 1.911,
|
| 744 |
+
"step": 700
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 35.5,
|
| 748 |
+
"learning_rate": 6.513157894736842e-06,
|
| 749 |
+
"loss": 0.0464,
|
| 750 |
+
"step": 710
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 36.0,
|
| 754 |
+
"learning_rate": 5.789473684210526e-06,
|
| 755 |
+
"loss": 0.0231,
|
| 756 |
+
"step": 720
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 36.0,
|
| 760 |
+
"eval_accuracy": 0.8166666666666667,
|
| 761 |
+
"eval_loss": 0.9361733198165894,
|
| 762 |
+
"eval_runtime": 1.0146,
|
| 763 |
+
"eval_samples_per_second": 59.135,
|
| 764 |
+
"eval_steps_per_second": 1.971,
|
| 765 |
+
"step": 720
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 36.5,
|
| 769 |
+
"learning_rate": 5.0657894736842104e-06,
|
| 770 |
+
"loss": 0.0272,
|
| 771 |
+
"step": 730
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 37.0,
|
| 775 |
+
"learning_rate": 4.342105263157895e-06,
|
| 776 |
+
"loss": 0.027,
|
| 777 |
+
"step": 740
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 37.0,
|
| 781 |
+
"eval_accuracy": 0.8166666666666667,
|
| 782 |
+
"eval_loss": 0.9138814210891724,
|
| 783 |
+
"eval_runtime": 1.0004,
|
| 784 |
+
"eval_samples_per_second": 59.974,
|
| 785 |
+
"eval_steps_per_second": 1.999,
|
| 786 |
+
"step": 740
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 37.5,
|
| 790 |
+
"learning_rate": 3.6184210526315788e-06,
|
| 791 |
+
"loss": 0.0253,
|
| 792 |
+
"step": 750
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 38.0,
|
| 796 |
+
"learning_rate": 2.894736842105263e-06,
|
| 797 |
+
"loss": 0.0214,
|
| 798 |
+
"step": 760
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 38.0,
|
| 802 |
+
"eval_accuracy": 0.8166666666666667,
|
| 803 |
+
"eval_loss": 0.8781832456588745,
|
| 804 |
+
"eval_runtime": 1.0219,
|
| 805 |
+
"eval_samples_per_second": 58.714,
|
| 806 |
+
"eval_steps_per_second": 1.957,
|
| 807 |
+
"step": 760
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 38.5,
|
| 811 |
+
"learning_rate": 2.1710526315789475e-06,
|
| 812 |
+
"loss": 0.0279,
|
| 813 |
+
"step": 770
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 39.0,
|
| 817 |
+
"learning_rate": 1.4473684210526315e-06,
|
| 818 |
+
"loss": 0.0191,
|
| 819 |
+
"step": 780
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 39.0,
|
| 823 |
+
"eval_accuracy": 0.8166666666666667,
|
| 824 |
+
"eval_loss": 0.8794050812721252,
|
| 825 |
+
"eval_runtime": 1.0338,
|
| 826 |
+
"eval_samples_per_second": 58.037,
|
| 827 |
+
"eval_steps_per_second": 1.935,
|
| 828 |
+
"step": 780
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 39.5,
|
| 832 |
+
"learning_rate": 7.236842105263157e-07,
|
| 833 |
+
"loss": 0.0161,
|
| 834 |
+
"step": 790
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 40.0,
|
| 838 |
+
"learning_rate": 0.0,
|
| 839 |
+
"loss": 0.0293,
|
| 840 |
+
"step": 800
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 40.0,
|
| 844 |
+
"eval_accuracy": 0.8166666666666667,
|
| 845 |
+
"eval_loss": 0.8929299712181091,
|
| 846 |
+
"eval_runtime": 1.0258,
|
| 847 |
+
"eval_samples_per_second": 58.493,
|
| 848 |
+
"eval_steps_per_second": 1.95,
|
| 849 |
+
"step": 800
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 40.0,
|
| 853 |
+
"step": 800,
|
| 854 |
+
"total_flos": 7.873327274596762e+18,
|
| 855 |
+
"train_loss": 0.1800640467181802,
|
| 856 |
+
"train_runtime": 1621.1538,
|
| 857 |
+
"train_samples_per_second": 62.671,
|
| 858 |
+
"train_steps_per_second": 0.493
|
| 859 |
+
}
|
| 860 |
+
],
|
| 861 |
+
"logging_steps": 10,
|
| 862 |
+
"max_steps": 800,
|
| 863 |
+
"num_input_tokens_seen": 0,
|
| 864 |
+
"num_train_epochs": 40,
|
| 865 |
+
"save_steps": 500,
|
| 866 |
+
"total_flos": 7.873327274596762e+18,
|
| 867 |
+
"train_batch_size": 32,
|
| 868 |
+
"trial_name": null,
|
| 869 |
+
"trial_params": null
|
| 870 |
+
}
|