End of training
Browse files- README.md +3 -3
- all_results.json +12 -0
- eval_results.json +8 -0
- runs/Jun12_13-24-49_DESKTOP-SKBE9FB/events.out.tfevents.1718220574.DESKTOP-SKBE9FB.8880.1 +3 -0
- train_results.json +7 -0
- trainer_state.json +984 -0
README.md
CHANGED
|
@@ -21,7 +21,7 @@ model-index:
|
|
| 21 |
metrics:
|
| 22 |
- name: Accuracy
|
| 23 |
type: accuracy
|
| 24 |
-
value: 0.
|
| 25 |
---
|
| 26 |
|
| 27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -31,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 31 |
|
| 32 |
This model is a fine-tuned version of [MBZUAI/swiftformer-xs](https://huggingface.co/MBZUAI/swiftformer-xs) on the imagefolder dataset.
|
| 33 |
It achieves the following results on the evaluation set:
|
| 34 |
-
- Loss: 0.
|
| 35 |
-
- Accuracy: 0.
|
| 36 |
|
| 37 |
## Model description
|
| 38 |
|
|
|
|
| 21 |
metrics:
|
| 22 |
- name: Accuracy
|
| 23 |
type: accuracy
|
| 24 |
+
value: 0.8043478260869565
|
| 25 |
---
|
| 26 |
|
| 27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 31 |
|
| 32 |
This model is a fine-tuned version of [MBZUAI/swiftformer-xs](https://huggingface.co/MBZUAI/swiftformer-xs) on the imagefolder dataset.
|
| 33 |
It achieves the following results on the evaluation set:
|
| 34 |
+
- Loss: 0.7032
|
| 35 |
+
- Accuracy: 0.8043
|
| 36 |
|
| 37 |
## Model description
|
| 38 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 73.85,
|
| 3 |
+
"eval_accuracy": 0.8043478260869565,
|
| 4 |
+
"eval_loss": 0.7032170295715332,
|
| 5 |
+
"eval_runtime": 0.8089,
|
| 6 |
+
"eval_samples_per_second": 56.865,
|
| 7 |
+
"eval_steps_per_second": 2.472,
|
| 8 |
+
"train_loss": 0.40781121912101903,
|
| 9 |
+
"train_runtime": 277.6094,
|
| 10 |
+
"train_samples_per_second": 236.015,
|
| 11 |
+
"train_steps_per_second": 1.729
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 73.85,
|
| 3 |
+
"eval_accuracy": 0.8043478260869565,
|
| 4 |
+
"eval_loss": 0.7032170295715332,
|
| 5 |
+
"eval_runtime": 0.8089,
|
| 6 |
+
"eval_samples_per_second": 56.865,
|
| 7 |
+
"eval_steps_per_second": 2.472
|
| 8 |
+
}
|
runs/Jun12_13-24-49_DESKTOP-SKBE9FB/events.out.tfevents.1718220574.DESKTOP-SKBE9FB.8880.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7537522c268e66a9feb2886c2413b5eb937c2982fa7388a65a843b7ce4699729
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 73.85,
|
| 3 |
+
"train_loss": 0.40781121912101903,
|
| 4 |
+
"train_runtime": 277.6094,
|
| 5 |
+
"train_samples_per_second": 236.015,
|
| 6 |
+
"train_steps_per_second": 1.729
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,984 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8043478260869565,
|
| 3 |
+
"best_model_checkpoint": "swiftformer-xs-ve-U13-b-80c\\checkpoint-175",
|
| 4 |
+
"epoch": 73.84615384615384,
|
| 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": 0.92,
|
| 13 |
+
"eval_accuracy": 0.2391304347826087,
|
| 14 |
+
"eval_loss": 1.3860037326812744,
|
| 15 |
+
"eval_runtime": 0.6497,
|
| 16 |
+
"eval_samples_per_second": 70.799,
|
| 17 |
+
"eval_steps_per_second": 3.078,
|
| 18 |
+
"step": 6
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 1.54,
|
| 22 |
+
"learning_rate": 2.777777777777778e-05,
|
| 23 |
+
"loss": 1.3859,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.0,
|
| 28 |
+
"eval_accuracy": 0.30434782608695654,
|
| 29 |
+
"eval_loss": 1.3843744993209839,
|
| 30 |
+
"eval_runtime": 0.6508,
|
| 31 |
+
"eval_samples_per_second": 70.684,
|
| 32 |
+
"eval_steps_per_second": 3.073,
|
| 33 |
+
"step": 13
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 2.92,
|
| 37 |
+
"eval_accuracy": 0.1956521739130435,
|
| 38 |
+
"eval_loss": 1.3819622993469238,
|
| 39 |
+
"eval_runtime": 0.6238,
|
| 40 |
+
"eval_samples_per_second": 73.745,
|
| 41 |
+
"eval_steps_per_second": 3.206,
|
| 42 |
+
"step": 19
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 3.08,
|
| 46 |
+
"learning_rate": 5.555555555555556e-05,
|
| 47 |
+
"loss": 1.381,
|
| 48 |
+
"step": 20
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 4.0,
|
| 52 |
+
"eval_accuracy": 0.17391304347826086,
|
| 53 |
+
"eval_loss": 1.3745858669281006,
|
| 54 |
+
"eval_runtime": 0.6174,
|
| 55 |
+
"eval_samples_per_second": 74.504,
|
| 56 |
+
"eval_steps_per_second": 3.239,
|
| 57 |
+
"step": 26
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 4.62,
|
| 61 |
+
"learning_rate": 8.333333333333334e-05,
|
| 62 |
+
"loss": 1.3573,
|
| 63 |
+
"step": 30
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 4.92,
|
| 67 |
+
"eval_accuracy": 0.1956521739130435,
|
| 68 |
+
"eval_loss": 1.3642687797546387,
|
| 69 |
+
"eval_runtime": 0.5993,
|
| 70 |
+
"eval_samples_per_second": 76.759,
|
| 71 |
+
"eval_steps_per_second": 3.337,
|
| 72 |
+
"step": 32
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 6.0,
|
| 76 |
+
"eval_accuracy": 0.15217391304347827,
|
| 77 |
+
"eval_loss": 1.3561071157455444,
|
| 78 |
+
"eval_runtime": 0.6092,
|
| 79 |
+
"eval_samples_per_second": 75.505,
|
| 80 |
+
"eval_steps_per_second": 3.283,
|
| 81 |
+
"step": 39
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 6.15,
|
| 85 |
+
"learning_rate": 0.00011111111111111112,
|
| 86 |
+
"loss": 1.2692,
|
| 87 |
+
"step": 40
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 6.92,
|
| 91 |
+
"eval_accuracy": 0.15217391304347827,
|
| 92 |
+
"eval_loss": 1.3582805395126343,
|
| 93 |
+
"eval_runtime": 0.6066,
|
| 94 |
+
"eval_samples_per_second": 75.83,
|
| 95 |
+
"eval_steps_per_second": 3.297,
|
| 96 |
+
"step": 45
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 7.69,
|
| 100 |
+
"learning_rate": 0.0001388888888888889,
|
| 101 |
+
"loss": 1.1682,
|
| 102 |
+
"step": 50
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 8.0,
|
| 106 |
+
"eval_accuracy": 0.17391304347826086,
|
| 107 |
+
"eval_loss": 1.3623026609420776,
|
| 108 |
+
"eval_runtime": 0.6189,
|
| 109 |
+
"eval_samples_per_second": 74.33,
|
| 110 |
+
"eval_steps_per_second": 3.232,
|
| 111 |
+
"step": 52
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 8.92,
|
| 115 |
+
"eval_accuracy": 0.2608695652173913,
|
| 116 |
+
"eval_loss": 1.3296467065811157,
|
| 117 |
+
"eval_runtime": 0.6038,
|
| 118 |
+
"eval_samples_per_second": 76.178,
|
| 119 |
+
"eval_steps_per_second": 3.312,
|
| 120 |
+
"step": 58
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 9.23,
|
| 124 |
+
"learning_rate": 0.0001666666666666667,
|
| 125 |
+
"loss": 1.1005,
|
| 126 |
+
"step": 60
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 10.0,
|
| 130 |
+
"eval_accuracy": 0.391304347826087,
|
| 131 |
+
"eval_loss": 1.266342282295227,
|
| 132 |
+
"eval_runtime": 0.6296,
|
| 133 |
+
"eval_samples_per_second": 73.06,
|
| 134 |
+
"eval_steps_per_second": 3.177,
|
| 135 |
+
"step": 65
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 10.77,
|
| 139 |
+
"learning_rate": 0.00019444444444444446,
|
| 140 |
+
"loss": 0.9884,
|
| 141 |
+
"step": 70
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 10.92,
|
| 145 |
+
"eval_accuracy": 0.3695652173913043,
|
| 146 |
+
"eval_loss": 1.3159973621368408,
|
| 147 |
+
"eval_runtime": 0.6014,
|
| 148 |
+
"eval_samples_per_second": 76.491,
|
| 149 |
+
"eval_steps_per_second": 3.326,
|
| 150 |
+
"step": 71
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 12.0,
|
| 154 |
+
"eval_accuracy": 0.4782608695652174,
|
| 155 |
+
"eval_loss": 1.1806195974349976,
|
| 156 |
+
"eval_runtime": 0.6259,
|
| 157 |
+
"eval_samples_per_second": 73.491,
|
| 158 |
+
"eval_steps_per_second": 3.195,
|
| 159 |
+
"step": 78
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 12.31,
|
| 163 |
+
"learning_rate": 0.000196078431372549,
|
| 164 |
+
"loss": 0.9111,
|
| 165 |
+
"step": 80
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 12.92,
|
| 169 |
+
"eval_accuracy": 0.6086956521739131,
|
| 170 |
+
"eval_loss": 1.15597403049469,
|
| 171 |
+
"eval_runtime": 0.6243,
|
| 172 |
+
"eval_samples_per_second": 73.68,
|
| 173 |
+
"eval_steps_per_second": 3.203,
|
| 174 |
+
"step": 84
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 13.85,
|
| 178 |
+
"learning_rate": 0.0001911764705882353,
|
| 179 |
+
"loss": 0.8464,
|
| 180 |
+
"step": 90
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 14.0,
|
| 184 |
+
"eval_accuracy": 0.5869565217391305,
|
| 185 |
+
"eval_loss": 1.1349503993988037,
|
| 186 |
+
"eval_runtime": 0.6226,
|
| 187 |
+
"eval_samples_per_second": 73.889,
|
| 188 |
+
"eval_steps_per_second": 3.213,
|
| 189 |
+
"step": 91
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 14.92,
|
| 193 |
+
"eval_accuracy": 0.6304347826086957,
|
| 194 |
+
"eval_loss": 1.0768355131149292,
|
| 195 |
+
"eval_runtime": 0.6092,
|
| 196 |
+
"eval_samples_per_second": 75.507,
|
| 197 |
+
"eval_steps_per_second": 3.283,
|
| 198 |
+
"step": 97
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 15.38,
|
| 202 |
+
"learning_rate": 0.00018627450980392157,
|
| 203 |
+
"loss": 0.7768,
|
| 204 |
+
"step": 100
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 16.0,
|
| 208 |
+
"eval_accuracy": 0.6086956521739131,
|
| 209 |
+
"eval_loss": 0.9706609845161438,
|
| 210 |
+
"eval_runtime": 0.6399,
|
| 211 |
+
"eval_samples_per_second": 71.887,
|
| 212 |
+
"eval_steps_per_second": 3.126,
|
| 213 |
+
"step": 104
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 16.92,
|
| 217 |
+
"learning_rate": 0.00018137254901960786,
|
| 218 |
+
"loss": 0.6754,
|
| 219 |
+
"step": 110
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 16.92,
|
| 223 |
+
"eval_accuracy": 0.6521739130434783,
|
| 224 |
+
"eval_loss": 0.9544328451156616,
|
| 225 |
+
"eval_runtime": 0.5992,
|
| 226 |
+
"eval_samples_per_second": 76.775,
|
| 227 |
+
"eval_steps_per_second": 3.338,
|
| 228 |
+
"step": 110
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 18.0,
|
| 232 |
+
"eval_accuracy": 0.6739130434782609,
|
| 233 |
+
"eval_loss": 0.9885360598564148,
|
| 234 |
+
"eval_runtime": 0.6261,
|
| 235 |
+
"eval_samples_per_second": 73.474,
|
| 236 |
+
"eval_steps_per_second": 3.195,
|
| 237 |
+
"step": 117
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 18.46,
|
| 241 |
+
"learning_rate": 0.00017647058823529413,
|
| 242 |
+
"loss": 0.657,
|
| 243 |
+
"step": 120
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 18.92,
|
| 247 |
+
"eval_accuracy": 0.6956521739130435,
|
| 248 |
+
"eval_loss": 0.85777348279953,
|
| 249 |
+
"eval_runtime": 0.6125,
|
| 250 |
+
"eval_samples_per_second": 75.103,
|
| 251 |
+
"eval_steps_per_second": 3.265,
|
| 252 |
+
"step": 123
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 20.0,
|
| 256 |
+
"learning_rate": 0.0001715686274509804,
|
| 257 |
+
"loss": 0.5408,
|
| 258 |
+
"step": 130
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 20.0,
|
| 262 |
+
"eval_accuracy": 0.7391304347826086,
|
| 263 |
+
"eval_loss": 0.7794063687324524,
|
| 264 |
+
"eval_runtime": 0.5998,
|
| 265 |
+
"eval_samples_per_second": 76.697,
|
| 266 |
+
"eval_steps_per_second": 3.335,
|
| 267 |
+
"step": 130
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 20.92,
|
| 271 |
+
"eval_accuracy": 0.7391304347826086,
|
| 272 |
+
"eval_loss": 0.8072043657302856,
|
| 273 |
+
"eval_runtime": 0.6119,
|
| 274 |
+
"eval_samples_per_second": 75.172,
|
| 275 |
+
"eval_steps_per_second": 3.268,
|
| 276 |
+
"step": 136
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 21.54,
|
| 280 |
+
"learning_rate": 0.0001666666666666667,
|
| 281 |
+
"loss": 0.5094,
|
| 282 |
+
"step": 140
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 22.0,
|
| 286 |
+
"eval_accuracy": 0.6739130434782609,
|
| 287 |
+
"eval_loss": 0.7917114496231079,
|
| 288 |
+
"eval_runtime": 0.6088,
|
| 289 |
+
"eval_samples_per_second": 75.563,
|
| 290 |
+
"eval_steps_per_second": 3.285,
|
| 291 |
+
"step": 143
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 22.92,
|
| 295 |
+
"eval_accuracy": 0.6739130434782609,
|
| 296 |
+
"eval_loss": 0.7974965572357178,
|
| 297 |
+
"eval_runtime": 0.6475,
|
| 298 |
+
"eval_samples_per_second": 71.039,
|
| 299 |
+
"eval_steps_per_second": 3.089,
|
| 300 |
+
"step": 149
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 23.08,
|
| 304 |
+
"learning_rate": 0.00016176470588235295,
|
| 305 |
+
"loss": 0.4546,
|
| 306 |
+
"step": 150
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 24.0,
|
| 310 |
+
"eval_accuracy": 0.7608695652173914,
|
| 311 |
+
"eval_loss": 0.758342981338501,
|
| 312 |
+
"eval_runtime": 0.6038,
|
| 313 |
+
"eval_samples_per_second": 76.184,
|
| 314 |
+
"eval_steps_per_second": 3.312,
|
| 315 |
+
"step": 156
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 24.62,
|
| 319 |
+
"learning_rate": 0.00015686274509803922,
|
| 320 |
+
"loss": 0.3722,
|
| 321 |
+
"step": 160
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 24.92,
|
| 325 |
+
"eval_accuracy": 0.782608695652174,
|
| 326 |
+
"eval_loss": 0.7073833346366882,
|
| 327 |
+
"eval_runtime": 0.6225,
|
| 328 |
+
"eval_samples_per_second": 73.896,
|
| 329 |
+
"eval_steps_per_second": 3.213,
|
| 330 |
+
"step": 162
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 26.0,
|
| 334 |
+
"eval_accuracy": 0.7391304347826086,
|
| 335 |
+
"eval_loss": 0.6909225583076477,
|
| 336 |
+
"eval_runtime": 0.6068,
|
| 337 |
+
"eval_samples_per_second": 75.807,
|
| 338 |
+
"eval_steps_per_second": 3.296,
|
| 339 |
+
"step": 169
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 26.15,
|
| 343 |
+
"learning_rate": 0.00015196078431372549,
|
| 344 |
+
"loss": 0.3494,
|
| 345 |
+
"step": 170
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 26.92,
|
| 349 |
+
"eval_accuracy": 0.8043478260869565,
|
| 350 |
+
"eval_loss": 0.7032170295715332,
|
| 351 |
+
"eval_runtime": 0.6101,
|
| 352 |
+
"eval_samples_per_second": 75.403,
|
| 353 |
+
"eval_steps_per_second": 3.278,
|
| 354 |
+
"step": 175
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 27.69,
|
| 358 |
+
"learning_rate": 0.00014705882352941178,
|
| 359 |
+
"loss": 0.3092,
|
| 360 |
+
"step": 180
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 28.0,
|
| 364 |
+
"eval_accuracy": 0.782608695652174,
|
| 365 |
+
"eval_loss": 0.8148682713508606,
|
| 366 |
+
"eval_runtime": 0.6369,
|
| 367 |
+
"eval_samples_per_second": 72.229,
|
| 368 |
+
"eval_steps_per_second": 3.14,
|
| 369 |
+
"step": 182
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 28.92,
|
| 373 |
+
"eval_accuracy": 0.782608695652174,
|
| 374 |
+
"eval_loss": 0.7898127436637878,
|
| 375 |
+
"eval_runtime": 0.6193,
|
| 376 |
+
"eval_samples_per_second": 74.278,
|
| 377 |
+
"eval_steps_per_second": 3.229,
|
| 378 |
+
"step": 188
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 29.23,
|
| 382 |
+
"learning_rate": 0.00014215686274509804,
|
| 383 |
+
"loss": 0.2643,
|
| 384 |
+
"step": 190
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 30.0,
|
| 388 |
+
"eval_accuracy": 0.8043478260869565,
|
| 389 |
+
"eval_loss": 0.7311907410621643,
|
| 390 |
+
"eval_runtime": 0.6043,
|
| 391 |
+
"eval_samples_per_second": 76.119,
|
| 392 |
+
"eval_steps_per_second": 3.31,
|
| 393 |
+
"step": 195
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 30.77,
|
| 397 |
+
"learning_rate": 0.0001372549019607843,
|
| 398 |
+
"loss": 0.2659,
|
| 399 |
+
"step": 200
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 30.92,
|
| 403 |
+
"eval_accuracy": 0.717391304347826,
|
| 404 |
+
"eval_loss": 0.7597643733024597,
|
| 405 |
+
"eval_runtime": 0.6226,
|
| 406 |
+
"eval_samples_per_second": 73.885,
|
| 407 |
+
"eval_steps_per_second": 3.212,
|
| 408 |
+
"step": 201
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 32.0,
|
| 412 |
+
"eval_accuracy": 0.7608695652173914,
|
| 413 |
+
"eval_loss": 0.7530593276023865,
|
| 414 |
+
"eval_runtime": 0.5971,
|
| 415 |
+
"eval_samples_per_second": 77.044,
|
| 416 |
+
"eval_steps_per_second": 3.35,
|
| 417 |
+
"step": 208
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 32.31,
|
| 421 |
+
"learning_rate": 0.0001323529411764706,
|
| 422 |
+
"loss": 0.2298,
|
| 423 |
+
"step": 210
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 32.92,
|
| 427 |
+
"eval_accuracy": 0.8043478260869565,
|
| 428 |
+
"eval_loss": 0.6876691579818726,
|
| 429 |
+
"eval_runtime": 0.6354,
|
| 430 |
+
"eval_samples_per_second": 72.394,
|
| 431 |
+
"eval_steps_per_second": 3.148,
|
| 432 |
+
"step": 214
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 33.85,
|
| 436 |
+
"learning_rate": 0.00012745098039215687,
|
| 437 |
+
"loss": 0.2147,
|
| 438 |
+
"step": 220
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 34.0,
|
| 442 |
+
"eval_accuracy": 0.8043478260869565,
|
| 443 |
+
"eval_loss": 0.6864094734191895,
|
| 444 |
+
"eval_runtime": 0.6204,
|
| 445 |
+
"eval_samples_per_second": 74.15,
|
| 446 |
+
"eval_steps_per_second": 3.224,
|
| 447 |
+
"step": 221
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 34.92,
|
| 451 |
+
"eval_accuracy": 0.7391304347826086,
|
| 452 |
+
"eval_loss": 0.7655704617500305,
|
| 453 |
+
"eval_runtime": 0.623,
|
| 454 |
+
"eval_samples_per_second": 73.835,
|
| 455 |
+
"eval_steps_per_second": 3.21,
|
| 456 |
+
"step": 227
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 35.38,
|
| 460 |
+
"learning_rate": 0.00012254901960784316,
|
| 461 |
+
"loss": 0.2457,
|
| 462 |
+
"step": 230
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 36.0,
|
| 466 |
+
"eval_accuracy": 0.7391304347826086,
|
| 467 |
+
"eval_loss": 0.8493983149528503,
|
| 468 |
+
"eval_runtime": 0.6074,
|
| 469 |
+
"eval_samples_per_second": 75.734,
|
| 470 |
+
"eval_steps_per_second": 3.293,
|
| 471 |
+
"step": 234
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 36.92,
|
| 475 |
+
"learning_rate": 0.00011764705882352942,
|
| 476 |
+
"loss": 0.1905,
|
| 477 |
+
"step": 240
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 36.92,
|
| 481 |
+
"eval_accuracy": 0.7608695652173914,
|
| 482 |
+
"eval_loss": 0.7319269776344299,
|
| 483 |
+
"eval_runtime": 0.6155,
|
| 484 |
+
"eval_samples_per_second": 74.733,
|
| 485 |
+
"eval_steps_per_second": 3.249,
|
| 486 |
+
"step": 240
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 38.0,
|
| 490 |
+
"eval_accuracy": 0.6956521739130435,
|
| 491 |
+
"eval_loss": 0.8289902806282043,
|
| 492 |
+
"eval_runtime": 0.6141,
|
| 493 |
+
"eval_samples_per_second": 74.91,
|
| 494 |
+
"eval_steps_per_second": 3.257,
|
| 495 |
+
"step": 247
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 38.46,
|
| 499 |
+
"learning_rate": 0.0001127450980392157,
|
| 500 |
+
"loss": 0.2073,
|
| 501 |
+
"step": 250
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 38.92,
|
| 505 |
+
"eval_accuracy": 0.7608695652173914,
|
| 506 |
+
"eval_loss": 0.7963315844535828,
|
| 507 |
+
"eval_runtime": 0.6558,
|
| 508 |
+
"eval_samples_per_second": 70.149,
|
| 509 |
+
"eval_steps_per_second": 3.05,
|
| 510 |
+
"step": 253
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 40.0,
|
| 514 |
+
"learning_rate": 0.00010784313725490196,
|
| 515 |
+
"loss": 0.1603,
|
| 516 |
+
"step": 260
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 40.0,
|
| 520 |
+
"eval_accuracy": 0.6956521739130435,
|
| 521 |
+
"eval_loss": 0.8692622780799866,
|
| 522 |
+
"eval_runtime": 0.5964,
|
| 523 |
+
"eval_samples_per_second": 77.127,
|
| 524 |
+
"eval_steps_per_second": 3.353,
|
| 525 |
+
"step": 260
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 40.92,
|
| 529 |
+
"eval_accuracy": 0.8043478260869565,
|
| 530 |
+
"eval_loss": 0.7137989401817322,
|
| 531 |
+
"eval_runtime": 0.6168,
|
| 532 |
+
"eval_samples_per_second": 74.577,
|
| 533 |
+
"eval_steps_per_second": 3.242,
|
| 534 |
+
"step": 266
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 41.54,
|
| 538 |
+
"learning_rate": 0.00010294117647058823,
|
| 539 |
+
"loss": 0.1852,
|
| 540 |
+
"step": 270
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 42.0,
|
| 544 |
+
"eval_accuracy": 0.7608695652173914,
|
| 545 |
+
"eval_loss": 0.7274174690246582,
|
| 546 |
+
"eval_runtime": 0.6771,
|
| 547 |
+
"eval_samples_per_second": 67.936,
|
| 548 |
+
"eval_steps_per_second": 2.954,
|
| 549 |
+
"step": 273
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 42.92,
|
| 553 |
+
"eval_accuracy": 0.6739130434782609,
|
| 554 |
+
"eval_loss": 0.8352705240249634,
|
| 555 |
+
"eval_runtime": 0.6424,
|
| 556 |
+
"eval_samples_per_second": 71.602,
|
| 557 |
+
"eval_steps_per_second": 3.113,
|
| 558 |
+
"step": 279
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 43.08,
|
| 562 |
+
"learning_rate": 9.80392156862745e-05,
|
| 563 |
+
"loss": 0.1641,
|
| 564 |
+
"step": 280
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 44.0,
|
| 568 |
+
"eval_accuracy": 0.6956521739130435,
|
| 569 |
+
"eval_loss": 0.9382135272026062,
|
| 570 |
+
"eval_runtime": 0.6048,
|
| 571 |
+
"eval_samples_per_second": 76.054,
|
| 572 |
+
"eval_steps_per_second": 3.307,
|
| 573 |
+
"step": 286
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 44.62,
|
| 577 |
+
"learning_rate": 9.313725490196079e-05,
|
| 578 |
+
"loss": 0.1568,
|
| 579 |
+
"step": 290
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 44.92,
|
| 583 |
+
"eval_accuracy": 0.717391304347826,
|
| 584 |
+
"eval_loss": 0.8655094504356384,
|
| 585 |
+
"eval_runtime": 0.6326,
|
| 586 |
+
"eval_samples_per_second": 72.716,
|
| 587 |
+
"eval_steps_per_second": 3.162,
|
| 588 |
+
"step": 292
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 46.0,
|
| 592 |
+
"eval_accuracy": 0.7391304347826086,
|
| 593 |
+
"eval_loss": 0.7620847821235657,
|
| 594 |
+
"eval_runtime": 0.6048,
|
| 595 |
+
"eval_samples_per_second": 76.056,
|
| 596 |
+
"eval_steps_per_second": 3.307,
|
| 597 |
+
"step": 299
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 46.15,
|
| 601 |
+
"learning_rate": 8.823529411764706e-05,
|
| 602 |
+
"loss": 0.1498,
|
| 603 |
+
"step": 300
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 46.92,
|
| 607 |
+
"eval_accuracy": 0.717391304347826,
|
| 608 |
+
"eval_loss": 0.794407069683075,
|
| 609 |
+
"eval_runtime": 0.6439,
|
| 610 |
+
"eval_samples_per_second": 71.44,
|
| 611 |
+
"eval_steps_per_second": 3.106,
|
| 612 |
+
"step": 305
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 47.69,
|
| 616 |
+
"learning_rate": 8.333333333333334e-05,
|
| 617 |
+
"loss": 0.1563,
|
| 618 |
+
"step": 310
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 48.0,
|
| 622 |
+
"eval_accuracy": 0.6956521739130435,
|
| 623 |
+
"eval_loss": 0.8432682752609253,
|
| 624 |
+
"eval_runtime": 0.6319,
|
| 625 |
+
"eval_samples_per_second": 72.801,
|
| 626 |
+
"eval_steps_per_second": 3.165,
|
| 627 |
+
"step": 312
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 48.92,
|
| 631 |
+
"eval_accuracy": 0.7608695652173914,
|
| 632 |
+
"eval_loss": 0.8633100986480713,
|
| 633 |
+
"eval_runtime": 0.6452,
|
| 634 |
+
"eval_samples_per_second": 71.293,
|
| 635 |
+
"eval_steps_per_second": 3.1,
|
| 636 |
+
"step": 318
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 49.23,
|
| 640 |
+
"learning_rate": 7.843137254901961e-05,
|
| 641 |
+
"loss": 0.1554,
|
| 642 |
+
"step": 320
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 50.0,
|
| 646 |
+
"eval_accuracy": 0.7391304347826086,
|
| 647 |
+
"eval_loss": 0.8542913198471069,
|
| 648 |
+
"eval_runtime": 0.6393,
|
| 649 |
+
"eval_samples_per_second": 71.95,
|
| 650 |
+
"eval_steps_per_second": 3.128,
|
| 651 |
+
"step": 325
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 50.77,
|
| 655 |
+
"learning_rate": 7.352941176470589e-05,
|
| 656 |
+
"loss": 0.1316,
|
| 657 |
+
"step": 330
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 50.92,
|
| 661 |
+
"eval_accuracy": 0.717391304347826,
|
| 662 |
+
"eval_loss": 0.9127072095870972,
|
| 663 |
+
"eval_runtime": 0.6018,
|
| 664 |
+
"eval_samples_per_second": 76.431,
|
| 665 |
+
"eval_steps_per_second": 3.323,
|
| 666 |
+
"step": 331
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 52.0,
|
| 670 |
+
"eval_accuracy": 0.6956521739130435,
|
| 671 |
+
"eval_loss": 0.9248411059379578,
|
| 672 |
+
"eval_runtime": 0.6005,
|
| 673 |
+
"eval_samples_per_second": 76.606,
|
| 674 |
+
"eval_steps_per_second": 3.331,
|
| 675 |
+
"step": 338
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 52.31,
|
| 679 |
+
"learning_rate": 6.862745098039216e-05,
|
| 680 |
+
"loss": 0.1264,
|
| 681 |
+
"step": 340
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 52.92,
|
| 685 |
+
"eval_accuracy": 0.6956521739130435,
|
| 686 |
+
"eval_loss": 0.9349088072776794,
|
| 687 |
+
"eval_runtime": 0.5946,
|
| 688 |
+
"eval_samples_per_second": 77.368,
|
| 689 |
+
"eval_steps_per_second": 3.364,
|
| 690 |
+
"step": 344
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 53.85,
|
| 694 |
+
"learning_rate": 6.372549019607843e-05,
|
| 695 |
+
"loss": 0.1082,
|
| 696 |
+
"step": 350
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 54.0,
|
| 700 |
+
"eval_accuracy": 0.6739130434782609,
|
| 701 |
+
"eval_loss": 0.978458046913147,
|
| 702 |
+
"eval_runtime": 0.6614,
|
| 703 |
+
"eval_samples_per_second": 69.548,
|
| 704 |
+
"eval_steps_per_second": 3.024,
|
| 705 |
+
"step": 351
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 54.92,
|
| 709 |
+
"eval_accuracy": 0.6739130434782609,
|
| 710 |
+
"eval_loss": 1.0165393352508545,
|
| 711 |
+
"eval_runtime": 0.6054,
|
| 712 |
+
"eval_samples_per_second": 75.984,
|
| 713 |
+
"eval_steps_per_second": 3.304,
|
| 714 |
+
"step": 357
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 55.38,
|
| 718 |
+
"learning_rate": 5.882352941176471e-05,
|
| 719 |
+
"loss": 0.1366,
|
| 720 |
+
"step": 360
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 56.0,
|
| 724 |
+
"eval_accuracy": 0.6956521739130435,
|
| 725 |
+
"eval_loss": 0.8369129300117493,
|
| 726 |
+
"eval_runtime": 0.6396,
|
| 727 |
+
"eval_samples_per_second": 71.916,
|
| 728 |
+
"eval_steps_per_second": 3.127,
|
| 729 |
+
"step": 364
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 56.92,
|
| 733 |
+
"learning_rate": 5.392156862745098e-05,
|
| 734 |
+
"loss": 0.1546,
|
| 735 |
+
"step": 370
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 56.92,
|
| 739 |
+
"eval_accuracy": 0.717391304347826,
|
| 740 |
+
"eval_loss": 0.8372054696083069,
|
| 741 |
+
"eval_runtime": 0.6015,
|
| 742 |
+
"eval_samples_per_second": 76.478,
|
| 743 |
+
"eval_steps_per_second": 3.325,
|
| 744 |
+
"step": 370
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 58.0,
|
| 748 |
+
"eval_accuracy": 0.6956521739130435,
|
| 749 |
+
"eval_loss": 0.8595665097236633,
|
| 750 |
+
"eval_runtime": 0.6434,
|
| 751 |
+
"eval_samples_per_second": 71.491,
|
| 752 |
+
"eval_steps_per_second": 3.108,
|
| 753 |
+
"step": 377
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 58.46,
|
| 757 |
+
"learning_rate": 4.901960784313725e-05,
|
| 758 |
+
"loss": 0.1218,
|
| 759 |
+
"step": 380
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 58.92,
|
| 763 |
+
"eval_accuracy": 0.717391304347826,
|
| 764 |
+
"eval_loss": 0.8054145574569702,
|
| 765 |
+
"eval_runtime": 0.6049,
|
| 766 |
+
"eval_samples_per_second": 76.042,
|
| 767 |
+
"eval_steps_per_second": 3.306,
|
| 768 |
+
"step": 383
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 60.0,
|
| 772 |
+
"learning_rate": 4.411764705882353e-05,
|
| 773 |
+
"loss": 0.1162,
|
| 774 |
+
"step": 390
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 60.0,
|
| 778 |
+
"eval_accuracy": 0.7391304347826086,
|
| 779 |
+
"eval_loss": 0.7963301539421082,
|
| 780 |
+
"eval_runtime": 0.6236,
|
| 781 |
+
"eval_samples_per_second": 73.763,
|
| 782 |
+
"eval_steps_per_second": 3.207,
|
| 783 |
+
"step": 390
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 60.92,
|
| 787 |
+
"eval_accuracy": 0.7391304347826086,
|
| 788 |
+
"eval_loss": 0.795264720916748,
|
| 789 |
+
"eval_runtime": 0.6138,
|
| 790 |
+
"eval_samples_per_second": 74.945,
|
| 791 |
+
"eval_steps_per_second": 3.258,
|
| 792 |
+
"step": 396
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 61.54,
|
| 796 |
+
"learning_rate": 3.9215686274509805e-05,
|
| 797 |
+
"loss": 0.0876,
|
| 798 |
+
"step": 400
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 62.0,
|
| 802 |
+
"eval_accuracy": 0.7391304347826086,
|
| 803 |
+
"eval_loss": 0.8229031562805176,
|
| 804 |
+
"eval_runtime": 0.6005,
|
| 805 |
+
"eval_samples_per_second": 76.603,
|
| 806 |
+
"eval_steps_per_second": 3.331,
|
| 807 |
+
"step": 403
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 62.92,
|
| 811 |
+
"eval_accuracy": 0.7391304347826086,
|
| 812 |
+
"eval_loss": 0.8364757895469666,
|
| 813 |
+
"eval_runtime": 0.626,
|
| 814 |
+
"eval_samples_per_second": 73.487,
|
| 815 |
+
"eval_steps_per_second": 3.195,
|
| 816 |
+
"step": 409
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 63.08,
|
| 820 |
+
"learning_rate": 3.431372549019608e-05,
|
| 821 |
+
"loss": 0.1032,
|
| 822 |
+
"step": 410
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 64.0,
|
| 826 |
+
"eval_accuracy": 0.7608695652173914,
|
| 827 |
+
"eval_loss": 0.8161815404891968,
|
| 828 |
+
"eval_runtime": 0.6165,
|
| 829 |
+
"eval_samples_per_second": 74.611,
|
| 830 |
+
"eval_steps_per_second": 3.244,
|
| 831 |
+
"step": 416
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 64.62,
|
| 835 |
+
"learning_rate": 2.9411764705882354e-05,
|
| 836 |
+
"loss": 0.0825,
|
| 837 |
+
"step": 420
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 64.92,
|
| 841 |
+
"eval_accuracy": 0.7391304347826086,
|
| 842 |
+
"eval_loss": 0.8645689487457275,
|
| 843 |
+
"eval_runtime": 0.608,
|
| 844 |
+
"eval_samples_per_second": 75.66,
|
| 845 |
+
"eval_steps_per_second": 3.29,
|
| 846 |
+
"step": 422
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 66.0,
|
| 850 |
+
"eval_accuracy": 0.7391304347826086,
|
| 851 |
+
"eval_loss": 0.9134983420372009,
|
| 852 |
+
"eval_runtime": 0.7022,
|
| 853 |
+
"eval_samples_per_second": 65.511,
|
| 854 |
+
"eval_steps_per_second": 2.848,
|
| 855 |
+
"step": 429
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 66.15,
|
| 859 |
+
"learning_rate": 2.4509803921568626e-05,
|
| 860 |
+
"loss": 0.1119,
|
| 861 |
+
"step": 430
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 66.92,
|
| 865 |
+
"eval_accuracy": 0.7391304347826086,
|
| 866 |
+
"eval_loss": 0.9164416193962097,
|
| 867 |
+
"eval_runtime": 0.6197,
|
| 868 |
+
"eval_samples_per_second": 74.228,
|
| 869 |
+
"eval_steps_per_second": 3.227,
|
| 870 |
+
"step": 435
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 67.69,
|
| 874 |
+
"learning_rate": 1.9607843137254903e-05,
|
| 875 |
+
"loss": 0.0949,
|
| 876 |
+
"step": 440
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 68.0,
|
| 880 |
+
"eval_accuracy": 0.7391304347826086,
|
| 881 |
+
"eval_loss": 0.9232246279716492,
|
| 882 |
+
"eval_runtime": 0.6325,
|
| 883 |
+
"eval_samples_per_second": 72.724,
|
| 884 |
+
"eval_steps_per_second": 3.162,
|
| 885 |
+
"step": 442
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 68.92,
|
| 889 |
+
"eval_accuracy": 0.7391304347826086,
|
| 890 |
+
"eval_loss": 0.9380779266357422,
|
| 891 |
+
"eval_runtime": 0.5791,
|
| 892 |
+
"eval_samples_per_second": 79.439,
|
| 893 |
+
"eval_steps_per_second": 3.454,
|
| 894 |
+
"step": 448
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 69.23,
|
| 898 |
+
"learning_rate": 1.4705882352941177e-05,
|
| 899 |
+
"loss": 0.1227,
|
| 900 |
+
"step": 450
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 70.0,
|
| 904 |
+
"eval_accuracy": 0.7391304347826086,
|
| 905 |
+
"eval_loss": 0.8997882604598999,
|
| 906 |
+
"eval_runtime": 0.606,
|
| 907 |
+
"eval_samples_per_second": 75.907,
|
| 908 |
+
"eval_steps_per_second": 3.3,
|
| 909 |
+
"step": 455
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 70.77,
|
| 913 |
+
"learning_rate": 9.803921568627451e-06,
|
| 914 |
+
"loss": 0.0872,
|
| 915 |
+
"step": 460
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 70.92,
|
| 919 |
+
"eval_accuracy": 0.717391304347826,
|
| 920 |
+
"eval_loss": 0.9632061123847961,
|
| 921 |
+
"eval_runtime": 0.5942,
|
| 922 |
+
"eval_samples_per_second": 77.419,
|
| 923 |
+
"eval_steps_per_second": 3.366,
|
| 924 |
+
"step": 461
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 72.0,
|
| 928 |
+
"eval_accuracy": 0.717391304347826,
|
| 929 |
+
"eval_loss": 0.8566347360610962,
|
| 930 |
+
"eval_runtime": 0.6595,
|
| 931 |
+
"eval_samples_per_second": 69.753,
|
| 932 |
+
"eval_steps_per_second": 3.033,
|
| 933 |
+
"step": 468
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 72.31,
|
| 937 |
+
"learning_rate": 4.901960784313726e-06,
|
| 938 |
+
"loss": 0.1033,
|
| 939 |
+
"step": 470
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 72.92,
|
| 943 |
+
"eval_accuracy": 0.717391304347826,
|
| 944 |
+
"eval_loss": 0.8909047842025757,
|
| 945 |
+
"eval_runtime": 0.6783,
|
| 946 |
+
"eval_samples_per_second": 67.817,
|
| 947 |
+
"eval_steps_per_second": 2.949,
|
| 948 |
+
"step": 474
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 73.85,
|
| 952 |
+
"learning_rate": 0.0,
|
| 953 |
+
"loss": 0.0876,
|
| 954 |
+
"step": 480
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 73.85,
|
| 958 |
+
"eval_accuracy": 0.7608695652173914,
|
| 959 |
+
"eval_loss": 0.8869202733039856,
|
| 960 |
+
"eval_runtime": 0.6277,
|
| 961 |
+
"eval_samples_per_second": 73.284,
|
| 962 |
+
"eval_steps_per_second": 3.186,
|
| 963 |
+
"step": 480
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 73.85,
|
| 967 |
+
"step": 480,
|
| 968 |
+
"total_flos": 1.6581977329862246e+17,
|
| 969 |
+
"train_loss": 0.40781121912101903,
|
| 970 |
+
"train_runtime": 277.6094,
|
| 971 |
+
"train_samples_per_second": 236.015,
|
| 972 |
+
"train_steps_per_second": 1.729
|
| 973 |
+
}
|
| 974 |
+
],
|
| 975 |
+
"logging_steps": 10,
|
| 976 |
+
"max_steps": 480,
|
| 977 |
+
"num_input_tokens_seen": 0,
|
| 978 |
+
"num_train_epochs": 80,
|
| 979 |
+
"save_steps": 500,
|
| 980 |
+
"total_flos": 1.6581977329862246e+17,
|
| 981 |
+
"train_batch_size": 32,
|
| 982 |
+
"trial_name": null,
|
| 983 |
+
"trial_params": null
|
| 984 |
+
}
|