Commit
•
02a0513
1
Parent(s):
a9c4ec7
End of training
Browse files- README.md +5 -3
- all_results.json +10 -10
- eval_results.json +6 -6
- runs/Jan17_21-31-37_c6ad14a30b7d/events.out.tfevents.1705530566.c6ad14a30b7d.8359.1 +3 -0
- train_results.json +5 -5
- trainer_state.json +1072 -7
README.md
CHANGED
|
@@ -2,6 +2,8 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: google/vit-base-patch16-224-in21k
|
| 4 |
tags:
|
|
|
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
- imagefolder
|
|
@@ -22,7 +24,7 @@ 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 +34,8 @@ 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-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss: 1.
|
| 36 |
-
- Accuracy: 0.
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: google/vit-base-patch16-224-in21k
|
| 4 |
tags:
|
| 5 |
+
- image-classification
|
| 6 |
+
- vision
|
| 7 |
- generated_from_trainer
|
| 8 |
datasets:
|
| 9 |
- imagefolder
|
|
|
|
| 24 |
metrics:
|
| 25 |
- name: Accuracy
|
| 26 |
type: accuracy
|
| 27 |
+
value: 0.7769230769230769
|
| 28 |
---
|
| 29 |
|
| 30 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 34 |
|
| 35 |
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
|
| 36 |
It achieves the following results on the evaluation set:
|
| 37 |
+
- Loss: 1.6098
|
| 38 |
+
- Accuracy: 0.7769
|
| 39 |
|
| 40 |
## Model description
|
| 41 |
|
all_results.json
CHANGED
|
@@ -1,12 +1,12 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss":
|
| 5 |
-
"eval_runtime": 2.
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 0.
|
| 8 |
-
"train_loss": 0.
|
| 9 |
-
"train_runtime":
|
| 10 |
-
"train_samples_per_second":
|
| 11 |
-
"train_steps_per_second": 0.
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 200.0,
|
| 3 |
+
"eval_accuracy": 0.7769230769230769,
|
| 4 |
+
"eval_loss": 1.6097954511642456,
|
| 5 |
+
"eval_runtime": 2.2046,
|
| 6 |
+
"eval_samples_per_second": 58.968,
|
| 7 |
+
"eval_steps_per_second": 0.907,
|
| 8 |
+
"train_loss": 0.39147548845836094,
|
| 9 |
+
"train_runtime": 3403.5317,
|
| 10 |
+
"train_samples_per_second": 30.556,
|
| 11 |
+
"train_steps_per_second": 0.411
|
| 12 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss":
|
| 5 |
-
"eval_runtime": 2.
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 200.0,
|
| 3 |
+
"eval_accuracy": 0.7769230769230769,
|
| 4 |
+
"eval_loss": 1.6097954511642456,
|
| 5 |
+
"eval_runtime": 2.2046,
|
| 6 |
+
"eval_samples_per_second": 58.968,
|
| 7 |
+
"eval_steps_per_second": 0.907
|
| 8 |
}
|
runs/Jan17_21-31-37_c6ad14a30b7d/events.out.tfevents.1705530566.c6ad14a30b7d.8359.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:03fcbbac7e99b1668601ea3ba58c311f35f655bf205c25b24d0c175be83d9550
|
| 3 |
+
size 411
|
train_results.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples_per_second":
|
| 6 |
-
"train_steps_per_second": 0.
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 200.0,
|
| 3 |
+
"train_loss": 0.39147548845836094,
|
| 4 |
+
"train_runtime": 3403.5317,
|
| 5 |
+
"train_samples_per_second": 30.556,
|
| 6 |
+
"train_steps_per_second": 0.411
|
| 7 |
}
|
trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_checkpoint": "./
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -1609,14 +1609,1079 @@
|
|
| 1609 |
"train_runtime": 892.0889,
|
| 1610 |
"train_samples_per_second": 69.948,
|
| 1611 |
"train_steps_per_second": 0.942
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1612 |
}
|
| 1613 |
],
|
| 1614 |
"logging_steps": 10,
|
| 1615 |
-
"max_steps":
|
| 1616 |
"num_input_tokens_seen": 0,
|
| 1617 |
-
"num_train_epochs":
|
| 1618 |
"save_steps": 500,
|
| 1619 |
-
"total_flos":
|
| 1620 |
"train_batch_size": 80,
|
| 1621 |
"trial_name": null,
|
| 1622 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.6097954511642456,
|
| 3 |
+
"best_model_checkpoint": "./outputs_letter3/checkpoint-1386",
|
| 4 |
+
"epoch": 200.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 1400,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1609 |
"train_runtime": 892.0889,
|
| 1610 |
"train_samples_per_second": 69.948,
|
| 1611 |
"train_steps_per_second": 0.942
|
| 1612 |
+
},
|
| 1613 |
+
{
|
| 1614 |
+
"epoch": 121.0,
|
| 1615 |
+
"eval_accuracy": 0.6692307692307692,
|
| 1616 |
+
"eval_loss": 2.35441255569458,
|
| 1617 |
+
"eval_runtime": 2.1277,
|
| 1618 |
+
"eval_samples_per_second": 61.098,
|
| 1619 |
+
"eval_steps_per_second": 0.94,
|
| 1620 |
+
"step": 847
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 121.43,
|
| 1624 |
+
"learning_rate": 1.985714285714286e-05,
|
| 1625 |
+
"loss": 1.4504,
|
| 1626 |
+
"step": 850
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 122.0,
|
| 1630 |
+
"eval_accuracy": 0.6461538461538462,
|
| 1631 |
+
"eval_loss": 2.3751370906829834,
|
| 1632 |
+
"eval_runtime": 2.1033,
|
| 1633 |
+
"eval_samples_per_second": 61.809,
|
| 1634 |
+
"eval_steps_per_second": 0.951,
|
| 1635 |
+
"step": 854
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 122.86,
|
| 1639 |
+
"learning_rate": 1.9714285714285718e-05,
|
| 1640 |
+
"loss": 1.3963,
|
| 1641 |
+
"step": 860
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 123.0,
|
| 1645 |
+
"eval_accuracy": 0.6538461538461539,
|
| 1646 |
+
"eval_loss": 2.3588593006134033,
|
| 1647 |
+
"eval_runtime": 2.0842,
|
| 1648 |
+
"eval_samples_per_second": 62.373,
|
| 1649 |
+
"eval_steps_per_second": 0.96,
|
| 1650 |
+
"step": 861
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 124.0,
|
| 1654 |
+
"eval_accuracy": 0.6538461538461539,
|
| 1655 |
+
"eval_loss": 2.353787899017334,
|
| 1656 |
+
"eval_runtime": 2.1043,
|
| 1657 |
+
"eval_samples_per_second": 61.78,
|
| 1658 |
+
"eval_steps_per_second": 0.95,
|
| 1659 |
+
"step": 868
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 124.29,
|
| 1663 |
+
"learning_rate": 1.9571428571428572e-05,
|
| 1664 |
+
"loss": 1.4087,
|
| 1665 |
+
"step": 870
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 125.0,
|
| 1669 |
+
"eval_accuracy": 0.6461538461538462,
|
| 1670 |
+
"eval_loss": 2.326305627822876,
|
| 1671 |
+
"eval_runtime": 2.1627,
|
| 1672 |
+
"eval_samples_per_second": 60.11,
|
| 1673 |
+
"eval_steps_per_second": 0.925,
|
| 1674 |
+
"step": 875
|
| 1675 |
+
},
|
| 1676 |
+
{
|
| 1677 |
+
"epoch": 125.71,
|
| 1678 |
+
"learning_rate": 1.942857142857143e-05,
|
| 1679 |
+
"loss": 1.3564,
|
| 1680 |
+
"step": 880
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 126.0,
|
| 1684 |
+
"eval_accuracy": 0.6230769230769231,
|
| 1685 |
+
"eval_loss": 2.3176610469818115,
|
| 1686 |
+
"eval_runtime": 2.2283,
|
| 1687 |
+
"eval_samples_per_second": 58.34,
|
| 1688 |
+
"eval_steps_per_second": 0.898,
|
| 1689 |
+
"step": 882
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 127.0,
|
| 1693 |
+
"eval_accuracy": 0.6615384615384615,
|
| 1694 |
+
"eval_loss": 2.263662099838257,
|
| 1695 |
+
"eval_runtime": 2.1946,
|
| 1696 |
+
"eval_samples_per_second": 59.236,
|
| 1697 |
+
"eval_steps_per_second": 0.911,
|
| 1698 |
+
"step": 889
|
| 1699 |
+
},
|
| 1700 |
+
{
|
| 1701 |
+
"epoch": 127.14,
|
| 1702 |
+
"learning_rate": 1.928571428571429e-05,
|
| 1703 |
+
"loss": 1.373,
|
| 1704 |
+
"step": 890
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 128.0,
|
| 1708 |
+
"eval_accuracy": 0.6538461538461539,
|
| 1709 |
+
"eval_loss": 2.2609002590179443,
|
| 1710 |
+
"eval_runtime": 2.3121,
|
| 1711 |
+
"eval_samples_per_second": 56.225,
|
| 1712 |
+
"eval_steps_per_second": 0.865,
|
| 1713 |
+
"step": 896
|
| 1714 |
+
},
|
| 1715 |
+
{
|
| 1716 |
+
"epoch": 128.57,
|
| 1717 |
+
"learning_rate": 1.9142857142857146e-05,
|
| 1718 |
+
"loss": 1.346,
|
| 1719 |
+
"step": 900
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 129.0,
|
| 1723 |
+
"eval_accuracy": 0.6538461538461539,
|
| 1724 |
+
"eval_loss": 2.259404182434082,
|
| 1725 |
+
"eval_runtime": 2.1822,
|
| 1726 |
+
"eval_samples_per_second": 59.572,
|
| 1727 |
+
"eval_steps_per_second": 0.916,
|
| 1728 |
+
"step": 903
|
| 1729 |
+
},
|
| 1730 |
+
{
|
| 1731 |
+
"epoch": 130.0,
|
| 1732 |
+
"learning_rate": 1.9e-05,
|
| 1733 |
+
"loss": 1.3307,
|
| 1734 |
+
"step": 910
|
| 1735 |
+
},
|
| 1736 |
+
{
|
| 1737 |
+
"epoch": 130.0,
|
| 1738 |
+
"eval_accuracy": 0.6538461538461539,
|
| 1739 |
+
"eval_loss": 2.2564494609832764,
|
| 1740 |
+
"eval_runtime": 2.3375,
|
| 1741 |
+
"eval_samples_per_second": 55.615,
|
| 1742 |
+
"eval_steps_per_second": 0.856,
|
| 1743 |
+
"step": 910
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 131.0,
|
| 1747 |
+
"eval_accuracy": 0.6307692307692307,
|
| 1748 |
+
"eval_loss": 2.2525382041931152,
|
| 1749 |
+
"eval_runtime": 2.2827,
|
| 1750 |
+
"eval_samples_per_second": 56.95,
|
| 1751 |
+
"eval_steps_per_second": 0.876,
|
| 1752 |
+
"step": 917
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 131.43,
|
| 1756 |
+
"learning_rate": 1.885714285714286e-05,
|
| 1757 |
+
"loss": 1.3124,
|
| 1758 |
+
"step": 920
|
| 1759 |
+
},
|
| 1760 |
+
{
|
| 1761 |
+
"epoch": 132.0,
|
| 1762 |
+
"eval_accuracy": 0.6461538461538462,
|
| 1763 |
+
"eval_loss": 2.218500852584839,
|
| 1764 |
+
"eval_runtime": 2.2212,
|
| 1765 |
+
"eval_samples_per_second": 58.526,
|
| 1766 |
+
"eval_steps_per_second": 0.9,
|
| 1767 |
+
"step": 924
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 132.86,
|
| 1771 |
+
"learning_rate": 1.8714285714285717e-05,
|
| 1772 |
+
"loss": 1.2848,
|
| 1773 |
+
"step": 930
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 133.0,
|
| 1777 |
+
"eval_accuracy": 0.6461538461538462,
|
| 1778 |
+
"eval_loss": 2.2194907665252686,
|
| 1779 |
+
"eval_runtime": 2.3384,
|
| 1780 |
+
"eval_samples_per_second": 55.594,
|
| 1781 |
+
"eval_steps_per_second": 0.855,
|
| 1782 |
+
"step": 931
|
| 1783 |
+
},
|
| 1784 |
+
{
|
| 1785 |
+
"epoch": 134.0,
|
| 1786 |
+
"eval_accuracy": 0.6307692307692307,
|
| 1787 |
+
"eval_loss": 2.204814910888672,
|
| 1788 |
+
"eval_runtime": 2.2103,
|
| 1789 |
+
"eval_samples_per_second": 58.814,
|
| 1790 |
+
"eval_steps_per_second": 0.905,
|
| 1791 |
+
"step": 938
|
| 1792 |
+
},
|
| 1793 |
+
{
|
| 1794 |
+
"epoch": 134.29,
|
| 1795 |
+
"learning_rate": 1.8571428571428575e-05,
|
| 1796 |
+
"loss": 1.256,
|
| 1797 |
+
"step": 940
|
| 1798 |
+
},
|
| 1799 |
+
{
|
| 1800 |
+
"epoch": 135.0,
|
| 1801 |
+
"eval_accuracy": 0.6461538461538462,
|
| 1802 |
+
"eval_loss": 2.193894624710083,
|
| 1803 |
+
"eval_runtime": 2.2027,
|
| 1804 |
+
"eval_samples_per_second": 59.018,
|
| 1805 |
+
"eval_steps_per_second": 0.908,
|
| 1806 |
+
"step": 945
|
| 1807 |
+
},
|
| 1808 |
+
{
|
| 1809 |
+
"epoch": 135.71,
|
| 1810 |
+
"learning_rate": 1.842857142857143e-05,
|
| 1811 |
+
"loss": 1.24,
|
| 1812 |
+
"step": 950
|
| 1813 |
+
},
|
| 1814 |
+
{
|
| 1815 |
+
"epoch": 136.0,
|
| 1816 |
+
"eval_accuracy": 0.6461538461538462,
|
| 1817 |
+
"eval_loss": 2.1721882820129395,
|
| 1818 |
+
"eval_runtime": 2.3539,
|
| 1819 |
+
"eval_samples_per_second": 55.226,
|
| 1820 |
+
"eval_steps_per_second": 0.85,
|
| 1821 |
+
"step": 952
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 137.0,
|
| 1825 |
+
"eval_accuracy": 0.6846153846153846,
|
| 1826 |
+
"eval_loss": 2.1497113704681396,
|
| 1827 |
+
"eval_runtime": 2.1949,
|
| 1828 |
+
"eval_samples_per_second": 59.23,
|
| 1829 |
+
"eval_steps_per_second": 0.911,
|
| 1830 |
+
"step": 959
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 137.14,
|
| 1834 |
+
"learning_rate": 1.8285714285714288e-05,
|
| 1835 |
+
"loss": 1.2318,
|
| 1836 |
+
"step": 960
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 138.0,
|
| 1840 |
+
"eval_accuracy": 0.6846153846153846,
|
| 1841 |
+
"eval_loss": 2.1332032680511475,
|
| 1842 |
+
"eval_runtime": 2.2346,
|
| 1843 |
+
"eval_samples_per_second": 58.176,
|
| 1844 |
+
"eval_steps_per_second": 0.895,
|
| 1845 |
+
"step": 966
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 138.57,
|
| 1849 |
+
"learning_rate": 1.8142857142857146e-05,
|
| 1850 |
+
"loss": 1.1905,
|
| 1851 |
+
"step": 970
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 139.0,
|
| 1855 |
+
"eval_accuracy": 0.6923076923076923,
|
| 1856 |
+
"eval_loss": 2.133913278579712,
|
| 1857 |
+
"eval_runtime": 2.1776,
|
| 1858 |
+
"eval_samples_per_second": 59.698,
|
| 1859 |
+
"eval_steps_per_second": 0.918,
|
| 1860 |
+
"step": 973
|
| 1861 |
+
},
|
| 1862 |
+
{
|
| 1863 |
+
"epoch": 140.0,
|
| 1864 |
+
"learning_rate": 1.8e-05,
|
| 1865 |
+
"loss": 1.186,
|
| 1866 |
+
"step": 980
|
| 1867 |
+
},
|
| 1868 |
+
{
|
| 1869 |
+
"epoch": 140.0,
|
| 1870 |
+
"eval_accuracy": 0.6692307692307692,
|
| 1871 |
+
"eval_loss": 2.1346120834350586,
|
| 1872 |
+
"eval_runtime": 2.3208,
|
| 1873 |
+
"eval_samples_per_second": 56.016,
|
| 1874 |
+
"eval_steps_per_second": 0.862,
|
| 1875 |
+
"step": 980
|
| 1876 |
+
},
|
| 1877 |
+
{
|
| 1878 |
+
"epoch": 141.0,
|
| 1879 |
+
"eval_accuracy": 0.7,
|
| 1880 |
+
"eval_loss": 2.092773914337158,
|
| 1881 |
+
"eval_runtime": 2.3738,
|
| 1882 |
+
"eval_samples_per_second": 54.764,
|
| 1883 |
+
"eval_steps_per_second": 0.843,
|
| 1884 |
+
"step": 987
|
| 1885 |
+
},
|
| 1886 |
+
{
|
| 1887 |
+
"epoch": 141.43,
|
| 1888 |
+
"learning_rate": 1.785714285714286e-05,
|
| 1889 |
+
"loss": 1.1759,
|
| 1890 |
+
"step": 990
|
| 1891 |
+
},
|
| 1892 |
+
{
|
| 1893 |
+
"epoch": 142.0,
|
| 1894 |
+
"eval_accuracy": 0.6846153846153846,
|
| 1895 |
+
"eval_loss": 2.1067099571228027,
|
| 1896 |
+
"eval_runtime": 2.356,
|
| 1897 |
+
"eval_samples_per_second": 55.178,
|
| 1898 |
+
"eval_steps_per_second": 0.849,
|
| 1899 |
+
"step": 994
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 142.86,
|
| 1903 |
+
"learning_rate": 1.7714285714285717e-05,
|
| 1904 |
+
"loss": 1.132,
|
| 1905 |
+
"step": 1000
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 143.0,
|
| 1909 |
+
"eval_accuracy": 0.6692307692307692,
|
| 1910 |
+
"eval_loss": 2.091548442840576,
|
| 1911 |
+
"eval_runtime": 2.3185,
|
| 1912 |
+
"eval_samples_per_second": 56.07,
|
| 1913 |
+
"eval_steps_per_second": 0.863,
|
| 1914 |
+
"step": 1001
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 144.0,
|
| 1918 |
+
"eval_accuracy": 0.676923076923077,
|
| 1919 |
+
"eval_loss": 2.0903213024139404,
|
| 1920 |
+
"eval_runtime": 2.1804,
|
| 1921 |
+
"eval_samples_per_second": 59.622,
|
| 1922 |
+
"eval_steps_per_second": 0.917,
|
| 1923 |
+
"step": 1008
|
| 1924 |
+
},
|
| 1925 |
+
{
|
| 1926 |
+
"epoch": 144.29,
|
| 1927 |
+
"learning_rate": 1.757142857142857e-05,
|
| 1928 |
+
"loss": 1.1206,
|
| 1929 |
+
"step": 1010
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 145.0,
|
| 1933 |
+
"eval_accuracy": 0.676923076923077,
|
| 1934 |
+
"eval_loss": 2.1074228286743164,
|
| 1935 |
+
"eval_runtime": 2.3685,
|
| 1936 |
+
"eval_samples_per_second": 54.887,
|
| 1937 |
+
"eval_steps_per_second": 0.844,
|
| 1938 |
+
"step": 1015
|
| 1939 |
+
},
|
| 1940 |
+
{
|
| 1941 |
+
"epoch": 145.71,
|
| 1942 |
+
"learning_rate": 1.742857142857143e-05,
|
| 1943 |
+
"loss": 1.1096,
|
| 1944 |
+
"step": 1020
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"epoch": 146.0,
|
| 1948 |
+
"eval_accuracy": 0.7230769230769231,
|
| 1949 |
+
"eval_loss": 2.0536632537841797,
|
| 1950 |
+
"eval_runtime": 2.5866,
|
| 1951 |
+
"eval_samples_per_second": 50.259,
|
| 1952 |
+
"eval_steps_per_second": 0.773,
|
| 1953 |
+
"step": 1022
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"epoch": 147.0,
|
| 1957 |
+
"eval_accuracy": 0.7,
|
| 1958 |
+
"eval_loss": 2.061009407043457,
|
| 1959 |
+
"eval_runtime": 2.3206,
|
| 1960 |
+
"eval_samples_per_second": 56.021,
|
| 1961 |
+
"eval_steps_per_second": 0.862,
|
| 1962 |
+
"step": 1029
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 147.14,
|
| 1966 |
+
"learning_rate": 1.7285714285714287e-05,
|
| 1967 |
+
"loss": 1.0814,
|
| 1968 |
+
"step": 1030
|
| 1969 |
+
},
|
| 1970 |
+
{
|
| 1971 |
+
"epoch": 148.0,
|
| 1972 |
+
"eval_accuracy": 0.7076923076923077,
|
| 1973 |
+
"eval_loss": 2.0476534366607666,
|
| 1974 |
+
"eval_runtime": 2.1912,
|
| 1975 |
+
"eval_samples_per_second": 59.33,
|
| 1976 |
+
"eval_steps_per_second": 0.913,
|
| 1977 |
+
"step": 1036
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 148.57,
|
| 1981 |
+
"learning_rate": 1.7142857142857142e-05,
|
| 1982 |
+
"loss": 1.0756,
|
| 1983 |
+
"step": 1040
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 149.0,
|
| 1987 |
+
"eval_accuracy": 0.7076923076923077,
|
| 1988 |
+
"eval_loss": 2.0184433460235596,
|
| 1989 |
+
"eval_runtime": 2.2139,
|
| 1990 |
+
"eval_samples_per_second": 58.72,
|
| 1991 |
+
"eval_steps_per_second": 0.903,
|
| 1992 |
+
"step": 1043
|
| 1993 |
+
},
|
| 1994 |
+
{
|
| 1995 |
+
"epoch": 150.0,
|
| 1996 |
+
"learning_rate": 1.7e-05,
|
| 1997 |
+
"loss": 1.0638,
|
| 1998 |
+
"step": 1050
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 150.0,
|
| 2002 |
+
"eval_accuracy": 0.6923076923076923,
|
| 2003 |
+
"eval_loss": 2.0189385414123535,
|
| 2004 |
+
"eval_runtime": 3.1458,
|
| 2005 |
+
"eval_samples_per_second": 41.325,
|
| 2006 |
+
"eval_steps_per_second": 0.636,
|
| 2007 |
+
"step": 1050
|
| 2008 |
+
},
|
| 2009 |
+
{
|
| 2010 |
+
"epoch": 151.0,
|
| 2011 |
+
"eval_accuracy": 0.7,
|
| 2012 |
+
"eval_loss": 2.01568865776062,
|
| 2013 |
+
"eval_runtime": 2.3668,
|
| 2014 |
+
"eval_samples_per_second": 54.926,
|
| 2015 |
+
"eval_steps_per_second": 0.845,
|
| 2016 |
+
"step": 1057
|
| 2017 |
+
},
|
| 2018 |
+
{
|
| 2019 |
+
"epoch": 151.43,
|
| 2020 |
+
"learning_rate": 1.6857142857142858e-05,
|
| 2021 |
+
"loss": 1.0343,
|
| 2022 |
+
"step": 1060
|
| 2023 |
+
},
|
| 2024 |
+
{
|
| 2025 |
+
"epoch": 152.0,
|
| 2026 |
+
"eval_accuracy": 0.6923076923076923,
|
| 2027 |
+
"eval_loss": 1.9978599548339844,
|
| 2028 |
+
"eval_runtime": 2.3546,
|
| 2029 |
+
"eval_samples_per_second": 55.211,
|
| 2030 |
+
"eval_steps_per_second": 0.849,
|
| 2031 |
+
"step": 1064
|
| 2032 |
+
},
|
| 2033 |
+
{
|
| 2034 |
+
"epoch": 152.86,
|
| 2035 |
+
"learning_rate": 1.6714285714285716e-05,
|
| 2036 |
+
"loss": 1.0187,
|
| 2037 |
+
"step": 1070
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 153.0,
|
| 2041 |
+
"eval_accuracy": 0.7230769230769231,
|
| 2042 |
+
"eval_loss": 1.9824119806289673,
|
| 2043 |
+
"eval_runtime": 2.2036,
|
| 2044 |
+
"eval_samples_per_second": 58.995,
|
| 2045 |
+
"eval_steps_per_second": 0.908,
|
| 2046 |
+
"step": 1071
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 154.0,
|
| 2050 |
+
"eval_accuracy": 0.7076923076923077,
|
| 2051 |
+
"eval_loss": 1.968167781829834,
|
| 2052 |
+
"eval_runtime": 2.422,
|
| 2053 |
+
"eval_samples_per_second": 53.675,
|
| 2054 |
+
"eval_steps_per_second": 0.826,
|
| 2055 |
+
"step": 1078
|
| 2056 |
+
},
|
| 2057 |
+
{
|
| 2058 |
+
"epoch": 154.29,
|
| 2059 |
+
"learning_rate": 1.6571428571428574e-05,
|
| 2060 |
+
"loss": 0.9993,
|
| 2061 |
+
"step": 1080
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 155.0,
|
| 2065 |
+
"eval_accuracy": 0.7230769230769231,
|
| 2066 |
+
"eval_loss": 1.9394822120666504,
|
| 2067 |
+
"eval_runtime": 2.3562,
|
| 2068 |
+
"eval_samples_per_second": 55.175,
|
| 2069 |
+
"eval_steps_per_second": 0.849,
|
| 2070 |
+
"step": 1085
|
| 2071 |
+
},
|
| 2072 |
+
{
|
| 2073 |
+
"epoch": 155.71,
|
| 2074 |
+
"learning_rate": 1.642857142857143e-05,
|
| 2075 |
+
"loss": 1.0029,
|
| 2076 |
+
"step": 1090
|
| 2077 |
+
},
|
| 2078 |
+
{
|
| 2079 |
+
"epoch": 156.0,
|
| 2080 |
+
"eval_accuracy": 0.7153846153846154,
|
| 2081 |
+
"eval_loss": 1.920530080795288,
|
| 2082 |
+
"eval_runtime": 2.3989,
|
| 2083 |
+
"eval_samples_per_second": 54.191,
|
| 2084 |
+
"eval_steps_per_second": 0.834,
|
| 2085 |
+
"step": 1092
|
| 2086 |
+
},
|
| 2087 |
+
{
|
| 2088 |
+
"epoch": 157.0,
|
| 2089 |
+
"eval_accuracy": 0.7076923076923077,
|
| 2090 |
+
"eval_loss": 1.906773567199707,
|
| 2091 |
+
"eval_runtime": 2.3766,
|
| 2092 |
+
"eval_samples_per_second": 54.699,
|
| 2093 |
+
"eval_steps_per_second": 0.842,
|
| 2094 |
+
"step": 1099
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 157.14,
|
| 2098 |
+
"learning_rate": 1.6285714285714287e-05,
|
| 2099 |
+
"loss": 0.9703,
|
| 2100 |
+
"step": 1100
|
| 2101 |
+
},
|
| 2102 |
+
{
|
| 2103 |
+
"epoch": 158.0,
|
| 2104 |
+
"eval_accuracy": 0.7384615384615385,
|
| 2105 |
+
"eval_loss": 1.899588704109192,
|
| 2106 |
+
"eval_runtime": 2.3516,
|
| 2107 |
+
"eval_samples_per_second": 55.282,
|
| 2108 |
+
"eval_steps_per_second": 0.85,
|
| 2109 |
+
"step": 1106
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 158.57,
|
| 2113 |
+
"learning_rate": 1.6142857142857145e-05,
|
| 2114 |
+
"loss": 0.9532,
|
| 2115 |
+
"step": 1110
|
| 2116 |
+
},
|
| 2117 |
+
{
|
| 2118 |
+
"epoch": 159.0,
|
| 2119 |
+
"eval_accuracy": 0.7076923076923077,
|
| 2120 |
+
"eval_loss": 1.8944636583328247,
|
| 2121 |
+
"eval_runtime": 2.2108,
|
| 2122 |
+
"eval_samples_per_second": 58.803,
|
| 2123 |
+
"eval_steps_per_second": 0.905,
|
| 2124 |
+
"step": 1113
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 160.0,
|
| 2128 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 2129 |
+
"loss": 0.9526,
|
| 2130 |
+
"step": 1120
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 160.0,
|
| 2134 |
+
"eval_accuracy": 0.7307692307692307,
|
| 2135 |
+
"eval_loss": 1.8939263820648193,
|
| 2136 |
+
"eval_runtime": 2.2202,
|
| 2137 |
+
"eval_samples_per_second": 58.553,
|
| 2138 |
+
"eval_steps_per_second": 0.901,
|
| 2139 |
+
"step": 1120
|
| 2140 |
+
},
|
| 2141 |
+
{
|
| 2142 |
+
"epoch": 161.0,
|
| 2143 |
+
"eval_accuracy": 0.7230769230769231,
|
| 2144 |
+
"eval_loss": 1.8937941789627075,
|
| 2145 |
+
"eval_runtime": 2.3259,
|
| 2146 |
+
"eval_samples_per_second": 55.892,
|
| 2147 |
+
"eval_steps_per_second": 0.86,
|
| 2148 |
+
"step": 1127
|
| 2149 |
+
},
|
| 2150 |
+
{
|
| 2151 |
+
"epoch": 161.43,
|
| 2152 |
+
"learning_rate": 1.5857142857142857e-05,
|
| 2153 |
+
"loss": 0.9365,
|
| 2154 |
+
"step": 1130
|
| 2155 |
+
},
|
| 2156 |
+
{
|
| 2157 |
+
"epoch": 162.0,
|
| 2158 |
+
"eval_accuracy": 0.7384615384615385,
|
| 2159 |
+
"eval_loss": 1.8544682264328003,
|
| 2160 |
+
"eval_runtime": 2.1829,
|
| 2161 |
+
"eval_samples_per_second": 59.554,
|
| 2162 |
+
"eval_steps_per_second": 0.916,
|
| 2163 |
+
"step": 1134
|
| 2164 |
+
},
|
| 2165 |
+
{
|
| 2166 |
+
"epoch": 162.86,
|
| 2167 |
+
"learning_rate": 1.5714285714285715e-05,
|
| 2168 |
+
"loss": 0.9301,
|
| 2169 |
+
"step": 1140
|
| 2170 |
+
},
|
| 2171 |
+
{
|
| 2172 |
+
"epoch": 163.0,
|
| 2173 |
+
"eval_accuracy": 0.7384615384615385,
|
| 2174 |
+
"eval_loss": 1.860898733139038,
|
| 2175 |
+
"eval_runtime": 2.2861,
|
| 2176 |
+
"eval_samples_per_second": 56.864,
|
| 2177 |
+
"eval_steps_per_second": 0.875,
|
| 2178 |
+
"step": 1141
|
| 2179 |
+
},
|
| 2180 |
+
{
|
| 2181 |
+
"epoch": 164.0,
|
| 2182 |
+
"eval_accuracy": 0.7230769230769231,
|
| 2183 |
+
"eval_loss": 1.8540517091751099,
|
| 2184 |
+
"eval_runtime": 2.2092,
|
| 2185 |
+
"eval_samples_per_second": 58.844,
|
| 2186 |
+
"eval_steps_per_second": 0.905,
|
| 2187 |
+
"step": 1148
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 164.29,
|
| 2191 |
+
"learning_rate": 1.5571428571428573e-05,
|
| 2192 |
+
"loss": 0.8856,
|
| 2193 |
+
"step": 1150
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 165.0,
|
| 2197 |
+
"eval_accuracy": 0.7076923076923077,
|
| 2198 |
+
"eval_loss": 1.884601354598999,
|
| 2199 |
+
"eval_runtime": 2.2447,
|
| 2200 |
+
"eval_samples_per_second": 57.915,
|
| 2201 |
+
"eval_steps_per_second": 0.891,
|
| 2202 |
+
"step": 1155
|
| 2203 |
+
},
|
| 2204 |
+
{
|
| 2205 |
+
"epoch": 165.71,
|
| 2206 |
+
"learning_rate": 1.542857142857143e-05,
|
| 2207 |
+
"loss": 0.8801,
|
| 2208 |
+
"step": 1160
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 166.0,
|
| 2212 |
+
"eval_accuracy": 0.7076923076923077,
|
| 2213 |
+
"eval_loss": 1.867126226425171,
|
| 2214 |
+
"eval_runtime": 2.2028,
|
| 2215 |
+
"eval_samples_per_second": 59.017,
|
| 2216 |
+
"eval_steps_per_second": 0.908,
|
| 2217 |
+
"step": 1162
|
| 2218 |
+
},
|
| 2219 |
+
{
|
| 2220 |
+
"epoch": 167.0,
|
| 2221 |
+
"eval_accuracy": 0.7230769230769231,
|
| 2222 |
+
"eval_loss": 1.8465133905410767,
|
| 2223 |
+
"eval_runtime": 2.3398,
|
| 2224 |
+
"eval_samples_per_second": 55.559,
|
| 2225 |
+
"eval_steps_per_second": 0.855,
|
| 2226 |
+
"step": 1169
|
| 2227 |
+
},
|
| 2228 |
+
{
|
| 2229 |
+
"epoch": 167.14,
|
| 2230 |
+
"learning_rate": 1.5285714285714286e-05,
|
| 2231 |
+
"loss": 0.8898,
|
| 2232 |
+
"step": 1170
|
| 2233 |
+
},
|
| 2234 |
+
{
|
| 2235 |
+
"epoch": 168.0,
|
| 2236 |
+
"eval_accuracy": 0.7230769230769231,
|
| 2237 |
+
"eval_loss": 1.8428664207458496,
|
| 2238 |
+
"eval_runtime": 2.1983,
|
| 2239 |
+
"eval_samples_per_second": 59.138,
|
| 2240 |
+
"eval_steps_per_second": 0.91,
|
| 2241 |
+
"step": 1176
|
| 2242 |
+
},
|
| 2243 |
+
{
|
| 2244 |
+
"epoch": 168.57,
|
| 2245 |
+
"learning_rate": 1.5142857142857144e-05,
|
| 2246 |
+
"loss": 0.8729,
|
| 2247 |
+
"step": 1180
|
| 2248 |
+
},
|
| 2249 |
+
{
|
| 2250 |
+
"epoch": 169.0,
|
| 2251 |
+
"eval_accuracy": 0.7384615384615385,
|
| 2252 |
+
"eval_loss": 1.832564115524292,
|
| 2253 |
+
"eval_runtime": 2.357,
|
| 2254 |
+
"eval_samples_per_second": 55.155,
|
| 2255 |
+
"eval_steps_per_second": 0.849,
|
| 2256 |
+
"step": 1183
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 170.0,
|
| 2260 |
+
"learning_rate": 1.5000000000000002e-05,
|
| 2261 |
+
"loss": 0.8632,
|
| 2262 |
+
"step": 1190
|
| 2263 |
+
},
|
| 2264 |
+
{
|
| 2265 |
+
"epoch": 170.0,
|
| 2266 |
+
"eval_accuracy": 0.7461538461538462,
|
| 2267 |
+
"eval_loss": 1.810370683670044,
|
| 2268 |
+
"eval_runtime": 2.4307,
|
| 2269 |
+
"eval_samples_per_second": 53.483,
|
| 2270 |
+
"eval_steps_per_second": 0.823,
|
| 2271 |
+
"step": 1190
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 171.0,
|
| 2275 |
+
"eval_accuracy": 0.7384615384615385,
|
| 2276 |
+
"eval_loss": 1.8017692565917969,
|
| 2277 |
+
"eval_runtime": 2.2052,
|
| 2278 |
+
"eval_samples_per_second": 58.951,
|
| 2279 |
+
"eval_steps_per_second": 0.907,
|
| 2280 |
+
"step": 1197
|
| 2281 |
+
},
|
| 2282 |
+
{
|
| 2283 |
+
"epoch": 171.43,
|
| 2284 |
+
"learning_rate": 1.4857142857142858e-05,
|
| 2285 |
+
"loss": 0.8423,
|
| 2286 |
+
"step": 1200
|
| 2287 |
+
},
|
| 2288 |
+
{
|
| 2289 |
+
"epoch": 172.0,
|
| 2290 |
+
"eval_accuracy": 0.7615384615384615,
|
| 2291 |
+
"eval_loss": 1.7875727415084839,
|
| 2292 |
+
"eval_runtime": 2.3658,
|
| 2293 |
+
"eval_samples_per_second": 54.949,
|
| 2294 |
+
"eval_steps_per_second": 0.845,
|
| 2295 |
+
"step": 1204
|
| 2296 |
+
},
|
| 2297 |
+
{
|
| 2298 |
+
"epoch": 172.86,
|
| 2299 |
+
"learning_rate": 1.4714285714285716e-05,
|
| 2300 |
+
"loss": 0.828,
|
| 2301 |
+
"step": 1210
|
| 2302 |
+
},
|
| 2303 |
+
{
|
| 2304 |
+
"epoch": 173.0,
|
| 2305 |
+
"eval_accuracy": 0.7538461538461538,
|
| 2306 |
+
"eval_loss": 1.787375569343567,
|
| 2307 |
+
"eval_runtime": 2.2488,
|
| 2308 |
+
"eval_samples_per_second": 57.808,
|
| 2309 |
+
"eval_steps_per_second": 0.889,
|
| 2310 |
+
"step": 1211
|
| 2311 |
+
},
|
| 2312 |
+
{
|
| 2313 |
+
"epoch": 174.0,
|
| 2314 |
+
"eval_accuracy": 0.7692307692307693,
|
| 2315 |
+
"eval_loss": 1.7785577774047852,
|
| 2316 |
+
"eval_runtime": 2.3295,
|
| 2317 |
+
"eval_samples_per_second": 55.807,
|
| 2318 |
+
"eval_steps_per_second": 0.859,
|
| 2319 |
+
"step": 1218
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 174.29,
|
| 2323 |
+
"learning_rate": 1.4571428571428573e-05,
|
| 2324 |
+
"loss": 0.8063,
|
| 2325 |
+
"step": 1220
|
| 2326 |
+
},
|
| 2327 |
+
{
|
| 2328 |
+
"epoch": 175.0,
|
| 2329 |
+
"eval_accuracy": 0.7461538461538462,
|
| 2330 |
+
"eval_loss": 1.7820396423339844,
|
| 2331 |
+
"eval_runtime": 2.2553,
|
| 2332 |
+
"eval_samples_per_second": 57.642,
|
| 2333 |
+
"eval_steps_per_second": 0.887,
|
| 2334 |
+
"step": 1225
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 175.71,
|
| 2338 |
+
"learning_rate": 1.4428571428571429e-05,
|
| 2339 |
+
"loss": 0.8084,
|
| 2340 |
+
"step": 1230
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 176.0,
|
| 2344 |
+
"eval_accuracy": 0.7538461538461538,
|
| 2345 |
+
"eval_loss": 1.800405502319336,
|
| 2346 |
+
"eval_runtime": 2.303,
|
| 2347 |
+
"eval_samples_per_second": 56.447,
|
| 2348 |
+
"eval_steps_per_second": 0.868,
|
| 2349 |
+
"step": 1232
|
| 2350 |
+
},
|
| 2351 |
+
{
|
| 2352 |
+
"epoch": 177.0,
|
| 2353 |
+
"eval_accuracy": 0.7615384615384615,
|
| 2354 |
+
"eval_loss": 1.787461757659912,
|
| 2355 |
+
"eval_runtime": 2.2538,
|
| 2356 |
+
"eval_samples_per_second": 57.679,
|
| 2357 |
+
"eval_steps_per_second": 0.887,
|
| 2358 |
+
"step": 1239
|
| 2359 |
+
},
|
| 2360 |
+
{
|
| 2361 |
+
"epoch": 177.14,
|
| 2362 |
+
"learning_rate": 1.4285714285714287e-05,
|
| 2363 |
+
"loss": 0.7948,
|
| 2364 |
+
"step": 1240
|
| 2365 |
+
},
|
| 2366 |
+
{
|
| 2367 |
+
"epoch": 178.0,
|
| 2368 |
+
"eval_accuracy": 0.7615384615384615,
|
| 2369 |
+
"eval_loss": 1.7639268636703491,
|
| 2370 |
+
"eval_runtime": 2.3516,
|
| 2371 |
+
"eval_samples_per_second": 55.281,
|
| 2372 |
+
"eval_steps_per_second": 0.85,
|
| 2373 |
+
"step": 1246
|
| 2374 |
+
},
|
| 2375 |
+
{
|
| 2376 |
+
"epoch": 178.57,
|
| 2377 |
+
"learning_rate": 1.4142857142857145e-05,
|
| 2378 |
+
"loss": 0.7687,
|
| 2379 |
+
"step": 1250
|
| 2380 |
+
},
|
| 2381 |
+
{
|
| 2382 |
+
"epoch": 179.0,
|
| 2383 |
+
"eval_accuracy": 0.7538461538461538,
|
| 2384 |
+
"eval_loss": 1.7797616720199585,
|
| 2385 |
+
"eval_runtime": 2.2016,
|
| 2386 |
+
"eval_samples_per_second": 59.047,
|
| 2387 |
+
"eval_steps_per_second": 0.908,
|
| 2388 |
+
"step": 1253
|
| 2389 |
+
},
|
| 2390 |
+
{
|
| 2391 |
+
"epoch": 180.0,
|
| 2392 |
+
"learning_rate": 1.4e-05,
|
| 2393 |
+
"loss": 0.7598,
|
| 2394 |
+
"step": 1260
|
| 2395 |
+
},
|
| 2396 |
+
{
|
| 2397 |
+
"epoch": 180.0,
|
| 2398 |
+
"eval_accuracy": 0.7538461538461538,
|
| 2399 |
+
"eval_loss": 1.7775954008102417,
|
| 2400 |
+
"eval_runtime": 2.2652,
|
| 2401 |
+
"eval_samples_per_second": 57.389,
|
| 2402 |
+
"eval_steps_per_second": 0.883,
|
| 2403 |
+
"step": 1260
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 181.0,
|
| 2407 |
+
"eval_accuracy": 0.7384615384615385,
|
| 2408 |
+
"eval_loss": 1.7582831382751465,
|
| 2409 |
+
"eval_runtime": 2.3301,
|
| 2410 |
+
"eval_samples_per_second": 55.792,
|
| 2411 |
+
"eval_steps_per_second": 0.858,
|
| 2412 |
+
"step": 1267
|
| 2413 |
+
},
|
| 2414 |
+
{
|
| 2415 |
+
"epoch": 181.43,
|
| 2416 |
+
"learning_rate": 1.3857142857142858e-05,
|
| 2417 |
+
"loss": 0.7622,
|
| 2418 |
+
"step": 1270
|
| 2419 |
+
},
|
| 2420 |
+
{
|
| 2421 |
+
"epoch": 182.0,
|
| 2422 |
+
"eval_accuracy": 0.7538461538461538,
|
| 2423 |
+
"eval_loss": 1.7546014785766602,
|
| 2424 |
+
"eval_runtime": 2.3427,
|
| 2425 |
+
"eval_samples_per_second": 55.493,
|
| 2426 |
+
"eval_steps_per_second": 0.854,
|
| 2427 |
+
"step": 1274
|
| 2428 |
+
},
|
| 2429 |
+
{
|
| 2430 |
+
"epoch": 182.86,
|
| 2431 |
+
"learning_rate": 1.3714285714285716e-05,
|
| 2432 |
+
"loss": 0.754,
|
| 2433 |
+
"step": 1280
|
| 2434 |
+
},
|
| 2435 |
+
{
|
| 2436 |
+
"epoch": 183.0,
|
| 2437 |
+
"eval_accuracy": 0.7615384615384615,
|
| 2438 |
+
"eval_loss": 1.7243136167526245,
|
| 2439 |
+
"eval_runtime": 2.2386,
|
| 2440 |
+
"eval_samples_per_second": 58.071,
|
| 2441 |
+
"eval_steps_per_second": 0.893,
|
| 2442 |
+
"step": 1281
|
| 2443 |
+
},
|
| 2444 |
+
{
|
| 2445 |
+
"epoch": 184.0,
|
| 2446 |
+
"eval_accuracy": 0.7538461538461538,
|
| 2447 |
+
"eval_loss": 1.7218064069747925,
|
| 2448 |
+
"eval_runtime": 2.3487,
|
| 2449 |
+
"eval_samples_per_second": 55.35,
|
| 2450 |
+
"eval_steps_per_second": 0.852,
|
| 2451 |
+
"step": 1288
|
| 2452 |
+
},
|
| 2453 |
+
{
|
| 2454 |
+
"epoch": 184.29,
|
| 2455 |
+
"learning_rate": 1.3571428571428574e-05,
|
| 2456 |
+
"loss": 0.7397,
|
| 2457 |
+
"step": 1290
|
| 2458 |
+
},
|
| 2459 |
+
{
|
| 2460 |
+
"epoch": 185.0,
|
| 2461 |
+
"eval_accuracy": 0.7538461538461538,
|
| 2462 |
+
"eval_loss": 1.6983821392059326,
|
| 2463 |
+
"eval_runtime": 2.2077,
|
| 2464 |
+
"eval_samples_per_second": 58.886,
|
| 2465 |
+
"eval_steps_per_second": 0.906,
|
| 2466 |
+
"step": 1295
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 185.71,
|
| 2470 |
+
"learning_rate": 1.3428571428571429e-05,
|
| 2471 |
+
"loss": 0.7171,
|
| 2472 |
+
"step": 1300
|
| 2473 |
+
},
|
| 2474 |
+
{
|
| 2475 |
+
"epoch": 186.0,
|
| 2476 |
+
"eval_accuracy": 0.7461538461538462,
|
| 2477 |
+
"eval_loss": 1.6678060293197632,
|
| 2478 |
+
"eval_runtime": 2.3645,
|
| 2479 |
+
"eval_samples_per_second": 54.98,
|
| 2480 |
+
"eval_steps_per_second": 0.846,
|
| 2481 |
+
"step": 1302
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 187.0,
|
| 2485 |
+
"eval_accuracy": 0.7692307692307693,
|
| 2486 |
+
"eval_loss": 1.6591731309890747,
|
| 2487 |
+
"eval_runtime": 2.3411,
|
| 2488 |
+
"eval_samples_per_second": 55.529,
|
| 2489 |
+
"eval_steps_per_second": 0.854,
|
| 2490 |
+
"step": 1309
|
| 2491 |
+
},
|
| 2492 |
+
{
|
| 2493 |
+
"epoch": 187.14,
|
| 2494 |
+
"learning_rate": 1.3285714285714287e-05,
|
| 2495 |
+
"loss": 0.7351,
|
| 2496 |
+
"step": 1310
|
| 2497 |
+
},
|
| 2498 |
+
{
|
| 2499 |
+
"epoch": 188.0,
|
| 2500 |
+
"eval_accuracy": 0.7538461538461538,
|
| 2501 |
+
"eval_loss": 1.67545747756958,
|
| 2502 |
+
"eval_runtime": 2.2255,
|
| 2503 |
+
"eval_samples_per_second": 58.414,
|
| 2504 |
+
"eval_steps_per_second": 0.899,
|
| 2505 |
+
"step": 1316
|
| 2506 |
+
},
|
| 2507 |
+
{
|
| 2508 |
+
"epoch": 188.57,
|
| 2509 |
+
"learning_rate": 1.3142857142857145e-05,
|
| 2510 |
+
"loss": 0.717,
|
| 2511 |
+
"step": 1320
|
| 2512 |
+
},
|
| 2513 |
+
{
|
| 2514 |
+
"epoch": 189.0,
|
| 2515 |
+
"eval_accuracy": 0.7846153846153846,
|
| 2516 |
+
"eval_loss": 1.6684316396713257,
|
| 2517 |
+
"eval_runtime": 2.2461,
|
| 2518 |
+
"eval_samples_per_second": 57.879,
|
| 2519 |
+
"eval_steps_per_second": 0.89,
|
| 2520 |
+
"step": 1323
|
| 2521 |
+
},
|
| 2522 |
+
{
|
| 2523 |
+
"epoch": 190.0,
|
| 2524 |
+
"learning_rate": 1.3000000000000001e-05,
|
| 2525 |
+
"loss": 0.703,
|
| 2526 |
+
"step": 1330
|
| 2527 |
+
},
|
| 2528 |
+
{
|
| 2529 |
+
"epoch": 190.0,
|
| 2530 |
+
"eval_accuracy": 0.7692307692307693,
|
| 2531 |
+
"eval_loss": 1.6624796390533447,
|
| 2532 |
+
"eval_runtime": 2.3197,
|
| 2533 |
+
"eval_samples_per_second": 56.043,
|
| 2534 |
+
"eval_steps_per_second": 0.862,
|
| 2535 |
+
"step": 1330
|
| 2536 |
+
},
|
| 2537 |
+
{
|
| 2538 |
+
"epoch": 191.0,
|
| 2539 |
+
"eval_accuracy": 0.7769230769230769,
|
| 2540 |
+
"eval_loss": 1.6624727249145508,
|
| 2541 |
+
"eval_runtime": 2.2578,
|
| 2542 |
+
"eval_samples_per_second": 57.577,
|
| 2543 |
+
"eval_steps_per_second": 0.886,
|
| 2544 |
+
"step": 1337
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 191.43,
|
| 2548 |
+
"learning_rate": 1.2857142857142859e-05,
|
| 2549 |
+
"loss": 0.7036,
|
| 2550 |
+
"step": 1340
|
| 2551 |
+
},
|
| 2552 |
+
{
|
| 2553 |
+
"epoch": 192.0,
|
| 2554 |
+
"eval_accuracy": 0.7615384615384615,
|
| 2555 |
+
"eval_loss": 1.6422407627105713,
|
| 2556 |
+
"eval_runtime": 2.4009,
|
| 2557 |
+
"eval_samples_per_second": 54.146,
|
| 2558 |
+
"eval_steps_per_second": 0.833,
|
| 2559 |
+
"step": 1344
|
| 2560 |
+
},
|
| 2561 |
+
{
|
| 2562 |
+
"epoch": 192.86,
|
| 2563 |
+
"learning_rate": 1.2714285714285715e-05,
|
| 2564 |
+
"loss": 0.698,
|
| 2565 |
+
"step": 1350
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 193.0,
|
| 2569 |
+
"eval_accuracy": 0.7538461538461538,
|
| 2570 |
+
"eval_loss": 1.6632704734802246,
|
| 2571 |
+
"eval_runtime": 2.2565,
|
| 2572 |
+
"eval_samples_per_second": 57.612,
|
| 2573 |
+
"eval_steps_per_second": 0.886,
|
| 2574 |
+
"step": 1351
|
| 2575 |
+
},
|
| 2576 |
+
{
|
| 2577 |
+
"epoch": 194.0,
|
| 2578 |
+
"eval_accuracy": 0.7615384615384615,
|
| 2579 |
+
"eval_loss": 1.663210153579712,
|
| 2580 |
+
"eval_runtime": 2.3463,
|
| 2581 |
+
"eval_samples_per_second": 55.406,
|
| 2582 |
+
"eval_steps_per_second": 0.852,
|
| 2583 |
+
"step": 1358
|
| 2584 |
+
},
|
| 2585 |
+
{
|
| 2586 |
+
"epoch": 194.29,
|
| 2587 |
+
"learning_rate": 1.2571428571428572e-05,
|
| 2588 |
+
"loss": 0.7002,
|
| 2589 |
+
"step": 1360
|
| 2590 |
+
},
|
| 2591 |
+
{
|
| 2592 |
+
"epoch": 195.0,
|
| 2593 |
+
"eval_accuracy": 0.7538461538461538,
|
| 2594 |
+
"eval_loss": 1.6452277898788452,
|
| 2595 |
+
"eval_runtime": 2.2223,
|
| 2596 |
+
"eval_samples_per_second": 58.497,
|
| 2597 |
+
"eval_steps_per_second": 0.9,
|
| 2598 |
+
"step": 1365
|
| 2599 |
+
},
|
| 2600 |
+
{
|
| 2601 |
+
"epoch": 195.71,
|
| 2602 |
+
"learning_rate": 1.242857142857143e-05,
|
| 2603 |
+
"loss": 0.6662,
|
| 2604 |
+
"step": 1370
|
| 2605 |
+
},
|
| 2606 |
+
{
|
| 2607 |
+
"epoch": 196.0,
|
| 2608 |
+
"eval_accuracy": 0.7615384615384615,
|
| 2609 |
+
"eval_loss": 1.6403251886367798,
|
| 2610 |
+
"eval_runtime": 2.3447,
|
| 2611 |
+
"eval_samples_per_second": 55.444,
|
| 2612 |
+
"eval_steps_per_second": 0.853,
|
| 2613 |
+
"step": 1372
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 197.0,
|
| 2617 |
+
"eval_accuracy": 0.7538461538461538,
|
| 2618 |
+
"eval_loss": 1.627591848373413,
|
| 2619 |
+
"eval_runtime": 2.3495,
|
| 2620 |
+
"eval_samples_per_second": 55.332,
|
| 2621 |
+
"eval_steps_per_second": 0.851,
|
| 2622 |
+
"step": 1379
|
| 2623 |
+
},
|
| 2624 |
+
{
|
| 2625 |
+
"epoch": 197.14,
|
| 2626 |
+
"learning_rate": 1.2285714285714288e-05,
|
| 2627 |
+
"loss": 0.6771,
|
| 2628 |
+
"step": 1380
|
| 2629 |
+
},
|
| 2630 |
+
{
|
| 2631 |
+
"epoch": 198.0,
|
| 2632 |
+
"eval_accuracy": 0.7769230769230769,
|
| 2633 |
+
"eval_loss": 1.6097954511642456,
|
| 2634 |
+
"eval_runtime": 2.2213,
|
| 2635 |
+
"eval_samples_per_second": 58.524,
|
| 2636 |
+
"eval_steps_per_second": 0.9,
|
| 2637 |
+
"step": 1386
|
| 2638 |
+
},
|
| 2639 |
+
{
|
| 2640 |
+
"epoch": 198.57,
|
| 2641 |
+
"learning_rate": 1.2142857142857142e-05,
|
| 2642 |
+
"loss": 0.6588,
|
| 2643 |
+
"step": 1390
|
| 2644 |
+
},
|
| 2645 |
+
{
|
| 2646 |
+
"epoch": 199.0,
|
| 2647 |
+
"eval_accuracy": 0.7692307692307693,
|
| 2648 |
+
"eval_loss": 1.622355580329895,
|
| 2649 |
+
"eval_runtime": 2.2376,
|
| 2650 |
+
"eval_samples_per_second": 58.098,
|
| 2651 |
+
"eval_steps_per_second": 0.894,
|
| 2652 |
+
"step": 1393
|
| 2653 |
+
},
|
| 2654 |
+
{
|
| 2655 |
+
"epoch": 200.0,
|
| 2656 |
+
"learning_rate": 1.2e-05,
|
| 2657 |
+
"loss": 0.6549,
|
| 2658 |
+
"step": 1400
|
| 2659 |
+
},
|
| 2660 |
+
{
|
| 2661 |
+
"epoch": 200.0,
|
| 2662 |
+
"eval_accuracy": 0.7461538461538462,
|
| 2663 |
+
"eval_loss": 1.6263408660888672,
|
| 2664 |
+
"eval_runtime": 2.3312,
|
| 2665 |
+
"eval_samples_per_second": 55.765,
|
| 2666 |
+
"eval_steps_per_second": 0.858,
|
| 2667 |
+
"step": 1400
|
| 2668 |
+
},
|
| 2669 |
+
{
|
| 2670 |
+
"epoch": 200.0,
|
| 2671 |
+
"step": 1400,
|
| 2672 |
+
"total_flos": 8.062778508115968e+18,
|
| 2673 |
+
"train_loss": 0.39147548845836094,
|
| 2674 |
+
"train_runtime": 3403.5317,
|
| 2675 |
+
"train_samples_per_second": 30.556,
|
| 2676 |
+
"train_steps_per_second": 0.411
|
| 2677 |
}
|
| 2678 |
],
|
| 2679 |
"logging_steps": 10,
|
| 2680 |
+
"max_steps": 1400,
|
| 2681 |
"num_input_tokens_seen": 0,
|
| 2682 |
+
"num_train_epochs": 200,
|
| 2683 |
"save_steps": 500,
|
| 2684 |
+
"total_flos": 8.062778508115968e+18,
|
| 2685 |
"train_batch_size": 80,
|
| 2686 |
"trial_name": null,
|
| 2687 |
"trial_params": null
|