Commit
•
9784e0a
1
Parent(s):
b8e384b
add model
Browse files- README.md +4 -4
- all_results.json +9 -9
- eval_results.json +5 -5
- pytorch_model.bin +1 -1
- tokenizer.json +0 -0
- train_results.json +4 -4
- trainer_state.json +7 -7
- training_args.bin +1 -1
README.md
CHANGED
@@ -21,7 +21,7 @@ model_index:
|
|
21 |
metric:
|
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 [albert-base-v2](https://huggingface.co/albert-base-v2) on the GLUE WNLI dataset.
|
33 |
It achieves the following results on the evaluation set:
|
34 |
-
- Loss: 0.
|
35 |
-
- Accuracy: 0.
|
36 |
|
37 |
## Model description
|
38 |
|
@@ -52,7 +52,7 @@ More information needed
|
|
52 |
|
53 |
The following hyperparameters were used during training:
|
54 |
- learning_rate: 2e-05
|
55 |
-
- train_batch_size:
|
56 |
- eval_batch_size: 8
|
57 |
- seed: 42
|
58 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
|
|
21 |
metric:
|
22 |
name: Accuracy
|
23 |
type: accuracy
|
24 |
+
value: 0.43661971830985913
|
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 [albert-base-v2](https://huggingface.co/albert-base-v2) on the GLUE WNLI dataset.
|
33 |
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 0.7083
|
35 |
+
- Accuracy: 0.4366
|
36 |
|
37 |
## Model description
|
38 |
|
|
|
52 |
|
53 |
The following hyperparameters were used during training:
|
54 |
- learning_rate: 2e-05
|
55 |
+
- train_batch_size: 32
|
56 |
- eval_batch_size: 8
|
57 |
- seed: 42
|
58 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
all_results.json
CHANGED
@@ -1,14 +1,14 @@
|
|
1 |
{
|
2 |
"epoch": 4.0,
|
3 |
-
"eval_accuracy": 0.
|
4 |
-
"eval_loss": 0.
|
5 |
-
"eval_runtime": 0.
|
6 |
"eval_samples": 71,
|
7 |
-
"eval_samples_per_second":
|
8 |
-
"eval_steps_per_second":
|
9 |
-
"train_loss": 0.
|
10 |
-
"train_runtime":
|
11 |
"train_samples": 635,
|
12 |
-
"train_samples_per_second":
|
13 |
-
"train_steps_per_second":
|
14 |
}
|
|
|
1 |
{
|
2 |
"epoch": 4.0,
|
3 |
+
"eval_accuracy": 0.43661971830985913,
|
4 |
+
"eval_loss": 0.7083150744438171,
|
5 |
+
"eval_runtime": 0.3695,
|
6 |
"eval_samples": 71,
|
7 |
+
"eval_samples_per_second": 192.154,
|
8 |
+
"eval_steps_per_second": 24.358,
|
9 |
+
"train_loss": 0.7118758201599121,
|
10 |
+
"train_runtime": 29.8471,
|
11 |
"train_samples": 635,
|
12 |
+
"train_samples_per_second": 85.1,
|
13 |
+
"train_steps_per_second": 2.68
|
14 |
}
|
eval_results.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"epoch": 4.0,
|
3 |
-
"eval_accuracy": 0.
|
4 |
-
"eval_loss": 0.
|
5 |
-
"eval_runtime": 0.
|
6 |
"eval_samples": 71,
|
7 |
-
"eval_samples_per_second":
|
8 |
-
"eval_steps_per_second":
|
9 |
}
|
|
|
1 |
{
|
2 |
"epoch": 4.0,
|
3 |
+
"eval_accuracy": 0.43661971830985913,
|
4 |
+
"eval_loss": 0.7083150744438171,
|
5 |
+
"eval_runtime": 0.3695,
|
6 |
"eval_samples": 71,
|
7 |
+
"eval_samples_per_second": 192.154,
|
8 |
+
"eval_steps_per_second": 24.358
|
9 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 46755537
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72aa754f30d527572866f65631831dd1ac8ca634865161cdd2eafe60495bb084
|
3 |
size 46755537
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 4.0,
|
3 |
-
"train_loss": 0.
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 635,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 4.0,
|
3 |
+
"train_loss": 0.7118758201599121,
|
4 |
+
"train_runtime": 29.8471,
|
5 |
"train_samples": 635,
|
6 |
+
"train_samples_per_second": 85.1,
|
7 |
+
"train_steps_per_second": 2.68
|
8 |
}
|
trainer_state.json
CHANGED
@@ -2,22 +2,22 @@
|
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
"epoch": 4.0,
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
"epoch": 4.0,
|
12 |
-
"step":
|
13 |
"total_flos": 15175294617600.0,
|
14 |
-
"train_loss": 0.
|
15 |
-
"train_runtime":
|
16 |
-
"train_samples_per_second":
|
17 |
-
"train_steps_per_second":
|
18 |
}
|
19 |
],
|
20 |
-
"max_steps":
|
21 |
"num_train_epochs": 4,
|
22 |
"total_flos": 15175294617600.0,
|
23 |
"trial_name": null,
|
|
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
"epoch": 4.0,
|
5 |
+
"global_step": 80,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
"epoch": 4.0,
|
12 |
+
"step": 80,
|
13 |
"total_flos": 15175294617600.0,
|
14 |
+
"train_loss": 0.7118758201599121,
|
15 |
+
"train_runtime": 29.8471,
|
16 |
+
"train_samples_per_second": 85.1,
|
17 |
+
"train_steps_per_second": 2.68
|
18 |
}
|
19 |
],
|
20 |
+
"max_steps": 80,
|
21 |
"num_train_epochs": 4,
|
22 |
"total_flos": 15175294617600.0,
|
23 |
"trial_name": null,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2607
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:88188319793dcb1cdbb8866aa84daceea3fbf0084cce61388fcde675f5cbd888
|
3 |
size 2607
|