tejaskamtam
commited on
Commit
•
8c82c3f
1
Parent(s):
59b6c06
End of training
Browse files- README.md +16 -4
- all_results.json +12 -12
- eval_results.json +7 -7
- train_results.json +5 -5
- trainer_state.json +17 -17
README.md
CHANGED
@@ -3,11 +3,23 @@ license: apache-2.0
|
|
3 |
base_model: bert-base-uncased
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
6 |
metrics:
|
7 |
- accuracy
|
8 |
model-index:
|
9 |
- name: testing
|
10 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
---
|
12 |
|
13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -15,10 +27,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# testing
|
17 |
|
18 |
-
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 1.
|
21 |
-
- Accuracy: 0.
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
3 |
base_model: bert-base-uncased
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- datasets/all_binary_and_xe_ey_fae_counterfactual
|
8 |
metrics:
|
9 |
- accuracy
|
10 |
model-index:
|
11 |
- name: testing
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Masked Language Modeling
|
15 |
+
type: fill-mask
|
16 |
+
dataset:
|
17 |
+
name: datasets/all_binary_and_xe_ey_fae_counterfactual
|
18 |
+
type: datasets/all_binary_and_xe_ey_fae_counterfactual
|
19 |
+
metrics:
|
20 |
+
- name: Accuracy
|
21 |
+
type: accuracy
|
22 |
+
value: 0.6740440005371309
|
23 |
---
|
24 |
|
25 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
27 |
|
28 |
# testing
|
29 |
|
30 |
+
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the datasets/all_binary_and_xe_ey_fae_counterfactual dataset.
|
31 |
It achieves the following results on the evaluation set:
|
32 |
+
- Loss: 1.7135
|
33 |
+
- Accuracy: 0.6740
|
34 |
|
35 |
## Model description
|
36 |
|
all_results.json
CHANGED
@@ -1,15 +1,15 @@
|
|
1 |
{
|
2 |
"epoch": 0.0,
|
3 |
-
"eval_accuracy": 0.
|
4 |
-
"eval_loss": 1.
|
5 |
-
"eval_runtime":
|
6 |
-
"eval_samples":
|
7 |
-
"eval_samples_per_second":
|
8 |
-
"eval_steps_per_second":
|
9 |
-
"perplexity": 5.
|
10 |
-
"train_loss": 1.
|
11 |
-
"train_runtime":
|
12 |
-
"train_samples":
|
13 |
-
"train_samples_per_second":
|
14 |
-
"train_steps_per_second": 0.
|
15 |
}
|
|
|
1 |
{
|
2 |
"epoch": 0.0,
|
3 |
+
"eval_accuracy": 0.6740440005371309,
|
4 |
+
"eval_loss": 1.7135361433029175,
|
5 |
+
"eval_runtime": 78.7535,
|
6 |
+
"eval_samples": 15525,
|
7 |
+
"eval_samples_per_second": 197.134,
|
8 |
+
"eval_steps_per_second": 24.647,
|
9 |
+
"perplexity": 5.548547286429599,
|
10 |
+
"train_loss": 1.9919448852539063,
|
11 |
+
"train_runtime": 160.975,
|
12 |
+
"train_samples": 124124,
|
13 |
+
"train_samples_per_second": 0.994,
|
14 |
+
"train_steps_per_second": 0.062
|
15 |
}
|
eval_results.json
CHANGED
@@ -1,10 +1,10 @@
|
|
1 |
{
|
2 |
"epoch": 0.0,
|
3 |
-
"eval_accuracy": 0.
|
4 |
-
"eval_loss": 1.
|
5 |
-
"eval_runtime":
|
6 |
-
"eval_samples":
|
7 |
-
"eval_samples_per_second":
|
8 |
-
"eval_steps_per_second":
|
9 |
-
"perplexity": 5.
|
10 |
}
|
|
|
1 |
{
|
2 |
"epoch": 0.0,
|
3 |
+
"eval_accuracy": 0.6740440005371309,
|
4 |
+
"eval_loss": 1.7135361433029175,
|
5 |
+
"eval_runtime": 78.7535,
|
6 |
+
"eval_samples": 15525,
|
7 |
+
"eval_samples_per_second": 197.134,
|
8 |
+
"eval_steps_per_second": 24.647,
|
9 |
+
"perplexity": 5.548547286429599
|
10 |
}
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 0.0,
|
3 |
-
"train_loss": 1.
|
4 |
-
"train_runtime":
|
5 |
-
"train_samples":
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 0.0,
|
3 |
+
"train_loss": 1.9919448852539063,
|
4 |
+
"train_runtime": 160.975,
|
5 |
+
"train_samples": 124124,
|
6 |
+
"train_samples_per_second": 0.994,
|
7 |
+
"train_steps_per_second": 0.062
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 5,
|
6 |
"global_step": 10,
|
7 |
"is_hyper_param_search": false,
|
@@ -11,41 +11,41 @@
|
|
11 |
{
|
12 |
"epoch": 0.0,
|
13 |
"learning_rate": 5e-05,
|
14 |
-
"loss": 2.
|
15 |
"step": 5
|
16 |
},
|
17 |
{
|
18 |
"epoch": 0.0,
|
19 |
-
"eval_accuracy": 0.
|
20 |
-
"eval_loss": 1.
|
21 |
-
"eval_runtime":
|
22 |
-
"eval_samples_per_second":
|
23 |
-
"eval_steps_per_second":
|
24 |
"step": 5
|
25 |
},
|
26 |
{
|
27 |
"epoch": 0.0,
|
28 |
"learning_rate": 0.0,
|
29 |
-
"loss": 1.
|
30 |
"step": 10
|
31 |
},
|
32 |
{
|
33 |
"epoch": 0.0,
|
34 |
-
"eval_accuracy": 0.
|
35 |
-
"eval_loss": 1.
|
36 |
-
"eval_runtime":
|
37 |
-
"eval_samples_per_second":
|
38 |
-
"eval_steps_per_second":
|
39 |
"step": 10
|
40 |
},
|
41 |
{
|
42 |
"epoch": 0.0,
|
43 |
"step": 10,
|
44 |
"total_flos": 42112770048000.0,
|
45 |
-
"train_loss": 1.
|
46 |
-
"train_runtime":
|
47 |
-
"train_samples_per_second":
|
48 |
-
"train_steps_per_second": 0.
|
49 |
}
|
50 |
],
|
51 |
"logging_steps": 5,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.001288992008249549,
|
5 |
"eval_steps": 5,
|
6 |
"global_step": 10,
|
7 |
"is_hyper_param_search": false,
|
|
|
11 |
{
|
12 |
"epoch": 0.0,
|
13 |
"learning_rate": 5e-05,
|
14 |
+
"loss": 2.068,
|
15 |
"step": 5
|
16 |
},
|
17 |
{
|
18 |
"epoch": 0.0,
|
19 |
+
"eval_accuracy": 0.6649938341745655,
|
20 |
+
"eval_loss": 1.775834321975708,
|
21 |
+
"eval_runtime": 78.5903,
|
22 |
+
"eval_samples_per_second": 197.544,
|
23 |
+
"eval_steps_per_second": 24.698,
|
24 |
"step": 5
|
25 |
},
|
26 |
{
|
27 |
"epoch": 0.0,
|
28 |
"learning_rate": 0.0,
|
29 |
+
"loss": 1.9159,
|
30 |
"step": 10
|
31 |
},
|
32 |
{
|
33 |
"epoch": 0.0,
|
34 |
+
"eval_accuracy": 0.6735738398990131,
|
35 |
+
"eval_loss": 1.719245433807373,
|
36 |
+
"eval_runtime": 79.477,
|
37 |
+
"eval_samples_per_second": 195.339,
|
38 |
+
"eval_steps_per_second": 24.422,
|
39 |
"step": 10
|
40 |
},
|
41 |
{
|
42 |
"epoch": 0.0,
|
43 |
"step": 10,
|
44 |
"total_flos": 42112770048000.0,
|
45 |
+
"train_loss": 1.9919448852539063,
|
46 |
+
"train_runtime": 160.975,
|
47 |
+
"train_samples_per_second": 0.994,
|
48 |
+
"train_steps_per_second": 0.062
|
49 |
}
|
50 |
],
|
51 |
"logging_steps": 5,
|