End of training
Browse files- README.md +17 -2
- all_results.json +15 -0
- eval_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +90 -0
README.md
CHANGED
@@ -1,14 +1,29 @@
|
|
1 |
---
|
2 |
library_name: transformers
|
|
|
|
|
3 |
license: apache-2.0
|
4 |
base_model: bert-base-uncased
|
5 |
tags:
|
6 |
- generated_from_trainer
|
|
|
|
|
7 |
metrics:
|
8 |
- accuracy
|
9 |
model-index:
|
10 |
- name: bert-base-uncased-finetuned-wnli
|
11 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
---
|
13 |
|
14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -16,7 +31,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
# bert-base-uncased-finetuned-wnli
|
18 |
|
19 |
-
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on
|
20 |
It achieves the following results on the evaluation set:
|
21 |
- Loss: 0.7029
|
22 |
- Accuracy: 0.5211
|
|
|
1 |
---
|
2 |
library_name: transformers
|
3 |
+
language:
|
4 |
+
- en
|
5 |
license: apache-2.0
|
6 |
base_model: bert-base-uncased
|
7 |
tags:
|
8 |
- generated_from_trainer
|
9 |
+
datasets:
|
10 |
+
- glue
|
11 |
metrics:
|
12 |
- accuracy
|
13 |
model-index:
|
14 |
- name: bert-base-uncased-finetuned-wnli
|
15 |
+
results:
|
16 |
+
- task:
|
17 |
+
name: Text Classification
|
18 |
+
type: text-classification
|
19 |
+
dataset:
|
20 |
+
name: GLUE WNLI
|
21 |
+
type: glue
|
22 |
+
args: wnli
|
23 |
+
metrics:
|
24 |
+
- name: Accuracy
|
25 |
+
type: accuracy
|
26 |
+
value: 0.5211267605633803
|
27 |
---
|
28 |
|
29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
31 |
|
32 |
# bert-base-uncased-finetuned-wnli
|
33 |
|
34 |
+
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the GLUE WNLI dataset.
|
35 |
It achieves the following results on the evaluation set:
|
36 |
- Loss: 0.7029
|
37 |
- Accuracy: 0.5211
|
all_results.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_accuracy": 0.5211267605633803,
|
4 |
+
"eval_loss": 0.7029412984848022,
|
5 |
+
"eval_runtime": 0.3122,
|
6 |
+
"eval_samples": 71,
|
7 |
+
"eval_samples_per_second": 227.442,
|
8 |
+
"eval_steps_per_second": 28.831,
|
9 |
+
"total_flos": 501226560460800.0,
|
10 |
+
"train_loss": 0.700636609395345,
|
11 |
+
"train_runtime": 43.2665,
|
12 |
+
"train_samples": 635,
|
13 |
+
"train_samples_per_second": 44.029,
|
14 |
+
"train_steps_per_second": 2.774
|
15 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_accuracy": 0.5211267605633803,
|
4 |
+
"eval_loss": 0.7029412984848022,
|
5 |
+
"eval_runtime": 0.3122,
|
6 |
+
"eval_samples": 71,
|
7 |
+
"eval_samples_per_second": 227.442,
|
8 |
+
"eval_steps_per_second": 28.831
|
9 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"total_flos": 501226560460800.0,
|
4 |
+
"train_loss": 0.700636609395345,
|
5 |
+
"train_runtime": 43.2665,
|
6 |
+
"train_samples": 635,
|
7 |
+
"train_samples_per_second": 44.029,
|
8 |
+
"train_steps_per_second": 2.774
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,90 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 120,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"grad_norm": 1.9622077941894531,
|
14 |
+
"learning_rate": 1.3333333333333333e-05,
|
15 |
+
"loss": 0.7054,
|
16 |
+
"step": 40
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_accuracy": 0.39436619718309857,
|
21 |
+
"eval_loss": 0.7037611603736877,
|
22 |
+
"eval_runtime": 0.3115,
|
23 |
+
"eval_samples_per_second": 227.899,
|
24 |
+
"eval_steps_per_second": 28.889,
|
25 |
+
"step": 40
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"grad_norm": 2.4183990955352783,
|
30 |
+
"learning_rate": 6.666666666666667e-06,
|
31 |
+
"loss": 0.7017,
|
32 |
+
"step": 80
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 2.0,
|
36 |
+
"eval_accuracy": 0.4225352112676056,
|
37 |
+
"eval_loss": 0.7019116878509521,
|
38 |
+
"eval_runtime": 0.3114,
|
39 |
+
"eval_samples_per_second": 228.007,
|
40 |
+
"eval_steps_per_second": 28.902,
|
41 |
+
"step": 80
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 3.0,
|
45 |
+
"grad_norm": 3.7433464527130127,
|
46 |
+
"learning_rate": 0.0,
|
47 |
+
"loss": 0.6947,
|
48 |
+
"step": 120
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 3.0,
|
52 |
+
"eval_accuracy": 0.5211267605633803,
|
53 |
+
"eval_loss": 0.7029412984848022,
|
54 |
+
"eval_runtime": 0.3126,
|
55 |
+
"eval_samples_per_second": 227.111,
|
56 |
+
"eval_steps_per_second": 28.789,
|
57 |
+
"step": 120
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 3.0,
|
61 |
+
"step": 120,
|
62 |
+
"total_flos": 501226560460800.0,
|
63 |
+
"train_loss": 0.700636609395345,
|
64 |
+
"train_runtime": 43.2665,
|
65 |
+
"train_samples_per_second": 44.029,
|
66 |
+
"train_steps_per_second": 2.774
|
67 |
+
}
|
68 |
+
],
|
69 |
+
"logging_steps": 500,
|
70 |
+
"max_steps": 120,
|
71 |
+
"num_input_tokens_seen": 0,
|
72 |
+
"num_train_epochs": 3,
|
73 |
+
"save_steps": 500,
|
74 |
+
"stateful_callbacks": {
|
75 |
+
"TrainerControl": {
|
76 |
+
"args": {
|
77 |
+
"should_epoch_stop": false,
|
78 |
+
"should_evaluate": false,
|
79 |
+
"should_log": false,
|
80 |
+
"should_save": true,
|
81 |
+
"should_training_stop": true
|
82 |
+
},
|
83 |
+
"attributes": {}
|
84 |
+
}
|
85 |
+
},
|
86 |
+
"total_flos": 501226560460800.0,
|
87 |
+
"train_batch_size": 16,
|
88 |
+
"trial_name": null,
|
89 |
+
"trial_params": null
|
90 |
+
}
|