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
@@ -1,13 +1,28 @@
|
|
1 |
---
|
|
|
|
|
2 |
license: apache-2.0
|
3 |
base_model: google/fnet-base
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
6 |
metrics:
|
7 |
- matthews_correlation
|
8 |
model-index:
|
9 |
- name: fnet-base-finetuned-cola
|
10 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
---
|
12 |
|
13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -15,7 +30,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# fnet-base-finetuned-cola
|
17 |
|
18 |
-
This model is a fine-tuned version of [google/fnet-base](https://huggingface.co/google/fnet-base) on
|
19 |
It achieves the following results on the evaluation set:
|
20 |
- Loss: 0.5648
|
21 |
- Matthews Correlation: 0.3263
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
license: apache-2.0
|
5 |
base_model: google/fnet-base
|
6 |
tags:
|
7 |
- generated_from_trainer
|
8 |
+
datasets:
|
9 |
+
- glue
|
10 |
metrics:
|
11 |
- matthews_correlation
|
12 |
model-index:
|
13 |
- name: fnet-base-finetuned-cola
|
14 |
+
results:
|
15 |
+
- task:
|
16 |
+
name: Text Classification
|
17 |
+
type: text-classification
|
18 |
+
dataset:
|
19 |
+
name: GLUE COLA
|
20 |
+
type: glue
|
21 |
+
args: cola
|
22 |
+
metrics:
|
23 |
+
- name: Matthews Correlation
|
24 |
+
type: matthews_correlation
|
25 |
+
value: 0.3262988329908328
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
30 |
|
31 |
# fnet-base-finetuned-cola
|
32 |
|
33 |
+
This model is a fine-tuned version of [google/fnet-base](https://huggingface.co/google/fnet-base) on the GLUE COLA dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
- Loss: 0.5648
|
36 |
- Matthews Correlation: 0.3263
|
all_results.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_loss": 0.5648320913314819,
|
4 |
+
"eval_matthews_correlation": 0.3262988329908328,
|
5 |
+
"eval_runtime": 8.5449,
|
6 |
+
"eval_samples": 1043,
|
7 |
+
"eval_samples_per_second": 122.062,
|
8 |
+
"eval_steps_per_second": 7.724,
|
9 |
+
"total_flos": 4562104380880896.0,
|
10 |
+
"train_loss": 0.5235365682573461,
|
11 |
+
"train_runtime": 487.6856,
|
12 |
+
"train_samples": 8551,
|
13 |
+
"train_samples_per_second": 52.602,
|
14 |
+
"train_steps_per_second": 1.649
|
15 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_loss": 0.5648320913314819,
|
4 |
+
"eval_matthews_correlation": 0.3262988329908328,
|
5 |
+
"eval_runtime": 8.5449,
|
6 |
+
"eval_samples": 1043,
|
7 |
+
"eval_samples_per_second": 122.062,
|
8 |
+
"eval_steps_per_second": 7.724
|
9 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"total_flos": 4562104380880896.0,
|
4 |
+
"train_loss": 0.5235365682573461,
|
5 |
+
"train_runtime": 487.6856,
|
6 |
+
"train_samples": 8551,
|
7 |
+
"train_samples_per_second": 52.602,
|
8 |
+
"train_steps_per_second": 1.649
|
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": 804,
|
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": 6.508703708648682,
|
14 |
+
"learning_rate": 1.3333333333333333e-05,
|
15 |
+
"loss": 0.6101,
|
16 |
+
"step": 268
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_loss": 0.6032158732414246,
|
21 |
+
"eval_matthews_correlation": 0.1345503796973939,
|
22 |
+
"eval_runtime": 8.5318,
|
23 |
+
"eval_samples_per_second": 122.249,
|
24 |
+
"eval_steps_per_second": 7.736,
|
25 |
+
"step": 268
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"grad_norm": 11.809653282165527,
|
30 |
+
"learning_rate": 6.666666666666667e-06,
|
31 |
+
"loss": 0.5325,
|
32 |
+
"step": 536
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 2.0,
|
36 |
+
"eval_loss": 0.5451133251190186,
|
37 |
+
"eval_matthews_correlation": 0.3134805838230471,
|
38 |
+
"eval_runtime": 8.5009,
|
39 |
+
"eval_samples_per_second": 122.693,
|
40 |
+
"eval_steps_per_second": 7.764,
|
41 |
+
"step": 536
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 3.0,
|
45 |
+
"grad_norm": 9.861120223999023,
|
46 |
+
"learning_rate": 0.0,
|
47 |
+
"loss": 0.428,
|
48 |
+
"step": 804
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 3.0,
|
52 |
+
"eval_loss": 0.5648320913314819,
|
53 |
+
"eval_matthews_correlation": 0.3262988329908328,
|
54 |
+
"eval_runtime": 8.5202,
|
55 |
+
"eval_samples_per_second": 122.414,
|
56 |
+
"eval_steps_per_second": 7.746,
|
57 |
+
"step": 804
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 3.0,
|
61 |
+
"step": 804,
|
62 |
+
"total_flos": 4562104380880896.0,
|
63 |
+
"train_loss": 0.5235365682573461,
|
64 |
+
"train_runtime": 487.6856,
|
65 |
+
"train_samples_per_second": 52.602,
|
66 |
+
"train_steps_per_second": 1.649
|
67 |
+
}
|
68 |
+
],
|
69 |
+
"logging_steps": 500,
|
70 |
+
"max_steps": 804,
|
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": 4562104380880896.0,
|
87 |
+
"train_batch_size": 32,
|
88 |
+
"trial_name": null,
|
89 |
+
"trial_params": null
|
90 |
+
}
|