Upload folder using huggingface_hub
Browse files- https:/huggingface.co/sixte99/distilbert-base-uncased-finetuned-cola/config.json +25 -0
- https:/huggingface.co/sixte99/distilbert-base-uncased-finetuned-cola/model.safetensors +3 -0
- https:/huggingface.co/sixte99/distilbert-base-uncased-finetuned-cola/optimizer.pt +3 -0
- https:/huggingface.co/sixte99/distilbert-base-uncased-finetuned-cola/rng_state.pth +3 -0
- https:/huggingface.co/sixte99/distilbert-base-uncased-finetuned-cola/scheduler.pt +3 -0
- https:/huggingface.co/sixte99/distilbert-base-uncased-finetuned-cola/special_tokens_map.json +7 -0
- https:/huggingface.co/sixte99/distilbert-base-uncased-finetuned-cola/tokenizer.json +0 -0
- https:/huggingface.co/sixte99/distilbert-base-uncased-finetuned-cola/tokenizer_config.json +55 -0
- https:/huggingface.co/sixte99/distilbert-base-uncased-finetuned-cola/trainer_state.json +101 -0
- https:/huggingface.co/sixte99/distilbert-base-uncased-finetuned-cola/training_args.bin +3 -0
- https:/huggingface.co/sixte99/distilbert-base-uncased-finetuned-cola/vocab.txt +0 -0
https:/huggingface.co/sixte99/distilbert-base-uncased-finetuned-cola/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"max_position_embeddings": 512,
|
13 |
+
"model_type": "distilbert",
|
14 |
+
"n_heads": 12,
|
15 |
+
"n_layers": 6,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"problem_type": "single_label_classification",
|
18 |
+
"qa_dropout": 0.1,
|
19 |
+
"seq_classif_dropout": 0.2,
|
20 |
+
"sinusoidal_pos_embds": false,
|
21 |
+
"tie_weights_": true,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.39.3",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
https:/huggingface.co/sixte99/distilbert-base-uncased-finetuned-cola/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:598acbc53955b3f329c90ef104bb543954acf3b162a1fd1fbdf25795b972b247
|
3 |
+
size 267832560
|
https:/huggingface.co/sixte99/distilbert-base-uncased-finetuned-cola/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:63b48335783347cec04cad373dca5303641e96db5898f2b0fa799f30c8541819
|
3 |
+
size 535724410
|
https:/huggingface.co/sixte99/distilbert-base-uncased-finetuned-cola/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2fed77b14fe062f6db72d68cedd6fd95bae3305b7a735eef3c85da43fd15d476
|
3 |
+
size 13990
|
https:/huggingface.co/sixte99/distilbert-base-uncased-finetuned-cola/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b35dfcc5fc0fb1ac3e0cb7ba3b81360998b5dd1cfc9a8eaf6dfcce51210c3ac
|
3 |
+
size 1064
|
https:/huggingface.co/sixte99/distilbert-base-uncased-finetuned-cola/special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
https:/huggingface.co/sixte99/distilbert-base-uncased-finetuned-cola/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
https:/huggingface.co/sixte99/distilbert-base-uncased-finetuned-cola/tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
https:/huggingface.co/sixte99/distilbert-base-uncased-finetuned-cola/trainer_state.json
ADDED
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.5406394412669151,
|
3 |
+
"best_model_checkpoint": "./output_dir/checkpoint-2140",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2140,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.93,
|
13 |
+
"grad_norm": 8.194293022155762,
|
14 |
+
"learning_rate": 1.6261682242990654e-05,
|
15 |
+
"loss": 0.5333,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_accuracy": 0.7670182166826462,
|
21 |
+
"eval_f1": 0.8439306358381502,
|
22 |
+
"eval_loss": 0.4723087251186371,
|
23 |
+
"eval_matthews": 0.41157003449441765,
|
24 |
+
"eval_precision": 0.7858851674641149,
|
25 |
+
"eval_recall": 0.9112343966712899,
|
26 |
+
"eval_runtime": 4.69,
|
27 |
+
"eval_samples_per_second": 222.389,
|
28 |
+
"eval_steps_per_second": 14.073,
|
29 |
+
"step": 535
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 1.87,
|
33 |
+
"grad_norm": 7.945075035095215,
|
34 |
+
"learning_rate": 1.2523364485981309e-05,
|
35 |
+
"loss": 0.3791,
|
36 |
+
"step": 1000
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 2.0,
|
40 |
+
"eval_accuracy": 0.8044103547459253,
|
41 |
+
"eval_f1": 0.8647214854111407,
|
42 |
+
"eval_loss": 0.48717230558395386,
|
43 |
+
"eval_matthews": 0.5206791471093309,
|
44 |
+
"eval_precision": 0.8284625158831004,
|
45 |
+
"eval_recall": 0.9042995839112344,
|
46 |
+
"eval_runtime": 4.7075,
|
47 |
+
"eval_samples_per_second": 221.563,
|
48 |
+
"eval_steps_per_second": 14.02,
|
49 |
+
"step": 1070
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 2.8,
|
53 |
+
"grad_norm": 9.216336250305176,
|
54 |
+
"learning_rate": 8.785046728971963e-06,
|
55 |
+
"loss": 0.2565,
|
56 |
+
"step": 1500
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 3.0,
|
60 |
+
"eval_accuracy": 0.8092042186001918,
|
61 |
+
"eval_f1": 0.8688200395517469,
|
62 |
+
"eval_loss": 0.6224496960639954,
|
63 |
+
"eval_matthews": 0.5308757570358055,
|
64 |
+
"eval_precision": 0.8278894472361809,
|
65 |
+
"eval_recall": 0.9140083217753121,
|
66 |
+
"eval_runtime": 2.44,
|
67 |
+
"eval_samples_per_second": 427.457,
|
68 |
+
"eval_steps_per_second": 27.049,
|
69 |
+
"step": 1605
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 3.74,
|
73 |
+
"grad_norm": 11.538783073425293,
|
74 |
+
"learning_rate": 5.046728971962617e-06,
|
75 |
+
"loss": 0.2031,
|
76 |
+
"step": 2000
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 4.0,
|
80 |
+
"eval_accuracy": 0.8130393096836049,
|
81 |
+
"eval_f1": 0.871456822676335,
|
82 |
+
"eval_loss": 0.7633702754974365,
|
83 |
+
"eval_matthews": 0.5406394412669151,
|
84 |
+
"eval_precision": 0.8304020100502513,
|
85 |
+
"eval_recall": 0.9167822468793343,
|
86 |
+
"eval_runtime": 2.3856,
|
87 |
+
"eval_samples_per_second": 437.202,
|
88 |
+
"eval_steps_per_second": 27.666,
|
89 |
+
"step": 2140
|
90 |
+
}
|
91 |
+
],
|
92 |
+
"logging_steps": 500,
|
93 |
+
"max_steps": 2675,
|
94 |
+
"num_input_tokens_seen": 0,
|
95 |
+
"num_train_epochs": 5,
|
96 |
+
"save_steps": 500,
|
97 |
+
"total_flos": 182967489688944.0,
|
98 |
+
"train_batch_size": 16,
|
99 |
+
"trial_name": null,
|
100 |
+
"trial_params": null
|
101 |
+
}
|
https:/huggingface.co/sixte99/distilbert-base-uncased-finetuned-cola/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92ad2d1d939a27135089adf5a0a989bacdf21269587869a9a3d57ab3ad58f0a7
|
3 |
+
size 4920
|
https:/huggingface.co/sixte99/distilbert-base-uncased-finetuned-cola/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|