Hugging Face's logo

pkairpsp
/
fine-tuned-blog-sentiment

Text Classification
Transformers
Safetensors
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Community
pkairpsp commited on
Commit
b7ce9b8
·
verified ·
1 Parent(s): 82eb079

Upload folder using huggingface_hub

Browse files
Files changed (33) hide show
  1. checkpoint-238/config.json +36 -0
  2. checkpoint-238/model.safetensors +3 -0
  3. checkpoint-238/optimizer.pt +3 -0
  4. checkpoint-238/rng_state.pth +3 -0
  5. checkpoint-238/scheduler.pt +3 -0
  6. checkpoint-238/special_tokens_map.json +37 -0
  7. checkpoint-238/tokenizer.json +0 -0
  8. checkpoint-238/tokenizer_config.json +65 -0
  9. checkpoint-238/trainer_state.json +45 -0
  10. checkpoint-238/training_args.bin +3 -0
  11. checkpoint-238/vocab.txt +0 -0
  12. checkpoint-476/config.json +36 -0
  13. checkpoint-476/model.safetensors +3 -0
  14. checkpoint-476/optimizer.pt +3 -0
  15. checkpoint-476/rng_state.pth +3 -0
  16. checkpoint-476/scheduler.pt +3 -0
  17. checkpoint-476/special_tokens_map.json +37 -0
  18. checkpoint-476/tokenizer.json +0 -0
  19. checkpoint-476/tokenizer_config.json +65 -0
  20. checkpoint-476/trainer_state.json +57 -0
  21. checkpoint-476/training_args.bin +3 -0
  22. checkpoint-476/vocab.txt +0 -0
  23. checkpoint-714/config.json +36 -0
  24. checkpoint-714/model.safetensors +3 -0
  25. checkpoint-714/optimizer.pt +3 -0
  26. checkpoint-714/rng_state.pth +3 -0
  27. checkpoint-714/scheduler.pt +3 -0
  28. checkpoint-714/special_tokens_map.json +37 -0
  29. checkpoint-714/tokenizer.json +0 -0
  30. checkpoint-714/tokenizer_config.json +65 -0
  31. checkpoint-714/trainer_state.json +76 -0
  32. checkpoint-714/training_args.bin +3 -0
  33. checkpoint-714/vocab.txt +0 -0
checkpoint-238/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "lxyuan/distilbert-base-multilingual-cased-sentiments-student",
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
+ "id2label": {
12
+ "0": "positive",
13
+ "1": "neutral",
14
+ "2": "negative"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "negative": 2,
19
+ "neutral": 1,
20
+ "positive": 0
21
+ },
22
+ "max_position_embeddings": 512,
23
+ "model_type": "distilbert",
24
+ "n_heads": 12,
25
+ "n_layers": 6,
26
+ "output_past": true,
27
+ "pad_token_id": 0,
28
+ "problem_type": "single_label_classification",
29
+ "qa_dropout": 0.1,
30
+ "seq_classif_dropout": 0.2,
31
+ "sinusoidal_pos_embds": false,
32
+ "tie_weights_": true,
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.48.2",
35
+ "vocab_size": 119547
36
+ }
checkpoint-238/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1799e7ac41b455ae6f71560b82c6855d2d2e3c456c104b73e8eddc3407106245
3
+ size 541320452
checkpoint-238/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:616b70eeecaef9ab77a91276c1fc19a4cc03cae2bbd8bde7fb31d70b40fd43a0
3
+ size 1082700154
checkpoint-238/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b452c3116d0684fa8abb970ebeb744784ffe3b664f3b2a67d4d1427fa15c23f
3
+ size 13990
checkpoint-238/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41bdca404a52091ce9b3b05d7e5b9e8fbc85c2940dd44523ae94aa1058f7cfdc
3
+ size 1064
checkpoint-238/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
checkpoint-238/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-238/tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "max_length": 512,
51
+ "model_max_length": 512,
52
+ "never_split": null,
53
+ "pad_to_multiple_of": null,
54
+ "pad_token": "[PAD]",
55
+ "pad_token_type_id": 0,
56
+ "padding_side": "right",
57
+ "sep_token": "[SEP]",
58
+ "stride": 0,
59
+ "strip_accents": null,
60
+ "tokenize_chinese_chars": true,
61
+ "tokenizer_class": "DistilBertTokenizer",
62
+ "truncation_side": "right",
63
+ "truncation_strategy": "longest_first",
64
+ "unk_token": "[UNK]"
65
+ }
checkpoint-238/trainer_state.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 238,
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
+ "eval_accuracy": 0.9245283018867925,
14
+ "eval_f1": 0.9242719879430212,
15
+ "eval_loss": 0.25112205743789673,
16
+ "eval_precision": 0.9315685227148311,
17
+ "eval_recall": 0.9245283018867925,
18
+ "eval_runtime": 292.267,
19
+ "eval_samples_per_second": 1.088,
20
+ "eval_steps_per_second": 0.137,
21
+ "step": 238
22
+ }
23
+ ],
24
+ "logging_steps": 500,
25
+ "max_steps": 714,
26
+ "num_input_tokens_seen": 0,
27
+ "num_train_epochs": 3,
28
+ "save_steps": 500,
29
+ "stateful_callbacks": {
30
+ "TrainerControl": {
31
+ "args": {
32
+ "should_epoch_stop": false,
33
+ "should_evaluate": false,
34
+ "should_log": false,
35
+ "should_save": true,
36
+ "should_training_stop": false
37
+ },
38
+ "attributes": {}
39
+ }
40
+ },
41
+ "total_flos": 251560076184576.0,
42
+ "train_batch_size": 8,
43
+ "trial_name": null,
44
+ "trial_params": null
45
+ }
checkpoint-238/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86abd7c46c1196bbbf8733498652cac4d01b411776297fbb620a2b871cbfda9b
3
+ size 5304
checkpoint-238/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-476/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "lxyuan/distilbert-base-multilingual-cased-sentiments-student",
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
+ "id2label": {
12
+ "0": "positive",
13
+ "1": "neutral",
14
+ "2": "negative"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "negative": 2,
19
+ "neutral": 1,
20
+ "positive": 0
21
+ },
22
+ "max_position_embeddings": 512,
23
+ "model_type": "distilbert",
24
+ "n_heads": 12,
25
+ "n_layers": 6,
26
+ "output_past": true,
27
+ "pad_token_id": 0,
28
+ "problem_type": "single_label_classification",
29
+ "qa_dropout": 0.1,
30
+ "seq_classif_dropout": 0.2,
31
+ "sinusoidal_pos_embds": false,
32
+ "tie_weights_": true,
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.48.2",
35
+ "vocab_size": 119547
36
+ }
checkpoint-476/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c33c5215bed4e231aa2ea521ffef4cb8cbd23996af6b45b1bcff2b914dc47c9
3
+ size 541320452
checkpoint-476/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6301ea64791855a023c8591e4ca24279dcf2ed3a6427b5497270d0c3d32bcb62
3
+ size 1082700154
checkpoint-476/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21e9377de387e81da5641d438c58da652edc70e4e1054413c019370365b92668
3
+ size 13990
checkpoint-476/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58afa012b4af9816e109a7c268738f37084e6bf720c5b16e7170a3740582f1f2
3
+ size 1064
checkpoint-476/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
checkpoint-476/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-476/tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "max_length": 512,
51
+ "model_max_length": 512,
52
+ "never_split": null,
53
+ "pad_to_multiple_of": null,
54
+ "pad_token": "[PAD]",
55
+ "pad_token_type_id": 0,
56
+ "padding_side": "right",
57
+ "sep_token": "[SEP]",
58
+ "stride": 0,
59
+ "strip_accents": null,
60
+ "tokenize_chinese_chars": true,
61
+ "tokenizer_class": "DistilBertTokenizer",
62
+ "truncation_side": "right",
63
+ "truncation_strategy": "longest_first",
64
+ "unk_token": "[UNK]"
65
+ }
checkpoint-476/trainer_state.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 476,
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
+ "eval_accuracy": 0.9245283018867925,
14
+ "eval_f1": 0.9242719879430212,
15
+ "eval_loss": 0.25112205743789673,
16
+ "eval_precision": 0.9315685227148311,
17
+ "eval_recall": 0.9245283018867925,
18
+ "eval_runtime": 292.267,
19
+ "eval_samples_per_second": 1.088,
20
+ "eval_steps_per_second": 0.137,
21
+ "step": 238
22
+ },
23
+ {
24
+ "epoch": 2.0,
25
+ "eval_accuracy": 0.9339622641509434,
26
+ "eval_f1": 0.933657504155167,
27
+ "eval_loss": 0.14069578051567078,
28
+ "eval_precision": 0.9421693229583453,
29
+ "eval_recall": 0.9339622641509434,
30
+ "eval_runtime": 289.7835,
31
+ "eval_samples_per_second": 1.097,
32
+ "eval_steps_per_second": 0.138,
33
+ "step": 476
34
+ }
35
+ ],
36
+ "logging_steps": 500,
37
+ "max_steps": 714,
38
+ "num_input_tokens_seen": 0,
39
+ "num_train_epochs": 3,
40
+ "save_steps": 500,
41
+ "stateful_callbacks": {
42
+ "TrainerControl": {
43
+ "args": {
44
+ "should_epoch_stop": false,
45
+ "should_evaluate": false,
46
+ "should_log": false,
47
+ "should_save": true,
48
+ "should_training_stop": false
49
+ },
50
+ "attributes": {}
51
+ }
52
+ },
53
+ "total_flos": 503120152369152.0,
54
+ "train_batch_size": 8,
55
+ "trial_name": null,
56
+ "trial_params": null
57
+ }
checkpoint-476/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86abd7c46c1196bbbf8733498652cac4d01b411776297fbb620a2b871cbfda9b
3
+ size 5304
checkpoint-476/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-714/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "lxyuan/distilbert-base-multilingual-cased-sentiments-student",
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
+ "id2label": {
12
+ "0": "positive",
13
+ "1": "neutral",
14
+ "2": "negative"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "negative": 2,
19
+ "neutral": 1,
20
+ "positive": 0
21
+ },
22
+ "max_position_embeddings": 512,
23
+ "model_type": "distilbert",
24
+ "n_heads": 12,
25
+ "n_layers": 6,
26
+ "output_past": true,
27
+ "pad_token_id": 0,
28
+ "problem_type": "single_label_classification",
29
+ "qa_dropout": 0.1,
30
+ "seq_classif_dropout": 0.2,
31
+ "sinusoidal_pos_embds": false,
32
+ "tie_weights_": true,
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.48.2",
35
+ "vocab_size": 119547
36
+ }
checkpoint-714/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c0ff7996a4877cee32eb9bfacd2aaab4a9f5a6a70ca301d119bc6f20431bdb5
3
+ size 541320452
checkpoint-714/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1394f230e2e499c85b6362d65139a57c17d4fab9128d8f239034d86bd1d05d60
3
+ size 1082700154
checkpoint-714/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23550270f41dd9b1b88f47c15a0ab60a6fea0d16274d0b4e3d2908b4138d0456
3
+ size 13990
checkpoint-714/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15697dbb71dffb8de0632092db9d80e708ce9b665d10b2108a5674c6a0471210
3
+ size 1064
checkpoint-714/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
checkpoint-714/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-714/tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "max_length": 512,
51
+ "model_max_length": 512,
52
+ "never_split": null,
53
+ "pad_to_multiple_of": null,
54
+ "pad_token": "[PAD]",
55
+ "pad_token_type_id": 0,
56
+ "padding_side": "right",
57
+ "sep_token": "[SEP]",
58
+ "stride": 0,
59
+ "strip_accents": null,
60
+ "tokenize_chinese_chars": true,
61
+ "tokenizer_class": "DistilBertTokenizer",
62
+ "truncation_side": "right",
63
+ "truncation_strategy": "longest_first",
64
+ "unk_token": "[UNK]"
65
+ }
checkpoint-714/trainer_state.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 714,
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
+ "eval_accuracy": 0.9245283018867925,
14
+ "eval_f1": 0.9242719879430212,
15
+ "eval_loss": 0.25112205743789673,
16
+ "eval_precision": 0.9315685227148311,
17
+ "eval_recall": 0.9245283018867925,
18
+ "eval_runtime": 292.267,
19
+ "eval_samples_per_second": 1.088,
20
+ "eval_steps_per_second": 0.137,
21
+ "step": 238
22
+ },
23
+ {
24
+ "epoch": 2.0,
25
+ "eval_accuracy": 0.9339622641509434,
26
+ "eval_f1": 0.933657504155167,
27
+ "eval_loss": 0.14069578051567078,
28
+ "eval_precision": 0.9421693229583453,
29
+ "eval_recall": 0.9339622641509434,
30
+ "eval_runtime": 289.7835,
31
+ "eval_samples_per_second": 1.097,
32
+ "eval_steps_per_second": 0.138,
33
+ "step": 476
34
+ },
35
+ {
36
+ "epoch": 2.100840336134454,
37
+ "grad_norm": 0.010930689983069897,
38
+ "learning_rate": 5.994397759103642e-06,
39
+ "loss": 0.1044,
40
+ "step": 500
41
+ },
42
+ {
43
+ "epoch": 3.0,
44
+ "eval_accuracy": 0.9308176100628931,
45
+ "eval_f1": 0.9305292147163376,
46
+ "eval_loss": 0.3272361159324646,
47
+ "eval_precision": 0.9385589054841049,
48
+ "eval_recall": 0.9308176100628931,
49
+ "eval_runtime": 294.9296,
50
+ "eval_samples_per_second": 1.078,
51
+ "eval_steps_per_second": 0.136,
52
+ "step": 714
53
+ }
54
+ ],
55
+ "logging_steps": 500,
56
+ "max_steps": 714,
57
+ "num_input_tokens_seen": 0,
58
+ "num_train_epochs": 3,
59
+ "save_steps": 500,
60
+ "stateful_callbacks": {
61
+ "TrainerControl": {
62
+ "args": {
63
+ "should_epoch_stop": false,
64
+ "should_evaluate": false,
65
+ "should_log": false,
66
+ "should_save": true,
67
+ "should_training_stop": true
68
+ },
69
+ "attributes": {}
70
+ }
71
+ },
72
+ "total_flos": 754680228553728.0,
73
+ "train_batch_size": 8,
74
+ "trial_name": null,
75
+ "trial_params": null
76
+ }
checkpoint-714/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86abd7c46c1196bbbf8733498652cac4d01b411776297fbb620a2b871cbfda9b
3
+ size 5304
checkpoint-714/vocab.txt ADDED
The diff for this file is too large to render. See raw diff