Hugging Face's logo

Recod
/
imdb_sentiment_classifier

Safetensors
Model card Files
xet
Community
Recod commited on
Commit
05a10dc
·
verified ·
1 Parent(s): ab2641c

Upload folder using huggingface_hub

Browse files
Files changed (22) hide show
  1. checkpoint-1563/config.json +32 -0
  2. checkpoint-1563/model.safetensors +3 -0
  3. checkpoint-1563/optimizer.pt +3 -0
  4. checkpoint-1563/rng_state.pth +3 -0
  5. checkpoint-1563/scheduler.pt +3 -0
  6. checkpoint-1563/special_tokens_map.json +7 -0
  7. checkpoint-1563/tokenizer.json +0 -0
  8. checkpoint-1563/tokenizer_config.json +56 -0
  9. checkpoint-1563/trainer_state.json +64 -0
  10. checkpoint-1563/training_args.bin +3 -0
  11. checkpoint-1563/vocab.txt +0 -0
  12. checkpoint-3126/config.json +32 -0
  13. checkpoint-3126/model.safetensors +3 -0
  14. checkpoint-3126/optimizer.pt +3 -0
  15. checkpoint-3126/rng_state.pth +3 -0
  16. checkpoint-3126/scheduler.pt +3 -0
  17. checkpoint-3126/special_tokens_map.json +7 -0
  18. checkpoint-3126/tokenizer.json +0 -0
  19. checkpoint-3126/tokenizer_config.json +56 -0
  20. checkpoint-3126/trainer_state.json +94 -0
  21. checkpoint-3126/training_args.bin +3 -0
  22. checkpoint-3126/vocab.txt +0 -0
checkpoint-1563/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "dim": 768,
8
+ "dropout": 0.1,
9
+ "hidden_dim": 3072,
10
+ "id2label": {
11
+ "0": "NEGATIVE",
12
+ "1": "POSITIVE"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "label2id": {
16
+ "NEGATIVE": 0,
17
+ "POSITIVE": 1
18
+ },
19
+ "max_position_embeddings": 512,
20
+ "model_type": "distilbert",
21
+ "n_heads": 12,
22
+ "n_layers": 6,
23
+ "pad_token_id": 0,
24
+ "problem_type": "single_label_classification",
25
+ "qa_dropout": 0.1,
26
+ "seq_classif_dropout": 0.2,
27
+ "sinusoidal_pos_embds": false,
28
+ "tie_weights_": true,
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.51.1",
31
+ "vocab_size": 30522
32
+ }
checkpoint-1563/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2450119d38933f356388274dd62e8ade691083105a00bde4f004ae73d5f6ce4f
3
+ size 267832560
checkpoint-1563/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:464f89753e8201fdccbb49fa9c5d1dc3105940d08b05be27d609cdba5002dfbd
3
+ size 535727290
checkpoint-1563/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acac9bd80d61a31c0be6e7ee3e8eac8bb0e8230e470ce8fa940655866c5bb14c
3
+ size 14244
checkpoint-1563/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:477935f92b5e7bff3b2fc8dc8549863ff04063fca652cfa6f7fa399840d6c318
3
+ size 1064
checkpoint-1563/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
+ }
checkpoint-1563/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1563/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "DistilBertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
checkpoint-1563/trainer_state.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1563,
3
+ "best_metric": 0.2116006463766098,
4
+ "best_model_checkpoint": "imdb_sentiment_classifier/checkpoint-1563",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1563,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.3198976327575176,
14
+ "grad_norm": 10.610838890075684,
15
+ "learning_rate": 1.6807421625079976e-05,
16
+ "loss": 0.3226,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.6397952655150352,
21
+ "grad_norm": 19.95803451538086,
22
+ "learning_rate": 1.36084452975048e-05,
23
+ "loss": 0.25,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.9596928982725528,
28
+ "grad_norm": 13.353290557861328,
29
+ "learning_rate": 1.0409468969929623e-05,
30
+ "loss": 0.2229,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 1.0,
35
+ "eval_accuracy": 0.91992,
36
+ "eval_loss": 0.2116006463766098,
37
+ "eval_runtime": 37.0434,
38
+ "eval_samples_per_second": 674.884,
39
+ "eval_steps_per_second": 42.194,
40
+ "step": 1563
41
+ }
42
+ ],
43
+ "logging_steps": 500,
44
+ "max_steps": 3126,
45
+ "num_input_tokens_seen": 0,
46
+ "num_train_epochs": 2,
47
+ "save_steps": 500,
48
+ "stateful_callbacks": {
49
+ "TrainerControl": {
50
+ "args": {
51
+ "should_epoch_stop": false,
52
+ "should_evaluate": false,
53
+ "should_log": false,
54
+ "should_save": true,
55
+ "should_training_stop": false
56
+ },
57
+ "attributes": {}
58
+ }
59
+ },
60
+ "total_flos": 3280166004732288.0,
61
+ "train_batch_size": 16,
62
+ "trial_name": null,
63
+ "trial_params": null
64
+ }
checkpoint-1563/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d16606da1b22bbc51c25b3f39e5f0ba33809a5694e20904ec27ef2bb4c365e04
3
+ size 5304
checkpoint-1563/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-3126/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "dim": 768,
8
+ "dropout": 0.1,
9
+ "hidden_dim": 3072,
10
+ "id2label": {
11
+ "0": "NEGATIVE",
12
+ "1": "POSITIVE"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "label2id": {
16
+ "NEGATIVE": 0,
17
+ "POSITIVE": 1
18
+ },
19
+ "max_position_embeddings": 512,
20
+ "model_type": "distilbert",
21
+ "n_heads": 12,
22
+ "n_layers": 6,
23
+ "pad_token_id": 0,
24
+ "problem_type": "single_label_classification",
25
+ "qa_dropout": 0.1,
26
+ "seq_classif_dropout": 0.2,
27
+ "sinusoidal_pos_embds": false,
28
+ "tie_weights_": true,
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.51.1",
31
+ "vocab_size": 30522
32
+ }
checkpoint-3126/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc1574fc53f44063248a946e95f8e7a1d5829b445c3938e873820cbbad55adb6
3
+ size 267832560
checkpoint-3126/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc23a007118099591f62927b32836741af19ad95e49d8714d3a077ecb7bb3bfa
3
+ size 535727290
checkpoint-3126/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83c690505d08492ed3760ffefee77bedb805889ccd35e3196faf939da03b0f20
3
+ size 14244
checkpoint-3126/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3325cc955f0727c2eb4fddfba7736a2bcb5b15a3b1b088eab4e9ab27747da27c
3
+ size 1064
checkpoint-3126/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
+ }
checkpoint-3126/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-3126/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "DistilBertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
checkpoint-3126/trainer_state.json ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1563,
3
+ "best_metric": 0.2116006463766098,
4
+ "best_model_checkpoint": "imdb_sentiment_classifier/checkpoint-1563",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 3126,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.3198976327575176,
14
+ "grad_norm": 10.610838890075684,
15
+ "learning_rate": 1.6807421625079976e-05,
16
+ "loss": 0.3226,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.6397952655150352,
21
+ "grad_norm": 19.95803451538086,
22
+ "learning_rate": 1.36084452975048e-05,
23
+ "loss": 0.25,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.9596928982725528,
28
+ "grad_norm": 13.353290557861328,
29
+ "learning_rate": 1.0409468969929623e-05,
30
+ "loss": 0.2229,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 1.0,
35
+ "eval_accuracy": 0.91992,
36
+ "eval_loss": 0.2116006463766098,
37
+ "eval_runtime": 37.0434,
38
+ "eval_samples_per_second": 674.884,
39
+ "eval_steps_per_second": 42.194,
40
+ "step": 1563
41
+ },
42
+ {
43
+ "epoch": 1.2795905310300704,
44
+ "grad_norm": 13.05849552154541,
45
+ "learning_rate": 7.210492642354448e-06,
46
+ "loss": 0.1641,
47
+ "step": 2000
48
+ },
49
+ {
50
+ "epoch": 1.599488163787588,
51
+ "grad_norm": 20.765056610107422,
52
+ "learning_rate": 4.0115163147792705e-06,
53
+ "loss": 0.1461,
54
+ "step": 2500
55
+ },
56
+ {
57
+ "epoch": 1.9193857965451055,
58
+ "grad_norm": 15.38147258758545,
59
+ "learning_rate": 8.125399872040947e-07,
60
+ "loss": 0.1439,
61
+ "step": 3000
62
+ },
63
+ {
64
+ "epoch": 2.0,
65
+ "eval_accuracy": 0.93032,
66
+ "eval_loss": 0.2347356677055359,
67
+ "eval_runtime": 37.4838,
68
+ "eval_samples_per_second": 666.954,
69
+ "eval_steps_per_second": 41.698,
70
+ "step": 3126
71
+ }
72
+ ],
73
+ "logging_steps": 500,
74
+ "max_steps": 3126,
75
+ "num_input_tokens_seen": 0,
76
+ "num_train_epochs": 2,
77
+ "save_steps": 500,
78
+ "stateful_callbacks": {
79
+ "TrainerControl": {
80
+ "args": {
81
+ "should_epoch_stop": false,
82
+ "should_evaluate": false,
83
+ "should_log": false,
84
+ "should_save": true,
85
+ "should_training_stop": true
86
+ },
87
+ "attributes": {}
88
+ }
89
+ },
90
+ "total_flos": 6556904415524352.0,
91
+ "train_batch_size": 16,
92
+ "trial_name": null,
93
+ "trial_params": null
94
+ }
checkpoint-3126/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d16606da1b22bbc51c25b3f39e5f0ba33809a5694e20904ec27ef2bb4c365e04
3
+ size 5304
checkpoint-3126/vocab.txt ADDED
The diff for this file is too large to render. See raw diff