Hugging Face's logo

HK0712
/
EA_MODEL

Keras
TensorBoard
Safetensors
Model card Files
xet
 Metrics Community
HK0712 commited on
Commit
c49a63a
·
1 Parent(s): db83f04

Upload model using LFS

Browse files
Files changed (39) hide show
  1. .gitattributes +1 -0
  2. bert_sentiment_model/checkpoint-10252/config.json +34 -0
  3. bert_sentiment_model/checkpoint-10252/model.safetensors +3 -0
  4. bert_sentiment_model/checkpoint-10252/optimizer.pt +3 -0
  5. bert_sentiment_model/checkpoint-10252/rng_state.pth +3 -0
  6. bert_sentiment_model/checkpoint-10252/scheduler.pt +3 -0
  7. bert_sentiment_model/checkpoint-10252/special_tokens_map.json +7 -0
  8. bert_sentiment_model/checkpoint-10252/tokenizer.json +0 -0
  9. bert_sentiment_model/checkpoint-10252/tokenizer_config.json +56 -0
  10. bert_sentiment_model/checkpoint-10252/trainer_state.json +192 -0
  11. bert_sentiment_model/checkpoint-10252/training_args.bin +3 -0
  12. bert_sentiment_model/checkpoint-10252/vocab.txt +0 -0
  13. bert_sentiment_model/checkpoint-15378/config.json +34 -0
  14. bert_sentiment_model/checkpoint-15378/model.safetensors +3 -0
  15. bert_sentiment_model/checkpoint-15378/optimizer.pt +3 -0
  16. bert_sentiment_model/checkpoint-15378/rng_state.pth +3 -0
  17. bert_sentiment_model/checkpoint-15378/scheduler.pt +3 -0
  18. bert_sentiment_model/checkpoint-15378/special_tokens_map.json +7 -0
  19. bert_sentiment_model/checkpoint-15378/tokenizer.json +0 -0
  20. bert_sentiment_model/checkpoint-15378/tokenizer_config.json +56 -0
  21. bert_sentiment_model/checkpoint-15378/trainer_state.json +271 -0
  22. bert_sentiment_model/checkpoint-15378/training_args.bin +3 -0
  23. bert_sentiment_model/checkpoint-15378/vocab.txt +0 -0
  24. bert_sentiment_model/checkpoint-5126/config.json +34 -0
  25. bert_sentiment_model/checkpoint-5126/model.safetensors +3 -0
  26. bert_sentiment_model/checkpoint-5126/optimizer.pt +3 -0
  27. bert_sentiment_model/checkpoint-5126/rng_state.pth +3 -0
  28. bert_sentiment_model/checkpoint-5126/scheduler.pt +3 -0
  29. bert_sentiment_model/checkpoint-5126/special_tokens_map.json +7 -0
  30. bert_sentiment_model/checkpoint-5126/tokenizer.json +0 -0
  31. bert_sentiment_model/checkpoint-5126/tokenizer_config.json +56 -0
  32. bert_sentiment_model/checkpoint-5126/trainer_state.json +113 -0
  33. bert_sentiment_model/checkpoint-5126/training_args.bin +3 -0
  34. bert_sentiment_model/checkpoint-5126/vocab.txt +0 -0
  35. bert_sentiment_model/runs/Nov22_15-25-42_0db92e0bbeed/events.out.tfevents.1763825143.0db92e0bbeed.48.0 +3 -0
  36. logistic_regression_model.pkl +3 -0
  37. lstm_model.keras +3 -0
  38. tfidf_vectorizer.pkl +3 -0
  39. tokenizer.pickle +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ *.keras filter=lfs diff=lfs merge=lfs -text
bert_sentiment_model/checkpoint-10252/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "neutral",
13
+ "2": "positive"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "negative": 0,
18
+ "neutral": 1,
19
+ "positive": 2
20
+ },
21
+ "max_position_embeddings": 512,
22
+ "model_type": "distilbert",
23
+ "n_heads": 12,
24
+ "n_layers": 6,
25
+ "pad_token_id": 0,
26
+ "problem_type": "single_label_classification",
27
+ "qa_dropout": 0.1,
28
+ "seq_classif_dropout": 0.2,
29
+ "sinusoidal_pos_embds": false,
30
+ "tie_weights_": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.53.3",
33
+ "vocab_size": 30522
34
+ }
bert_sentiment_model/checkpoint-10252/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:873e0bfc4370c12d3d114845be4849002d2871bc76ff75ef1a25526addb6008d
3
+ size 267835644
bert_sentiment_model/checkpoint-10252/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ce435dc5353a073f95c1258305b3f4eaf966a71d457368b94b343212f087bc9
3
+ size 535733434
bert_sentiment_model/checkpoint-10252/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:573615d54ee208f6d30568ba007e9517eb8027171c8891372c9bfebab5e6e0fd
3
+ size 14244
bert_sentiment_model/checkpoint-10252/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47b57e09f419cb0c457fce10ef2f66ea75a5f5335b3903fe41dc7d8031375c35
3
+ size 1064
bert_sentiment_model/checkpoint-10252/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
+ }
bert_sentiment_model/checkpoint-10252/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
bert_sentiment_model/checkpoint-10252/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
+ }
bert_sentiment_model/checkpoint-10252/trainer_state.json ADDED
@@ -0,0 +1,192 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 5126,
3
+ "best_metric": 0.14533720910549164,
4
+ "best_model_checkpoint": "bert_sentiment_model/checkpoint-5126",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 10252,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.09754194303550527,
14
+ "grad_norm": 1.0485230684280396,
15
+ "learning_rate": 1.9351020939003774e-05,
16
+ "loss": 0.2321,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.19508388607101054,
21
+ "grad_norm": 3.7028684616088867,
22
+ "learning_rate": 1.870074131876707e-05,
23
+ "loss": 0.1714,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.2926258291065158,
28
+ "grad_norm": 0.6240711212158203,
29
+ "learning_rate": 1.805046169853037e-05,
30
+ "loss": 0.1624,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 0.3901677721420211,
35
+ "grad_norm": 1.1150747537612915,
36
+ "learning_rate": 1.7400182078293668e-05,
37
+ "loss": 0.1627,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 0.4877097151775263,
42
+ "grad_norm": 0.31245458126068115,
43
+ "learning_rate": 1.6749902458056965e-05,
44
+ "loss": 0.1477,
45
+ "step": 2500
46
+ },
47
+ {
48
+ "epoch": 0.5852516582130316,
49
+ "grad_norm": 1.4625613689422607,
50
+ "learning_rate": 1.6099622837820262e-05,
51
+ "loss": 0.1574,
52
+ "step": 3000
53
+ },
54
+ {
55
+ "epoch": 0.6827936012485368,
56
+ "grad_norm": 0.7397491931915283,
57
+ "learning_rate": 1.5449343217583563e-05,
58
+ "loss": 0.146,
59
+ "step": 3500
60
+ },
61
+ {
62
+ "epoch": 0.7803355442840422,
63
+ "grad_norm": 3.28501033782959,
64
+ "learning_rate": 1.4799063597346861e-05,
65
+ "loss": 0.1471,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 0.8778774873195474,
70
+ "grad_norm": 5.020526885986328,
71
+ "learning_rate": 1.4148783977110158e-05,
72
+ "loss": 0.1509,
73
+ "step": 4500
74
+ },
75
+ {
76
+ "epoch": 0.9754194303550526,
77
+ "grad_norm": 3.897925615310669,
78
+ "learning_rate": 1.3498504356873457e-05,
79
+ "loss": 0.1454,
80
+ "step": 5000
81
+ },
82
+ {
83
+ "epoch": 1.0,
84
+ "eval_accuracy": 0.9512789875393206,
85
+ "eval_loss": 0.14533720910549164,
86
+ "eval_runtime": 74.7449,
87
+ "eval_samples_per_second": 548.653,
88
+ "eval_steps_per_second": 17.152,
89
+ "step": 5126
90
+ },
91
+ {
92
+ "epoch": 1.0729613733905579,
93
+ "grad_norm": 1.9805785417556763,
94
+ "learning_rate": 1.2848224736636754e-05,
95
+ "loss": 0.13,
96
+ "step": 5500
97
+ },
98
+ {
99
+ "epoch": 1.1705033164260632,
100
+ "grad_norm": 1.3755881786346436,
101
+ "learning_rate": 1.2197945116400054e-05,
102
+ "loss": 0.1276,
103
+ "step": 6000
104
+ },
105
+ {
106
+ "epoch": 1.2680452594615685,
107
+ "grad_norm": 3.5536131858825684,
108
+ "learning_rate": 1.1547665496163351e-05,
109
+ "loss": 0.1185,
110
+ "step": 6500
111
+ },
112
+ {
113
+ "epoch": 1.3655872024970737,
114
+ "grad_norm": 1.3367644548416138,
115
+ "learning_rate": 1.089738587592665e-05,
116
+ "loss": 0.1262,
117
+ "step": 7000
118
+ },
119
+ {
120
+ "epoch": 1.463129145532579,
121
+ "grad_norm": 3.0645148754119873,
122
+ "learning_rate": 1.0247106255689946e-05,
123
+ "loss": 0.1253,
124
+ "step": 7500
125
+ },
126
+ {
127
+ "epoch": 1.5606710885680841,
128
+ "grad_norm": 0.6243263483047485,
129
+ "learning_rate": 9.596826635453245e-06,
130
+ "loss": 0.1209,
131
+ "step": 8000
132
+ },
133
+ {
134
+ "epoch": 1.6582130316035895,
135
+ "grad_norm": 4.116105556488037,
136
+ "learning_rate": 8.946547015216544e-06,
137
+ "loss": 0.1242,
138
+ "step": 8500
139
+ },
140
+ {
141
+ "epoch": 1.7557549746390948,
142
+ "grad_norm": 4.457709789276123,
143
+ "learning_rate": 8.296267394979842e-06,
144
+ "loss": 0.1267,
145
+ "step": 9000
146
+ },
147
+ {
148
+ "epoch": 1.8532969176746001,
149
+ "grad_norm": 0.8020169734954834,
150
+ "learning_rate": 7.64598777474314e-06,
151
+ "loss": 0.1289,
152
+ "step": 9500
153
+ },
154
+ {
155
+ "epoch": 1.9508388607101055,
156
+ "grad_norm": 3.107414722442627,
157
+ "learning_rate": 6.995708154506439e-06,
158
+ "loss": 0.1166,
159
+ "step": 10000
160
+ },
161
+ {
162
+ "epoch": 2.0,
163
+ "eval_accuracy": 0.9529371601355799,
164
+ "eval_loss": 0.1457434594631195,
165
+ "eval_runtime": 74.98,
166
+ "eval_samples_per_second": 546.933,
167
+ "eval_steps_per_second": 17.098,
168
+ "step": 10252
169
+ }
170
+ ],
171
+ "logging_steps": 500,
172
+ "max_steps": 15378,
173
+ "num_input_tokens_seen": 0,
174
+ "num_train_epochs": 3,
175
+ "save_steps": 500,
176
+ "stateful_callbacks": {
177
+ "TrainerControl": {
178
+ "args": {
179
+ "should_epoch_stop": false,
180
+ "should_evaluate": false,
181
+ "should_log": false,
182
+ "should_save": true,
183
+ "should_training_stop": false
184
+ },
185
+ "attributes": {}
186
+ }
187
+ },
188
+ "total_flos": 1.0864639920144384e+16,
189
+ "train_batch_size": 32,
190
+ "trial_name": null,
191
+ "trial_params": null
192
+ }
bert_sentiment_model/checkpoint-10252/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:821493876e4c41dba842c49ce5fab3b065233a721a9d4cedcdac3b251c6aa960
3
+ size 5368
bert_sentiment_model/checkpoint-10252/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
bert_sentiment_model/checkpoint-15378/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "neutral",
13
+ "2": "positive"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "negative": 0,
18
+ "neutral": 1,
19
+ "positive": 2
20
+ },
21
+ "max_position_embeddings": 512,
22
+ "model_type": "distilbert",
23
+ "n_heads": 12,
24
+ "n_layers": 6,
25
+ "pad_token_id": 0,
26
+ "problem_type": "single_label_classification",
27
+ "qa_dropout": 0.1,
28
+ "seq_classif_dropout": 0.2,
29
+ "sinusoidal_pos_embds": false,
30
+ "tie_weights_": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.53.3",
33
+ "vocab_size": 30522
34
+ }
bert_sentiment_model/checkpoint-15378/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68b0a910bf6f5c17ac24cb683004cc4075d767dc2160f7b643cacd7ac667869d
3
+ size 267835644
bert_sentiment_model/checkpoint-15378/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a00717569fd9026ec62b066c6023adbd6790e5956d07de6ad2c7fb500848cb2
3
+ size 535733434
bert_sentiment_model/checkpoint-15378/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4862b0bf1b18079fd5c0fd4173184b6252f4b1c0d947e4a00fa81dfc5957441b
3
+ size 14244
bert_sentiment_model/checkpoint-15378/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:841c99b9d7f187355e3eec55000db7f69fa46446c720f65f52914164633e8d3c
3
+ size 1064
bert_sentiment_model/checkpoint-15378/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
+ }
bert_sentiment_model/checkpoint-15378/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
bert_sentiment_model/checkpoint-15378/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
+ }
bert_sentiment_model/checkpoint-15378/trainer_state.json ADDED
@@ -0,0 +1,271 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 5126,
3
+ "best_metric": 0.14533720910549164,
4
+ "best_model_checkpoint": "bert_sentiment_model/checkpoint-5126",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 15378,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.09754194303550527,
14
+ "grad_norm": 1.0485230684280396,
15
+ "learning_rate": 1.9351020939003774e-05,
16
+ "loss": 0.2321,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.19508388607101054,
21
+ "grad_norm": 3.7028684616088867,
22
+ "learning_rate": 1.870074131876707e-05,
23
+ "loss": 0.1714,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.2926258291065158,
28
+ "grad_norm": 0.6240711212158203,
29
+ "learning_rate": 1.805046169853037e-05,
30
+ "loss": 0.1624,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 0.3901677721420211,
35
+ "grad_norm": 1.1150747537612915,
36
+ "learning_rate": 1.7400182078293668e-05,
37
+ "loss": 0.1627,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 0.4877097151775263,
42
+ "grad_norm": 0.31245458126068115,
43
+ "learning_rate": 1.6749902458056965e-05,
44
+ "loss": 0.1477,
45
+ "step": 2500
46
+ },
47
+ {
48
+ "epoch": 0.5852516582130316,
49
+ "grad_norm": 1.4625613689422607,
50
+ "learning_rate": 1.6099622837820262e-05,
51
+ "loss": 0.1574,
52
+ "step": 3000
53
+ },
54
+ {
55
+ "epoch": 0.6827936012485368,
56
+ "grad_norm": 0.7397491931915283,
57
+ "learning_rate": 1.5449343217583563e-05,
58
+ "loss": 0.146,
59
+ "step": 3500
60
+ },
61
+ {
62
+ "epoch": 0.7803355442840422,
63
+ "grad_norm": 3.28501033782959,
64
+ "learning_rate": 1.4799063597346861e-05,
65
+ "loss": 0.1471,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 0.8778774873195474,
70
+ "grad_norm": 5.020526885986328,
71
+ "learning_rate": 1.4148783977110158e-05,
72
+ "loss": 0.1509,
73
+ "step": 4500
74
+ },
75
+ {
76
+ "epoch": 0.9754194303550526,
77
+ "grad_norm": 3.897925615310669,
78
+ "learning_rate": 1.3498504356873457e-05,
79
+ "loss": 0.1454,
80
+ "step": 5000
81
+ },
82
+ {
83
+ "epoch": 1.0,
84
+ "eval_accuracy": 0.9512789875393206,
85
+ "eval_loss": 0.14533720910549164,
86
+ "eval_runtime": 74.7449,
87
+ "eval_samples_per_second": 548.653,
88
+ "eval_steps_per_second": 17.152,
89
+ "step": 5126
90
+ },
91
+ {
92
+ "epoch": 1.0729613733905579,
93
+ "grad_norm": 1.9805785417556763,
94
+ "learning_rate": 1.2848224736636754e-05,
95
+ "loss": 0.13,
96
+ "step": 5500
97
+ },
98
+ {
99
+ "epoch": 1.1705033164260632,
100
+ "grad_norm": 1.3755881786346436,
101
+ "learning_rate": 1.2197945116400054e-05,
102
+ "loss": 0.1276,
103
+ "step": 6000
104
+ },
105
+ {
106
+ "epoch": 1.2680452594615685,
107
+ "grad_norm": 3.5536131858825684,
108
+ "learning_rate": 1.1547665496163351e-05,
109
+ "loss": 0.1185,
110
+ "step": 6500
111
+ },
112
+ {
113
+ "epoch": 1.3655872024970737,
114
+ "grad_norm": 1.3367644548416138,
115
+ "learning_rate": 1.089738587592665e-05,
116
+ "loss": 0.1262,
117
+ "step": 7000
118
+ },
119
+ {
120
+ "epoch": 1.463129145532579,
121
+ "grad_norm": 3.0645148754119873,
122
+ "learning_rate": 1.0247106255689946e-05,
123
+ "loss": 0.1253,
124
+ "step": 7500
125
+ },
126
+ {
127
+ "epoch": 1.5606710885680841,
128
+ "grad_norm": 0.6243263483047485,
129
+ "learning_rate": 9.596826635453245e-06,
130
+ "loss": 0.1209,
131
+ "step": 8000
132
+ },
133
+ {
134
+ "epoch": 1.6582130316035895,
135
+ "grad_norm": 4.116105556488037,
136
+ "learning_rate": 8.946547015216544e-06,
137
+ "loss": 0.1242,
138
+ "step": 8500
139
+ },
140
+ {
141
+ "epoch": 1.7557549746390948,
142
+ "grad_norm": 4.457709789276123,
143
+ "learning_rate": 8.296267394979842e-06,
144
+ "loss": 0.1267,
145
+ "step": 9000
146
+ },
147
+ {
148
+ "epoch": 1.8532969176746001,
149
+ "grad_norm": 0.8020169734954834,
150
+ "learning_rate": 7.64598777474314e-06,
151
+ "loss": 0.1289,
152
+ "step": 9500
153
+ },
154
+ {
155
+ "epoch": 1.9508388607101055,
156
+ "grad_norm": 3.107414722442627,
157
+ "learning_rate": 6.995708154506439e-06,
158
+ "loss": 0.1166,
159
+ "step": 10000
160
+ },
161
+ {
162
+ "epoch": 2.0,
163
+ "eval_accuracy": 0.9529371601355799,
164
+ "eval_loss": 0.1457434594631195,
165
+ "eval_runtime": 74.98,
166
+ "eval_samples_per_second": 546.933,
167
+ "eval_steps_per_second": 17.098,
168
+ "step": 10252
169
+ },
170
+ {
171
+ "epoch": 2.048380803745611,
172
+ "grad_norm": 1.5238676071166992,
173
+ "learning_rate": 6.345428534269737e-06,
174
+ "loss": 0.1146,
175
+ "step": 10500
176
+ },
177
+ {
178
+ "epoch": 2.1459227467811157,
179
+ "grad_norm": 0.5615836977958679,
180
+ "learning_rate": 5.695148914033035e-06,
181
+ "loss": 0.0978,
182
+ "step": 11000
183
+ },
184
+ {
185
+ "epoch": 2.243464689816621,
186
+ "grad_norm": 2.8565406799316406,
187
+ "learning_rate": 5.044869293796333e-06,
188
+ "loss": 0.1008,
189
+ "step": 11500
190
+ },
191
+ {
192
+ "epoch": 2.3410066328521264,
193
+ "grad_norm": 0.9610119462013245,
194
+ "learning_rate": 4.394589673559631e-06,
195
+ "loss": 0.1066,
196
+ "step": 12000
197
+ },
198
+ {
199
+ "epoch": 2.4385485758876317,
200
+ "grad_norm": 5.30699348449707,
201
+ "learning_rate": 3.7443100533229294e-06,
202
+ "loss": 0.1002,
203
+ "step": 12500
204
+ },
205
+ {
206
+ "epoch": 2.536090518923137,
207
+ "grad_norm": 3.4920408725738525,
208
+ "learning_rate": 3.0940304330862276e-06,
209
+ "loss": 0.0966,
210
+ "step": 13000
211
+ },
212
+ {
213
+ "epoch": 2.6336324619586424,
214
+ "grad_norm": 1.7962068319320679,
215
+ "learning_rate": 2.4437508128495254e-06,
216
+ "loss": 0.1044,
217
+ "step": 13500
218
+ },
219
+ {
220
+ "epoch": 2.7311744049941473,
221
+ "grad_norm": 1.224229097366333,
222
+ "learning_rate": 1.7934711926128236e-06,
223
+ "loss": 0.0972,
224
+ "step": 14000
225
+ },
226
+ {
227
+ "epoch": 2.8287163480296527,
228
+ "grad_norm": 1.4311927556991577,
229
+ "learning_rate": 1.1431915723761218e-06,
230
+ "loss": 0.1059,
231
+ "step": 14500
232
+ },
233
+ {
234
+ "epoch": 2.926258291065158,
235
+ "grad_norm": 0.935365617275238,
236
+ "learning_rate": 4.9291195213942e-07,
237
+ "loss": 0.1074,
238
+ "step": 15000
239
+ },
240
+ {
241
+ "epoch": 3.0,
242
+ "eval_accuracy": 0.9533273183935234,
243
+ "eval_loss": 0.15521423518657684,
244
+ "eval_runtime": 74.605,
245
+ "eval_samples_per_second": 549.682,
246
+ "eval_steps_per_second": 17.184,
247
+ "step": 15378
248
+ }
249
+ ],
250
+ "logging_steps": 500,
251
+ "max_steps": 15378,
252
+ "num_input_tokens_seen": 0,
253
+ "num_train_epochs": 3,
254
+ "save_steps": 500,
255
+ "stateful_callbacks": {
256
+ "TrainerControl": {
257
+ "args": {
258
+ "should_epoch_stop": false,
259
+ "should_evaluate": false,
260
+ "should_log": false,
261
+ "should_save": true,
262
+ "should_training_stop": true
263
+ },
264
+ "attributes": {}
265
+ }
266
+ },
267
+ "total_flos": 1.6296959880216576e+16,
268
+ "train_batch_size": 32,
269
+ "trial_name": null,
270
+ "trial_params": null
271
+ }
bert_sentiment_model/checkpoint-15378/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:821493876e4c41dba842c49ce5fab3b065233a721a9d4cedcdac3b251c6aa960
3
+ size 5368
bert_sentiment_model/checkpoint-15378/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
bert_sentiment_model/checkpoint-5126/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "neutral",
13
+ "2": "positive"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "negative": 0,
18
+ "neutral": 1,
19
+ "positive": 2
20
+ },
21
+ "max_position_embeddings": 512,
22
+ "model_type": "distilbert",
23
+ "n_heads": 12,
24
+ "n_layers": 6,
25
+ "pad_token_id": 0,
26
+ "problem_type": "single_label_classification",
27
+ "qa_dropout": 0.1,
28
+ "seq_classif_dropout": 0.2,
29
+ "sinusoidal_pos_embds": false,
30
+ "tie_weights_": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.53.3",
33
+ "vocab_size": 30522
34
+ }
bert_sentiment_model/checkpoint-5126/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dec3328f2136cd119e3e22196d97cfabe5f711be78842ec0fe551baad38456b0
3
+ size 267835644
bert_sentiment_model/checkpoint-5126/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e60f8ba4cc8d1bca385deeba83bf27f0b2d3b9c39e8de40068d97b0d194fc21b
3
+ size 535733434
bert_sentiment_model/checkpoint-5126/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:165190f7ffac334db3297fcb4a413ea429cd8803d5378fac54f9bd2e56e99972
3
+ size 14244
bert_sentiment_model/checkpoint-5126/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:014e9daed1ba7c27e9f119594e65400c03926866b2dfaae2399cb10c18de61ae
3
+ size 1064
bert_sentiment_model/checkpoint-5126/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
+ }
bert_sentiment_model/checkpoint-5126/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
bert_sentiment_model/checkpoint-5126/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
+ }
bert_sentiment_model/checkpoint-5126/trainer_state.json ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 5126,
3
+ "best_metric": 0.14533720910549164,
4
+ "best_model_checkpoint": "bert_sentiment_model/checkpoint-5126",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 5126,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.09754194303550527,
14
+ "grad_norm": 1.0485230684280396,
15
+ "learning_rate": 1.9351020939003774e-05,
16
+ "loss": 0.2321,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.19508388607101054,
21
+ "grad_norm": 3.7028684616088867,
22
+ "learning_rate": 1.870074131876707e-05,
23
+ "loss": 0.1714,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.2926258291065158,
28
+ "grad_norm": 0.6240711212158203,
29
+ "learning_rate": 1.805046169853037e-05,
30
+ "loss": 0.1624,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 0.3901677721420211,
35
+ "grad_norm": 1.1150747537612915,
36
+ "learning_rate": 1.7400182078293668e-05,
37
+ "loss": 0.1627,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 0.4877097151775263,
42
+ "grad_norm": 0.31245458126068115,
43
+ "learning_rate": 1.6749902458056965e-05,
44
+ "loss": 0.1477,
45
+ "step": 2500
46
+ },
47
+ {
48
+ "epoch": 0.5852516582130316,
49
+ "grad_norm": 1.4625613689422607,
50
+ "learning_rate": 1.6099622837820262e-05,
51
+ "loss": 0.1574,
52
+ "step": 3000
53
+ },
54
+ {
55
+ "epoch": 0.6827936012485368,
56
+ "grad_norm": 0.7397491931915283,
57
+ "learning_rate": 1.5449343217583563e-05,
58
+ "loss": 0.146,
59
+ "step": 3500
60
+ },
61
+ {
62
+ "epoch": 0.7803355442840422,
63
+ "grad_norm": 3.28501033782959,
64
+ "learning_rate": 1.4799063597346861e-05,
65
+ "loss": 0.1471,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 0.8778774873195474,
70
+ "grad_norm": 5.020526885986328,
71
+ "learning_rate": 1.4148783977110158e-05,
72
+ "loss": 0.1509,
73
+ "step": 4500
74
+ },
75
+ {
76
+ "epoch": 0.9754194303550526,
77
+ "grad_norm": 3.897925615310669,
78
+ "learning_rate": 1.3498504356873457e-05,
79
+ "loss": 0.1454,
80
+ "step": 5000
81
+ },
82
+ {
83
+ "epoch": 1.0,
84
+ "eval_accuracy": 0.9512789875393206,
85
+ "eval_loss": 0.14533720910549164,
86
+ "eval_runtime": 74.7449,
87
+ "eval_samples_per_second": 548.653,
88
+ "eval_steps_per_second": 17.152,
89
+ "step": 5126
90
+ }
91
+ ],
92
+ "logging_steps": 500,
93
+ "max_steps": 15378,
94
+ "num_input_tokens_seen": 0,
95
+ "num_train_epochs": 3,
96
+ "save_steps": 500,
97
+ "stateful_callbacks": {
98
+ "TrainerControl": {
99
+ "args": {
100
+ "should_epoch_stop": false,
101
+ "should_evaluate": false,
102
+ "should_log": false,
103
+ "should_save": true,
104
+ "should_training_stop": false
105
+ },
106
+ "attributes": {}
107
+ }
108
+ },
109
+ "total_flos": 5432319960072192.0,
110
+ "train_batch_size": 32,
111
+ "trial_name": null,
112
+ "trial_params": null
113
+ }
bert_sentiment_model/checkpoint-5126/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:821493876e4c41dba842c49ce5fab3b065233a721a9d4cedcdac3b251c6aa960
3
+ size 5368
bert_sentiment_model/checkpoint-5126/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
bert_sentiment_model/runs/Nov22_15-25-42_0db92e0bbeed/events.out.tfevents.1763825143.0db92e0bbeed.48.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:722143b2b87a2fa3bee692b56d80fb7ca82226bfd46543009ef47db25caece7c
3
+ size 12660
logistic_regression_model.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09bdc6a433fdd19d821451cae54d6475d360b4d41e168b0f25ddee0395d33676
3
+ size 480931
lstm_model.keras ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae7cc154c422d9a844884d821176f4702f054bd25bc940a75d0ed8f5861d1f6e
3
+ size 33928028
tfidf_vectorizer.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:098fb11fbad95b6e55cfe4233c13eff78fc2ac3ade0c6ec86d2d849553adcdff
3
+ size 1244923
tokenizer.pickle ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21e4fd61bb2bccd17a7fa7cf3d3d4bfd11152717e35c7bc22be7d005183dbada
3
+ size 467490