Hugging Face's logo

hallisky
/
sarcasm-classifier-gpt4-data

Text Classification
Transformers
TensorBoard
Safetensors
roberta
Inference Endpoints
Model card Files Metrics Community
hallisky commited on
Commit
dfc86c9
•
1 Parent(s): 05c9ed5

Upload 12 files

Browse files
Files changed (12) hide show
  1. config.json +36 -0
  2. merges.txt +0 -0
  3. model.safetensors +3 -0
  4. optimizer.pt +3 -0
  5. rng_state.pth +3 -0
  6. scheduler.pt +3 -0
  7. special_tokens_map.json +15 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +57 -0
  10. trainer_state.json +154 -0
  11. training_args.bin +3 -0
  12. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-large",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "sarcasm_less",
15
+ "1": "sarcasm_more"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 4096,
19
+ "label2id": {
20
+ "sarcasm_less": 0,
21
+ "sarcasm_more": 1
22
+ },
23
+ "layer_norm_eps": 1e-05,
24
+ "max_position_embeddings": 514,
25
+ "model_type": "roberta",
26
+ "num_attention_heads": 16,
27
+ "num_hidden_layers": 24,
28
+ "pad_token_id": 1,
29
+ "position_embedding_type": "absolute",
30
+ "problem_type": "single_label_classification",
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.38.0",
33
+ "type_vocab_size": 1,
34
+ "use_cache": true,
35
+ "vocab_size": 50265
36
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:002ecebef5b83da13749cedcbbcd94e290ce75041b28ad4c36d421b4c63103aa
3
+ size 1421495416
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:861d29d99c55fa512961df174c0c86ce062218f0d870caac8759e09a70f3337f
3
+ size 2843223277
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e664afdb13ecb28649b87ac826cae1e43dab2c1cdaa1372649e5292881fed538
3
+ size 14180
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5926e77df901c424daf6420009aa33b241773f64f3a8c96a907bff1ad7804f44
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 512,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
trainer_state.json ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.0,
3
+ "best_model_checkpoint": "train_binary/05-13-2024_11:56:46/checkpoint-20",
4
+ "epoch": 3.5,
5
+ "eval_steps": 10,
6
+ "global_step": 70,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.5,
13
+ "grad_norm": 9.57083797454834,
14
+ "learning_rate": 5e-05,
15
+ "loss": 0.543,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.5,
20
+ "eval_acc_product": 0.9359294458762887,
21
+ "eval_loss": 0.07417334616184235,
22
+ "eval_overall_acc": 0.9711111111111111,
23
+ "eval_runtime": 2.1515,
24
+ "eval_samples_per_second": 209.161,
25
+ "eval_sarcasm_less_acc": 0.9921875,
26
+ "eval_sarcasm_more_acc": 0.9432989690721649,
27
+ "eval_steps_per_second": 1.859,
28
+ "step": 10
29
+ },
30
+ {
31
+ "epoch": 1.0,
32
+ "grad_norm": 7.6136794090271,
33
+ "learning_rate": 4.4444444444444447e-05,
34
+ "loss": 0.0292,
35
+ "step": 20
36
+ },
37
+ {
38
+ "epoch": 1.0,
39
+ "eval_acc_product": 1.0,
40
+ "eval_loss": 0.0033113760873675346,
41
+ "eval_overall_acc": 1.0,
42
+ "eval_runtime": 2.1413,
43
+ "eval_samples_per_second": 210.153,
44
+ "eval_sarcasm_less_acc": 1.0,
45
+ "eval_sarcasm_more_acc": 1.0,
46
+ "eval_steps_per_second": 1.868,
47
+ "step": 20
48
+ },
49
+ {
50
+ "epoch": 1.5,
51
+ "grad_norm": 0.8403103351593018,
52
+ "learning_rate": 3.888888888888889e-05,
53
+ "loss": 0.0208,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 1.5,
58
+ "eval_acc_product": 0.9948453608247423,
59
+ "eval_loss": 0.01030806079506874,
60
+ "eval_overall_acc": 0.9977777777777778,
61
+ "eval_runtime": 2.1431,
62
+ "eval_samples_per_second": 209.98,
63
+ "eval_sarcasm_less_acc": 1.0,
64
+ "eval_sarcasm_more_acc": 0.9948453608247423,
65
+ "eval_steps_per_second": 1.866,
66
+ "step": 30
67
+ },
68
+ {
69
+ "epoch": 2.0,
70
+ "grad_norm": 0.03753209486603737,
71
+ "learning_rate": 3.3333333333333335e-05,
72
+ "loss": 0.0177,
73
+ "step": 40
74
+ },
75
+ {
76
+ "epoch": 2.0,
77
+ "eval_acc_product": 0.9896907216494846,
78
+ "eval_loss": 0.01667691580951214,
79
+ "eval_overall_acc": 0.9955555555555555,
80
+ "eval_runtime": 2.1482,
81
+ "eval_samples_per_second": 209.475,
82
+ "eval_sarcasm_less_acc": 1.0,
83
+ "eval_sarcasm_more_acc": 0.9896907216494846,
84
+ "eval_steps_per_second": 1.862,
85
+ "step": 40
86
+ },
87
+ {
88
+ "epoch": 2.5,
89
+ "grad_norm": 0.07835885137319565,
90
+ "learning_rate": 2.777777777777778e-05,
91
+ "loss": 0.0142,
92
+ "step": 50
93
+ },
94
+ {
95
+ "epoch": 2.5,
96
+ "eval_acc_product": 1.0,
97
+ "eval_loss": 0.0007662121206521988,
98
+ "eval_overall_acc": 1.0,
99
+ "eval_runtime": 2.1491,
100
+ "eval_samples_per_second": 209.392,
101
+ "eval_sarcasm_less_acc": 1.0,
102
+ "eval_sarcasm_more_acc": 1.0,
103
+ "eval_steps_per_second": 1.861,
104
+ "step": 50
105
+ },
106
+ {
107
+ "epoch": 3.0,
108
+ "grad_norm": 0.010010856203734875,
109
+ "learning_rate": 2.2222222222222223e-05,
110
+ "loss": 0.0063,
111
+ "step": 60
112
+ },
113
+ {
114
+ "epoch": 3.0,
115
+ "eval_acc_product": 1.0,
116
+ "eval_loss": 0.001220210688188672,
117
+ "eval_overall_acc": 1.0,
118
+ "eval_runtime": 2.1485,
119
+ "eval_samples_per_second": 209.449,
120
+ "eval_sarcasm_less_acc": 1.0,
121
+ "eval_sarcasm_more_acc": 1.0,
122
+ "eval_steps_per_second": 1.862,
123
+ "step": 60
124
+ },
125
+ {
126
+ "epoch": 3.5,
127
+ "grad_norm": 0.007230594754219055,
128
+ "learning_rate": 1.6666666666666667e-05,
129
+ "loss": 0.0032,
130
+ "step": 70
131
+ },
132
+ {
133
+ "epoch": 3.5,
134
+ "eval_acc_product": 1.0,
135
+ "eval_loss": 0.0004007717070635408,
136
+ "eval_overall_acc": 1.0,
137
+ "eval_runtime": 2.1484,
138
+ "eval_samples_per_second": 209.459,
139
+ "eval_sarcasm_less_acc": 1.0,
140
+ "eval_sarcasm_more_acc": 1.0,
141
+ "eval_steps_per_second": 1.862,
142
+ "step": 70
143
+ }
144
+ ],
145
+ "logging_steps": 10,
146
+ "max_steps": 100,
147
+ "num_input_tokens_seen": 0,
148
+ "num_train_epochs": 5,
149
+ "save_steps": 10,
150
+ "total_flos": 2080536768629760.0,
151
+ "train_batch_size": 128,
152
+ "trial_name": null,
153
+ "trial_params": null
154
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97251e30862c88547810d7fadd7bca6fb7e717af3a5e06ac953a7896b9013565
3
+ size 4920
vocab.json ADDED
The diff for this file is too large to render. See raw diff