Hugging Face's logo

Gyimah3
/
Finetuned_roberta

Text Classification
Transformers
PyTorch
TensorBoard
roberta
text-embeddings-inference
Model card Files
xet
 Metrics Community
1
Gyimah3 commited on
Commit
42025dd
·
1 Parent(s): 8cf2738

Upload 13 files

Browse files
Files changed (13) hide show
  1. config.json +39 -0
  2. optimizer.pt +3 -0
  3. pytorch_model.bin +3 -0
  4. rng_state.pth +3 -0
  5. run_3/events.out.tfevents.1673780232.ba20d0542bb3.219.0 +3 -0
  6. run_3/events.out.tfevents.1673782651.ba20d0542bb3.219.2 +3 -0
  7. scheduler.pt +3 -0
  8. special_tokens_map.json +15 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +66 -0
  11. trainer_state.json +163 -0
  12. training_args.bin +3 -0
  13. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cardiffnlp/twitter-roberta-base-sentiment",
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
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "LABEL_0",
16
+ "1": "LABEL_1",
17
+ "2": "LABEL_2"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "LABEL_0": 0,
23
+ "LABEL_1": 1,
24
+ "LABEL_2": 2
25
+ },
26
+ "layer_norm_eps": 1e-05,
27
+ "max_position_embeddings": 514,
28
+ "model_type": "roberta",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "pad_token_id": 1,
32
+ "position_embedding_type": "absolute",
33
+ "problem_type": "single_label_classification",
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.25.1",
36
+ "type_vocab_size": 1,
37
+ "use_cache": true,
38
+ "vocab_size": 50265
39
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2eddd87783e32566700884cdb66a0c17b65ed4cf0298a6fde8b27b0ffd04a38d
3
+ size 997301381
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b42cdee2c9fe8da6e53aa944da1118107f3c311dc6e2239dc9f8b131f1ffcff
3
+ size 498665141
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cdd59c6002917d8b1f1f3d630f684524a4868d39e1cc6b1190c951bab1201f6
3
+ size 14575
run_3/events.out.tfevents.1673780232.ba20d0542bb3.219.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ca9b15ff40f43dca99e8f90c1ba211299da0cf8371e7ebe24f6adc3c976cf47
3
+ size 13876
run_3/events.out.tfevents.1673782651.ba20d0542bb3.219.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db8cc088ac29b7362c6f3951f68ce5392972ad6dae56b26be50fab037c7dc28b
3
+ size 363
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50a0d184c4d0773194e5f6a8e083a2e7267118faafec7f8687d96c5ec60e21d1
3
+ size 627
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 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "cls_token": {
12
+ "__type": "AddedToken",
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "eos_token": {
20
+ "__type": "AddedToken",
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "errors": "replace",
28
+ "mask_token": {
29
+ "__type": "AddedToken",
30
+ "content": "<mask>",
31
+ "lstrip": true,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ },
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "name_or_path": "cardiffnlp/twitter-roberta-base-sentiment",
38
+ "num_labels": 3,
39
+ "pad_token": {
40
+ "__type": "AddedToken",
41
+ "content": "<pad>",
42
+ "lstrip": false,
43
+ "normalized": true,
44
+ "rstrip": false,
45
+ "single_word": false
46
+ },
47
+ "sep_token": {
48
+ "__type": "AddedToken",
49
+ "content": "</s>",
50
+ "lstrip": false,
51
+ "normalized": true,
52
+ "rstrip": false,
53
+ "single_word": false
54
+ },
55
+ "special_tokens_map_file": "/root/.cache/huggingface/hub/models--cardiffnlp--twitter-roberta-base-sentiment/snapshots/08b4d993d880171203539b37794af581debb55ca/special_tokens_map.json",
56
+ "tokenizer_class": "RobertaTokenizer",
57
+ "trim_offsets": true,
58
+ "unk_token": {
59
+ "__type": "AddedToken",
60
+ "content": "<unk>",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ }
66
+ }
trainer_state.json ADDED
@@ -0,0 +1,163 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5495731830596924,
3
+ "best_model_checkpoint": "Finetuned_distilbert/checkpoint-1000",
4
+ "epoch": 7.0,
5
+ "global_step": 7000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.5,
12
+ "learning_rate": 1.9333333333333333e-05,
13
+ "loss": 0.7074,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "learning_rate": 1.866666666666667e-05,
19
+ "loss": 0.5864,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 1.0,
24
+ "eval_accuracy": 0.7885,
25
+ "eval_loss": 0.5495731830596924,
26
+ "eval_runtime": 5.6815,
27
+ "eval_samples_per_second": 352.018,
28
+ "eval_steps_per_second": 44.002,
29
+ "step": 1000
30
+ },
31
+ {
32
+ "epoch": 1.5,
33
+ "learning_rate": 1.8e-05,
34
+ "loss": 0.4665,
35
+ "step": 1500
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "learning_rate": 1.7333333333333336e-05,
40
+ "loss": 0.4908,
41
+ "step": 2000
42
+ },
43
+ {
44
+ "epoch": 2.0,
45
+ "eval_accuracy": 0.791,
46
+ "eval_loss": 0.6509228944778442,
47
+ "eval_runtime": 5.7448,
48
+ "eval_samples_per_second": 348.143,
49
+ "eval_steps_per_second": 43.518,
50
+ "step": 2000
51
+ },
52
+ {
53
+ "epoch": 2.5,
54
+ "learning_rate": 1.6666666666666667e-05,
55
+ "loss": 0.3567,
56
+ "step": 2500
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "learning_rate": 1.6000000000000003e-05,
61
+ "loss": 0.3684,
62
+ "step": 3000
63
+ },
64
+ {
65
+ "epoch": 3.0,
66
+ "eval_accuracy": 0.787,
67
+ "eval_loss": 0.8537377119064331,
68
+ "eval_runtime": 5.7003,
69
+ "eval_samples_per_second": 350.862,
70
+ "eval_steps_per_second": 43.858,
71
+ "step": 3000
72
+ },
73
+ {
74
+ "epoch": 3.5,
75
+ "learning_rate": 1.5333333333333334e-05,
76
+ "loss": 0.2482,
77
+ "step": 3500
78
+ },
79
+ {
80
+ "epoch": 4.0,
81
+ "learning_rate": 1.4666666666666666e-05,
82
+ "loss": 0.2601,
83
+ "step": 4000
84
+ },
85
+ {
86
+ "epoch": 4.0,
87
+ "eval_accuracy": 0.787,
88
+ "eval_loss": 1.0617473125457764,
89
+ "eval_runtime": 5.6754,
90
+ "eval_samples_per_second": 352.397,
91
+ "eval_steps_per_second": 44.05,
92
+ "step": 4000
93
+ },
94
+ {
95
+ "epoch": 4.5,
96
+ "learning_rate": 1.4e-05,
97
+ "loss": 0.1828,
98
+ "step": 4500
99
+ },
100
+ {
101
+ "epoch": 5.0,
102
+ "learning_rate": 1.3333333333333333e-05,
103
+ "loss": 0.1671,
104
+ "step": 5000
105
+ },
106
+ {
107
+ "epoch": 5.0,
108
+ "eval_accuracy": 0.7825,
109
+ "eval_loss": 1.2580657005310059,
110
+ "eval_runtime": 5.6568,
111
+ "eval_samples_per_second": 353.556,
112
+ "eval_steps_per_second": 44.195,
113
+ "step": 5000
114
+ },
115
+ {
116
+ "epoch": 5.5,
117
+ "learning_rate": 1.2666666666666667e-05,
118
+ "loss": 0.1325,
119
+ "step": 5500
120
+ },
121
+ {
122
+ "epoch": 6.0,
123
+ "learning_rate": 1.2e-05,
124
+ "loss": 0.1454,
125
+ "step": 6000
126
+ },
127
+ {
128
+ "epoch": 6.0,
129
+ "eval_accuracy": 0.7765,
130
+ "eval_loss": 1.3939642906188965,
131
+ "eval_runtime": 5.745,
132
+ "eval_samples_per_second": 348.129,
133
+ "eval_steps_per_second": 43.516,
134
+ "step": 6000
135
+ },
136
+ {
137
+ "epoch": 6.5,
138
+ "learning_rate": 1.1333333333333334e-05,
139
+ "loss": 0.0857,
140
+ "step": 6500
141
+ },
142
+ {
143
+ "epoch": 7.0,
144
+ "learning_rate": 1.0666666666666667e-05,
145
+ "loss": 0.1154,
146
+ "step": 7000
147
+ },
148
+ {
149
+ "epoch": 7.0,
150
+ "eval_accuracy": 0.7845,
151
+ "eval_loss": 1.5688139200210571,
152
+ "eval_runtime": 5.715,
153
+ "eval_samples_per_second": 349.955,
154
+ "eval_steps_per_second": 43.744,
155
+ "step": 7000
156
+ }
157
+ ],
158
+ "max_steps": 15000,
159
+ "num_train_epochs": 15,
160
+ "total_flos": 1224266732688384.0,
161
+ "trial_name": null,
162
+ "trial_params": null
163
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:494184f3671a5f3b491e44fa07633c26fa26acce456394bfa6bb020f8aece9dc
3
+ size 3451
vocab.json ADDED
The diff for this file is too large to render. See raw diff