Hugging Face's logo

Theoreticallyhugo
/
longformer-full_labels

Token Classification
Transformers
Safetensors
longformer
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
Theoreticallyhugo commited on
Commit
598e33d
•
1 Parent(s): a7d5aef

Training in progress, epoch 15, checkpoint

Browse files
Files changed (12) hide show
  1. checkpoint-615/config.json +61 -0
  2. checkpoint-615/merges.txt +0 -0
  3. checkpoint-615/model.safetensors +3 -0
  4. checkpoint-615/optimizer.pt +3 -0
  5. checkpoint-615/rng_state.pth +3 -0
  6. checkpoint-615/scheduler.pt +3 -0
  7. checkpoint-615/special_tokens_map.json +15 -0
  8. checkpoint-615/tokenizer.json +0 -0
  9. checkpoint-615/tokenizer_config.json +57 -0
  10. checkpoint-615/trainer_state.json +972 -0
  11. checkpoint-615/training_args.bin +3 -0
  12. checkpoint-615/vocab.json +0 -0
checkpoint-615/config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "allenai/longformer-base-4096",
3
+ "architectures": [
4
+ "LongformerForTokenClassification"
5
+ ],
6
+ "attention_mode": "longformer",
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "attention_window": [
9
+ 700,
10
+ 700,
11
+ 700,
12
+ 700,
13
+ 700,
14
+ 700,
15
+ 700,
16
+ 700,
17
+ 700,
18
+ 700,
19
+ 700,
20
+ 700
21
+ ],
22
+ "bos_token_id": 0,
23
+ "eos_token_id": 2,
24
+ "gradient_checkpointing": false,
25
+ "hidden_act": "gelu",
26
+ "hidden_dropout_prob": 0.1,
27
+ "hidden_size": 768,
28
+ "id2label": {
29
+ "0": "O",
30
+ "1": "B-MajorClaim",
31
+ "2": "I-MajorClaim",
32
+ "3": "B-Claim",
33
+ "4": "I-Claim",
34
+ "5": "B-Premise",
35
+ "6": "I-Premise"
36
+ },
37
+ "ignore_attention_mask": false,
38
+ "initializer_range": 0.02,
39
+ "intermediate_size": 3072,
40
+ "label2id": {
41
+ "B-Claim": 3,
42
+ "B-MajorClaim": 1,
43
+ "B-Premise": 5,
44
+ "I-Claim": 4,
45
+ "I-MajorClaim": 2,
46
+ "I-Premise": 6,
47
+ "O": 0
48
+ },
49
+ "layer_norm_eps": 1e-05,
50
+ "max_position_embeddings": 4098,
51
+ "model_type": "longformer",
52
+ "num_attention_heads": 12,
53
+ "num_hidden_layers": 12,
54
+ "onnx_export": false,
55
+ "pad_token_id": 1,
56
+ "sep_token_id": 2,
57
+ "torch_dtype": "float32",
58
+ "transformers_version": "4.37.2",
59
+ "type_vocab_size": 1,
60
+ "vocab_size": 50265
61
+ }
checkpoint-615/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-615/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:223637ee51e19946ac5c6d217941c49adaa3a2e1ae0f0bb7e0ec85accfc77b35
3
+ size 592330980
checkpoint-615/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba729b1c786e959b70e1aeb66f44ab4fa9c7c6beb9c545279dad3e175d683742
3
+ size 1014670074
checkpoint-615/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60d73cd4de91f0357130d4e4cf004c9af20e1519786ee889e727d7e40790e3e3
3
+ size 14244
checkpoint-615/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd51b0c91b998e8eb1af654a99ec608c0d09f203d69a278de7c58661b45b72ab
3
+ size 1064
checkpoint-615/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
+ }
checkpoint-615/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-615/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
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": 4096,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "LongformerTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
checkpoint-615/trainer_state.json ADDED
@@ -0,0 +1,972 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 15.0,
5
+ "eval_steps": 500,
6
+ "global_step": 615,
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_B-Claim": {
14
+ "f1-score": 0.0,
15
+ "precision": 0.0,
16
+ "recall": 0.0,
17
+ "support": 284.0
18
+ },
19
+ "eval_B-MajorClaim": {
20
+ "f1-score": 0.0,
21
+ "precision": 0.0,
22
+ "recall": 0.0,
23
+ "support": 141.0
24
+ },
25
+ "eval_B-Premise": {
26
+ "f1-score": 0.1548223350253807,
27
+ "precision": 0.7625,
28
+ "recall": 0.08615819209039548,
29
+ "support": 708.0
30
+ },
31
+ "eval_I-Claim": {
32
+ "f1-score": 0.320846509365118,
33
+ "precision": 0.31821471652593486,
34
+ "recall": 0.3235221976943831,
35
+ "support": 4077.0
36
+ },
37
+ "eval_I-MajorClaim": {
38
+ "f1-score": 0.30944741532976827,
39
+ "precision": 0.5556978233034571,
40
+ "recall": 0.21442687747035574,
41
+ "support": 2024.0
42
+ },
43
+ "eval_I-Premise": {
44
+ "f1-score": 0.8325705005167576,
45
+ "precision": 0.758950201884253,
46
+ "recall": 0.9220078482668411,
47
+ "support": 12232.0
48
+ },
49
+ "eval_O": {
50
+ "f1-score": 0.8424700041373604,
51
+ "precision": 0.8602661596958175,
52
+ "recall": 0.8253952168625861,
53
+ "support": 9868.0
54
+ },
55
+ "eval_accuracy": 0.7239721824503988,
56
+ "eval_loss": 0.7399080395698547,
57
+ "eval_macro avg": {
58
+ "f1-score": 0.35145096633919787,
59
+ "precision": 0.4650898430584946,
60
+ "recall": 0.33878719034065163,
61
+ "support": 29334.0
62
+ },
63
+ "eval_runtime": 1.4174,
64
+ "eval_samples_per_second": 56.441,
65
+ "eval_steps_per_second": 7.055,
66
+ "eval_weighted avg": {
67
+ "f1-score": 0.7002632905043792,
68
+ "precision": 0.70684288289933,
69
+ "recall": 0.7239721824503988,
70
+ "support": 29334.0
71
+ },
72
+ "step": 41
73
+ },
74
+ {
75
+ "epoch": 2.0,
76
+ "eval_B-Claim": {
77
+ "f1-score": 0.027491408934707903,
78
+ "precision": 0.5714285714285714,
79
+ "recall": 0.014084507042253521,
80
+ "support": 284.0
81
+ },
82
+ "eval_B-MajorClaim": {
83
+ "f1-score": 0.0,
84
+ "precision": 0.0,
85
+ "recall": 0.0,
86
+ "support": 141.0
87
+ },
88
+ "eval_B-Premise": {
89
+ "f1-score": 0.6804835924006908,
90
+ "precision": 0.5743440233236151,
91
+ "recall": 0.8347457627118644,
92
+ "support": 708.0
93
+ },
94
+ "eval_I-Claim": {
95
+ "f1-score": 0.42355671598491446,
96
+ "precision": 0.5182818601348953,
97
+ "recall": 0.35810645082168263,
98
+ "support": 4077.0
99
+ },
100
+ "eval_I-MajorClaim": {
101
+ "f1-score": 0.5595744680851064,
102
+ "precision": 0.6059907834101382,
103
+ "recall": 0.5197628458498024,
104
+ "support": 2024.0
105
+ },
106
+ "eval_I-Premise": {
107
+ "f1-score": 0.8694257788637754,
108
+ "precision": 0.8156160458452723,
109
+ "recall": 0.9308371484630478,
110
+ "support": 12232.0
111
+ },
112
+ "eval_O": {
113
+ "f1-score": 0.8708085279601078,
114
+ "precision": 0.8745017884517118,
115
+ "recall": 0.867146331576814,
116
+ "support": 9868.0
117
+ },
118
+ "eval_accuracy": 0.7857775959637281,
119
+ "eval_loss": 0.5717769861221313,
120
+ "eval_macro avg": {
121
+ "f1-score": 0.4901914988899004,
122
+ "precision": 0.5657375817991721,
123
+ "recall": 0.5035261494950664,
124
+ "support": 29334.0
125
+ },
126
+ "eval_runtime": 1.4179,
127
+ "eval_samples_per_second": 56.421,
128
+ "eval_steps_per_second": 7.053,
129
+ "eval_weighted avg": {
130
+ "f1-score": 0.7696517378810916,
131
+ "precision": 0.767528495718681,
132
+ "recall": 0.7857775959637281,
133
+ "support": 29334.0
134
+ },
135
+ "step": 82
136
+ },
137
+ {
138
+ "epoch": 3.0,
139
+ "eval_B-Claim": {
140
+ "f1-score": 0.45522388059701496,
141
+ "precision": 0.48412698412698413,
142
+ "recall": 0.4295774647887324,
143
+ "support": 284.0
144
+ },
145
+ "eval_B-MajorClaim": {
146
+ "f1-score": 0.14814814814814814,
147
+ "precision": 0.5714285714285714,
148
+ "recall": 0.0851063829787234,
149
+ "support": 141.0
150
+ },
151
+ "eval_B-Premise": {
152
+ "f1-score": 0.7349014621741894,
153
+ "precision": 0.6682080924855491,
154
+ "recall": 0.8163841807909604,
155
+ "support": 708.0
156
+ },
157
+ "eval_I-Claim": {
158
+ "f1-score": 0.5597381342062193,
159
+ "precision": 0.504127358490566,
160
+ "recall": 0.6291390728476821,
161
+ "support": 4077.0
162
+ },
163
+ "eval_I-MajorClaim": {
164
+ "f1-score": 0.7027804410354747,
165
+ "precision": 0.6824953445065177,
166
+ "recall": 0.724308300395257,
167
+ "support": 2024.0
168
+ },
169
+ "eval_I-Premise": {
170
+ "f1-score": 0.8580818643561399,
171
+ "precision": 0.8977404661963025,
172
+ "recall": 0.8217789404839765,
173
+ "support": 12232.0
174
+ },
175
+ "eval_O": {
176
+ "f1-score": 0.8938923131781367,
177
+ "precision": 0.8986991703369865,
178
+ "recall": 0.8891366031617349,
179
+ "support": 9868.0
180
+ },
181
+ "eval_accuracy": 0.8034703756732802,
182
+ "eval_loss": 0.5305466651916504,
183
+ "eval_macro avg": {
184
+ "f1-score": 0.6218237490993319,
185
+ "precision": 0.6724037125102111,
186
+ "recall": 0.6279187064924381,
187
+ "support": 29334.0
188
+ },
189
+ "eval_runtime": 1.4138,
190
+ "eval_samples_per_second": 56.587,
191
+ "eval_steps_per_second": 7.073,
192
+ "eval_weighted avg": {
193
+ "f1-score": 0.8076617373443268,
194
+ "precision": 0.8173920172765067,
195
+ "recall": 0.8034703756732802,
196
+ "support": 29334.0
197
+ },
198
+ "step": 123
199
+ },
200
+ {
201
+ "epoch": 4.0,
202
+ "eval_B-Claim": {
203
+ "f1-score": 0.48312611012433393,
204
+ "precision": 0.4874551971326165,
205
+ "recall": 0.4788732394366197,
206
+ "support": 284.0
207
+ },
208
+ "eval_B-MajorClaim": {
209
+ "f1-score": 0.6104417670682731,
210
+ "precision": 0.7037037037037037,
211
+ "recall": 0.5390070921985816,
212
+ "support": 141.0
213
+ },
214
+ "eval_B-Premise": {
215
+ "f1-score": 0.7560050568900126,
216
+ "precision": 0.6842105263157895,
217
+ "recall": 0.844632768361582,
218
+ "support": 708.0
219
+ },
220
+ "eval_I-Claim": {
221
+ "f1-score": 0.5483343808925204,
222
+ "precision": 0.5624033006704486,
223
+ "recall": 0.5349521707137601,
224
+ "support": 4077.0
225
+ },
226
+ "eval_I-MajorClaim": {
227
+ "f1-score": 0.7212475633528265,
228
+ "precision": 0.8264199106573069,
229
+ "recall": 0.6398221343873518,
230
+ "support": 2024.0
231
+ },
232
+ "eval_I-Premise": {
233
+ "f1-score": 0.8794421774097699,
234
+ "precision": 0.8531785686832193,
235
+ "recall": 0.9073741007194245,
236
+ "support": 12232.0
237
+ },
238
+ "eval_O": {
239
+ "f1-score": 0.8933134910453123,
240
+ "precision": 0.9048757667117164,
241
+ "recall": 0.8820429671665991,
242
+ "support": 9868.0
243
+ },
244
+ "eval_accuracy": 0.8211972455171473,
245
+ "eval_loss": 0.52641761302948,
246
+ "eval_macro avg": {
247
+ "f1-score": 0.6988443638261499,
248
+ "precision": 0.7174638534106857,
249
+ "recall": 0.6895292104262741,
250
+ "support": 29334.0
251
+ },
252
+ "eval_runtime": 1.4223,
253
+ "eval_samples_per_second": 56.246,
254
+ "eval_steps_per_second": 7.031,
255
+ "eval_weighted avg": {
256
+ "f1-score": 0.81906491673643,
257
+ "precision": 0.8199722855692243,
258
+ "recall": 0.8211972455171473,
259
+ "support": 29334.0
260
+ },
261
+ "step": 164
262
+ },
263
+ {
264
+ "epoch": 5.0,
265
+ "eval_B-Claim": {
266
+ "f1-score": 0.5169230769230769,
267
+ "precision": 0.45901639344262296,
268
+ "recall": 0.5915492957746479,
269
+ "support": 284.0
270
+ },
271
+ "eval_B-MajorClaim": {
272
+ "f1-score": 0.6466165413533834,
273
+ "precision": 0.688,
274
+ "recall": 0.6099290780141844,
275
+ "support": 141.0
276
+ },
277
+ "eval_B-Premise": {
278
+ "f1-score": 0.7462879276952873,
279
+ "precision": 0.6872770511296076,
280
+ "recall": 0.8163841807909604,
281
+ "support": 708.0
282
+ },
283
+ "eval_I-Claim": {
284
+ "f1-score": 0.5599537037037038,
285
+ "precision": 0.5301336839798378,
286
+ "recall": 0.5933284277655139,
287
+ "support": 4077.0
288
+ },
289
+ "eval_I-MajorClaim": {
290
+ "f1-score": 0.7108050847457628,
291
+ "precision": 0.7659817351598174,
292
+ "recall": 0.6630434782608695,
293
+ "support": 2024.0
294
+ },
295
+ "eval_I-Premise": {
296
+ "f1-score": 0.8764307593100111,
297
+ "precision": 0.864308426073132,
298
+ "recall": 0.8888979725310661,
299
+ "support": 12232.0
300
+ },
301
+ "eval_O": {
302
+ "f1-score": 0.8840052700922265,
303
+ "precision": 0.9209399363127265,
304
+ "recall": 0.8499189298743413,
305
+ "support": 9868.0
306
+ },
307
+ "eval_accuracy": 0.8131519738187768,
308
+ "eval_loss": 0.5400775074958801,
309
+ "eval_macro avg": {
310
+ "f1-score": 0.7058603376890645,
311
+ "precision": 0.702236746585392,
312
+ "recall": 0.7161501947159407,
313
+ "support": 29334.0
314
+ },
315
+ "eval_runtime": 1.4191,
316
+ "eval_samples_per_second": 56.374,
317
+ "eval_steps_per_second": 7.047,
318
+ "eval_weighted avg": {
319
+ "f1-score": 0.8158388468555539,
320
+ "precision": 0.8210853899484308,
321
+ "recall": 0.8131519738187768,
322
+ "support": 29334.0
323
+ },
324
+ "step": 205
325
+ },
326
+ {
327
+ "epoch": 6.0,
328
+ "eval_B-Claim": {
329
+ "f1-score": 0.5396290050590219,
330
+ "precision": 0.517799352750809,
331
+ "recall": 0.5633802816901409,
332
+ "support": 284.0
333
+ },
334
+ "eval_B-MajorClaim": {
335
+ "f1-score": 0.6879432624113475,
336
+ "precision": 0.6879432624113475,
337
+ "recall": 0.6879432624113475,
338
+ "support": 141.0
339
+ },
340
+ "eval_B-Premise": {
341
+ "f1-score": 0.7728459530026109,
342
+ "precision": 0.7184466019417476,
343
+ "recall": 0.8361581920903954,
344
+ "support": 708.0
345
+ },
346
+ "eval_I-Claim": {
347
+ "f1-score": 0.5682792406613595,
348
+ "precision": 0.5675146771037182,
349
+ "recall": 0.5690458670591121,
350
+ "support": 4077.0
351
+ },
352
+ "eval_I-MajorClaim": {
353
+ "f1-score": 0.744126659856997,
354
+ "precision": 0.7700845665961945,
355
+ "recall": 0.7198616600790514,
356
+ "support": 2024.0
357
+ },
358
+ "eval_I-Premise": {
359
+ "f1-score": 0.8782814316059476,
360
+ "precision": 0.8614670964698482,
361
+ "recall": 0.8957652060170046,
362
+ "support": 12232.0
363
+ },
364
+ "eval_O": {
365
+ "f1-score": 0.891362005304488,
366
+ "precision": 0.915500480717872,
367
+ "recall": 0.8684637211187677,
368
+ "support": 9868.0
369
+ },
370
+ "eval_accuracy": 0.8233790141133156,
371
+ "eval_loss": 0.5608550906181335,
372
+ "eval_macro avg": {
373
+ "f1-score": 0.7260667939859674,
374
+ "precision": 0.7198222911416482,
375
+ "recall": 0.7343740272094027,
376
+ "support": 29334.0
377
+ },
378
+ "eval_runtime": 1.42,
379
+ "eval_samples_per_second": 56.337,
380
+ "eval_steps_per_second": 7.042,
381
+ "eval_weighted avg": {
382
+ "f1-score": 0.8236011159623022,
383
+ "precision": 0.8248703886084983,
384
+ "recall": 0.8233790141133156,
385
+ "support": 29334.0
386
+ },
387
+ "step": 246
388
+ },
389
+ {
390
+ "epoch": 7.0,
391
+ "eval_B-Claim": {
392
+ "f1-score": 0.5528455284552846,
393
+ "precision": 0.513595166163142,
394
+ "recall": 0.5985915492957746,
395
+ "support": 284.0
396
+ },
397
+ "eval_B-MajorClaim": {
398
+ "f1-score": 0.6936026936026936,
399
+ "precision": 0.6602564102564102,
400
+ "recall": 0.7304964539007093,
401
+ "support": 141.0
402
+ },
403
+ "eval_B-Premise": {
404
+ "f1-score": 0.7722908093278464,
405
+ "precision": 0.7506666666666667,
406
+ "recall": 0.7951977401129944,
407
+ "support": 708.0
408
+ },
409
+ "eval_I-Claim": {
410
+ "f1-score": 0.5735997058463046,
411
+ "precision": 0.5732484076433121,
412
+ "recall": 0.5739514348785872,
413
+ "support": 4077.0
414
+ },
415
+ "eval_I-MajorClaim": {
416
+ "f1-score": 0.7633703329969728,
417
+ "precision": 0.7798969072164949,
418
+ "recall": 0.7475296442687747,
419
+ "support": 2024.0
420
+ },
421
+ "eval_I-Premise": {
422
+ "f1-score": 0.883062701951,
423
+ "precision": 0.8836048129655398,
424
+ "recall": 0.8825212557226946,
425
+ "support": 12232.0
426
+ },
427
+ "eval_O": {
428
+ "f1-score": 0.9022609753624656,
429
+ "precision": 0.9027186041793467,
430
+ "recall": 0.901803810295906,
431
+ "support": 9868.0
432
+ },
433
+ "eval_accuracy": 0.8312197450057953,
434
+ "eval_loss": 0.5639435648918152,
435
+ "eval_macro avg": {
436
+ "f1-score": 0.7344332496489382,
437
+ "precision": 0.7234267107272733,
438
+ "recall": 0.74715598406792,
439
+ "support": 29334.0
440
+ },
441
+ "eval_runtime": 1.4196,
442
+ "eval_samples_per_second": 56.355,
443
+ "eval_steps_per_second": 7.044,
444
+ "eval_weighted avg": {
445
+ "f1-score": 0.8314703017913034,
446
+ "precision": 0.8318795778768913,
447
+ "recall": 0.8312197450057953,
448
+ "support": 29334.0
449
+ },
450
+ "step": 287
451
+ },
452
+ {
453
+ "epoch": 8.0,
454
+ "eval_B-Claim": {
455
+ "f1-score": 0.556836902800659,
456
+ "precision": 0.5232198142414861,
457
+ "recall": 0.5950704225352113,
458
+ "support": 284.0
459
+ },
460
+ "eval_B-MajorClaim": {
461
+ "f1-score": 0.7013888888888888,
462
+ "precision": 0.6870748299319728,
463
+ "recall": 0.7163120567375887,
464
+ "support": 141.0
465
+ },
466
+ "eval_B-Premise": {
467
+ "f1-score": 0.7824296499656829,
468
+ "precision": 0.7610146862483311,
469
+ "recall": 0.8050847457627118,
470
+ "support": 708.0
471
+ },
472
+ "eval_I-Claim": {
473
+ "f1-score": 0.5778475661311753,
474
+ "precision": 0.5692527367920038,
475
+ "recall": 0.5867059112092224,
476
+ "support": 4077.0
477
+ },
478
+ "eval_I-MajorClaim": {
479
+ "f1-score": 0.7583943448624085,
480
+ "precision": 0.7754259163655137,
481
+ "recall": 0.7420948616600791,
482
+ "support": 2024.0
483
+ },
484
+ "eval_I-Premise": {
485
+ "f1-score": 0.8827766863130322,
486
+ "precision": 0.8839344262295082,
487
+ "recall": 0.881621975147155,
488
+ "support": 12232.0
489
+ },
490
+ "eval_O": {
491
+ "f1-score": 0.9058236611688048,
492
+ "precision": 0.9100859247135843,
493
+ "recall": 0.9016011349817592,
494
+ "support": 9868.0
495
+ },
496
+ "eval_accuracy": 0.8323106293038794,
497
+ "eval_loss": 0.5765838623046875,
498
+ "eval_macro avg": {
499
+ "f1-score": 0.7379282428758074,
500
+ "precision": 0.7300011906460572,
501
+ "recall": 0.7469273011476754,
502
+ "support": 29334.0
503
+ },
504
+ "eval_runtime": 1.4173,
505
+ "eval_samples_per_second": 56.444,
506
+ "eval_steps_per_second": 7.056,
507
+ "eval_weighted avg": {
508
+ "f1-score": 0.8331173621878202,
509
+ "precision": 0.834103417381421,
510
+ "recall": 0.8323106293038794,
511
+ "support": 29334.0
512
+ },
513
+ "step": 328
514
+ },
515
+ {
516
+ "epoch": 9.0,
517
+ "eval_B-Claim": {
518
+ "f1-score": 0.5608108108108107,
519
+ "precision": 0.538961038961039,
520
+ "recall": 0.5845070422535211,
521
+ "support": 284.0
522
+ },
523
+ "eval_B-MajorClaim": {
524
+ "f1-score": 0.7062706270627063,
525
+ "precision": 0.6604938271604939,
526
+ "recall": 0.7588652482269503,
527
+ "support": 141.0
528
+ },
529
+ "eval_B-Premise": {
530
+ "f1-score": 0.7868852459016393,
531
+ "precision": 0.7619047619047619,
532
+ "recall": 0.8135593220338984,
533
+ "support": 708.0
534
+ },
535
+ "eval_I-Claim": {
536
+ "f1-score": 0.5757501829714565,
537
+ "precision": 0.5726765348216453,
538
+ "recall": 0.5788570026980623,
539
+ "support": 4077.0
540
+ },
541
+ "eval_I-MajorClaim": {
542
+ "f1-score": 0.7613469985358712,
543
+ "precision": 0.7521697203471552,
544
+ "recall": 0.7707509881422925,
545
+ "support": 2024.0
546
+ },
547
+ "eval_I-Premise": {
548
+ "f1-score": 0.881003613332792,
549
+ "precision": 0.8750705702072747,
550
+ "recall": 0.8870176586003924,
551
+ "support": 12232.0
552
+ },
553
+ "eval_O": {
554
+ "f1-score": 0.8976369827675162,
555
+ "precision": 0.914336766869876,
556
+ "recall": 0.8815362788812323,
557
+ "support": 9868.0
558
+ },
559
+ "eval_accuracy": 0.829003886275312,
560
+ "eval_loss": 0.6423923373222351,
561
+ "eval_macro avg": {
562
+ "f1-score": 0.7385292087689704,
563
+ "precision": 0.725087602896035,
564
+ "recall": 0.75358479154805,
565
+ "support": 29334.0
566
+ },
567
+ "eval_runtime": 1.4177,
568
+ "eval_samples_per_second": 56.429,
569
+ "eval_steps_per_second": 7.054,
570
+ "eval_weighted avg": {
571
+ "f1-score": 0.8297056980988704,
572
+ "precision": 0.8307545957871735,
573
+ "recall": 0.829003886275312,
574
+ "support": 29334.0
575
+ },
576
+ "step": 369
577
+ },
578
+ {
579
+ "epoch": 10.0,
580
+ "eval_B-Claim": {
581
+ "f1-score": 0.5340699815837938,
582
+ "precision": 0.5598455598455598,
583
+ "recall": 0.5105633802816901,
584
+ "support": 284.0
585
+ },
586
+ "eval_B-MajorClaim": {
587
+ "f1-score": 0.6917808219178082,
588
+ "precision": 0.6688741721854304,
589
+ "recall": 0.7163120567375887,
590
+ "support": 141.0
591
+ },
592
+ "eval_B-Premise": {
593
+ "f1-score": 0.7902695595003287,
594
+ "precision": 0.7392373923739237,
595
+ "recall": 0.8488700564971752,
596
+ "support": 708.0
597
+ },
598
+ "eval_I-Claim": {
599
+ "f1-score": 0.5523707473881597,
600
+ "precision": 0.6084390675715551,
601
+ "recall": 0.5057640421878833,
602
+ "support": 4077.0
603
+ },
604
+ "eval_I-MajorClaim": {
605
+ "f1-score": 0.7558022199798183,
606
+ "precision": 0.7721649484536083,
607
+ "recall": 0.7401185770750988,
608
+ "support": 2024.0
609
+ },
610
+ "eval_I-Premise": {
611
+ "f1-score": 0.8884279732321058,
612
+ "precision": 0.8521132047143608,
613
+ "recall": 0.92797580117724,
614
+ "support": 12232.0
615
+ },
616
+ "eval_O": {
617
+ "f1-score": 0.8982358114749858,
618
+ "precision": 0.9175562836909418,
619
+ "recall": 0.8797122010539117,
620
+ "support": 9868.0
621
+ },
622
+ "eval_accuracy": 0.8331287925274425,
623
+ "eval_loss": 0.6874521374702454,
624
+ "eval_macro avg": {
625
+ "f1-score": 0.7301367307252857,
626
+ "precision": 0.7311758041193401,
627
+ "recall": 0.7327594450015126,
628
+ "support": 29334.0
629
+ },
630
+ "eval_runtime": 1.4184,
631
+ "eval_samples_per_second": 56.401,
632
+ "eval_steps_per_second": 7.05,
633
+ "eval_weighted avg": {
634
+ "f1-score": 0.8291241905412626,
635
+ "precision": 0.8283101361138144,
636
+ "recall": 0.8331287925274425,
637
+ "support": 29334.0
638
+ },
639
+ "step": 410
640
+ },
641
+ {
642
+ "epoch": 11.0,
643
+ "eval_B-Claim": {
644
+ "f1-score": 0.539568345323741,
645
+ "precision": 0.5514705882352942,
646
+ "recall": 0.528169014084507,
647
+ "support": 284.0
648
+ },
649
+ "eval_B-MajorClaim": {
650
+ "f1-score": 0.7,
651
+ "precision": 0.7050359712230215,
652
+ "recall": 0.6950354609929078,
653
+ "support": 141.0
654
+ },
655
+ "eval_B-Premise": {
656
+ "f1-score": 0.7853820598006644,
657
+ "precision": 0.7415307402760352,
658
+ "recall": 0.8347457627118644,
659
+ "support": 708.0
660
+ },
661
+ "eval_I-Claim": {
662
+ "f1-score": 0.5730817610062893,
663
+ "precision": 0.5881745416989413,
664
+ "recall": 0.5587441746382144,
665
+ "support": 4077.0
666
+ },
667
+ "eval_I-MajorClaim": {
668
+ "f1-score": 0.7655137334689724,
669
+ "precision": 0.7887840670859538,
670
+ "recall": 0.7435770750988142,
671
+ "support": 2024.0
672
+ },
673
+ "eval_I-Premise": {
674
+ "f1-score": 0.8855510725841887,
675
+ "precision": 0.8658698539176627,
676
+ "recall": 0.9061478090255068,
677
+ "support": 12232.0
678
+ },
679
+ "eval_O": {
680
+ "f1-score": 0.9009890789202555,
681
+ "precision": 0.9162824811399832,
682
+ "recall": 0.8861978111066072,
683
+ "support": 9868.0
684
+ },
685
+ "eval_accuracy": 0.8335378741392241,
686
+ "eval_loss": 0.722274899482727,
687
+ "eval_macro avg": {
688
+ "f1-score": 0.7357265787291587,
689
+ "precision": 0.7367354633681273,
690
+ "recall": 0.7360881582369173,
691
+ "support": 29334.0
692
+ },
693
+ "eval_runtime": 1.4133,
694
+ "eval_samples_per_second": 56.605,
695
+ "eval_steps_per_second": 7.076,
696
+ "eval_weighted avg": {
697
+ "f1-score": 0.8323741390608008,
698
+ "precision": 0.8320963257113063,
699
+ "recall": 0.8335378741392241,
700
+ "support": 29334.0
701
+ },
702
+ "step": 451
703
+ },
704
+ {
705
+ "epoch": 12.0,
706
+ "eval_B-Claim": {
707
+ "f1-score": 0.5542168674698795,
708
+ "precision": 0.4842105263157895,
709
+ "recall": 0.647887323943662,
710
+ "support": 284.0
711
+ },
712
+ "eval_B-MajorClaim": {
713
+ "f1-score": 0.6983050847457627,
714
+ "precision": 0.6688311688311688,
715
+ "recall": 0.7304964539007093,
716
+ "support": 141.0
717
+ },
718
+ "eval_B-Premise": {
719
+ "f1-score": 0.7742837176799442,
720
+ "precision": 0.7662517289073306,
721
+ "recall": 0.7824858757062146,
722
+ "support": 708.0
723
+ },
724
+ "eval_I-Claim": {
725
+ "f1-score": 0.5857796629088069,
726
+ "precision": 0.5374846374436706,
727
+ "recall": 0.6436104979151337,
728
+ "support": 4077.0
729
+ },
730
+ "eval_I-MajorClaim": {
731
+ "f1-score": 0.7506209637357178,
732
+ "precision": 0.7547452547452548,
733
+ "recall": 0.7465415019762845,
734
+ "support": 2024.0
735
+ },
736
+ "eval_I-Premise": {
737
+ "f1-score": 0.8754445455297329,
738
+ "precision": 0.8857740585774059,
739
+ "recall": 0.8653531720078482,
740
+ "support": 12232.0
741
+ },
742
+ "eval_O": {
743
+ "f1-score": 0.8975982418502434,
744
+ "precision": 0.9279454722492697,
745
+ "recall": 0.8691730847182814,
746
+ "support": 9868.0
747
+ },
748
+ "eval_accuracy": 0.8228676620985886,
749
+ "eval_loss": 0.7228854298591614,
750
+ "eval_macro avg": {
751
+ "f1-score": 0.7337498691314411,
752
+ "precision": 0.7178918352956986,
753
+ "recall": 0.755078272881162,
754
+ "support": 29334.0
755
+ },
756
+ "eval_runtime": 1.4154,
757
+ "eval_samples_per_second": 56.521,
758
+ "eval_steps_per_second": 7.065,
759
+ "eval_weighted avg": {
760
+ "f1-score": 0.8276221833778615,
761
+ "precision": 0.8346973026345582,
762
+ "recall": 0.8228676620985886,
763
+ "support": 29334.0
764
+ },
765
+ "step": 492
766
+ },
767
+ {
768
+ "epoch": 12.2,
769
+ "learning_rate": 4.75609756097561e-06,
770
+ "loss": 0.3184,
771
+ "step": 500
772
+ },
773
+ {
774
+ "epoch": 13.0,
775
+ "eval_B-Claim": {
776
+ "f1-score": 0.5582191780821917,
777
+ "precision": 0.5433333333333333,
778
+ "recall": 0.573943661971831,
779
+ "support": 284.0
780
+ },
781
+ "eval_B-MajorClaim": {
782
+ "f1-score": 0.7194244604316545,
783
+ "precision": 0.7299270072992701,
784
+ "recall": 0.7092198581560284,
785
+ "support": 141.0
786
+ },
787
+ "eval_B-Premise": {
788
+ "f1-score": 0.784366576819407,
789
+ "precision": 0.75,
790
+ "recall": 0.8220338983050848,
791
+ "support": 708.0
792
+ },
793
+ "eval_I-Claim": {
794
+ "f1-score": 0.577593563330489,
795
+ "precision": 0.5741638390693166,
796
+ "recall": 0.5810645082168261,
797
+ "support": 4077.0
798
+ },
799
+ "eval_I-MajorClaim": {
800
+ "f1-score": 0.7581699346405228,
801
+ "precision": 0.8051082731815657,
802
+ "recall": 0.7164031620553359,
803
+ "support": 2024.0
804
+ },
805
+ "eval_I-Premise": {
806
+ "f1-score": 0.8835273197542839,
807
+ "precision": 0.873641304347826,
808
+ "recall": 0.8936396337475474,
809
+ "support": 12232.0
810
+ },
811
+ "eval_O": {
812
+ "f1-score": 0.8996419437340154,
813
+ "precision": 0.9082834125180748,
814
+ "recall": 0.8911633563032023,
815
+ "support": 9868.0
816
+ },
817
+ "eval_accuracy": 0.8314242858116861,
818
+ "eval_loss": 0.7460470795631409,
819
+ "eval_macro avg": {
820
+ "f1-score": 0.7401347109703663,
821
+ "precision": 0.7406367385356267,
822
+ "recall": 0.7410668683936937,
823
+ "support": 29334.0
824
+ },
825
+ "eval_runtime": 1.4168,
826
+ "eval_samples_per_second": 56.464,
827
+ "eval_steps_per_second": 7.058,
828
+ "eval_weighted avg": {
829
+ "f1-score": 0.8314468675699472,
830
+ "precision": 0.8320703838894091,
831
+ "recall": 0.8314242858116861,
832
+ "support": 29334.0
833
+ },
834
+ "step": 533
835
+ },
836
+ {
837
+ "epoch": 14.0,
838
+ "eval_B-Claim": {
839
+ "f1-score": 0.5551839464882944,
840
+ "precision": 0.5286624203821656,
841
+ "recall": 0.5845070422535211,
842
+ "support": 284.0
843
+ },
844
+ "eval_B-MajorClaim": {
845
+ "f1-score": 0.7038327526132405,
846
+ "precision": 0.6917808219178082,
847
+ "recall": 0.7163120567375887,
848
+ "support": 141.0
849
+ },
850
+ "eval_B-Premise": {
851
+ "f1-score": 0.7854251012145749,
852
+ "precision": 0.751937984496124,
853
+ "recall": 0.8220338983050848,
854
+ "support": 708.0
855
+ },
856
+ "eval_I-Claim": {
857
+ "f1-score": 0.5741286205203731,
858
+ "precision": 0.5745517071972488,
859
+ "recall": 0.5737061564876135,
860
+ "support": 4077.0
861
+ },
862
+ "eval_I-MajorClaim": {
863
+ "f1-score": 0.7577986304844027,
864
+ "precision": 0.7785304846274101,
865
+ "recall": 0.7381422924901185,
866
+ "support": 2024.0
867
+ },
868
+ "eval_I-Premise": {
869
+ "f1-score": 0.8831628955632499,
870
+ "precision": 0.8700618752974774,
871
+ "recall": 0.8966644865925442,
872
+ "support": 12232.0
873
+ },
874
+ "eval_O": {
875
+ "f1-score": 0.8997522196985339,
876
+ "precision": 0.9169823232323232,
877
+ "recall": 0.8831576813944062,
878
+ "support": 9868.0
879
+ },
880
+ "eval_accuracy": 0.830606122588123,
881
+ "eval_loss": 0.7718554735183716,
882
+ "eval_macro avg": {
883
+ "f1-score": 0.7370405952260956,
884
+ "precision": 0.7303582310215082,
885
+ "recall": 0.7449319448944111,
886
+ "support": 29334.0
887
+ },
888
+ "eval_runtime": 1.4183,
889
+ "eval_samples_per_second": 56.405,
890
+ "eval_steps_per_second": 7.051,
891
+ "eval_weighted avg": {
892
+ "f1-score": 0.8307460246491396,
893
+ "precision": 0.8314455836819585,
894
+ "recall": 0.830606122588123,
895
+ "support": 29334.0
896
+ },
897
+ "step": 574
898
+ },
899
+ {
900
+ "epoch": 15.0,
901
+ "eval_B-Claim": {
902
+ "f1-score": 0.564935064935065,
903
+ "precision": 0.5240963855421686,
904
+ "recall": 0.6126760563380281,
905
+ "support": 284.0
906
+ },
907
+ "eval_B-MajorClaim": {
908
+ "f1-score": 0.7062937062937064,
909
+ "precision": 0.696551724137931,
910
+ "recall": 0.7163120567375887,
911
+ "support": 141.0
912
+ },
913
+ "eval_B-Premise": {
914
+ "f1-score": 0.7829036635006784,
915
+ "precision": 0.7532637075718016,
916
+ "recall": 0.8149717514124294,
917
+ "support": 708.0
918
+ },
919
+ "eval_I-Claim": {
920
+ "f1-score": 0.583969465648855,
921
+ "precision": 0.5683770605990248,
922
+ "recall": 0.6004415011037527,
923
+ "support": 4077.0
924
+ },
925
+ "eval_I-MajorClaim": {
926
+ "f1-score": 0.7649605296664119,
927
+ "precision": 0.789280084077772,
928
+ "recall": 0.7420948616600791,
929
+ "support": 2024.0
930
+ },
931
+ "eval_I-Premise": {
932
+ "f1-score": 0.8827731774638741,
933
+ "precision": 0.8766526926797807,
934
+ "recall": 0.8889797253106606,
935
+ "support": 12232.0
936
+ },
937
+ "eval_O": {
938
+ "f1-score": 0.8997673817523908,
939
+ "precision": 0.9183285849952516,
940
+ "recall": 0.8819416295095257,
941
+ "support": 9868.0
942
+ },
943
+ "eval_accuracy": 0.8310833844685348,
944
+ "eval_loss": 0.773708164691925,
945
+ "eval_macro avg": {
946
+ "f1-score": 0.7408004270372831,
947
+ "precision": 0.7323643199433901,
948
+ "recall": 0.7510596545817235,
949
+ "support": 29334.0
950
+ },
951
+ "eval_runtime": 1.4104,
952
+ "eval_samples_per_second": 56.722,
953
+ "eval_steps_per_second": 7.09,
954
+ "eval_weighted avg": {
955
+ "f1-score": 0.8324958893486518,
956
+ "precision": 0.8345410190013676,
957
+ "recall": 0.8310833844685348,
958
+ "support": 29334.0
959
+ },
960
+ "step": 615
961
+ }
962
+ ],
963
+ "logging_steps": 500,
964
+ "max_steps": 656,
965
+ "num_input_tokens_seen": 0,
966
+ "num_train_epochs": 16,
967
+ "save_steps": 500,
968
+ "total_flos": 2156862190770000.0,
969
+ "train_batch_size": 8,
970
+ "trial_name": null,
971
+ "trial_params": null
972
+ }
checkpoint-615/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82ac531ece3e5264f5a6be71a649db6a14a73aa49f10c8ea8f08c0485ea3ffcc
3
+ size 4664
checkpoint-615/vocab.json ADDED
The diff for this file is too large to render. See raw diff