Hugging Face's logo

Theoreticallyhugo
/
longformer-spans

Token Classification
Transformers
Safetensors
longformer
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
Theoreticallyhugo commited on
Commit
e689d7a
•
1 Parent(s): e4a11ea

Training in progress, epoch 12, checkpoint

Browse files
Files changed (12) hide show
  1. checkpoint-492/config.json +53 -0
  2. checkpoint-492/merges.txt +0 -0
  3. checkpoint-492/model.safetensors +3 -0
  4. checkpoint-492/optimizer.pt +3 -0
  5. checkpoint-492/rng_state.pth +3 -0
  6. checkpoint-492/scheduler.pt +3 -0
  7. checkpoint-492/special_tokens_map.json +15 -0
  8. checkpoint-492/tokenizer.json +0 -0
  9. checkpoint-492/tokenizer_config.json +57 -0
  10. checkpoint-492/trainer_state.json +489 -0
  11. checkpoint-492/training_args.bin +3 -0
  12. checkpoint-492/vocab.json +0 -0
checkpoint-492/config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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",
31
+ "2": "I"
32
+ },
33
+ "ignore_attention_mask": false,
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 3072,
36
+ "label2id": {
37
+ "B": 1,
38
+ "I": 2,
39
+ "O": 0
40
+ },
41
+ "layer_norm_eps": 1e-05,
42
+ "max_position_embeddings": 4098,
43
+ "model_type": "longformer",
44
+ "num_attention_heads": 12,
45
+ "num_hidden_layers": 12,
46
+ "onnx_export": false,
47
+ "pad_token_id": 1,
48
+ "sep_token_id": 2,
49
+ "torch_dtype": "float32",
50
+ "transformers_version": "4.37.2",
51
+ "type_vocab_size": 1,
52
+ "vocab_size": 50265
53
+ }
checkpoint-492/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-492/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f654de3cb6d034f7cd2b5c93ed8a374660f2efaa5ac98bc8f2d3769665276a0
3
+ size 592318676
checkpoint-492/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a88e4378c93ca8b85a34fe8b3624410a08726bd6ae258d2eb3c2997f59f610ec
3
+ size 1014645498
checkpoint-492/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c189466643703424c77db24cb1c70bb1b76b65752ddeeaa3d7bb424b6ea3dcb
3
+ size 14244
checkpoint-492/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e40ce765a2db50b61afa20f73544a6db3531a7c20a21e8ebd94c0459daeb642
3
+ size 1064
checkpoint-492/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-492/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-492/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-492/trainer_state.json ADDED
@@ -0,0 +1,489 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 12.0,
5
+ "eval_steps": 500,
6
+ "global_step": 492,
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": {
14
+ "f1-score": 0.3128571428571429,
15
+ "precision": 0.8202247191011236,
16
+ "recall": 0.19329214474845544,
17
+ "support": 1133.0
18
+ },
19
+ "eval_I": {
20
+ "f1-score": 0.9039097402761301,
21
+ "precision": 0.8412101850981866,
22
+ "recall": 0.9767086674303169,
23
+ "support": 18333.0
24
+ },
25
+ "eval_O": {
26
+ "f1-score": 0.8155702872684006,
27
+ "precision": 0.9249453797712376,
28
+ "recall": 0.7293271179570329,
29
+ "support": 9868.0
30
+ },
31
+ "eval_accuracy": 0.8632303811277017,
32
+ "eval_loss": 0.36073023080825806,
33
+ "eval_macro avg": {
34
+ "f1-score": 0.6774457234672245,
35
+ "precision": 0.8621267613235158,
36
+ "recall": 0.6331093100452684,
37
+ "support": 29334.0
38
+ },
39
+ "eval_runtime": 1.3518,
40
+ "eval_samples_per_second": 59.181,
41
+ "eval_steps_per_second": 7.398,
42
+ "eval_weighted avg": {
43
+ "f1-score": 0.8513633328596172,
44
+ "precision": 0.8685682804162133,
45
+ "recall": 0.8632303811277017,
46
+ "support": 29334.0
47
+ },
48
+ "step": 41
49
+ },
50
+ {
51
+ "epoch": 2.0,
52
+ "eval_B": {
53
+ "f1-score": 0.8334742180896026,
54
+ "precision": 0.7996755879967559,
55
+ "recall": 0.8702559576345984,
56
+ "support": 1133.0
57
+ },
58
+ "eval_I": {
59
+ "f1-score": 0.937247128465528,
60
+ "precision": 0.9331675137882557,
61
+ "recall": 0.9413625702285496,
62
+ "support": 18333.0
63
+ },
64
+ "eval_O": {
65
+ "f1-score": 0.878356867779204,
66
+ "precision": 0.8902883314250026,
67
+ "recall": 0.8667409809485205,
68
+ "support": 9868.0
69
+ },
70
+ "eval_accuracy": 0.9135133292425173,
71
+ "eval_loss": 0.2531818747520447,
72
+ "eval_macro avg": {
73
+ "f1-score": 0.8830260714447782,
74
+ "precision": 0.874377144403338,
75
+ "recall": 0.892786502937223,
76
+ "support": 29334.0
77
+ },
78
+ "eval_runtime": 1.3577,
79
+ "eval_samples_per_second": 58.925,
80
+ "eval_steps_per_second": 7.366,
81
+ "eval_weighted avg": {
82
+ "f1-score": 0.9134282220801536,
83
+ "precision": 0.9135868864110707,
84
+ "recall": 0.9135133292425173,
85
+ "support": 29334.0
86
+ },
87
+ "step": 82
88
+ },
89
+ {
90
+ "epoch": 3.0,
91
+ "eval_B": {
92
+ "f1-score": 0.8486869528970404,
93
+ "precision": 0.8041074249605056,
94
+ "recall": 0.8984995586937334,
95
+ "support": 1133.0
96
+ },
97
+ "eval_I": {
98
+ "f1-score": 0.9447329870821681,
99
+ "precision": 0.9231209660628774,
100
+ "recall": 0.9673812251131839,
101
+ "support": 18333.0
102
+ },
103
+ "eval_O": {
104
+ "f1-score": 0.8850672933133945,
105
+ "precision": 0.9356368563685636,
106
+ "recall": 0.8396838265099311,
107
+ "support": 9868.0
108
+ },
109
+ "eval_accuracy": 0.9217631417467785,
110
+ "eval_loss": 0.22803974151611328,
111
+ "eval_macro avg": {
112
+ "f1-score": 0.8928290777642011,
113
+ "precision": 0.8876217491306488,
114
+ "recall": 0.9018548701056162,
115
+ "support": 29334.0
116
+ },
117
+ "eval_runtime": 1.356,
118
+ "eval_samples_per_second": 58.998,
119
+ "eval_steps_per_second": 7.375,
120
+ "eval_weighted avg": {
121
+ "f1-score": 0.9209516676970857,
122
+ "precision": 0.9227345360999514,
123
+ "recall": 0.9217631417467785,
124
+ "support": 29334.0
125
+ },
126
+ "step": 123
127
+ },
128
+ {
129
+ "epoch": 4.0,
130
+ "eval_B": {
131
+ "f1-score": 0.854157960718763,
132
+ "precision": 0.8111111111111111,
133
+ "recall": 0.9020300088261254,
134
+ "support": 1133.0
135
+ },
136
+ "eval_I": {
137
+ "f1-score": 0.9440852236591055,
138
+ "precision": 0.9180539091893006,
139
+ "recall": 0.9716358479245077,
140
+ "support": 18333.0
141
+ },
142
+ "eval_O": {
143
+ "f1-score": 0.8818167107179459,
144
+ "precision": 0.9426825049013955,
145
+ "recall": 0.8283340089177138,
146
+ "support": 9868.0
147
+ },
148
+ "eval_accuracy": 0.9207404377173246,
149
+ "eval_loss": 0.2642991840839386,
150
+ "eval_macro avg": {
151
+ "f1-score": 0.8933532983652714,
152
+ "precision": 0.8906158417339357,
153
+ "recall": 0.9006666218894489,
154
+ "support": 29334.0
155
+ },
156
+ "eval_runtime": 1.3563,
157
+ "eval_samples_per_second": 58.983,
158
+ "eval_steps_per_second": 7.373,
159
+ "eval_weighted avg": {
160
+ "f1-score": 0.9196646443104053,
161
+ "precision": 0.9222084326864153,
162
+ "recall": 0.9207404377173246,
163
+ "support": 29334.0
164
+ },
165
+ "step": 164
166
+ },
167
+ {
168
+ "epoch": 5.0,
169
+ "eval_B": {
170
+ "f1-score": 0.8555835432409741,
171
+ "precision": 0.8158526821457166,
172
+ "recall": 0.8993821712268314,
173
+ "support": 1133.0
174
+ },
175
+ "eval_I": {
176
+ "f1-score": 0.9461865426257119,
177
+ "precision": 0.9278074866310161,
178
+ "recall": 0.965308460153821,
179
+ "support": 18333.0
180
+ },
181
+ "eval_O": {
182
+ "f1-score": 0.8893479527517347,
183
+ "precision": 0.9316391077571856,
184
+ "recall": 0.8507296311309283,
185
+ "support": 9868.0
186
+ },
187
+ "eval_accuracy": 0.9242176314174678,
188
+ "eval_loss": 0.2475498616695404,
189
+ "eval_macro avg": {
190
+ "f1-score": 0.8970393462061402,
191
+ "precision": 0.8917664255113061,
192
+ "recall": 0.9051400875038601,
193
+ "support": 29334.0
194
+ },
195
+ "eval_runtime": 1.35,
196
+ "eval_samples_per_second": 59.258,
197
+ "eval_steps_per_second": 7.407,
198
+ "eval_weighted avg": {
199
+ "f1-score": 0.9235664975183513,
200
+ "precision": 0.924772293469197,
201
+ "recall": 0.9242176314174678,
202
+ "support": 29334.0
203
+ },
204
+ "step": 205
205
+ },
206
+ {
207
+ "epoch": 6.0,
208
+ "eval_B": {
209
+ "f1-score": 0.8523908523908524,
210
+ "precision": 0.8058176100628931,
211
+ "recall": 0.9046778464254193,
212
+ "support": 1133.0
213
+ },
214
+ "eval_I": {
215
+ "f1-score": 0.946049991866833,
216
+ "precision": 0.9404408990459764,
217
+ "recall": 0.951726395025364,
218
+ "support": 18333.0
219
+ },
220
+ "eval_O": {
221
+ "f1-score": 0.894565722248026,
222
+ "precision": 0.9114523083394679,
223
+ "recall": 0.8782934738548844,
224
+ "support": 9868.0
225
+ },
226
+ "eval_accuracy": 0.9252062453126065,
227
+ "eval_loss": 0.25544244050979614,
228
+ "eval_macro avg": {
229
+ "f1-score": 0.8976688555019038,
230
+ "precision": 0.8859036058161124,
231
+ "recall": 0.9115659051018893,
232
+ "support": 29334.0
233
+ },
234
+ "eval_runtime": 1.3498,
235
+ "eval_samples_per_second": 59.268,
236
+ "eval_steps_per_second": 7.408,
237
+ "eval_weighted avg": {
238
+ "f1-score": 0.9251131071042821,
239
+ "precision": 0.9254893888697421,
240
+ "recall": 0.9252062453126065,
241
+ "support": 29334.0
242
+ },
243
+ "step": 246
244
+ },
245
+ {
246
+ "epoch": 7.0,
247
+ "eval_B": {
248
+ "f1-score": 0.8621276595744681,
249
+ "precision": 0.8323746918652424,
250
+ "recall": 0.8940864960282436,
251
+ "support": 1133.0
252
+ },
253
+ "eval_I": {
254
+ "f1-score": 0.9492181202643882,
255
+ "precision": 0.9353455123113582,
256
+ "recall": 0.9635084274259532,
257
+ "support": 18333.0
258
+ },
259
+ "eval_O": {
260
+ "f1-score": 0.8978010471204189,
261
+ "precision": 0.9287261698440208,
262
+ "recall": 0.8688690717470612,
263
+ "support": 9868.0
264
+ },
265
+ "eval_accuracy": 0.9289902502215859,
266
+ "eval_loss": 0.2822054922580719,
267
+ "eval_macro avg": {
268
+ "f1-score": 0.9030489423197584,
269
+ "precision": 0.8988154580068738,
270
+ "recall": 0.9088213317337527,
271
+ "support": 29334.0
272
+ },
273
+ "eval_runtime": 1.3549,
274
+ "eval_samples_per_second": 59.046,
275
+ "eval_steps_per_second": 7.381,
276
+ "eval_weighted avg": {
277
+ "f1-score": 0.9285575499450874,
278
+ "precision": 0.9291415983878176,
279
+ "recall": 0.9289902502215859,
280
+ "support": 29334.0
281
+ },
282
+ "step": 287
283
+ },
284
+ {
285
+ "epoch": 8.0,
286
+ "eval_B": {
287
+ "f1-score": 0.8576228475430492,
288
+ "precision": 0.8181089743589743,
289
+ "recall": 0.9011473962930273,
290
+ "support": 1133.0
291
+ },
292
+ "eval_I": {
293
+ "f1-score": 0.9478573729996776,
294
+ "precision": 0.933372111469515,
295
+ "recall": 0.9627993236240658,
296
+ "support": 18333.0
297
+ },
298
+ "eval_O": {
299
+ "f1-score": 0.8941868403087749,
300
+ "precision": 0.9279564032697548,
301
+ "recall": 0.8627888123226591,
302
+ "support": 9868.0
303
+ },
304
+ "eval_accuracy": 0.9267743914911025,
305
+ "eval_loss": 0.30678361654281616,
306
+ "eval_macro avg": {
307
+ "f1-score": 0.899889020283834,
308
+ "precision": 0.8931458296994147,
309
+ "recall": 0.9089118440799174,
310
+ "support": 29334.0
311
+ },
312
+ "eval_runtime": 1.3533,
313
+ "eval_samples_per_second": 59.116,
314
+ "eval_steps_per_second": 7.39,
315
+ "eval_weighted avg": {
316
+ "f1-score": 0.926317298889901,
317
+ "precision": 0.9270983219126366,
318
+ "recall": 0.9267743914911025,
319
+ "support": 29334.0
320
+ },
321
+ "step": 328
322
+ },
323
+ {
324
+ "epoch": 9.0,
325
+ "eval_B": {
326
+ "f1-score": 0.8592150170648465,
327
+ "precision": 0.8315441783649876,
328
+ "recall": 0.8887908208296558,
329
+ "support": 1133.0
330
+ },
331
+ "eval_I": {
332
+ "f1-score": 0.9436033408458174,
333
+ "precision": 0.9180683108038387,
334
+ "recall": 0.9705994654448262,
335
+ "support": 18333.0
336
+ },
337
+ "eval_O": {
338
+ "f1-score": 0.8819388467945618,
339
+ "precision": 0.9387941883079739,
340
+ "recall": 0.8315768139440616,
341
+ "support": 9868.0
342
+ },
343
+ "eval_accuracy": 0.9206722574486943,
344
+ "eval_loss": 0.3574488162994385,
345
+ "eval_macro avg": {
346
+ "f1-score": 0.8949190682350753,
347
+ "precision": 0.8961355591589334,
348
+ "recall": 0.8969890334061811,
349
+ "support": 29334.0
350
+ },
351
+ "eval_runtime": 1.3536,
352
+ "eval_samples_per_second": 59.1,
353
+ "eval_steps_per_second": 7.388,
354
+ "eval_weighted avg": {
355
+ "f1-score": 0.9195998909875767,
356
+ "precision": 0.9216986072911089,
357
+ "recall": 0.9206722574486943,
358
+ "support": 29334.0
359
+ },
360
+ "step": 369
361
+ },
362
+ {
363
+ "epoch": 10.0,
364
+ "eval_B": {
365
+ "f1-score": 0.8638334778837814,
366
+ "precision": 0.8491048593350383,
367
+ "recall": 0.8790820829655781,
368
+ "support": 1133.0
369
+ },
370
+ "eval_I": {
371
+ "f1-score": 0.9512108939686336,
372
+ "precision": 0.9479900314226893,
373
+ "recall": 0.9544537173403153,
374
+ "support": 18333.0
375
+ },
376
+ "eval_O": {
377
+ "f1-score": 0.9047059424658934,
378
+ "precision": 0.9123982273523652,
379
+ "recall": 0.897142278070531,
380
+ "support": 9868.0
381
+ },
382
+ "eval_accuracy": 0.9322629031158383,
383
+ "eval_loss": 0.3227890431880951,
384
+ "eval_macro avg": {
385
+ "f1-score": 0.9065834381061029,
386
+ "precision": 0.9031643727033641,
387
+ "recall": 0.9102260261254749,
388
+ "support": 29334.0
389
+ },
390
+ "eval_runtime": 1.3497,
391
+ "eval_samples_per_second": 59.273,
392
+ "eval_steps_per_second": 7.409,
393
+ "eval_weighted avg": {
394
+ "f1-score": 0.9321916850692957,
395
+ "precision": 0.9321975441198576,
396
+ "recall": 0.9322629031158383,
397
+ "support": 29334.0
398
+ },
399
+ "step": 410
400
+ },
401
+ {
402
+ "epoch": 11.0,
403
+ "eval_B": {
404
+ "f1-score": 0.8647237929534581,
405
+ "precision": 0.8524871355060034,
406
+ "recall": 0.8773168578993822,
407
+ "support": 1133.0
408
+ },
409
+ "eval_I": {
410
+ "f1-score": 0.9492643877109477,
411
+ "precision": 0.941372096765542,
412
+ "recall": 0.9572901325478645,
413
+ "support": 18333.0
414
+ },
415
+ "eval_O": {
416
+ "f1-score": 0.9002217294900223,
417
+ "precision": 0.9164304461942258,
418
+ "recall": 0.8845764085934333,
419
+ "support": 9868.0
420
+ },
421
+ "eval_accuracy": 0.9297402331765187,
422
+ "eval_loss": 0.3397265374660492,
423
+ "eval_macro avg": {
424
+ "f1-score": 0.9047366367181428,
425
+ "precision": 0.9034298928219237,
426
+ "recall": 0.9063944663468934,
427
+ "support": 29334.0
428
+ },
429
+ "eval_runtime": 1.3481,
430
+ "eval_samples_per_second": 59.344,
431
+ "eval_steps_per_second": 7.418,
432
+ "eval_weighted avg": {
433
+ "f1-score": 0.9295010603371041,
434
+ "precision": 0.9295485858585807,
435
+ "recall": 0.9297402331765187,
436
+ "support": 29334.0
437
+ },
438
+ "step": 451
439
+ },
440
+ {
441
+ "epoch": 12.0,
442
+ "eval_B": {
443
+ "f1-score": 0.8619354838709679,
444
+ "precision": 0.8406040268456376,
445
+ "recall": 0.884377758164166,
446
+ "support": 1133.0
447
+ },
448
+ "eval_I": {
449
+ "f1-score": 0.9481537342777884,
450
+ "precision": 0.9364758459246648,
451
+ "recall": 0.9601265477554137,
452
+ "support": 18333.0
453
+ },
454
+ "eval_O": {
455
+ "f1-score": 0.8965337774539398,
456
+ "precision": 0.9215707254440403,
457
+ "recall": 0.8728212403729225,
458
+ "support": 9868.0
459
+ },
460
+ "eval_accuracy": 0.9278311856548714,
461
+ "eval_loss": 0.37686192989349365,
462
+ "eval_macro avg": {
463
+ "f1-score": 0.9022076652008987,
464
+ "precision": 0.8995501994047809,
465
+ "recall": 0.9057751820975007,
466
+ "support": 29334.0
467
+ },
468
+ "eval_runtime": 1.3518,
469
+ "eval_samples_per_second": 59.18,
470
+ "eval_steps_per_second": 7.397,
471
+ "eval_weighted avg": {
472
+ "f1-score": 0.927458601951864,
473
+ "precision": 0.9277587769971628,
474
+ "recall": 0.9278311856548714,
475
+ "support": 29334.0
476
+ },
477
+ "step": 492
478
+ }
479
+ ],
480
+ "logging_steps": 500,
481
+ "max_steps": 656,
482
+ "num_input_tokens_seen": 0,
483
+ "num_train_epochs": 16,
484
+ "save_steps": 500,
485
+ "total_flos": 1725439832827200.0,
486
+ "train_batch_size": 8,
487
+ "trial_name": null,
488
+ "trial_params": null
489
+ }
checkpoint-492/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a85704f2105e1c46ca0823f01fbb52a10555bceb380a6c1ee60701ae82dec74
3
+ size 4664
checkpoint-492/vocab.json ADDED
The diff for this file is too large to render. See raw diff