Theoreticallyhugo commited on
Commit
25c5403
1 Parent(s): 0112dde

Training in progress, epoch 5, checkpoint

Browse files
checkpoint-405/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": "4.38.2",
59
+ "type_vocab_size": 1,
60
+ "vocab_size": 50265
61
+ }
checkpoint-405/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-405/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df728ffc3e43c8dc2505f9e292b6ca0ca11c27bf801dc68a991c8fb56c93d072
3
+ size 592330980
checkpoint-405/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aae6672f1d6034a195c3f1384396affeeb5cf5ea6584e4ad132d57ae8a060b2c
3
+ size 1014670074
checkpoint-405/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf337692f531efc3a23b910237391cc3da6dc28e56ab2fbd5db20c81d4fb98bd
3
+ size 14244
checkpoint-405/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c73756f22c58a684dfffbbc966a96d1e3e061222bcc1371ddea16fc12be01725
3
+ size 1064
checkpoint-405/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-405/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-405/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-405/trainer_state.json ADDED
@@ -0,0 +1,336 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 405,
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": 0.32421052631578945,
15
+ "precision": 0.42777777777777776,
16
+ "recall": 0.26101694915254237,
17
+ "support": 295.0
18
+ },
19
+ "eval_B-MajorClaim": {
20
+ "f1-score": 0.192090395480226,
21
+ "precision": 0.8095238095238095,
22
+ "recall": 0.10897435897435898,
23
+ "support": 156.0
24
+ },
25
+ "eval_B-Premise": {
26
+ "f1-score": 0.8566265060240965,
27
+ "precision": 0.7620578778135049,
28
+ "recall": 0.9779917469050894,
29
+ "support": 727.0
30
+ },
31
+ "eval_I-Claim": {
32
+ "f1-score": 0.5001390820584144,
33
+ "precision": 0.5900886117492615,
34
+ "recall": 0.43398503499879315,
35
+ "support": 4143.0
36
+ },
37
+ "eval_I-MajorClaim": {
38
+ "f1-score": 0.776470588235294,
39
+ "precision": 0.6649333766655834,
40
+ "recall": 0.93296853625171,
41
+ "support": 2193.0
42
+ },
43
+ "eval_I-Premise": {
44
+ "f1-score": 0.8861458374413376,
45
+ "precision": 0.8781460059402845,
46
+ "recall": 0.8942927644670858,
47
+ "support": 12563.0
48
+ },
49
+ "eval_O": {
50
+ "f1-score": 0.9987647926046939,
51
+ "precision": 0.9977708781147998,
52
+ "recall": 0.9997606892150607,
53
+ "support": 12536.0
54
+ },
55
+ "eval_accuracy": 0.8713396498328887,
56
+ "eval_loss": 0.3092103600502014,
57
+ "eval_macro avg": {
58
+ "f1-score": 0.647778246879979,
59
+ "precision": 0.732899762512146,
60
+ "recall": 0.6584271542806628,
61
+ "support": 32613.0
62
+ },
63
+ "eval_runtime": 4.965,
64
+ "eval_samples_per_second": 16.314,
65
+ "eval_steps_per_second": 2.215,
66
+ "eval_weighted avg": {
67
+ "f1-score": 0.8639627599323451,
68
+ "precision": 0.8662078389010613,
69
+ "recall": 0.8713396498328887,
70
+ "support": 32613.0
71
+ },
72
+ "step": 81
73
+ },
74
+ {
75
+ "epoch": 2.0,
76
+ "eval_B-Claim": {
77
+ "f1-score": 0.6186291739894552,
78
+ "precision": 0.6423357664233577,
79
+ "recall": 0.5966101694915255,
80
+ "support": 295.0
81
+ },
82
+ "eval_B-MajorClaim": {
83
+ "f1-score": 0.8113879003558718,
84
+ "precision": 0.912,
85
+ "recall": 0.7307692307692307,
86
+ "support": 156.0
87
+ },
88
+ "eval_B-Premise": {
89
+ "f1-score": 0.8871181938911022,
90
+ "precision": 0.8575096277278562,
91
+ "recall": 0.9188445667125172,
92
+ "support": 727.0
93
+ },
94
+ "eval_I-Claim": {
95
+ "f1-score": 0.656253149249219,
96
+ "precision": 0.5633217993079584,
97
+ "recall": 0.7859039343470915,
98
+ "support": 4143.0
99
+ },
100
+ "eval_I-MajorClaim": {
101
+ "f1-score": 0.8368159203980099,
102
+ "precision": 0.9206349206349206,
103
+ "recall": 0.7669858641130871,
104
+ "support": 2193.0
105
+ },
106
+ "eval_I-Premise": {
107
+ "f1-score": 0.8831027253668763,
108
+ "precision": 0.933020288827855,
109
+ "recall": 0.8382551938231314,
110
+ "support": 12563.0
111
+ },
112
+ "eval_O": {
113
+ "f1-score": 0.9998006141085457,
114
+ "precision": 0.9996013077107089,
115
+ "recall": 1.0,
116
+ "support": 12536.0
117
+ },
118
+ "eval_accuracy": 0.8880814399165977,
119
+ "eval_loss": 0.2581149935722351,
120
+ "eval_macro avg": {
121
+ "f1-score": 0.8133010967655829,
122
+ "precision": 0.8326319586618081,
123
+ "recall": 0.8053384227509405,
124
+ "support": 32613.0
125
+ },
126
+ "eval_runtime": 5.0296,
127
+ "eval_samples_per_second": 16.105,
128
+ "eval_steps_per_second": 2.187,
129
+ "eval_weighted avg": {
130
+ "f1-score": 0.8933836566327042,
131
+ "precision": 0.9064023864086126,
132
+ "recall": 0.8880814399165977,
133
+ "support": 32613.0
134
+ },
135
+ "step": 162
136
+ },
137
+ {
138
+ "epoch": 3.0,
139
+ "eval_B-Claim": {
140
+ "f1-score": 0.6576271186440678,
141
+ "precision": 0.6576271186440678,
142
+ "recall": 0.6576271186440678,
143
+ "support": 295.0
144
+ },
145
+ "eval_B-MajorClaim": {
146
+ "f1-score": 0.8673139158576051,
147
+ "precision": 0.8758169934640523,
148
+ "recall": 0.8589743589743589,
149
+ "support": 156.0
150
+ },
151
+ "eval_B-Premise": {
152
+ "f1-score": 0.8838487972508591,
153
+ "precision": 0.8832417582417582,
154
+ "recall": 0.8844566712517193,
155
+ "support": 727.0
156
+ },
157
+ "eval_I-Claim": {
158
+ "f1-score": 0.6468460321049062,
159
+ "precision": 0.6083351052519669,
160
+ "recall": 0.6905623944001931,
161
+ "support": 4143.0
162
+ },
163
+ "eval_I-MajorClaim": {
164
+ "f1-score": 0.8695855771482088,
165
+ "precision": 0.8936477382098171,
166
+ "recall": 0.8467852257181943,
167
+ "support": 2193.0
168
+ },
169
+ "eval_I-Premise": {
170
+ "f1-score": 0.8926256077795786,
171
+ "precision": 0.9090533960551291,
172
+ "recall": 0.8767810236408501,
173
+ "support": 12563.0
174
+ },
175
+ "eval_O": {
176
+ "f1-score": 0.9998803589232302,
177
+ "precision": 0.9997607464710104,
178
+ "recall": 1.0,
179
+ "support": 12536.0
180
+ },
181
+ "eval_accuracy": 0.8965749854352559,
182
+ "eval_loss": 0.2399493306875229,
183
+ "eval_macro avg": {
184
+ "f1-score": 0.8311039153869222,
185
+ "precision": 0.8324975509054003,
186
+ "recall": 0.8307409703756262,
187
+ "support": 32613.0
188
+ },
189
+ "eval_runtime": 5.0024,
190
+ "eval_samples_per_second": 16.192,
191
+ "eval_steps_per_second": 2.199,
192
+ "eval_weighted avg": {
193
+ "f1-score": 0.8986385496019461,
194
+ "precision": 0.9016737059631544,
195
+ "recall": 0.8965749854352559,
196
+ "support": 32613.0
197
+ },
198
+ "step": 243
199
+ },
200
+ {
201
+ "epoch": 4.0,
202
+ "eval_B-Claim": {
203
+ "f1-score": 0.6106346483704975,
204
+ "precision": 0.6180555555555556,
205
+ "recall": 0.6033898305084746,
206
+ "support": 295.0
207
+ },
208
+ "eval_B-MajorClaim": {
209
+ "f1-score": 0.8498583569405098,
210
+ "precision": 0.7614213197969543,
211
+ "recall": 0.9615384615384616,
212
+ "support": 156.0
213
+ },
214
+ "eval_B-Premise": {
215
+ "f1-score": 0.8746478873239436,
216
+ "precision": 0.8961038961038961,
217
+ "recall": 0.8541953232462174,
218
+ "support": 727.0
219
+ },
220
+ "eval_I-Claim": {
221
+ "f1-score": 0.5964912280701754,
222
+ "precision": 0.6109845608706657,
223
+ "recall": 0.5826695631185131,
224
+ "support": 4143.0
225
+ },
226
+ "eval_I-MajorClaim": {
227
+ "f1-score": 0.8631961259079903,
228
+ "precision": 0.7741585233441911,
229
+ "recall": 0.9753761969904241,
230
+ "support": 2193.0
231
+ },
232
+ "eval_I-Premise": {
233
+ "f1-score": 0.8933694290678411,
234
+ "precision": 0.9071885770556376,
235
+ "recall": 0.8799649765183475,
236
+ "support": 12563.0
237
+ },
238
+ "eval_O": {
239
+ "f1-score": 0.9999601132782897,
240
+ "precision": 1.0,
241
+ "recall": 0.9999202297383536,
242
+ "support": 12536.0
243
+ },
244
+ "eval_accuracy": 0.8920369177935179,
245
+ "eval_loss": 0.2815629839897156,
246
+ "eval_macro avg": {
247
+ "f1-score": 0.8125939698513209,
248
+ "precision": 0.7954160618181286,
249
+ "recall": 0.8367220830941131,
250
+ "support": 32613.0
251
+ },
252
+ "eval_runtime": 4.9474,
253
+ "eval_samples_per_second": 16.372,
254
+ "eval_steps_per_second": 2.223,
255
+ "eval_weighted avg": {
256
+ "f1-score": 0.8914155863760895,
257
+ "precision": 0.892730641712682,
258
+ "recall": 0.8920369177935179,
259
+ "support": 32613.0
260
+ },
261
+ "step": 324
262
+ },
263
+ {
264
+ "epoch": 5.0,
265
+ "eval_B-Claim": {
266
+ "f1-score": 0.6796116504854369,
267
+ "precision": 0.6501547987616099,
268
+ "recall": 0.711864406779661,
269
+ "support": 295.0
270
+ },
271
+ "eval_B-MajorClaim": {
272
+ "f1-score": 0.8746177370030581,
273
+ "precision": 0.8362573099415205,
274
+ "recall": 0.9166666666666666,
275
+ "support": 156.0
276
+ },
277
+ "eval_B-Premise": {
278
+ "f1-score": 0.8836879432624114,
279
+ "precision": 0.9121522693997072,
280
+ "recall": 0.8569463548830811,
281
+ "support": 727.0
282
+ },
283
+ "eval_I-Claim": {
284
+ "f1-score": 0.6557152635181382,
285
+ "precision": 0.6216742375081116,
286
+ "recall": 0.6937002172338885,
287
+ "support": 4143.0
288
+ },
289
+ "eval_I-MajorClaim": {
290
+ "f1-score": 0.8859746610357857,
291
+ "precision": 0.8642671292281006,
292
+ "recall": 0.9088007295941632,
293
+ "support": 2193.0
294
+ },
295
+ "eval_I-Premise": {
296
+ "f1-score": 0.8956745077255495,
297
+ "precision": 0.9180177168644492,
298
+ "recall": 0.874393058982727,
299
+ "support": 12563.0
300
+ },
301
+ "eval_O": {
302
+ "f1-score": 0.9998006141085457,
303
+ "precision": 0.9996013077107089,
304
+ "recall": 1.0,
305
+ "support": 12536.0
306
+ },
307
+ "eval_accuracy": 0.9003771502161715,
308
+ "eval_loss": 0.2959797978401184,
309
+ "eval_macro avg": {
310
+ "f1-score": 0.839297482448418,
311
+ "precision": 0.8288749670591724,
312
+ "recall": 0.8517673477343124,
313
+ "support": 32613.0
314
+ },
315
+ "eval_runtime": 4.9768,
316
+ "eval_samples_per_second": 16.275,
317
+ "eval_steps_per_second": 2.21,
318
+ "eval_weighted avg": {
319
+ "f1-score": 0.9022413468876027,
320
+ "precision": 0.9051721478141229,
321
+ "recall": 0.9003771502161715,
322
+ "support": 32613.0
323
+ },
324
+ "step": 405
325
+ }
326
+ ],
327
+ "logging_steps": 500,
328
+ "max_steps": 4050,
329
+ "num_input_tokens_seen": 0,
330
+ "num_train_epochs": 50,
331
+ "save_steps": 500,
332
+ "total_flos": 716721286995000.0,
333
+ "train_batch_size": 4,
334
+ "trial_name": null,
335
+ "trial_params": null
336
+ }
checkpoint-405/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5eff186592c44100b7fd5c301c21b9eebfc7f8bd335567cdc6ffe4a4d32ec927
3
+ size 4920
checkpoint-405/vocab.json ADDED
The diff for this file is too large to render. See raw diff