PhaaNe commited on
Commit
1bee971
·
verified ·
1 Parent(s): b65d30c

Add explore checkpoint explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064 (job 67f9c6a5cf0d5cd98879, factcheck-ablations)

Browse files
Files changed (21) hide show
  1. explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/model.safetensors +3 -0
  2. explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-1141/model.safetensors +3 -0
  3. explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-1141/optimizer.pt +3 -0
  4. explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-1141/rng_state.pth +3 -0
  5. explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-1141/scheduler.pt +3 -0
  6. explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-1141/sentencepiece.bpe.model +3 -0
  7. explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-1141/special_tokens_map.json +15 -0
  8. explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-1141/tokenizer.json +0 -0
  9. explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-1141/tokenizer_config.json +56 -0
  10. explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-1141/trainer_state.json +435 -0
  11. explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-1141/training_args.bin +3 -0
  12. explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-652/model.safetensors +3 -0
  13. explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-652/optimizer.pt +3 -0
  14. explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-652/rng_state.pth +3 -0
  15. explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-652/scheduler.pt +3 -0
  16. explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-652/sentencepiece.bpe.model +3 -0
  17. explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-652/special_tokens_map.json +15 -0
  18. explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-652/tokenizer.json +0 -0
  19. explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-652/tokenizer_config.json +56 -0
  20. explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-652/trainer_state.json +269 -0
  21. explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-652/training_args.bin +3 -0
explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5723f8b7353de7fd84dcde5d4e15774fc9d92fc35f39ed0283a9fe3b64a9fd05
3
+ size 390297060
explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-1141/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:718a9e73ab1b2bfb7bcf99827dce49e089f16698230dacc278b8cb5034d4c115
3
+ size 390297092
explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-1141/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:189ae69cb408b58913cada2a0b96f2f8ca84d389e2a276a214280efb9e88a07f
3
+ size 775987770
explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-1141/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:905642ff214c53ff33cae4510686bcae1ef915e852c734ae5af46f79e00eb785
3
+ size 14244
explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-1141/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de0ddcd1c7002c3feb012aac545f82daba512f7da257c6d1e7d47264713fa9e9
3
+ size 1064
explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-1141/sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02aaf05cda4db99e86b7c76eba6258867ce4d043da0fed19c87a7d46c8b53a65
3
+ size 470732
explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-1141/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
+ }
explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-1141/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-1141/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "15001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "extra_special_tokens": {},
49
+ "mask_token": "<mask>",
50
+ "model_max_length": 512,
51
+ "pad_token": "<pad>",
52
+ "sep_token": "</s>",
53
+ "sp_model_kwargs": {},
54
+ "tokenizer_class": "XLMRobertaTokenizer",
55
+ "unk_token": "<unk>"
56
+ }
explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-1141/trainer_state.json ADDED
@@ -0,0 +1,435 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 652,
3
+ "best_metric": 0.4861673619709203,
4
+ "best_model_checkpoint": "/root/VNEncoder/explore/workspaces/67f9c6a5cf0d5cd98879/results/checkpoints/explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-652",
5
+ "epoch": 7.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1141,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.15408320493066255,
14
+ "grad_norm": 25.025745391845703,
15
+ "learning_rate": 1.47239263803681e-06,
16
+ "loss": 4.7632,
17
+ "step": 25
18
+ },
19
+ {
20
+ "epoch": 0.3081664098613251,
21
+ "grad_norm": 22.662744522094727,
22
+ "learning_rate": 3.0061349693251535e-06,
23
+ "loss": 4.5483,
24
+ "step": 50
25
+ },
26
+ {
27
+ "epoch": 0.4622496147919877,
28
+ "grad_norm": 22.524274826049805,
29
+ "learning_rate": 4.539877300613497e-06,
30
+ "loss": 4.5211,
31
+ "step": 75
32
+ },
33
+ {
34
+ "epoch": 0.6163328197226502,
35
+ "grad_norm": 29.397296905517578,
36
+ "learning_rate": 6.073619631901841e-06,
37
+ "loss": 4.4791,
38
+ "step": 100
39
+ },
40
+ {
41
+ "epoch": 0.7704160246533128,
42
+ "grad_norm": 24.79282569885254,
43
+ "learning_rate": 7.6073619631901856e-06,
44
+ "loss": 4.3831,
45
+ "step": 125
46
+ },
47
+ {
48
+ "epoch": 0.9244992295839753,
49
+ "grad_norm": 20.706857681274414,
50
+ "learning_rate": 9.14110429447853e-06,
51
+ "loss": 4.3772,
52
+ "step": 150
53
+ },
54
+ {
55
+ "epoch": 1.0,
56
+ "eval_accuracy": 0.41424418604651164,
57
+ "eval_loss": 1.0746020078659058,
58
+ "eval_macro_f1": 0.35214046667803595,
59
+ "eval_runtime": 0.4984,
60
+ "eval_samples_per_second": 1380.469,
61
+ "eval_steps_per_second": 86.279,
62
+ "eval_weighted_f1": 0.3549509574424407,
63
+ "step": 163
64
+ },
65
+ {
66
+ "epoch": 1.073959938366718,
67
+ "grad_norm": 25.96282386779785,
68
+ "learning_rate": 1.0674846625766873e-05,
69
+ "loss": 4.2633,
70
+ "step": 175
71
+ },
72
+ {
73
+ "epoch": 1.2280431432973806,
74
+ "grad_norm": 32.3751220703125,
75
+ "learning_rate": 1.2208588957055216e-05,
76
+ "loss": 4.3012,
77
+ "step": 200
78
+ },
79
+ {
80
+ "epoch": 1.3821263482280433,
81
+ "grad_norm": 25.018341064453125,
82
+ "learning_rate": 1.374233128834356e-05,
83
+ "loss": 4.2452,
84
+ "step": 225
85
+ },
86
+ {
87
+ "epoch": 1.5362095531587057,
88
+ "grad_norm": 28.93145179748535,
89
+ "learning_rate": 1.5276073619631903e-05,
90
+ "loss": 4.1669,
91
+ "step": 250
92
+ },
93
+ {
94
+ "epoch": 1.6902927580893683,
95
+ "grad_norm": 19.801076889038086,
96
+ "learning_rate": 1.6809815950920248e-05,
97
+ "loss": 4.17,
98
+ "step": 275
99
+ },
100
+ {
101
+ "epoch": 1.8443759630200307,
102
+ "grad_norm": 24.793441772460938,
103
+ "learning_rate": 1.834355828220859e-05,
104
+ "loss": 4.1991,
105
+ "step": 300
106
+ },
107
+ {
108
+ "epoch": 1.9984591679506933,
109
+ "grad_norm": 34.49897766113281,
110
+ "learning_rate": 1.9877300613496935e-05,
111
+ "loss": 4.1375,
112
+ "step": 325
113
+ },
114
+ {
115
+ "epoch": 2.0,
116
+ "eval_accuracy": 0.4418604651162791,
117
+ "eval_loss": 1.0844818353652954,
118
+ "eval_macro_f1": 0.39389089657546034,
119
+ "eval_runtime": 0.5133,
120
+ "eval_samples_per_second": 1340.325,
121
+ "eval_steps_per_second": 83.77,
122
+ "eval_weighted_f1": 0.3977212423911347,
123
+ "step": 326
124
+ },
125
+ {
126
+ "epoch": 2.147919876733436,
127
+ "grad_norm": 28.54678726196289,
128
+ "learning_rate": 1.9843217450579417e-05,
129
+ "loss": 3.7232,
130
+ "step": 350
131
+ },
132
+ {
133
+ "epoch": 2.3020030816640986,
134
+ "grad_norm": 28.841978073120117,
135
+ "learning_rate": 1.967280163599182e-05,
136
+ "loss": 3.7931,
137
+ "step": 375
138
+ },
139
+ {
140
+ "epoch": 2.4560862865947612,
141
+ "grad_norm": 27.90904998779297,
142
+ "learning_rate": 1.9502385821404228e-05,
143
+ "loss": 3.7284,
144
+ "step": 400
145
+ },
146
+ {
147
+ "epoch": 2.610169491525424,
148
+ "grad_norm": 26.746492385864258,
149
+ "learning_rate": 1.9331970006816635e-05,
150
+ "loss": 3.5896,
151
+ "step": 425
152
+ },
153
+ {
154
+ "epoch": 2.7642526964560865,
155
+ "grad_norm": 18.919471740722656,
156
+ "learning_rate": 1.916155419222904e-05,
157
+ "loss": 3.6653,
158
+ "step": 450
159
+ },
160
+ {
161
+ "epoch": 2.9183359013867487,
162
+ "grad_norm": 22.600746154785156,
163
+ "learning_rate": 1.8991138377641446e-05,
164
+ "loss": 3.8156,
165
+ "step": 475
166
+ },
167
+ {
168
+ "epoch": 3.0,
169
+ "eval_accuracy": 0.45494186046511625,
170
+ "eval_loss": 1.1120589971542358,
171
+ "eval_macro_f1": 0.43583810221956987,
172
+ "eval_runtime": 0.5147,
173
+ "eval_samples_per_second": 1336.749,
174
+ "eval_steps_per_second": 83.547,
175
+ "eval_weighted_f1": 0.43334032720709476,
176
+ "step": 489
177
+ },
178
+ {
179
+ "epoch": 3.0677966101694913,
180
+ "grad_norm": 39.956398010253906,
181
+ "learning_rate": 1.8820722563053853e-05,
182
+ "loss": 3.2595,
183
+ "step": 500
184
+ },
185
+ {
186
+ "epoch": 3.221879815100154,
187
+ "grad_norm": 23.67790412902832,
188
+ "learning_rate": 1.8650306748466257e-05,
189
+ "loss": 3.0,
190
+ "step": 525
191
+ },
192
+ {
193
+ "epoch": 3.3759630200308166,
194
+ "grad_norm": 40.72322463989258,
195
+ "learning_rate": 1.8479890933878664e-05,
196
+ "loss": 2.7817,
197
+ "step": 550
198
+ },
199
+ {
200
+ "epoch": 3.5300462249614792,
201
+ "grad_norm": 45.60294723510742,
202
+ "learning_rate": 1.8309475119291072e-05,
203
+ "loss": 2.8431,
204
+ "step": 575
205
+ },
206
+ {
207
+ "epoch": 3.684129429892142,
208
+ "grad_norm": 30.013134002685547,
209
+ "learning_rate": 1.8139059304703476e-05,
210
+ "loss": 2.7464,
211
+ "step": 600
212
+ },
213
+ {
214
+ "epoch": 3.8382126348228045,
215
+ "grad_norm": 42.12672424316406,
216
+ "learning_rate": 1.7968643490115886e-05,
217
+ "loss": 2.7535,
218
+ "step": 625
219
+ },
220
+ {
221
+ "epoch": 3.992295839753467,
222
+ "grad_norm": 74.28974914550781,
223
+ "learning_rate": 1.779822767552829e-05,
224
+ "loss": 3.0439,
225
+ "step": 650
226
+ },
227
+ {
228
+ "epoch": 4.0,
229
+ "eval_accuracy": 0.4883720930232558,
230
+ "eval_loss": 1.1961463689804077,
231
+ "eval_macro_f1": 0.4861673619709203,
232
+ "eval_runtime": 0.5488,
233
+ "eval_samples_per_second": 1253.608,
234
+ "eval_steps_per_second": 78.351,
235
+ "eval_weighted_f1": 0.48544763353284553,
236
+ "step": 652
237
+ },
238
+ {
239
+ "epoch": 4.141756548536209,
240
+ "grad_norm": 32.40179443359375,
241
+ "learning_rate": 1.7627811860940697e-05,
242
+ "loss": 1.8409,
243
+ "step": 675
244
+ },
245
+ {
246
+ "epoch": 4.295839753466872,
247
+ "grad_norm": 37.02064514160156,
248
+ "learning_rate": 1.7457396046353105e-05,
249
+ "loss": 1.6131,
250
+ "step": 700
251
+ },
252
+ {
253
+ "epoch": 4.449922958397535,
254
+ "grad_norm": 43.65619659423828,
255
+ "learning_rate": 1.728698023176551e-05,
256
+ "loss": 1.5859,
257
+ "step": 725
258
+ },
259
+ {
260
+ "epoch": 4.604006163328197,
261
+ "grad_norm": 61.30013656616211,
262
+ "learning_rate": 1.7116564417177916e-05,
263
+ "loss": 1.7293,
264
+ "step": 750
265
+ },
266
+ {
267
+ "epoch": 4.75808936825886,
268
+ "grad_norm": 48.466182708740234,
269
+ "learning_rate": 1.6946148602590323e-05,
270
+ "loss": 1.5663,
271
+ "step": 775
272
+ },
273
+ {
274
+ "epoch": 4.9121725731895225,
275
+ "grad_norm": 70.21631622314453,
276
+ "learning_rate": 1.6775732788002727e-05,
277
+ "loss": 1.8387,
278
+ "step": 800
279
+ },
280
+ {
281
+ "epoch": 5.0,
282
+ "eval_accuracy": 0.45348837209302323,
283
+ "eval_loss": 1.6644985675811768,
284
+ "eval_macro_f1": 0.4422109752759198,
285
+ "eval_runtime": 0.5434,
286
+ "eval_samples_per_second": 1266.027,
287
+ "eval_steps_per_second": 79.127,
288
+ "eval_weighted_f1": 0.44137593979372475,
289
+ "step": 815
290
+ },
291
+ {
292
+ "epoch": 5.061633281972265,
293
+ "grad_norm": 40.12567901611328,
294
+ "learning_rate": 1.6605316973415134e-05,
295
+ "loss": 1.3072,
296
+ "step": 825
297
+ },
298
+ {
299
+ "epoch": 5.215716486902927,
300
+ "grad_norm": 61.85525894165039,
301
+ "learning_rate": 1.643490115882754e-05,
302
+ "loss": 0.8207,
303
+ "step": 850
304
+ },
305
+ {
306
+ "epoch": 5.36979969183359,
307
+ "grad_norm": 47.9658203125,
308
+ "learning_rate": 1.6264485344239945e-05,
309
+ "loss": 0.6424,
310
+ "step": 875
311
+ },
312
+ {
313
+ "epoch": 5.523882896764253,
314
+ "grad_norm": 49.86366271972656,
315
+ "learning_rate": 1.6094069529652356e-05,
316
+ "loss": 0.7136,
317
+ "step": 900
318
+ },
319
+ {
320
+ "epoch": 5.677966101694915,
321
+ "grad_norm": 25.742820739746094,
322
+ "learning_rate": 1.592365371506476e-05,
323
+ "loss": 0.8844,
324
+ "step": 925
325
+ },
326
+ {
327
+ "epoch": 5.832049306625578,
328
+ "grad_norm": 46.200191497802734,
329
+ "learning_rate": 1.5753237900477167e-05,
330
+ "loss": 0.7356,
331
+ "step": 950
332
+ },
333
+ {
334
+ "epoch": 5.9861325115562405,
335
+ "grad_norm": 36.1185417175293,
336
+ "learning_rate": 1.5582822085889574e-05,
337
+ "loss": 0.775,
338
+ "step": 975
339
+ },
340
+ {
341
+ "epoch": 6.0,
342
+ "eval_accuracy": 0.45203488372093026,
343
+ "eval_loss": 2.4498987197875977,
344
+ "eval_macro_f1": 0.4257217051091391,
345
+ "eval_runtime": 0.5154,
346
+ "eval_samples_per_second": 1334.899,
347
+ "eval_steps_per_second": 83.431,
348
+ "eval_weighted_f1": 0.42661573178749174,
349
+ "step": 978
350
+ },
351
+ {
352
+ "epoch": 6.135593220338983,
353
+ "grad_norm": 17.029922485351562,
354
+ "learning_rate": 1.5412406271301978e-05,
355
+ "loss": 0.3486,
356
+ "step": 1000
357
+ },
358
+ {
359
+ "epoch": 6.289676425269645,
360
+ "grad_norm": 42.387516021728516,
361
+ "learning_rate": 1.5241990456714383e-05,
362
+ "loss": 0.2761,
363
+ "step": 1025
364
+ },
365
+ {
366
+ "epoch": 6.443759630200308,
367
+ "grad_norm": 38.67579650878906,
368
+ "learning_rate": 1.5071574642126792e-05,
369
+ "loss": 0.505,
370
+ "step": 1050
371
+ },
372
+ {
373
+ "epoch": 6.597842835130971,
374
+ "grad_norm": 61.74009704589844,
375
+ "learning_rate": 1.4901158827539198e-05,
376
+ "loss": 0.4247,
377
+ "step": 1075
378
+ },
379
+ {
380
+ "epoch": 6.751926040061633,
381
+ "grad_norm": 52.512908935546875,
382
+ "learning_rate": 1.4730743012951603e-05,
383
+ "loss": 0.5489,
384
+ "step": 1100
385
+ },
386
+ {
387
+ "epoch": 6.906009244992296,
388
+ "grad_norm": 18.177906036376953,
389
+ "learning_rate": 1.456032719836401e-05,
390
+ "loss": 0.5706,
391
+ "step": 1125
392
+ },
393
+ {
394
+ "epoch": 7.0,
395
+ "eval_accuracy": 0.4563953488372093,
396
+ "eval_loss": 2.7934722900390625,
397
+ "eval_macro_f1": 0.44781054352184063,
398
+ "eval_runtime": 0.5149,
399
+ "eval_samples_per_second": 1336.056,
400
+ "eval_steps_per_second": 83.503,
401
+ "eval_weighted_f1": 0.44696607220173196,
402
+ "step": 1141
403
+ }
404
+ ],
405
+ "logging_steps": 25,
406
+ "max_steps": 3260,
407
+ "num_input_tokens_seen": 0,
408
+ "num_train_epochs": 20,
409
+ "save_steps": 500,
410
+ "stateful_callbacks": {
411
+ "EarlyStoppingCallback": {
412
+ "args": {
413
+ "early_stopping_patience": 3,
414
+ "early_stopping_threshold": 0.0
415
+ },
416
+ "attributes": {
417
+ "early_stopping_patience_counter": 3
418
+ }
419
+ },
420
+ "TrainerControl": {
421
+ "args": {
422
+ "should_epoch_stop": false,
423
+ "should_evaluate": false,
424
+ "should_log": false,
425
+ "should_save": true,
426
+ "should_training_stop": true
427
+ },
428
+ "attributes": {}
429
+ }
430
+ },
431
+ "total_flos": 0.0,
432
+ "train_batch_size": 8,
433
+ "trial_name": null,
434
+ "trial_params": null
435
+ }
explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-1141/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d5afc30ba0a91e04a06b1a795316e68cdae541746521214bdc40154043e3f62
3
+ size 5752
explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-652/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f5c8a0ec9eea49f31dc3adf9deb211b3d1507bdaf181aea48c85fd2d24d31f9
3
+ size 390297092
explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-652/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2ada543c1dd7b2a69d55aa4f87ca6ec1a17cf72d6475e7998ce337882b67249
3
+ size 775987770
explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-652/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa2e8c958a74d5f11b0d7534850e20ac37aef4330cb4f372a17fafc479fbceda
3
+ size 14244
explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-652/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d11e46f9cdc3bb6b3623ae91dab13e412cc10215e3b4aeca43c9d2208a0e839
3
+ size 1064
explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-652/sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02aaf05cda4db99e86b7c76eba6258867ce4d043da0fed19c87a7d46c8b53a65
3
+ size 470732
explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-652/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
+ }
explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-652/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-652/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "15001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "extra_special_tokens": {},
49
+ "mask_token": "<mask>",
50
+ "model_max_length": 512,
51
+ "pad_token": "<pad>",
52
+ "sep_token": "</s>",
53
+ "sp_model_kwargs": {},
54
+ "tokenizer_class": "XLMRobertaTokenizer",
55
+ "unk_token": "<unk>"
56
+ }
explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-652/trainer_state.json ADDED
@@ -0,0 +1,269 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 652,
3
+ "best_metric": 0.4861673619709203,
4
+ "best_model_checkpoint": "/root/VNEncoder/explore/workspaces/67f9c6a5cf0d5cd98879/results/checkpoints/explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-652",
5
+ "epoch": 4.0,
6
+ "eval_steps": 500,
7
+ "global_step": 652,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.15408320493066255,
14
+ "grad_norm": 25.025745391845703,
15
+ "learning_rate": 1.47239263803681e-06,
16
+ "loss": 4.7632,
17
+ "step": 25
18
+ },
19
+ {
20
+ "epoch": 0.3081664098613251,
21
+ "grad_norm": 22.662744522094727,
22
+ "learning_rate": 3.0061349693251535e-06,
23
+ "loss": 4.5483,
24
+ "step": 50
25
+ },
26
+ {
27
+ "epoch": 0.4622496147919877,
28
+ "grad_norm": 22.524274826049805,
29
+ "learning_rate": 4.539877300613497e-06,
30
+ "loss": 4.5211,
31
+ "step": 75
32
+ },
33
+ {
34
+ "epoch": 0.6163328197226502,
35
+ "grad_norm": 29.397296905517578,
36
+ "learning_rate": 6.073619631901841e-06,
37
+ "loss": 4.4791,
38
+ "step": 100
39
+ },
40
+ {
41
+ "epoch": 0.7704160246533128,
42
+ "grad_norm": 24.79282569885254,
43
+ "learning_rate": 7.6073619631901856e-06,
44
+ "loss": 4.3831,
45
+ "step": 125
46
+ },
47
+ {
48
+ "epoch": 0.9244992295839753,
49
+ "grad_norm": 20.706857681274414,
50
+ "learning_rate": 9.14110429447853e-06,
51
+ "loss": 4.3772,
52
+ "step": 150
53
+ },
54
+ {
55
+ "epoch": 1.0,
56
+ "eval_accuracy": 0.41424418604651164,
57
+ "eval_loss": 1.0746020078659058,
58
+ "eval_macro_f1": 0.35214046667803595,
59
+ "eval_runtime": 0.4984,
60
+ "eval_samples_per_second": 1380.469,
61
+ "eval_steps_per_second": 86.279,
62
+ "eval_weighted_f1": 0.3549509574424407,
63
+ "step": 163
64
+ },
65
+ {
66
+ "epoch": 1.073959938366718,
67
+ "grad_norm": 25.96282386779785,
68
+ "learning_rate": 1.0674846625766873e-05,
69
+ "loss": 4.2633,
70
+ "step": 175
71
+ },
72
+ {
73
+ "epoch": 1.2280431432973806,
74
+ "grad_norm": 32.3751220703125,
75
+ "learning_rate": 1.2208588957055216e-05,
76
+ "loss": 4.3012,
77
+ "step": 200
78
+ },
79
+ {
80
+ "epoch": 1.3821263482280433,
81
+ "grad_norm": 25.018341064453125,
82
+ "learning_rate": 1.374233128834356e-05,
83
+ "loss": 4.2452,
84
+ "step": 225
85
+ },
86
+ {
87
+ "epoch": 1.5362095531587057,
88
+ "grad_norm": 28.93145179748535,
89
+ "learning_rate": 1.5276073619631903e-05,
90
+ "loss": 4.1669,
91
+ "step": 250
92
+ },
93
+ {
94
+ "epoch": 1.6902927580893683,
95
+ "grad_norm": 19.801076889038086,
96
+ "learning_rate": 1.6809815950920248e-05,
97
+ "loss": 4.17,
98
+ "step": 275
99
+ },
100
+ {
101
+ "epoch": 1.8443759630200307,
102
+ "grad_norm": 24.793441772460938,
103
+ "learning_rate": 1.834355828220859e-05,
104
+ "loss": 4.1991,
105
+ "step": 300
106
+ },
107
+ {
108
+ "epoch": 1.9984591679506933,
109
+ "grad_norm": 34.49897766113281,
110
+ "learning_rate": 1.9877300613496935e-05,
111
+ "loss": 4.1375,
112
+ "step": 325
113
+ },
114
+ {
115
+ "epoch": 2.0,
116
+ "eval_accuracy": 0.4418604651162791,
117
+ "eval_loss": 1.0844818353652954,
118
+ "eval_macro_f1": 0.39389089657546034,
119
+ "eval_runtime": 0.5133,
120
+ "eval_samples_per_second": 1340.325,
121
+ "eval_steps_per_second": 83.77,
122
+ "eval_weighted_f1": 0.3977212423911347,
123
+ "step": 326
124
+ },
125
+ {
126
+ "epoch": 2.147919876733436,
127
+ "grad_norm": 28.54678726196289,
128
+ "learning_rate": 1.9843217450579417e-05,
129
+ "loss": 3.7232,
130
+ "step": 350
131
+ },
132
+ {
133
+ "epoch": 2.3020030816640986,
134
+ "grad_norm": 28.841978073120117,
135
+ "learning_rate": 1.967280163599182e-05,
136
+ "loss": 3.7931,
137
+ "step": 375
138
+ },
139
+ {
140
+ "epoch": 2.4560862865947612,
141
+ "grad_norm": 27.90904998779297,
142
+ "learning_rate": 1.9502385821404228e-05,
143
+ "loss": 3.7284,
144
+ "step": 400
145
+ },
146
+ {
147
+ "epoch": 2.610169491525424,
148
+ "grad_norm": 26.746492385864258,
149
+ "learning_rate": 1.9331970006816635e-05,
150
+ "loss": 3.5896,
151
+ "step": 425
152
+ },
153
+ {
154
+ "epoch": 2.7642526964560865,
155
+ "grad_norm": 18.919471740722656,
156
+ "learning_rate": 1.916155419222904e-05,
157
+ "loss": 3.6653,
158
+ "step": 450
159
+ },
160
+ {
161
+ "epoch": 2.9183359013867487,
162
+ "grad_norm": 22.600746154785156,
163
+ "learning_rate": 1.8991138377641446e-05,
164
+ "loss": 3.8156,
165
+ "step": 475
166
+ },
167
+ {
168
+ "epoch": 3.0,
169
+ "eval_accuracy": 0.45494186046511625,
170
+ "eval_loss": 1.1120589971542358,
171
+ "eval_macro_f1": 0.43583810221956987,
172
+ "eval_runtime": 0.5147,
173
+ "eval_samples_per_second": 1336.749,
174
+ "eval_steps_per_second": 83.547,
175
+ "eval_weighted_f1": 0.43334032720709476,
176
+ "step": 489
177
+ },
178
+ {
179
+ "epoch": 3.0677966101694913,
180
+ "grad_norm": 39.956398010253906,
181
+ "learning_rate": 1.8820722563053853e-05,
182
+ "loss": 3.2595,
183
+ "step": 500
184
+ },
185
+ {
186
+ "epoch": 3.221879815100154,
187
+ "grad_norm": 23.67790412902832,
188
+ "learning_rate": 1.8650306748466257e-05,
189
+ "loss": 3.0,
190
+ "step": 525
191
+ },
192
+ {
193
+ "epoch": 3.3759630200308166,
194
+ "grad_norm": 40.72322463989258,
195
+ "learning_rate": 1.8479890933878664e-05,
196
+ "loss": 2.7817,
197
+ "step": 550
198
+ },
199
+ {
200
+ "epoch": 3.5300462249614792,
201
+ "grad_norm": 45.60294723510742,
202
+ "learning_rate": 1.8309475119291072e-05,
203
+ "loss": 2.8431,
204
+ "step": 575
205
+ },
206
+ {
207
+ "epoch": 3.684129429892142,
208
+ "grad_norm": 30.013134002685547,
209
+ "learning_rate": 1.8139059304703476e-05,
210
+ "loss": 2.7464,
211
+ "step": 600
212
+ },
213
+ {
214
+ "epoch": 3.8382126348228045,
215
+ "grad_norm": 42.12672424316406,
216
+ "learning_rate": 1.7968643490115886e-05,
217
+ "loss": 2.7535,
218
+ "step": 625
219
+ },
220
+ {
221
+ "epoch": 3.992295839753467,
222
+ "grad_norm": 74.28974914550781,
223
+ "learning_rate": 1.779822767552829e-05,
224
+ "loss": 3.0439,
225
+ "step": 650
226
+ },
227
+ {
228
+ "epoch": 4.0,
229
+ "eval_accuracy": 0.4883720930232558,
230
+ "eval_loss": 1.1961463689804077,
231
+ "eval_macro_f1": 0.4861673619709203,
232
+ "eval_runtime": 0.5488,
233
+ "eval_samples_per_second": 1253.608,
234
+ "eval_steps_per_second": 78.351,
235
+ "eval_weighted_f1": 0.48544763353284553,
236
+ "step": 652
237
+ }
238
+ ],
239
+ "logging_steps": 25,
240
+ "max_steps": 3260,
241
+ "num_input_tokens_seen": 0,
242
+ "num_train_epochs": 20,
243
+ "save_steps": 500,
244
+ "stateful_callbacks": {
245
+ "EarlyStoppingCallback": {
246
+ "args": {
247
+ "early_stopping_patience": 3,
248
+ "early_stopping_threshold": 0.0
249
+ },
250
+ "attributes": {
251
+ "early_stopping_patience_counter": 0
252
+ }
253
+ },
254
+ "TrainerControl": {
255
+ "args": {
256
+ "should_epoch_stop": false,
257
+ "should_evaluate": false,
258
+ "should_log": false,
259
+ "should_save": true,
260
+ "should_training_stop": false
261
+ },
262
+ "attributes": {}
263
+ }
264
+ },
265
+ "total_flos": 0.0,
266
+ "train_batch_size": 8,
267
+ "trial_name": null,
268
+ "trial_params": null
269
+ }
explore-factcheck-ablations-vifactcheck-visobert-s43-20261114T114710Z-1a169064/trainer/checkpoint-652/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d5afc30ba0a91e04a06b1a795316e68cdae541746521214bdc40154043e3f62
3
+ size 5752