PhaaNe commited on
Commit
de65ecc
·
verified ·
1 Parent(s): fd090b8

Add explore checkpoint explore-factcheck-ablations-vifactcheck-visobert-s44-20261114T115900Z-59e46264 (job eb5f0352b3159567ae3f, factcheck-ablations)

Browse files
Files changed (21) hide show
  1. explore-factcheck-ablations-vifactcheck-visobert-s44-20261114T115900Z-59e46264/model.safetensors +3 -0
  2. explore-factcheck-ablations-vifactcheck-visobert-s44-20261114T115900Z-59e46264/trainer/checkpoint-489/model.safetensors +3 -0
  3. explore-factcheck-ablations-vifactcheck-visobert-s44-20261114T115900Z-59e46264/trainer/checkpoint-489/optimizer.pt +3 -0
  4. explore-factcheck-ablations-vifactcheck-visobert-s44-20261114T115900Z-59e46264/trainer/checkpoint-489/rng_state.pth +3 -0
  5. explore-factcheck-ablations-vifactcheck-visobert-s44-20261114T115900Z-59e46264/trainer/checkpoint-489/scheduler.pt +3 -0
  6. explore-factcheck-ablations-vifactcheck-visobert-s44-20261114T115900Z-59e46264/trainer/checkpoint-489/sentencepiece.bpe.model +3 -0
  7. explore-factcheck-ablations-vifactcheck-visobert-s44-20261114T115900Z-59e46264/trainer/checkpoint-489/special_tokens_map.json +15 -0
  8. explore-factcheck-ablations-vifactcheck-visobert-s44-20261114T115900Z-59e46264/trainer/checkpoint-489/tokenizer.json +0 -0
  9. explore-factcheck-ablations-vifactcheck-visobert-s44-20261114T115900Z-59e46264/trainer/checkpoint-489/tokenizer_config.json +56 -0
  10. explore-factcheck-ablations-vifactcheck-visobert-s44-20261114T115900Z-59e46264/trainer/checkpoint-489/trainer_state.json +209 -0
  11. explore-factcheck-ablations-vifactcheck-visobert-s44-20261114T115900Z-59e46264/trainer/checkpoint-489/training_args.bin +3 -0
  12. explore-factcheck-ablations-vifactcheck-visobert-s44-20261114T115900Z-59e46264/trainer/checkpoint-978/model.safetensors +3 -0
  13. explore-factcheck-ablations-vifactcheck-visobert-s44-20261114T115900Z-59e46264/trainer/checkpoint-978/optimizer.pt +3 -0
  14. explore-factcheck-ablations-vifactcheck-visobert-s44-20261114T115900Z-59e46264/trainer/checkpoint-978/rng_state.pth +3 -0
  15. explore-factcheck-ablations-vifactcheck-visobert-s44-20261114T115900Z-59e46264/trainer/checkpoint-978/scheduler.pt +3 -0
  16. explore-factcheck-ablations-vifactcheck-visobert-s44-20261114T115900Z-59e46264/trainer/checkpoint-978/sentencepiece.bpe.model +3 -0
  17. explore-factcheck-ablations-vifactcheck-visobert-s44-20261114T115900Z-59e46264/trainer/checkpoint-978/special_tokens_map.json +15 -0
  18. explore-factcheck-ablations-vifactcheck-visobert-s44-20261114T115900Z-59e46264/trainer/checkpoint-978/tokenizer.json +0 -0
  19. explore-factcheck-ablations-vifactcheck-visobert-s44-20261114T115900Z-59e46264/trainer/checkpoint-978/tokenizer_config.json +56 -0
  20. explore-factcheck-ablations-vifactcheck-visobert-s44-20261114T115900Z-59e46264/trainer/checkpoint-978/trainer_state.json +382 -0
  21. explore-factcheck-ablations-vifactcheck-visobert-s44-20261114T115900Z-59e46264/trainer/checkpoint-978/training_args.bin +3 -0
explore-factcheck-ablations-vifactcheck-visobert-s44-20261114T115900Z-59e46264/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:071871039167c3a95ecb32e1031215f8f569ea1fe6fefe69beaa024dbbe9bcb5
3
+ size 390297060
explore-factcheck-ablations-vifactcheck-visobert-s44-20261114T115900Z-59e46264/trainer/checkpoint-489/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b14bd6c8784eb29001a98890b2da0cbb43aacd47534a2300e2c57378a6025fa3
3
+ size 390297092
explore-factcheck-ablations-vifactcheck-visobert-s44-20261114T115900Z-59e46264/trainer/checkpoint-489/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:437d30ead53a1fca3f2904b97de0c063a7d3697dbbd53bc2918d665c070cce96
3
+ size 775987770
explore-factcheck-ablations-vifactcheck-visobert-s44-20261114T115900Z-59e46264/trainer/checkpoint-489/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8a75eb6e007b1d59818cef5dff49c71618e659a591288c4838765573936057e
3
+ size 14244
explore-factcheck-ablations-vifactcheck-visobert-s44-20261114T115900Z-59e46264/trainer/checkpoint-489/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b713fea1a71c91d8b2b7515d27d1c866698e4345ee50f3a53836f3e067cd133
3
+ size 1064
explore-factcheck-ablations-vifactcheck-visobert-s44-20261114T115900Z-59e46264/trainer/checkpoint-489/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-s44-20261114T115900Z-59e46264/trainer/checkpoint-489/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-s44-20261114T115900Z-59e46264/trainer/checkpoint-489/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
explore-factcheck-ablations-vifactcheck-visobert-s44-20261114T115900Z-59e46264/trainer/checkpoint-489/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-s44-20261114T115900Z-59e46264/trainer/checkpoint-489/trainer_state.json ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 489,
3
+ "best_metric": 0.4561052941377414,
4
+ "best_model_checkpoint": "/root/VNEncoder/explore/workspaces/eb5f0352b3159567ae3f/results/checkpoints/explore-factcheck-ablations-vifactcheck-visobert-s44-20261114T115900Z-59e46264/trainer/checkpoint-489",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 489,
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": 26.18512535095215,
15
+ "learning_rate": 1.47239263803681e-06,
16
+ "loss": 4.8039,
17
+ "step": 25
18
+ },
19
+ {
20
+ "epoch": 0.3081664098613251,
21
+ "grad_norm": 23.501117706298828,
22
+ "learning_rate": 3.0061349693251535e-06,
23
+ "loss": 4.5663,
24
+ "step": 50
25
+ },
26
+ {
27
+ "epoch": 0.4622496147919877,
28
+ "grad_norm": 30.07345199584961,
29
+ "learning_rate": 4.539877300613497e-06,
30
+ "loss": 4.3556,
31
+ "step": 75
32
+ },
33
+ {
34
+ "epoch": 0.6163328197226502,
35
+ "grad_norm": 22.460676193237305,
36
+ "learning_rate": 6.073619631901841e-06,
37
+ "loss": 4.3901,
38
+ "step": 100
39
+ },
40
+ {
41
+ "epoch": 0.7704160246533128,
42
+ "grad_norm": 19.21281623840332,
43
+ "learning_rate": 7.6073619631901856e-06,
44
+ "loss": 4.2739,
45
+ "step": 125
46
+ },
47
+ {
48
+ "epoch": 0.9244992295839753,
49
+ "grad_norm": 31.142452239990234,
50
+ "learning_rate": 9.14110429447853e-06,
51
+ "loss": 4.3314,
52
+ "step": 150
53
+ },
54
+ {
55
+ "epoch": 1.0,
56
+ "eval_accuracy": 0.4331395348837209,
57
+ "eval_loss": 1.0662841796875,
58
+ "eval_macro_f1": 0.4325818234561818,
59
+ "eval_runtime": 0.5224,
60
+ "eval_samples_per_second": 1316.893,
61
+ "eval_steps_per_second": 82.306,
62
+ "eval_weighted_f1": 0.43295810595327466,
63
+ "step": 163
64
+ },
65
+ {
66
+ "epoch": 1.073959938366718,
67
+ "grad_norm": 30.027835845947266,
68
+ "learning_rate": 1.0674846625766873e-05,
69
+ "loss": 4.0454,
70
+ "step": 175
71
+ },
72
+ {
73
+ "epoch": 1.2280431432973806,
74
+ "grad_norm": 28.664989471435547,
75
+ "learning_rate": 1.2208588957055216e-05,
76
+ "loss": 4.1832,
77
+ "step": 200
78
+ },
79
+ {
80
+ "epoch": 1.3821263482280433,
81
+ "grad_norm": 29.199169158935547,
82
+ "learning_rate": 1.374233128834356e-05,
83
+ "loss": 4.2434,
84
+ "step": 225
85
+ },
86
+ {
87
+ "epoch": 1.5362095531587057,
88
+ "grad_norm": 44.700767517089844,
89
+ "learning_rate": 1.5276073619631903e-05,
90
+ "loss": 4.2709,
91
+ "step": 250
92
+ },
93
+ {
94
+ "epoch": 1.6902927580893683,
95
+ "grad_norm": 17.18649673461914,
96
+ "learning_rate": 1.6809815950920248e-05,
97
+ "loss": 4.1264,
98
+ "step": 275
99
+ },
100
+ {
101
+ "epoch": 1.8443759630200307,
102
+ "grad_norm": 18.20244598388672,
103
+ "learning_rate": 1.834355828220859e-05,
104
+ "loss": 4.0579,
105
+ "step": 300
106
+ },
107
+ {
108
+ "epoch": 1.9984591679506933,
109
+ "grad_norm": 16.312583923339844,
110
+ "learning_rate": 1.9877300613496935e-05,
111
+ "loss": 4.273,
112
+ "step": 325
113
+ },
114
+ {
115
+ "epoch": 2.0,
116
+ "eval_accuracy": 0.44476744186046513,
117
+ "eval_loss": 1.0604538917541504,
118
+ "eval_macro_f1": 0.4264499308796011,
119
+ "eval_runtime": 0.5307,
120
+ "eval_samples_per_second": 1296.508,
121
+ "eval_steps_per_second": 81.032,
122
+ "eval_weighted_f1": 0.4247022385127954,
123
+ "step": 326
124
+ },
125
+ {
126
+ "epoch": 2.147919876733436,
127
+ "grad_norm": 53.90155029296875,
128
+ "learning_rate": 1.9843217450579417e-05,
129
+ "loss": 3.8448,
130
+ "step": 350
131
+ },
132
+ {
133
+ "epoch": 2.3020030816640986,
134
+ "grad_norm": 23.702350616455078,
135
+ "learning_rate": 1.967280163599182e-05,
136
+ "loss": 4.003,
137
+ "step": 375
138
+ },
139
+ {
140
+ "epoch": 2.4560862865947612,
141
+ "grad_norm": 20.542009353637695,
142
+ "learning_rate": 1.9502385821404228e-05,
143
+ "loss": 3.937,
144
+ "step": 400
145
+ },
146
+ {
147
+ "epoch": 2.610169491525424,
148
+ "grad_norm": 25.69508171081543,
149
+ "learning_rate": 1.9331970006816635e-05,
150
+ "loss": 3.9825,
151
+ "step": 425
152
+ },
153
+ {
154
+ "epoch": 2.7642526964560865,
155
+ "grad_norm": 27.31049156188965,
156
+ "learning_rate": 1.916155419222904e-05,
157
+ "loss": 3.8787,
158
+ "step": 450
159
+ },
160
+ {
161
+ "epoch": 2.9183359013867487,
162
+ "grad_norm": 36.959739685058594,
163
+ "learning_rate": 1.8991138377641446e-05,
164
+ "loss": 3.8863,
165
+ "step": 475
166
+ },
167
+ {
168
+ "epoch": 3.0,
169
+ "eval_accuracy": 0.4694767441860465,
170
+ "eval_loss": 1.0507975816726685,
171
+ "eval_macro_f1": 0.4561052941377414,
172
+ "eval_runtime": 0.5451,
173
+ "eval_samples_per_second": 1262.078,
174
+ "eval_steps_per_second": 78.88,
175
+ "eval_weighted_f1": 0.45593530514158637,
176
+ "step": 489
177
+ }
178
+ ],
179
+ "logging_steps": 25,
180
+ "max_steps": 3260,
181
+ "num_input_tokens_seen": 0,
182
+ "num_train_epochs": 20,
183
+ "save_steps": 500,
184
+ "stateful_callbacks": {
185
+ "EarlyStoppingCallback": {
186
+ "args": {
187
+ "early_stopping_patience": 3,
188
+ "early_stopping_threshold": 0.0
189
+ },
190
+ "attributes": {
191
+ "early_stopping_patience_counter": 0
192
+ }
193
+ },
194
+ "TrainerControl": {
195
+ "args": {
196
+ "should_epoch_stop": false,
197
+ "should_evaluate": false,
198
+ "should_log": false,
199
+ "should_save": true,
200
+ "should_training_stop": false
201
+ },
202
+ "attributes": {}
203
+ }
204
+ },
205
+ "total_flos": 0.0,
206
+ "train_batch_size": 8,
207
+ "trial_name": null,
208
+ "trial_params": null
209
+ }
explore-factcheck-ablations-vifactcheck-visobert-s44-20261114T115900Z-59e46264/trainer/checkpoint-489/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e01afdf8941355e68bb517f88f71e3ea90e5fe17e06b3b231d37563822902f29
3
+ size 5752
explore-factcheck-ablations-vifactcheck-visobert-s44-20261114T115900Z-59e46264/trainer/checkpoint-978/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:737eb4de09ae91bd8013d8af3a5517ff0a48fbd1ff08fd0ab0032927b4e4a580
3
+ size 390297092
explore-factcheck-ablations-vifactcheck-visobert-s44-20261114T115900Z-59e46264/trainer/checkpoint-978/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b1b070202d59190169cabe78e21099f2d8c33f924f8ea82e0d96f41afc23c37
3
+ size 775987770
explore-factcheck-ablations-vifactcheck-visobert-s44-20261114T115900Z-59e46264/trainer/checkpoint-978/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95623a23290d5b6f3eb2ad5f9bdf3234b78b03a57ce91580d6ab098b3c654401
3
+ size 14244
explore-factcheck-ablations-vifactcheck-visobert-s44-20261114T115900Z-59e46264/trainer/checkpoint-978/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41bbb7587835b76282874a4955e409946c8f4481c34a7d896baa402b205ab9e3
3
+ size 1064
explore-factcheck-ablations-vifactcheck-visobert-s44-20261114T115900Z-59e46264/trainer/checkpoint-978/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-s44-20261114T115900Z-59e46264/trainer/checkpoint-978/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-s44-20261114T115900Z-59e46264/trainer/checkpoint-978/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
explore-factcheck-ablations-vifactcheck-visobert-s44-20261114T115900Z-59e46264/trainer/checkpoint-978/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-s44-20261114T115900Z-59e46264/trainer/checkpoint-978/trainer_state.json ADDED
@@ -0,0 +1,382 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 489,
3
+ "best_metric": 0.4561052941377414,
4
+ "best_model_checkpoint": "/root/VNEncoder/explore/workspaces/eb5f0352b3159567ae3f/results/checkpoints/explore-factcheck-ablations-vifactcheck-visobert-s44-20261114T115900Z-59e46264/trainer/checkpoint-489",
5
+ "epoch": 6.0,
6
+ "eval_steps": 500,
7
+ "global_step": 978,
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": 26.18512535095215,
15
+ "learning_rate": 1.47239263803681e-06,
16
+ "loss": 4.8039,
17
+ "step": 25
18
+ },
19
+ {
20
+ "epoch": 0.3081664098613251,
21
+ "grad_norm": 23.501117706298828,
22
+ "learning_rate": 3.0061349693251535e-06,
23
+ "loss": 4.5663,
24
+ "step": 50
25
+ },
26
+ {
27
+ "epoch": 0.4622496147919877,
28
+ "grad_norm": 30.07345199584961,
29
+ "learning_rate": 4.539877300613497e-06,
30
+ "loss": 4.3556,
31
+ "step": 75
32
+ },
33
+ {
34
+ "epoch": 0.6163328197226502,
35
+ "grad_norm": 22.460676193237305,
36
+ "learning_rate": 6.073619631901841e-06,
37
+ "loss": 4.3901,
38
+ "step": 100
39
+ },
40
+ {
41
+ "epoch": 0.7704160246533128,
42
+ "grad_norm": 19.21281623840332,
43
+ "learning_rate": 7.6073619631901856e-06,
44
+ "loss": 4.2739,
45
+ "step": 125
46
+ },
47
+ {
48
+ "epoch": 0.9244992295839753,
49
+ "grad_norm": 31.142452239990234,
50
+ "learning_rate": 9.14110429447853e-06,
51
+ "loss": 4.3314,
52
+ "step": 150
53
+ },
54
+ {
55
+ "epoch": 1.0,
56
+ "eval_accuracy": 0.4331395348837209,
57
+ "eval_loss": 1.0662841796875,
58
+ "eval_macro_f1": 0.4325818234561818,
59
+ "eval_runtime": 0.5224,
60
+ "eval_samples_per_second": 1316.893,
61
+ "eval_steps_per_second": 82.306,
62
+ "eval_weighted_f1": 0.43295810595327466,
63
+ "step": 163
64
+ },
65
+ {
66
+ "epoch": 1.073959938366718,
67
+ "grad_norm": 30.027835845947266,
68
+ "learning_rate": 1.0674846625766873e-05,
69
+ "loss": 4.0454,
70
+ "step": 175
71
+ },
72
+ {
73
+ "epoch": 1.2280431432973806,
74
+ "grad_norm": 28.664989471435547,
75
+ "learning_rate": 1.2208588957055216e-05,
76
+ "loss": 4.1832,
77
+ "step": 200
78
+ },
79
+ {
80
+ "epoch": 1.3821263482280433,
81
+ "grad_norm": 29.199169158935547,
82
+ "learning_rate": 1.374233128834356e-05,
83
+ "loss": 4.2434,
84
+ "step": 225
85
+ },
86
+ {
87
+ "epoch": 1.5362095531587057,
88
+ "grad_norm": 44.700767517089844,
89
+ "learning_rate": 1.5276073619631903e-05,
90
+ "loss": 4.2709,
91
+ "step": 250
92
+ },
93
+ {
94
+ "epoch": 1.6902927580893683,
95
+ "grad_norm": 17.18649673461914,
96
+ "learning_rate": 1.6809815950920248e-05,
97
+ "loss": 4.1264,
98
+ "step": 275
99
+ },
100
+ {
101
+ "epoch": 1.8443759630200307,
102
+ "grad_norm": 18.20244598388672,
103
+ "learning_rate": 1.834355828220859e-05,
104
+ "loss": 4.0579,
105
+ "step": 300
106
+ },
107
+ {
108
+ "epoch": 1.9984591679506933,
109
+ "grad_norm": 16.312583923339844,
110
+ "learning_rate": 1.9877300613496935e-05,
111
+ "loss": 4.273,
112
+ "step": 325
113
+ },
114
+ {
115
+ "epoch": 2.0,
116
+ "eval_accuracy": 0.44476744186046513,
117
+ "eval_loss": 1.0604538917541504,
118
+ "eval_macro_f1": 0.4264499308796011,
119
+ "eval_runtime": 0.5307,
120
+ "eval_samples_per_second": 1296.508,
121
+ "eval_steps_per_second": 81.032,
122
+ "eval_weighted_f1": 0.4247022385127954,
123
+ "step": 326
124
+ },
125
+ {
126
+ "epoch": 2.147919876733436,
127
+ "grad_norm": 53.90155029296875,
128
+ "learning_rate": 1.9843217450579417e-05,
129
+ "loss": 3.8448,
130
+ "step": 350
131
+ },
132
+ {
133
+ "epoch": 2.3020030816640986,
134
+ "grad_norm": 23.702350616455078,
135
+ "learning_rate": 1.967280163599182e-05,
136
+ "loss": 4.003,
137
+ "step": 375
138
+ },
139
+ {
140
+ "epoch": 2.4560862865947612,
141
+ "grad_norm": 20.542009353637695,
142
+ "learning_rate": 1.9502385821404228e-05,
143
+ "loss": 3.937,
144
+ "step": 400
145
+ },
146
+ {
147
+ "epoch": 2.610169491525424,
148
+ "grad_norm": 25.69508171081543,
149
+ "learning_rate": 1.9331970006816635e-05,
150
+ "loss": 3.9825,
151
+ "step": 425
152
+ },
153
+ {
154
+ "epoch": 2.7642526964560865,
155
+ "grad_norm": 27.31049156188965,
156
+ "learning_rate": 1.916155419222904e-05,
157
+ "loss": 3.8787,
158
+ "step": 450
159
+ },
160
+ {
161
+ "epoch": 2.9183359013867487,
162
+ "grad_norm": 36.959739685058594,
163
+ "learning_rate": 1.8991138377641446e-05,
164
+ "loss": 3.8863,
165
+ "step": 475
166
+ },
167
+ {
168
+ "epoch": 3.0,
169
+ "eval_accuracy": 0.4694767441860465,
170
+ "eval_loss": 1.0507975816726685,
171
+ "eval_macro_f1": 0.4561052941377414,
172
+ "eval_runtime": 0.5451,
173
+ "eval_samples_per_second": 1262.078,
174
+ "eval_steps_per_second": 78.88,
175
+ "eval_weighted_f1": 0.45593530514158637,
176
+ "step": 489
177
+ },
178
+ {
179
+ "epoch": 3.0677966101694913,
180
+ "grad_norm": 39.750083923339844,
181
+ "learning_rate": 1.8820722563053853e-05,
182
+ "loss": 3.5064,
183
+ "step": 500
184
+ },
185
+ {
186
+ "epoch": 3.221879815100154,
187
+ "grad_norm": 26.4195613861084,
188
+ "learning_rate": 1.8650306748466257e-05,
189
+ "loss": 3.2998,
190
+ "step": 525
191
+ },
192
+ {
193
+ "epoch": 3.3759630200308166,
194
+ "grad_norm": 38.536067962646484,
195
+ "learning_rate": 1.8479890933878664e-05,
196
+ "loss": 3.2444,
197
+ "step": 550
198
+ },
199
+ {
200
+ "epoch": 3.5300462249614792,
201
+ "grad_norm": 34.36570358276367,
202
+ "learning_rate": 1.8309475119291072e-05,
203
+ "loss": 3.248,
204
+ "step": 575
205
+ },
206
+ {
207
+ "epoch": 3.684129429892142,
208
+ "grad_norm": 21.88361930847168,
209
+ "learning_rate": 1.8139059304703476e-05,
210
+ "loss": 3.4815,
211
+ "step": 600
212
+ },
213
+ {
214
+ "epoch": 3.8382126348228045,
215
+ "grad_norm": 30.08089256286621,
216
+ "learning_rate": 1.7968643490115886e-05,
217
+ "loss": 3.2135,
218
+ "step": 625
219
+ },
220
+ {
221
+ "epoch": 3.992295839753467,
222
+ "grad_norm": 41.80133056640625,
223
+ "learning_rate": 1.779822767552829e-05,
224
+ "loss": 3.3777,
225
+ "step": 650
226
+ },
227
+ {
228
+ "epoch": 4.0,
229
+ "eval_accuracy": 0.4258720930232558,
230
+ "eval_loss": 1.2215962409973145,
231
+ "eval_macro_f1": 0.4139381077647378,
232
+ "eval_runtime": 0.5444,
233
+ "eval_samples_per_second": 1263.736,
234
+ "eval_steps_per_second": 78.983,
235
+ "eval_weighted_f1": 0.41234793851550716,
236
+ "step": 652
237
+ },
238
+ {
239
+ "epoch": 4.141756548536209,
240
+ "grad_norm": 32.72038650512695,
241
+ "learning_rate": 1.7627811860940697e-05,
242
+ "loss": 2.5703,
243
+ "step": 675
244
+ },
245
+ {
246
+ "epoch": 4.295839753466872,
247
+ "grad_norm": 30.933374404907227,
248
+ "learning_rate": 1.7457396046353105e-05,
249
+ "loss": 2.379,
250
+ "step": 700
251
+ },
252
+ {
253
+ "epoch": 4.449922958397535,
254
+ "grad_norm": 41.27059555053711,
255
+ "learning_rate": 1.728698023176551e-05,
256
+ "loss": 2.3013,
257
+ "step": 725
258
+ },
259
+ {
260
+ "epoch": 4.604006163328197,
261
+ "grad_norm": 44.552589416503906,
262
+ "learning_rate": 1.7116564417177916e-05,
263
+ "loss": 2.4477,
264
+ "step": 750
265
+ },
266
+ {
267
+ "epoch": 4.75808936825886,
268
+ "grad_norm": 32.14017105102539,
269
+ "learning_rate": 1.6946148602590323e-05,
270
+ "loss": 2.5305,
271
+ "step": 775
272
+ },
273
+ {
274
+ "epoch": 4.9121725731895225,
275
+ "grad_norm": 52.507667541503906,
276
+ "learning_rate": 1.6775732788002727e-05,
277
+ "loss": 2.4726,
278
+ "step": 800
279
+ },
280
+ {
281
+ "epoch": 5.0,
282
+ "eval_accuracy": 0.4476744186046512,
283
+ "eval_loss": 1.3299803733825684,
284
+ "eval_macro_f1": 0.4312807079753993,
285
+ "eval_runtime": 0.5317,
286
+ "eval_samples_per_second": 1293.863,
287
+ "eval_steps_per_second": 80.866,
288
+ "eval_weighted_f1": 0.43219322970991875,
289
+ "step": 815
290
+ },
291
+ {
292
+ "epoch": 5.061633281972265,
293
+ "grad_norm": 43.44347381591797,
294
+ "learning_rate": 1.6605316973415134e-05,
295
+ "loss": 2.1862,
296
+ "step": 825
297
+ },
298
+ {
299
+ "epoch": 5.215716486902927,
300
+ "grad_norm": 34.3838005065918,
301
+ "learning_rate": 1.643490115882754e-05,
302
+ "loss": 1.3594,
303
+ "step": 850
304
+ },
305
+ {
306
+ "epoch": 5.36979969183359,
307
+ "grad_norm": 26.53452491760254,
308
+ "learning_rate": 1.6264485344239945e-05,
309
+ "loss": 1.4035,
310
+ "step": 875
311
+ },
312
+ {
313
+ "epoch": 5.523882896764253,
314
+ "grad_norm": 65.30026245117188,
315
+ "learning_rate": 1.6094069529652356e-05,
316
+ "loss": 1.6344,
317
+ "step": 900
318
+ },
319
+ {
320
+ "epoch": 5.677966101694915,
321
+ "grad_norm": 24.045738220214844,
322
+ "learning_rate": 1.592365371506476e-05,
323
+ "loss": 1.3127,
324
+ "step": 925
325
+ },
326
+ {
327
+ "epoch": 5.832049306625578,
328
+ "grad_norm": 74.62187957763672,
329
+ "learning_rate": 1.5753237900477167e-05,
330
+ "loss": 1.7081,
331
+ "step": 950
332
+ },
333
+ {
334
+ "epoch": 5.9861325115562405,
335
+ "grad_norm": 32.97041320800781,
336
+ "learning_rate": 1.5582822085889574e-05,
337
+ "loss": 1.7123,
338
+ "step": 975
339
+ },
340
+ {
341
+ "epoch": 6.0,
342
+ "eval_accuracy": 0.436046511627907,
343
+ "eval_loss": 1.6606853008270264,
344
+ "eval_macro_f1": 0.4329387850151633,
345
+ "eval_runtime": 0.5292,
346
+ "eval_samples_per_second": 1300.061,
347
+ "eval_steps_per_second": 81.254,
348
+ "eval_weighted_f1": 0.433455034582224,
349
+ "step": 978
350
+ }
351
+ ],
352
+ "logging_steps": 25,
353
+ "max_steps": 3260,
354
+ "num_input_tokens_seen": 0,
355
+ "num_train_epochs": 20,
356
+ "save_steps": 500,
357
+ "stateful_callbacks": {
358
+ "EarlyStoppingCallback": {
359
+ "args": {
360
+ "early_stopping_patience": 3,
361
+ "early_stopping_threshold": 0.0
362
+ },
363
+ "attributes": {
364
+ "early_stopping_patience_counter": 3
365
+ }
366
+ },
367
+ "TrainerControl": {
368
+ "args": {
369
+ "should_epoch_stop": false,
370
+ "should_evaluate": false,
371
+ "should_log": false,
372
+ "should_save": true,
373
+ "should_training_stop": true
374
+ },
375
+ "attributes": {}
376
+ }
377
+ },
378
+ "total_flos": 0.0,
379
+ "train_batch_size": 8,
380
+ "trial_name": null,
381
+ "trial_params": null
382
+ }
explore-factcheck-ablations-vifactcheck-visobert-s44-20261114T115900Z-59e46264/trainer/checkpoint-978/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e01afdf8941355e68bb517f88f71e3ea90e5fe17e06b3b231d37563822902f29
3
+ size 5752