Hugging Face's logo

vectorlessspace
/
microsoft_deberta-v3-base_cpt_43a4470a

Safetensors
Model card Files
xet
Community
vectorlessspace commited on
Commit
4e7f9db
·
verified ·
1 Parent(s): 8aa4d1c

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. checkpoint-12275/added_tokens.json +3 -0
  2. checkpoint-12275/config.json +35 -0
  3. checkpoint-12275/model.safetensors +3 -0
  4. checkpoint-12275/optimizer.pt +3 -0
  5. checkpoint-12275/rng_state.pth +3 -0
  6. checkpoint-12275/scheduler.pt +3 -0
  7. checkpoint-12275/special_tokens_map.json +15 -0
  8. checkpoint-12275/spm.model +3 -0
  9. checkpoint-12275/tokenizer.json +0 -0
  10. checkpoint-12275/tokenizer_config.json +58 -0
  11. checkpoint-12275/trainer_state.json +223 -0
  12. checkpoint-12275/training_args.bin +3 -0
  13. checkpoint-14730/added_tokens.json +3 -0
  14. checkpoint-14730/config.json +35 -0
  15. checkpoint-14730/model.safetensors +3 -0
  16. checkpoint-14730/optimizer.pt +3 -0
  17. checkpoint-14730/rng_state.pth +3 -0
  18. checkpoint-14730/scheduler.pt +3 -0
  19. checkpoint-14730/special_tokens_map.json +15 -0
  20. checkpoint-14730/spm.model +3 -0
  21. checkpoint-14730/tokenizer.json +0 -0
  22. checkpoint-14730/tokenizer_config.json +58 -0
  23. checkpoint-14730/trainer_state.json +265 -0
  24. checkpoint-14730/training_args.bin +3 -0
  25. checkpoint-17185/added_tokens.json +3 -0
  26. checkpoint-17185/config.json +35 -0
  27. checkpoint-17185/model.safetensors +3 -0
  28. checkpoint-17185/optimizer.pt +3 -0
  29. checkpoint-17185/rng_state.pth +3 -0
  30. checkpoint-17185/scheduler.pt +3 -0
  31. checkpoint-17185/special_tokens_map.json +15 -0
  32. checkpoint-17185/spm.model +3 -0
  33. checkpoint-17185/tokenizer.json +0 -0
  34. checkpoint-17185/tokenizer_config.json +58 -0
  35. checkpoint-17185/trainer_state.json +307 -0
  36. checkpoint-17185/training_args.bin +3 -0
  37. checkpoint-2455/added_tokens.json +3 -0
  38. checkpoint-2455/config.json +35 -0
  39. checkpoint-2455/model.safetensors +3 -0
  40. checkpoint-2455/optimizer.pt +3 -0
  41. checkpoint-2455/rng_state.pth +3 -0
  42. checkpoint-2455/scheduler.pt +3 -0
  43. checkpoint-2455/special_tokens_map.json +15 -0
  44. checkpoint-2455/spm.model +3 -0
  45. checkpoint-2455/tokenizer.json +0 -0
  46. checkpoint-2455/tokenizer_config.json +58 -0
  47. checkpoint-2455/trainer_state.json +55 -0
  48. checkpoint-2455/training_args.bin +3 -0
  49. checkpoint-4910/added_tokens.json +3 -0
  50. checkpoint-4910/config.json +35 -0
checkpoint-12275/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
checkpoint-12275/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/deberta-v3-base",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 3072,
12
+ "layer_norm_eps": 1e-07,
13
+ "max_position_embeddings": 512,
14
+ "max_relative_positions": -1,
15
+ "model_type": "deberta-v2",
16
+ "norm_rel_ebd": "layer_norm",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 768,
23
+ "pos_att_type": [
24
+ "p2c",
25
+ "c2p"
26
+ ],
27
+ "position_biased_input": false,
28
+ "position_buckets": 256,
29
+ "relative_attention": true,
30
+ "share_att_key": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.35.2",
33
+ "type_vocab_size": 0,
34
+ "vocab_size": 128100
35
+ }
checkpoint-12275/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e3ec562e9bc0af8e72efe55e98a848510c269a51bc406b9fd21c436ab3cea7b
3
+ size 737719272
checkpoint-12275/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:265ad7e9e8d35a115ed3f5a3e9eea057033cca42468edbba95b2474dcd0b3b99
3
+ size 1475558394
checkpoint-12275/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8aaa4298a0c223cb83812de0b9df340e50527bfc2a4763c51af0c60860c893b9
3
+ size 14244
checkpoint-12275/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac344fbd579f854a7f1ba9bd98c78ec505d9913450847414535ba91e9a4a0191
3
+ size 1064
checkpoint-12275/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": {
9
+ "content": "[UNK]",
10
+ "lstrip": false,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ }
15
+ }
checkpoint-12275/spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
checkpoint-12275/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-12275/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
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": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128000": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "sp_model_kwargs": {},
54
+ "split_by_punct": false,
55
+ "tokenizer_class": "DebertaV2Tokenizer",
56
+ "unk_token": "[UNK]",
57
+ "vocab_type": "spm"
58
+ }
checkpoint-12275/trainer_state.json ADDED
@@ -0,0 +1,223 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.15075480937957764,
3
+ "best_model_checkpoint": "/home/paperspace/microsoft_deberta-v3-base_cpt_64aa255e/checkpoint-9820",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 12275,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.2,
13
+ "learning_rate": 9.709048588885654e-07,
14
+ "loss": 0.5526,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.41,
19
+ "learning_rate": 9.418097177771311e-07,
20
+ "loss": 0.2449,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.61,
25
+ "learning_rate": 9.127145766656967e-07,
26
+ "loss": 0.1637,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.81,
31
+ "learning_rate": 8.836194355542625e-07,
32
+ "loss": 0.1627,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 1.0,
37
+ "eval_accuracy": 0.9574516238542492,
38
+ "eval_f1": 0.9576402605174089,
39
+ "eval_loss": 0.15390127897262573,
40
+ "eval_precision": 0.9583932523988209,
41
+ "eval_recall": 0.9574516238542492,
42
+ "eval_runtime": 11.3772,
43
+ "eval_samples_per_second": 776.73,
44
+ "eval_steps_per_second": 48.606,
45
+ "step": 2455
46
+ },
47
+ {
48
+ "epoch": 1.02,
49
+ "learning_rate": 8.54524294442828e-07,
50
+ "loss": 0.1536,
51
+ "step": 2500
52
+ },
53
+ {
54
+ "epoch": 1.22,
55
+ "learning_rate": 8.254291533313936e-07,
56
+ "loss": 0.1497,
57
+ "step": 3000
58
+ },
59
+ {
60
+ "epoch": 1.43,
61
+ "learning_rate": 7.963340122199592e-07,
62
+ "loss": 0.1478,
63
+ "step": 3500
64
+ },
65
+ {
66
+ "epoch": 1.63,
67
+ "learning_rate": 7.672388711085248e-07,
68
+ "loss": 0.1452,
69
+ "step": 4000
70
+ },
71
+ {
72
+ "epoch": 1.83,
73
+ "learning_rate": 7.381437299970904e-07,
74
+ "loss": 0.149,
75
+ "step": 4500
76
+ },
77
+ {
78
+ "epoch": 2.0,
79
+ "eval_accuracy": 0.9596016747765078,
80
+ "eval_f1": 0.9597684084567597,
81
+ "eval_loss": 0.15375804901123047,
82
+ "eval_precision": 0.9604205146694305,
83
+ "eval_recall": 0.9596016747765078,
84
+ "eval_runtime": 11.4943,
85
+ "eval_samples_per_second": 768.813,
86
+ "eval_steps_per_second": 48.111,
87
+ "step": 4910
88
+ },
89
+ {
90
+ "epoch": 2.04,
91
+ "learning_rate": 7.090485888856561e-07,
92
+ "loss": 0.1415,
93
+ "step": 5000
94
+ },
95
+ {
96
+ "epoch": 2.24,
97
+ "learning_rate": 6.799534477742217e-07,
98
+ "loss": 0.1358,
99
+ "step": 5500
100
+ },
101
+ {
102
+ "epoch": 2.44,
103
+ "learning_rate": 6.508583066627873e-07,
104
+ "loss": 0.1382,
105
+ "step": 6000
106
+ },
107
+ {
108
+ "epoch": 2.65,
109
+ "learning_rate": 6.217631655513529e-07,
110
+ "loss": 0.1289,
111
+ "step": 6500
112
+ },
113
+ {
114
+ "epoch": 2.85,
115
+ "learning_rate": 5.926680244399185e-07,
116
+ "loss": 0.1329,
117
+ "step": 7000
118
+ },
119
+ {
120
+ "epoch": 3.0,
121
+ "eval_accuracy": 0.9591490324770849,
122
+ "eval_f1": 0.9593624018161547,
123
+ "eval_loss": 0.16056260466575623,
124
+ "eval_precision": 0.9603821831580927,
125
+ "eval_recall": 0.9591490324770849,
126
+ "eval_runtime": 11.3768,
127
+ "eval_samples_per_second": 776.759,
128
+ "eval_steps_per_second": 48.608,
129
+ "step": 7365
130
+ },
131
+ {
132
+ "epoch": 3.05,
133
+ "learning_rate": 5.63572883328484e-07,
134
+ "loss": 0.1321,
135
+ "step": 7500
136
+ },
137
+ {
138
+ "epoch": 3.26,
139
+ "learning_rate": 5.344777422170497e-07,
140
+ "loss": 0.1324,
141
+ "step": 8000
142
+ },
143
+ {
144
+ "epoch": 3.46,
145
+ "learning_rate": 5.053826011056153e-07,
146
+ "loss": 0.1299,
147
+ "step": 8500
148
+ },
149
+ {
150
+ "epoch": 3.67,
151
+ "learning_rate": 4.7628745999418097e-07,
152
+ "loss": 0.136,
153
+ "step": 9000
154
+ },
155
+ {
156
+ "epoch": 3.87,
157
+ "learning_rate": 4.4719231888274657e-07,
158
+ "loss": 0.1308,
159
+ "step": 9500
160
+ },
161
+ {
162
+ "epoch": 4.0,
163
+ "eval_accuracy": 0.9608464410999208,
164
+ "eval_f1": 0.9610329418449746,
165
+ "eval_loss": 0.15075480937957764,
166
+ "eval_precision": 0.9618808519987467,
167
+ "eval_recall": 0.9608464410999208,
168
+ "eval_runtime": 11.2225,
169
+ "eval_samples_per_second": 787.436,
170
+ "eval_steps_per_second": 49.276,
171
+ "step": 9820
172
+ },
173
+ {
174
+ "epoch": 4.07,
175
+ "learning_rate": 4.1809717777131217e-07,
176
+ "loss": 0.1211,
177
+ "step": 10000
178
+ },
179
+ {
180
+ "epoch": 4.28,
181
+ "learning_rate": 3.890020366598778e-07,
182
+ "loss": 0.1233,
183
+ "step": 10500
184
+ },
185
+ {
186
+ "epoch": 4.48,
187
+ "learning_rate": 3.599068955484434e-07,
188
+ "loss": 0.1241,
189
+ "step": 11000
190
+ },
191
+ {
192
+ "epoch": 4.68,
193
+ "learning_rate": 3.3081175443700896e-07,
194
+ "loss": 0.1209,
195
+ "step": 11500
196
+ },
197
+ {
198
+ "epoch": 4.89,
199
+ "learning_rate": 3.017166133255746e-07,
200
+ "loss": 0.1225,
201
+ "step": 12000
202
+ },
203
+ {
204
+ "epoch": 5.0,
205
+ "eval_accuracy": 0.9617517256987665,
206
+ "eval_f1": 0.9619212980183091,
207
+ "eval_loss": 0.15455789864063263,
208
+ "eval_precision": 0.9626580984908996,
209
+ "eval_recall": 0.9617517256987665,
210
+ "eval_runtime": 11.421,
211
+ "eval_samples_per_second": 773.752,
212
+ "eval_steps_per_second": 48.42,
213
+ "step": 12275
214
+ }
215
+ ],
216
+ "logging_steps": 500,
217
+ "max_steps": 17185,
218
+ "num_train_epochs": 7,
219
+ "save_steps": 500,
220
+ "total_flos": 4760249984397900.0,
221
+ "trial_name": null,
222
+ "trial_params": null
223
+ }
checkpoint-12275/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e70840e0cfcf8fb576d1fc12469df9415b94e472002c13a74d5f660c5fc0120f
3
+ size 4664
checkpoint-14730/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
checkpoint-14730/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/deberta-v3-base",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 3072,
12
+ "layer_norm_eps": 1e-07,
13
+ "max_position_embeddings": 512,
14
+ "max_relative_positions": -1,
15
+ "model_type": "deberta-v2",
16
+ "norm_rel_ebd": "layer_norm",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 768,
23
+ "pos_att_type": [
24
+ "p2c",
25
+ "c2p"
26
+ ],
27
+ "position_biased_input": false,
28
+ "position_buckets": 256,
29
+ "relative_attention": true,
30
+ "share_att_key": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.35.2",
33
+ "type_vocab_size": 0,
34
+ "vocab_size": 128100
35
+ }
checkpoint-14730/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbd1a3b3cf0db22c98370a60ecdab6f0c36da2d58563317e94f1fcee4c5dd2e7
3
+ size 737719272
checkpoint-14730/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c07de338eaf350d40fb04c24c8db404ab1e6640ada443c428e362ab02448447
3
+ size 1475558394
checkpoint-14730/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d36a8b4674a19e51d99f47cb8c4e195a0979c6365bd6b5fd106581f3b2f7a02a
3
+ size 14244
checkpoint-14730/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8f70b3ffd38dba67f5f50dd1257644b8a40c9602d48d726e2cf51402477bb21
3
+ size 1064
checkpoint-14730/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": {
9
+ "content": "[UNK]",
10
+ "lstrip": false,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ }
15
+ }
checkpoint-14730/spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
checkpoint-14730/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-14730/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
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": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128000": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "sp_model_kwargs": {},
54
+ "split_by_punct": false,
55
+ "tokenizer_class": "DebertaV2Tokenizer",
56
+ "unk_token": "[UNK]",
57
+ "vocab_type": "spm"
58
+ }
checkpoint-14730/trainer_state.json ADDED
@@ -0,0 +1,265 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.15075480937957764,
3
+ "best_model_checkpoint": "/home/paperspace/microsoft_deberta-v3-base_cpt_64aa255e/checkpoint-9820",
4
+ "epoch": 6.0,
5
+ "eval_steps": 500,
6
+ "global_step": 14730,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.2,
13
+ "learning_rate": 9.709048588885654e-07,
14
+ "loss": 0.5526,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.41,
19
+ "learning_rate": 9.418097177771311e-07,
20
+ "loss": 0.2449,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.61,
25
+ "learning_rate": 9.127145766656967e-07,
26
+ "loss": 0.1637,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.81,
31
+ "learning_rate": 8.836194355542625e-07,
32
+ "loss": 0.1627,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 1.0,
37
+ "eval_accuracy": 0.9574516238542492,
38
+ "eval_f1": 0.9576402605174089,
39
+ "eval_loss": 0.15390127897262573,
40
+ "eval_precision": 0.9583932523988209,
41
+ "eval_recall": 0.9574516238542492,
42
+ "eval_runtime": 11.3772,
43
+ "eval_samples_per_second": 776.73,
44
+ "eval_steps_per_second": 48.606,
45
+ "step": 2455
46
+ },
47
+ {
48
+ "epoch": 1.02,
49
+ "learning_rate": 8.54524294442828e-07,
50
+ "loss": 0.1536,
51
+ "step": 2500
52
+ },
53
+ {
54
+ "epoch": 1.22,
55
+ "learning_rate": 8.254291533313936e-07,
56
+ "loss": 0.1497,
57
+ "step": 3000
58
+ },
59
+ {
60
+ "epoch": 1.43,
61
+ "learning_rate": 7.963340122199592e-07,
62
+ "loss": 0.1478,
63
+ "step": 3500
64
+ },
65
+ {
66
+ "epoch": 1.63,
67
+ "learning_rate": 7.672388711085248e-07,
68
+ "loss": 0.1452,
69
+ "step": 4000
70
+ },
71
+ {
72
+ "epoch": 1.83,
73
+ "learning_rate": 7.381437299970904e-07,
74
+ "loss": 0.149,
75
+ "step": 4500
76
+ },
77
+ {
78
+ "epoch": 2.0,
79
+ "eval_accuracy": 0.9596016747765078,
80
+ "eval_f1": 0.9597684084567597,
81
+ "eval_loss": 0.15375804901123047,
82
+ "eval_precision": 0.9604205146694305,
83
+ "eval_recall": 0.9596016747765078,
84
+ "eval_runtime": 11.4943,
85
+ "eval_samples_per_second": 768.813,
86
+ "eval_steps_per_second": 48.111,
87
+ "step": 4910
88
+ },
89
+ {
90
+ "epoch": 2.04,
91
+ "learning_rate": 7.090485888856561e-07,
92
+ "loss": 0.1415,
93
+ "step": 5000
94
+ },
95
+ {
96
+ "epoch": 2.24,
97
+ "learning_rate": 6.799534477742217e-07,
98
+ "loss": 0.1358,
99
+ "step": 5500
100
+ },
101
+ {
102
+ "epoch": 2.44,
103
+ "learning_rate": 6.508583066627873e-07,
104
+ "loss": 0.1382,
105
+ "step": 6000
106
+ },
107
+ {
108
+ "epoch": 2.65,
109
+ "learning_rate": 6.217631655513529e-07,
110
+ "loss": 0.1289,
111
+ "step": 6500
112
+ },
113
+ {
114
+ "epoch": 2.85,
115
+ "learning_rate": 5.926680244399185e-07,
116
+ "loss": 0.1329,
117
+ "step": 7000
118
+ },
119
+ {
120
+ "epoch": 3.0,
121
+ "eval_accuracy": 0.9591490324770849,
122
+ "eval_f1": 0.9593624018161547,
123
+ "eval_loss": 0.16056260466575623,
124
+ "eval_precision": 0.9603821831580927,
125
+ "eval_recall": 0.9591490324770849,
126
+ "eval_runtime": 11.3768,
127
+ "eval_samples_per_second": 776.759,
128
+ "eval_steps_per_second": 48.608,
129
+ "step": 7365
130
+ },
131
+ {
132
+ "epoch": 3.05,
133
+ "learning_rate": 5.63572883328484e-07,
134
+ "loss": 0.1321,
135
+ "step": 7500
136
+ },
137
+ {
138
+ "epoch": 3.26,
139
+ "learning_rate": 5.344777422170497e-07,
140
+ "loss": 0.1324,
141
+ "step": 8000
142
+ },
143
+ {
144
+ "epoch": 3.46,
145
+ "learning_rate": 5.053826011056153e-07,
146
+ "loss": 0.1299,
147
+ "step": 8500
148
+ },
149
+ {
150
+ "epoch": 3.67,
151
+ "learning_rate": 4.7628745999418097e-07,
152
+ "loss": 0.136,
153
+ "step": 9000
154
+ },
155
+ {
156
+ "epoch": 3.87,
157
+ "learning_rate": 4.4719231888274657e-07,
158
+ "loss": 0.1308,
159
+ "step": 9500
160
+ },
161
+ {
162
+ "epoch": 4.0,
163
+ "eval_accuracy": 0.9608464410999208,
164
+ "eval_f1": 0.9610329418449746,
165
+ "eval_loss": 0.15075480937957764,
166
+ "eval_precision": 0.9618808519987467,
167
+ "eval_recall": 0.9608464410999208,
168
+ "eval_runtime": 11.2225,
169
+ "eval_samples_per_second": 787.436,
170
+ "eval_steps_per_second": 49.276,
171
+ "step": 9820
172
+ },
173
+ {
174
+ "epoch": 4.07,
175
+ "learning_rate": 4.1809717777131217e-07,
176
+ "loss": 0.1211,
177
+ "step": 10000
178
+ },
179
+ {
180
+ "epoch": 4.28,
181
+ "learning_rate": 3.890020366598778e-07,
182
+ "loss": 0.1233,
183
+ "step": 10500
184
+ },
185
+ {
186
+ "epoch": 4.48,
187
+ "learning_rate": 3.599068955484434e-07,
188
+ "loss": 0.1241,
189
+ "step": 11000
190
+ },
191
+ {
192
+ "epoch": 4.68,
193
+ "learning_rate": 3.3081175443700896e-07,
194
+ "loss": 0.1209,
195
+ "step": 11500
196
+ },
197
+ {
198
+ "epoch": 4.89,
199
+ "learning_rate": 3.017166133255746e-07,
200
+ "loss": 0.1225,
201
+ "step": 12000
202
+ },
203
+ {
204
+ "epoch": 5.0,
205
+ "eval_accuracy": 0.9617517256987665,
206
+ "eval_f1": 0.9619212980183091,
207
+ "eval_loss": 0.15455789864063263,
208
+ "eval_precision": 0.9626580984908996,
209
+ "eval_recall": 0.9617517256987665,
210
+ "eval_runtime": 11.421,
211
+ "eval_samples_per_second": 773.752,
212
+ "eval_steps_per_second": 48.42,
213
+ "step": 12275
214
+ },
215
+ {
216
+ "epoch": 5.09,
217
+ "learning_rate": 2.726214722141402e-07,
218
+ "loss": 0.1164,
219
+ "step": 12500
220
+ },
221
+ {
222
+ "epoch": 5.3,
223
+ "learning_rate": 2.4352633110270586e-07,
224
+ "loss": 0.1227,
225
+ "step": 13000
226
+ },
227
+ {
228
+ "epoch": 5.5,
229
+ "learning_rate": 2.1443118999127143e-07,
230
+ "loss": 0.1134,
231
+ "step": 13500
232
+ },
233
+ {
234
+ "epoch": 5.7,
235
+ "learning_rate": 1.8533604887983705e-07,
236
+ "loss": 0.125,
237
+ "step": 14000
238
+ },
239
+ {
240
+ "epoch": 5.91,
241
+ "learning_rate": 1.5624090776840268e-07,
242
+ "loss": 0.1181,
243
+ "step": 14500
244
+ },
245
+ {
246
+ "epoch": 6.0,
247
+ "eval_accuracy": 0.9615254045490551,
248
+ "eval_f1": 0.9617002293060223,
249
+ "eval_loss": 0.15432989597320557,
250
+ "eval_precision": 0.9624729485181595,
251
+ "eval_recall": 0.9615254045490551,
252
+ "eval_runtime": 11.4696,
253
+ "eval_samples_per_second": 770.472,
254
+ "eval_steps_per_second": 48.214,
255
+ "step": 14730
256
+ }
257
+ ],
258
+ "logging_steps": 500,
259
+ "max_steps": 17185,
260
+ "num_train_epochs": 7,
261
+ "save_steps": 500,
262
+ "total_flos": 5713568281531608.0,
263
+ "trial_name": null,
264
+ "trial_params": null
265
+ }
checkpoint-14730/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e70840e0cfcf8fb576d1fc12469df9415b94e472002c13a74d5f660c5fc0120f
3
+ size 4664
checkpoint-17185/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
checkpoint-17185/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/deberta-v3-base",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 3072,
12
+ "layer_norm_eps": 1e-07,
13
+ "max_position_embeddings": 512,
14
+ "max_relative_positions": -1,
15
+ "model_type": "deberta-v2",
16
+ "norm_rel_ebd": "layer_norm",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 768,
23
+ "pos_att_type": [
24
+ "p2c",
25
+ "c2p"
26
+ ],
27
+ "position_biased_input": false,
28
+ "position_buckets": 256,
29
+ "relative_attention": true,
30
+ "share_att_key": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.35.2",
33
+ "type_vocab_size": 0,
34
+ "vocab_size": 128100
35
+ }
checkpoint-17185/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4c455a9c55ce1eab7dd51252a0ee863730cd617914fd153393c43be1d5572cf
3
+ size 737719272
checkpoint-17185/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab8516924dc0c30b5a7449d30fe6ea9688facd87bb71057bf2e4502d327e4258
3
+ size 1475558394
checkpoint-17185/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c939cc4f9e2189831f82740c2ca8f58cb188335126f3eca45ab7d1252ad3f9a7
3
+ size 14244
checkpoint-17185/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26e0c146fecbc31e7300c5f236ddc754ca8ef2f39800b7d7bd9cd37745bca8c9
3
+ size 1064
checkpoint-17185/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": {
9
+ "content": "[UNK]",
10
+ "lstrip": false,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ }
15
+ }
checkpoint-17185/spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
checkpoint-17185/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-17185/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
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": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128000": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "sp_model_kwargs": {},
54
+ "split_by_punct": false,
55
+ "tokenizer_class": "DebertaV2Tokenizer",
56
+ "unk_token": "[UNK]",
57
+ "vocab_type": "spm"
58
+ }
checkpoint-17185/trainer_state.json ADDED
@@ -0,0 +1,307 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.15075480937957764,
3
+ "best_model_checkpoint": "/home/paperspace/microsoft_deberta-v3-base_cpt_64aa255e/checkpoint-9820",
4
+ "epoch": 7.0,
5
+ "eval_steps": 500,
6
+ "global_step": 17185,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.2,
13
+ "learning_rate": 9.709048588885654e-07,
14
+ "loss": 0.5526,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.41,
19
+ "learning_rate": 9.418097177771311e-07,
20
+ "loss": 0.2449,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.61,
25
+ "learning_rate": 9.127145766656967e-07,
26
+ "loss": 0.1637,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.81,
31
+ "learning_rate": 8.836194355542625e-07,
32
+ "loss": 0.1627,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 1.0,
37
+ "eval_accuracy": 0.9574516238542492,
38
+ "eval_f1": 0.9576402605174089,
39
+ "eval_loss": 0.15390127897262573,
40
+ "eval_precision": 0.9583932523988209,
41
+ "eval_recall": 0.9574516238542492,
42
+ "eval_runtime": 11.3772,
43
+ "eval_samples_per_second": 776.73,
44
+ "eval_steps_per_second": 48.606,
45
+ "step": 2455
46
+ },
47
+ {
48
+ "epoch": 1.02,
49
+ "learning_rate": 8.54524294442828e-07,
50
+ "loss": 0.1536,
51
+ "step": 2500
52
+ },
53
+ {
54
+ "epoch": 1.22,
55
+ "learning_rate": 8.254291533313936e-07,
56
+ "loss": 0.1497,
57
+ "step": 3000
58
+ },
59
+ {
60
+ "epoch": 1.43,
61
+ "learning_rate": 7.963340122199592e-07,
62
+ "loss": 0.1478,
63
+ "step": 3500
64
+ },
65
+ {
66
+ "epoch": 1.63,
67
+ "learning_rate": 7.672388711085248e-07,
68
+ "loss": 0.1452,
69
+ "step": 4000
70
+ },
71
+ {
72
+ "epoch": 1.83,
73
+ "learning_rate": 7.381437299970904e-07,
74
+ "loss": 0.149,
75
+ "step": 4500
76
+ },
77
+ {
78
+ "epoch": 2.0,
79
+ "eval_accuracy": 0.9596016747765078,
80
+ "eval_f1": 0.9597684084567597,
81
+ "eval_loss": 0.15375804901123047,
82
+ "eval_precision": 0.9604205146694305,
83
+ "eval_recall": 0.9596016747765078,
84
+ "eval_runtime": 11.4943,
85
+ "eval_samples_per_second": 768.813,
86
+ "eval_steps_per_second": 48.111,
87
+ "step": 4910
88
+ },
89
+ {
90
+ "epoch": 2.04,
91
+ "learning_rate": 7.090485888856561e-07,
92
+ "loss": 0.1415,
93
+ "step": 5000
94
+ },
95
+ {
96
+ "epoch": 2.24,
97
+ "learning_rate": 6.799534477742217e-07,
98
+ "loss": 0.1358,
99
+ "step": 5500
100
+ },
101
+ {
102
+ "epoch": 2.44,
103
+ "learning_rate": 6.508583066627873e-07,
104
+ "loss": 0.1382,
105
+ "step": 6000
106
+ },
107
+ {
108
+ "epoch": 2.65,
109
+ "learning_rate": 6.217631655513529e-07,
110
+ "loss": 0.1289,
111
+ "step": 6500
112
+ },
113
+ {
114
+ "epoch": 2.85,
115
+ "learning_rate": 5.926680244399185e-07,
116
+ "loss": 0.1329,
117
+ "step": 7000
118
+ },
119
+ {
120
+ "epoch": 3.0,
121
+ "eval_accuracy": 0.9591490324770849,
122
+ "eval_f1": 0.9593624018161547,
123
+ "eval_loss": 0.16056260466575623,
124
+ "eval_precision": 0.9603821831580927,
125
+ "eval_recall": 0.9591490324770849,
126
+ "eval_runtime": 11.3768,
127
+ "eval_samples_per_second": 776.759,
128
+ "eval_steps_per_second": 48.608,
129
+ "step": 7365
130
+ },
131
+ {
132
+ "epoch": 3.05,
133
+ "learning_rate": 5.63572883328484e-07,
134
+ "loss": 0.1321,
135
+ "step": 7500
136
+ },
137
+ {
138
+ "epoch": 3.26,
139
+ "learning_rate": 5.344777422170497e-07,
140
+ "loss": 0.1324,
141
+ "step": 8000
142
+ },
143
+ {
144
+ "epoch": 3.46,
145
+ "learning_rate": 5.053826011056153e-07,
146
+ "loss": 0.1299,
147
+ "step": 8500
148
+ },
149
+ {
150
+ "epoch": 3.67,
151
+ "learning_rate": 4.7628745999418097e-07,
152
+ "loss": 0.136,
153
+ "step": 9000
154
+ },
155
+ {
156
+ "epoch": 3.87,
157
+ "learning_rate": 4.4719231888274657e-07,
158
+ "loss": 0.1308,
159
+ "step": 9500
160
+ },
161
+ {
162
+ "epoch": 4.0,
163
+ "eval_accuracy": 0.9608464410999208,
164
+ "eval_f1": 0.9610329418449746,
165
+ "eval_loss": 0.15075480937957764,
166
+ "eval_precision": 0.9618808519987467,
167
+ "eval_recall": 0.9608464410999208,
168
+ "eval_runtime": 11.2225,
169
+ "eval_samples_per_second": 787.436,
170
+ "eval_steps_per_second": 49.276,
171
+ "step": 9820
172
+ },
173
+ {
174
+ "epoch": 4.07,
175
+ "learning_rate": 4.1809717777131217e-07,
176
+ "loss": 0.1211,
177
+ "step": 10000
178
+ },
179
+ {
180
+ "epoch": 4.28,
181
+ "learning_rate": 3.890020366598778e-07,
182
+ "loss": 0.1233,
183
+ "step": 10500
184
+ },
185
+ {
186
+ "epoch": 4.48,
187
+ "learning_rate": 3.599068955484434e-07,
188
+ "loss": 0.1241,
189
+ "step": 11000
190
+ },
191
+ {
192
+ "epoch": 4.68,
193
+ "learning_rate": 3.3081175443700896e-07,
194
+ "loss": 0.1209,
195
+ "step": 11500
196
+ },
197
+ {
198
+ "epoch": 4.89,
199
+ "learning_rate": 3.017166133255746e-07,
200
+ "loss": 0.1225,
201
+ "step": 12000
202
+ },
203
+ {
204
+ "epoch": 5.0,
205
+ "eval_accuracy": 0.9617517256987665,
206
+ "eval_f1": 0.9619212980183091,
207
+ "eval_loss": 0.15455789864063263,
208
+ "eval_precision": 0.9626580984908996,
209
+ "eval_recall": 0.9617517256987665,
210
+ "eval_runtime": 11.421,
211
+ "eval_samples_per_second": 773.752,
212
+ "eval_steps_per_second": 48.42,
213
+ "step": 12275
214
+ },
215
+ {
216
+ "epoch": 5.09,
217
+ "learning_rate": 2.726214722141402e-07,
218
+ "loss": 0.1164,
219
+ "step": 12500
220
+ },
221
+ {
222
+ "epoch": 5.3,
223
+ "learning_rate": 2.4352633110270586e-07,
224
+ "loss": 0.1227,
225
+ "step": 13000
226
+ },
227
+ {
228
+ "epoch": 5.5,
229
+ "learning_rate": 2.1443118999127143e-07,
230
+ "loss": 0.1134,
231
+ "step": 13500
232
+ },
233
+ {
234
+ "epoch": 5.7,
235
+ "learning_rate": 1.8533604887983705e-07,
236
+ "loss": 0.125,
237
+ "step": 14000
238
+ },
239
+ {
240
+ "epoch": 5.91,
241
+ "learning_rate": 1.5624090776840268e-07,
242
+ "loss": 0.1181,
243
+ "step": 14500
244
+ },
245
+ {
246
+ "epoch": 6.0,
247
+ "eval_accuracy": 0.9615254045490551,
248
+ "eval_f1": 0.9617002293060223,
249
+ "eval_loss": 0.15432989597320557,
250
+ "eval_precision": 0.9624729485181595,
251
+ "eval_recall": 0.9615254045490551,
252
+ "eval_runtime": 11.4696,
253
+ "eval_samples_per_second": 770.472,
254
+ "eval_steps_per_second": 48.214,
255
+ "step": 14730
256
+ },
257
+ {
258
+ "epoch": 6.11,
259
+ "learning_rate": 1.2714576665696827e-07,
260
+ "loss": 0.1203,
261
+ "step": 15000
262
+ },
263
+ {
264
+ "epoch": 6.31,
265
+ "learning_rate": 9.80506255455339e-08,
266
+ "loss": 0.1054,
267
+ "step": 15500
268
+ },
269
+ {
270
+ "epoch": 6.52,
271
+ "learning_rate": 6.89554844340995e-08,
272
+ "loss": 0.1154,
273
+ "step": 16000
274
+ },
275
+ {
276
+ "epoch": 6.72,
277
+ "learning_rate": 3.986034332266511e-08,
278
+ "loss": 0.1164,
279
+ "step": 16500
280
+ },
281
+ {
282
+ "epoch": 6.92,
283
+ "learning_rate": 1.0765202211230723e-08,
284
+ "loss": 0.1321,
285
+ "step": 17000
286
+ },
287
+ {
288
+ "epoch": 7.0,
289
+ "eval_accuracy": 0.9624306891479009,
290
+ "eval_f1": 0.9625909933285097,
291
+ "eval_loss": 0.15378057956695557,
292
+ "eval_precision": 0.9632742135234372,
293
+ "eval_recall": 0.9624306891479009,
294
+ "eval_runtime": 11.6127,
295
+ "eval_samples_per_second": 760.975,
296
+ "eval_steps_per_second": 47.62,
297
+ "step": 17185
298
+ }
299
+ ],
300
+ "logging_steps": 500,
301
+ "max_steps": 17185,
302
+ "num_train_epochs": 7,
303
+ "save_steps": 500,
304
+ "total_flos": 6667692884621040.0,
305
+ "trial_name": null,
306
+ "trial_params": null
307
+ }
checkpoint-17185/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e70840e0cfcf8fb576d1fc12469df9415b94e472002c13a74d5f660c5fc0120f
3
+ size 4664
checkpoint-2455/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
checkpoint-2455/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/deberta-v3-base",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 3072,
12
+ "layer_norm_eps": 1e-07,
13
+ "max_position_embeddings": 512,
14
+ "max_relative_positions": -1,
15
+ "model_type": "deberta-v2",
16
+ "norm_rel_ebd": "layer_norm",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 768,
23
+ "pos_att_type": [
24
+ "p2c",
25
+ "c2p"
26
+ ],
27
+ "position_biased_input": false,
28
+ "position_buckets": 256,
29
+ "relative_attention": true,
30
+ "share_att_key": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.35.2",
33
+ "type_vocab_size": 0,
34
+ "vocab_size": 128100
35
+ }
checkpoint-2455/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f68ca4fb46060c8fe1e411e0d6410b861ecfca9a5a8bbd19dd6e3f8d2c56db78
3
+ size 737719272
checkpoint-2455/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f114448823bbb737a34f2b1e253cf70e2be1840ab6ef1a170ea7c4e11104c58
3
+ size 1475558394
checkpoint-2455/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49c5172d65792973516f853d1e5247822c579b673921f047995e0a9eca923964
3
+ size 14244
checkpoint-2455/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25542d5ea2d544e81dd598e9017386b9456fbf00465b6499237825aaa30c5512
3
+ size 1064
checkpoint-2455/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": {
9
+ "content": "[UNK]",
10
+ "lstrip": false,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ }
15
+ }
checkpoint-2455/spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
checkpoint-2455/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2455/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
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": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128000": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "sp_model_kwargs": {},
54
+ "split_by_punct": false,
55
+ "tokenizer_class": "DebertaV2Tokenizer",
56
+ "unk_token": "[UNK]",
57
+ "vocab_type": "spm"
58
+ }
checkpoint-2455/trainer_state.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.15390127897262573,
3
+ "best_model_checkpoint": "/home/paperspace/microsoft_deberta-v3-base_cpt_64aa255e/checkpoint-2455",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2455,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.2,
13
+ "learning_rate": 9.709048588885654e-07,
14
+ "loss": 0.5526,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.41,
19
+ "learning_rate": 9.418097177771311e-07,
20
+ "loss": 0.2449,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.61,
25
+ "learning_rate": 9.127145766656967e-07,
26
+ "loss": 0.1637,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.81,
31
+ "learning_rate": 8.836194355542625e-07,
32
+ "loss": 0.1627,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 1.0,
37
+ "eval_accuracy": 0.9574516238542492,
38
+ "eval_f1": 0.9576402605174089,
39
+ "eval_loss": 0.15390127897262573,
40
+ "eval_precision": 0.9583932523988209,
41
+ "eval_recall": 0.9574516238542492,
42
+ "eval_runtime": 11.3772,
43
+ "eval_samples_per_second": 776.73,
44
+ "eval_steps_per_second": 48.606,
45
+ "step": 2455
46
+ }
47
+ ],
48
+ "logging_steps": 500,
49
+ "max_steps": 17185,
50
+ "num_train_epochs": 7,
51
+ "save_steps": 500,
52
+ "total_flos": 953230934474388.0,
53
+ "trial_name": null,
54
+ "trial_params": null
55
+ }
checkpoint-2455/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e70840e0cfcf8fb576d1fc12469df9415b94e472002c13a74d5f660c5fc0120f
3
+ size 4664
checkpoint-4910/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
checkpoint-4910/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/deberta-v3-base",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 3072,
12
+ "layer_norm_eps": 1e-07,
13
+ "max_position_embeddings": 512,
14
+ "max_relative_positions": -1,
15
+ "model_type": "deberta-v2",
16
+ "norm_rel_ebd": "layer_norm",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 768,
23
+ "pos_att_type": [
24
+ "p2c",
25
+ "c2p"
26
+ ],
27
+ "position_biased_input": false,
28
+ "position_buckets": 256,
29
+ "relative_attention": true,
30
+ "share_att_key": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.35.2",
33
+ "type_vocab_size": 0,
34
+ "vocab_size": 128100
35
+ }