Hugging Face's logo

Shrav20
/
job-ner-deberta

Token Classification
Transformers
Safetensors
deberta-v2
Model card Files
xet
Community
Shrav20 commited on
Commit
1211eca
·
verified ·
1 Parent(s): 8ddc087

Upload folder using huggingface_hub

Browse files
Files changed (29) hide show
  1. checkpoint-5000/added_tokens.json +3 -0
  2. checkpoint-5000/config.json +59 -0
  3. checkpoint-5000/model.safetensors +3 -0
  4. checkpoint-5000/optimizer.pt +3 -0
  5. checkpoint-5000/rng_state.pth +3 -0
  6. checkpoint-5000/scaler.pt +3 -0
  7. checkpoint-5000/scheduler.pt +3 -0
  8. checkpoint-5000/special_tokens_map.json +15 -0
  9. checkpoint-5000/spm.model +3 -0
  10. checkpoint-5000/tokenizer.json +0 -0
  11. checkpoint-5000/tokenizer_config.json +59 -0
  12. checkpoint-5000/trainer_state.json +752 -0
  13. checkpoint-5000/training_args.bin +3 -0
  14. checkpoint-5064/added_tokens.json +3 -0
  15. checkpoint-5064/config.json +59 -0
  16. checkpoint-5064/model.safetensors +3 -0
  17. checkpoint-5064/optimizer.pt +3 -0
  18. checkpoint-5064/rng_state.pth +3 -0
  19. checkpoint-5064/scaler.pt +3 -0
  20. checkpoint-5064/scheduler.pt +3 -0
  21. checkpoint-5064/special_tokens_map.json +15 -0
  22. checkpoint-5064/spm.model +3 -0
  23. checkpoint-5064/tokenizer.json +0 -0
  24. checkpoint-5064/tokenizer_config.json +59 -0
  25. checkpoint-5064/trainer_state.json +759 -0
  26. checkpoint-5064/training_args.bin +3 -0
  27. config.json +18 -18
  28. tokenizer.json +1 -6
  29. training_args.bin +3 -0
checkpoint-5000/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
checkpoint-5000/config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DebertaV2ForTokenClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 1,
7
+ "dtype": "float32",
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2",
16
+ "3": "LABEL_3",
17
+ "4": "LABEL_4",
18
+ "5": "LABEL_5",
19
+ "6": "LABEL_6",
20
+ "7": "LABEL_7",
21
+ "8": "LABEL_8"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "LABEL_0": 0,
27
+ "LABEL_1": 1,
28
+ "LABEL_2": 2,
29
+ "LABEL_3": 3,
30
+ "LABEL_4": 4,
31
+ "LABEL_5": 5,
32
+ "LABEL_6": 6,
33
+ "LABEL_7": 7,
34
+ "LABEL_8": 8
35
+ },
36
+ "layer_norm_eps": 1e-07,
37
+ "legacy": true,
38
+ "max_position_embeddings": 512,
39
+ "max_relative_positions": -1,
40
+ "model_type": "deberta-v2",
41
+ "norm_rel_ebd": "layer_norm",
42
+ "num_attention_heads": 12,
43
+ "num_hidden_layers": 12,
44
+ "pad_token_id": 0,
45
+ "pooler_dropout": 0,
46
+ "pooler_hidden_act": "gelu",
47
+ "pooler_hidden_size": 768,
48
+ "pos_att_type": [
49
+ "p2c",
50
+ "c2p"
51
+ ],
52
+ "position_biased_input": false,
53
+ "position_buckets": 256,
54
+ "relative_attention": true,
55
+ "share_att_key": true,
56
+ "transformers_version": "4.56.1",
57
+ "type_vocab_size": 0,
58
+ "vocab_size": 128100
59
+ }
checkpoint-5000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29caa67a5a5d3c257059d7bf9719ae6a49fbd154be64ef7866c62aaf36b681ec
3
+ size 735378268
checkpoint-5000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:621dc4d4656d0480d1a56778748ba2b4b22c61d167927a05a38e4a241a203c56
3
+ size 1470878283
checkpoint-5000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b48dfd571d881f4a8068c767e2be8fb52102ed0832c2de99c399a418d2d658c6
3
+ size 14645
checkpoint-5000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:203b45607d9b09c4083e736a94ab0083b09046bdeb2eb3cf626d7fe59682b08f
3
+ size 1383
checkpoint-5000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ee65c2046475aac0172642791112a7b39d987d84e2ba816f08aa22687a5e9d9
3
+ size 1465
checkpoint-5000/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-5000/spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
checkpoint-5000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-5000/tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "extra_special_tokens": {},
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "sp_model_kwargs": {},
55
+ "split_by_punct": false,
56
+ "tokenizer_class": "DebertaV2Tokenizer",
57
+ "unk_token": "[UNK]",
58
+ "vocab_type": "spm"
59
+ }
checkpoint-5000/trainer_state.json ADDED
@@ -0,0 +1,752 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.962085308056872,
6
+ "eval_steps": 500,
7
+ "global_step": 5000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.02962085308056872,
14
+ "grad_norm": 0.0359644778072834,
15
+ "learning_rate": 4.951619273301738e-05,
16
+ "loss": 0.3566,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.05924170616113744,
21
+ "grad_norm": 0.045561712235212326,
22
+ "learning_rate": 4.902251184834124e-05,
23
+ "loss": 0.0019,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.08886255924170616,
28
+ "grad_norm": 0.011206220835447311,
29
+ "learning_rate": 4.852883096366509e-05,
30
+ "loss": 0.0017,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.11848341232227488,
35
+ "grad_norm": 0.008807787671685219,
36
+ "learning_rate": 4.8035150078988947e-05,
37
+ "loss": 0.0006,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.1481042654028436,
42
+ "grad_norm": 0.005796543322503567,
43
+ "learning_rate": 4.75414691943128e-05,
44
+ "loss": 0.0009,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 0.17772511848341233,
49
+ "grad_norm": 0.005227432586252689,
50
+ "learning_rate": 4.7047788309636656e-05,
51
+ "loss": 0.0006,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 0.20734597156398105,
56
+ "grad_norm": 0.003554289462044835,
57
+ "learning_rate": 4.655410742496051e-05,
58
+ "loss": 0.0005,
59
+ "step": 350
60
+ },
61
+ {
62
+ "epoch": 0.23696682464454977,
63
+ "grad_norm": 0.0033741986844688654,
64
+ "learning_rate": 4.6060426540284365e-05,
65
+ "loss": 0.0012,
66
+ "step": 400
67
+ },
68
+ {
69
+ "epoch": 0.2665876777251185,
70
+ "grad_norm": 0.002832002704963088,
71
+ "learning_rate": 4.556674565560822e-05,
72
+ "loss": 0.0002,
73
+ "step": 450
74
+ },
75
+ {
76
+ "epoch": 0.2962085308056872,
77
+ "grad_norm": 0.002275377744808793,
78
+ "learning_rate": 4.5073064770932074e-05,
79
+ "loss": 0.0007,
80
+ "step": 500
81
+ },
82
+ {
83
+ "epoch": 0.32582938388625593,
84
+ "grad_norm": 0.003911971114575863,
85
+ "learning_rate": 4.457938388625593e-05,
86
+ "loss": 0.0006,
87
+ "step": 550
88
+ },
89
+ {
90
+ "epoch": 0.35545023696682465,
91
+ "grad_norm": 0.006926015485078096,
92
+ "learning_rate": 4.408570300157978e-05,
93
+ "loss": 0.0014,
94
+ "step": 600
95
+ },
96
+ {
97
+ "epoch": 0.38507109004739337,
98
+ "grad_norm": 0.0027338722720742226,
99
+ "learning_rate": 4.359202211690364e-05,
100
+ "loss": 0.0008,
101
+ "step": 650
102
+ },
103
+ {
104
+ "epoch": 0.4146919431279621,
105
+ "grad_norm": 0.001827694708481431,
106
+ "learning_rate": 4.309834123222749e-05,
107
+ "loss": 0.0003,
108
+ "step": 700
109
+ },
110
+ {
111
+ "epoch": 0.4443127962085308,
112
+ "grad_norm": 0.0012653936864808202,
113
+ "learning_rate": 4.2604660347551346e-05,
114
+ "loss": 0.0001,
115
+ "step": 750
116
+ },
117
+ {
118
+ "epoch": 0.47393364928909953,
119
+ "grad_norm": 0.0022165332920849323,
120
+ "learning_rate": 4.21109794628752e-05,
121
+ "loss": 0.0004,
122
+ "step": 800
123
+ },
124
+ {
125
+ "epoch": 0.5035545023696683,
126
+ "grad_norm": 0.0063213687390089035,
127
+ "learning_rate": 4.1617298578199055e-05,
128
+ "loss": 0.0007,
129
+ "step": 850
130
+ },
131
+ {
132
+ "epoch": 0.533175355450237,
133
+ "grad_norm": 0.024515969678759575,
134
+ "learning_rate": 4.112361769352291e-05,
135
+ "loss": 0.001,
136
+ "step": 900
137
+ },
138
+ {
139
+ "epoch": 0.5627962085308057,
140
+ "grad_norm": 0.003376233857125044,
141
+ "learning_rate": 4.0629936808846765e-05,
142
+ "loss": 0.0005,
143
+ "step": 950
144
+ },
145
+ {
146
+ "epoch": 0.5924170616113744,
147
+ "grad_norm": 0.001513678696937859,
148
+ "learning_rate": 4.013625592417062e-05,
149
+ "loss": 0.0002,
150
+ "step": 1000
151
+ },
152
+ {
153
+ "epoch": 0.6220379146919431,
154
+ "grad_norm": 0.013340185396373272,
155
+ "learning_rate": 3.9642575039494474e-05,
156
+ "loss": 0.0004,
157
+ "step": 1050
158
+ },
159
+ {
160
+ "epoch": 0.6516587677725119,
161
+ "grad_norm": 0.0008107981411740184,
162
+ "learning_rate": 3.914889415481833e-05,
163
+ "loss": 0.0001,
164
+ "step": 1100
165
+ },
166
+ {
167
+ "epoch": 0.6812796208530806,
168
+ "grad_norm": 0.000826548261102289,
169
+ "learning_rate": 3.865521327014218e-05,
170
+ "loss": 0.0,
171
+ "step": 1150
172
+ },
173
+ {
174
+ "epoch": 0.7109004739336493,
175
+ "grad_norm": 0.0015754875494167209,
176
+ "learning_rate": 3.816153238546604e-05,
177
+ "loss": 0.0003,
178
+ "step": 1200
179
+ },
180
+ {
181
+ "epoch": 0.740521327014218,
182
+ "grad_norm": 0.0010875407606363297,
183
+ "learning_rate": 3.766785150078989e-05,
184
+ "loss": 0.0001,
185
+ "step": 1250
186
+ },
187
+ {
188
+ "epoch": 0.7701421800947867,
189
+ "grad_norm": 0.0013485795352607965,
190
+ "learning_rate": 3.7174170616113746e-05,
191
+ "loss": 0.0002,
192
+ "step": 1300
193
+ },
194
+ {
195
+ "epoch": 0.7997630331753555,
196
+ "grad_norm": 0.002195018110796809,
197
+ "learning_rate": 3.66804897314376e-05,
198
+ "loss": 0.0008,
199
+ "step": 1350
200
+ },
201
+ {
202
+ "epoch": 0.8293838862559242,
203
+ "grad_norm": 0.0013226654846221209,
204
+ "learning_rate": 3.6186808846761455e-05,
205
+ "loss": 0.0004,
206
+ "step": 1400
207
+ },
208
+ {
209
+ "epoch": 0.8590047393364929,
210
+ "grad_norm": 0.020256407558918,
211
+ "learning_rate": 3.569312796208531e-05,
212
+ "loss": 0.0011,
213
+ "step": 1450
214
+ },
215
+ {
216
+ "epoch": 0.8886255924170616,
217
+ "grad_norm": 0.0060112737119197845,
218
+ "learning_rate": 3.5199447077409164e-05,
219
+ "loss": 0.0003,
220
+ "step": 1500
221
+ },
222
+ {
223
+ "epoch": 0.9182464454976303,
224
+ "grad_norm": 0.0010298583656549454,
225
+ "learning_rate": 3.470576619273302e-05,
226
+ "loss": 0.0002,
227
+ "step": 1550
228
+ },
229
+ {
230
+ "epoch": 0.9478672985781991,
231
+ "grad_norm": 0.0008804717799648643,
232
+ "learning_rate": 3.4212085308056873e-05,
233
+ "loss": 0.0003,
234
+ "step": 1600
235
+ },
236
+ {
237
+ "epoch": 0.9774881516587678,
238
+ "grad_norm": 0.0007368926890194416,
239
+ "learning_rate": 3.371840442338073e-05,
240
+ "loss": 0.0002,
241
+ "step": 1650
242
+ },
243
+ {
244
+ "epoch": 1.0,
245
+ "eval_loss": 6.839788693469018e-05,
246
+ "eval_report": " precision recall f1-score support\n\nCERTIFICATION 1.00 1.00 1.00 1410\n EDUCATION 1.00 1.00 1.00 2241\n LANGUAGE 1.00 1.00 1.00 3014\n SKILL 1.00 1.00 1.00 3069\n\n micro avg 1.00 1.00 1.00 9734\n macro avg 1.00 1.00 1.00 9734\n weighted avg 1.00 1.00 1.00 9734\n",
247
+ "eval_runtime": 7.1833,
248
+ "eval_samples_per_second": 208.818,
249
+ "eval_steps_per_second": 26.172,
250
+ "step": 1688
251
+ },
252
+ {
253
+ "epoch": 1.0071090047393365,
254
+ "grad_norm": 0.0006786159938201308,
255
+ "learning_rate": 3.322472353870458e-05,
256
+ "loss": 0.0002,
257
+ "step": 1700
258
+ },
259
+ {
260
+ "epoch": 1.0367298578199051,
261
+ "grad_norm": 0.005513947457075119,
262
+ "learning_rate": 3.273104265402844e-05,
263
+ "loss": 0.0001,
264
+ "step": 1750
265
+ },
266
+ {
267
+ "epoch": 1.066350710900474,
268
+ "grad_norm": 0.000574503734242171,
269
+ "learning_rate": 3.223736176935229e-05,
270
+ "loss": 0.0001,
271
+ "step": 1800
272
+ },
273
+ {
274
+ "epoch": 1.0959715639810426,
275
+ "grad_norm": 0.004586311522871256,
276
+ "learning_rate": 3.1743680884676146e-05,
277
+ "loss": 0.0006,
278
+ "step": 1850
279
+ },
280
+ {
281
+ "epoch": 1.1255924170616114,
282
+ "grad_norm": 0.000738324539270252,
283
+ "learning_rate": 3.125e-05,
284
+ "loss": 0.0002,
285
+ "step": 1900
286
+ },
287
+ {
288
+ "epoch": 1.15521327014218,
289
+ "grad_norm": 0.0006399003323167562,
290
+ "learning_rate": 3.0756319115323855e-05,
291
+ "loss": 0.0001,
292
+ "step": 1950
293
+ },
294
+ {
295
+ "epoch": 1.1848341232227488,
296
+ "grad_norm": 0.0004596344952005893,
297
+ "learning_rate": 3.026263823064771e-05,
298
+ "loss": 0.0,
299
+ "step": 2000
300
+ },
301
+ {
302
+ "epoch": 1.2144549763033174,
303
+ "grad_norm": 0.0004429569817148149,
304
+ "learning_rate": 2.9768957345971564e-05,
305
+ "loss": 0.0001,
306
+ "step": 2050
307
+ },
308
+ {
309
+ "epoch": 1.2440758293838863,
310
+ "grad_norm": 0.0004196607042104006,
311
+ "learning_rate": 2.927527646129542e-05,
312
+ "loss": 0.0,
313
+ "step": 2100
314
+ },
315
+ {
316
+ "epoch": 1.2736966824644549,
317
+ "grad_norm": 0.0004485426179599017,
318
+ "learning_rate": 2.8781595576619273e-05,
319
+ "loss": 0.0,
320
+ "step": 2150
321
+ },
322
+ {
323
+ "epoch": 1.3033175355450237,
324
+ "grad_norm": 0.0005169134237803519,
325
+ "learning_rate": 2.8287914691943128e-05,
326
+ "loss": 0.0001,
327
+ "step": 2200
328
+ },
329
+ {
330
+ "epoch": 1.3329383886255926,
331
+ "grad_norm": 0.0005291880224831402,
332
+ "learning_rate": 2.7794233807266982e-05,
333
+ "loss": 0.0002,
334
+ "step": 2250
335
+ },
336
+ {
337
+ "epoch": 1.3625592417061612,
338
+ "grad_norm": 0.00048425907152704895,
339
+ "learning_rate": 2.7300552922590837e-05,
340
+ "loss": 0.0001,
341
+ "step": 2300
342
+ },
343
+ {
344
+ "epoch": 1.3921800947867298,
345
+ "grad_norm": 0.0004068867419846356,
346
+ "learning_rate": 2.6806872037914695e-05,
347
+ "loss": 0.0,
348
+ "step": 2350
349
+ },
350
+ {
351
+ "epoch": 1.4218009478672986,
352
+ "grad_norm": 0.0003516751166898757,
353
+ "learning_rate": 2.631319115323855e-05,
354
+ "loss": 0.0,
355
+ "step": 2400
356
+ },
357
+ {
358
+ "epoch": 1.4514218009478674,
359
+ "grad_norm": 0.0003432795056141913,
360
+ "learning_rate": 2.5819510268562404e-05,
361
+ "loss": 0.0,
362
+ "step": 2450
363
+ },
364
+ {
365
+ "epoch": 1.481042654028436,
366
+ "grad_norm": 0.00032765124342404306,
367
+ "learning_rate": 2.532582938388626e-05,
368
+ "loss": 0.0,
369
+ "step": 2500
370
+ },
371
+ {
372
+ "epoch": 1.5106635071090047,
373
+ "grad_norm": 0.00030620096367783844,
374
+ "learning_rate": 2.4832148499210113e-05,
375
+ "loss": 0.0,
376
+ "step": 2550
377
+ },
378
+ {
379
+ "epoch": 1.5402843601895735,
380
+ "grad_norm": 0.00032276054844260216,
381
+ "learning_rate": 2.4338467614533967e-05,
382
+ "loss": 0.0,
383
+ "step": 2600
384
+ },
385
+ {
386
+ "epoch": 1.5699052132701423,
387
+ "grad_norm": 0.0003284791891928762,
388
+ "learning_rate": 2.3844786729857822e-05,
389
+ "loss": 0.0,
390
+ "step": 2650
391
+ },
392
+ {
393
+ "epoch": 1.599526066350711,
394
+ "grad_norm": 0.0005517126410268247,
395
+ "learning_rate": 2.3351105845181677e-05,
396
+ "loss": 0.0001,
397
+ "step": 2700
398
+ },
399
+ {
400
+ "epoch": 1.6291469194312795,
401
+ "grad_norm": 0.0004335689009167254,
402
+ "learning_rate": 2.285742496050553e-05,
403
+ "loss": 0.0,
404
+ "step": 2750
405
+ },
406
+ {
407
+ "epoch": 1.6587677725118484,
408
+ "grad_norm": 0.00938709732145071,
409
+ "learning_rate": 2.2363744075829386e-05,
410
+ "loss": 0.0011,
411
+ "step": 2800
412
+ },
413
+ {
414
+ "epoch": 1.6883886255924172,
415
+ "grad_norm": 0.002625273773446679,
416
+ "learning_rate": 2.187006319115324e-05,
417
+ "loss": 0.0,
418
+ "step": 2850
419
+ },
420
+ {
421
+ "epoch": 1.7180094786729858,
422
+ "grad_norm": 0.00048340365174226463,
423
+ "learning_rate": 2.1376382306477095e-05,
424
+ "loss": 0.0,
425
+ "step": 2900
426
+ },
427
+ {
428
+ "epoch": 1.7476303317535544,
429
+ "grad_norm": 0.0035711589735001326,
430
+ "learning_rate": 2.088270142180095e-05,
431
+ "loss": 0.0005,
432
+ "step": 2950
433
+ },
434
+ {
435
+ "epoch": 1.7772511848341233,
436
+ "grad_norm": 0.0005380721995607018,
437
+ "learning_rate": 2.0389020537124804e-05,
438
+ "loss": 0.0001,
439
+ "step": 3000
440
+ },
441
+ {
442
+ "epoch": 1.806872037914692,
443
+ "grad_norm": 0.00039379362715408206,
444
+ "learning_rate": 1.9895339652448658e-05,
445
+ "loss": 0.0,
446
+ "step": 3050
447
+ },
448
+ {
449
+ "epoch": 1.8364928909952607,
450
+ "grad_norm": 0.00031137277255766094,
451
+ "learning_rate": 1.9401658767772513e-05,
452
+ "loss": 0.0001,
453
+ "step": 3100
454
+ },
455
+ {
456
+ "epoch": 1.8661137440758293,
457
+ "grad_norm": 0.00033859844552353024,
458
+ "learning_rate": 1.8907977883096367e-05,
459
+ "loss": 0.0003,
460
+ "step": 3150
461
+ },
462
+ {
463
+ "epoch": 1.8957345971563981,
464
+ "grad_norm": 0.0003177137696184218,
465
+ "learning_rate": 1.8414296998420222e-05,
466
+ "loss": 0.0,
467
+ "step": 3200
468
+ },
469
+ {
470
+ "epoch": 1.925355450236967,
471
+ "grad_norm": 0.5252463817596436,
472
+ "learning_rate": 1.7920616113744076e-05,
473
+ "loss": 0.0001,
474
+ "step": 3250
475
+ },
476
+ {
477
+ "epoch": 1.9549763033175356,
478
+ "grad_norm": 0.000578847888391465,
479
+ "learning_rate": 1.742693522906793e-05,
480
+ "loss": 0.0002,
481
+ "step": 3300
482
+ },
483
+ {
484
+ "epoch": 1.9845971563981042,
485
+ "grad_norm": 0.00031036767177283764,
486
+ "learning_rate": 1.6933254344391785e-05,
487
+ "loss": 0.0,
488
+ "step": 3350
489
+ },
490
+ {
491
+ "epoch": 2.0,
492
+ "eval_loss": 0.0002486561133991927,
493
+ "eval_report": " precision recall f1-score support\n\nCERTIFICATION 1.00 1.00 1.00 1410\n EDUCATION 1.00 1.00 1.00 2241\n LANGUAGE 1.00 1.00 1.00 3014\n SKILL 1.00 1.00 1.00 3069\n\n micro avg 1.00 1.00 1.00 9734\n macro avg 1.00 1.00 1.00 9734\n weighted avg 1.00 1.00 1.00 9734\n",
494
+ "eval_runtime": 7.0179,
495
+ "eval_samples_per_second": 213.738,
496
+ "eval_steps_per_second": 26.788,
497
+ "step": 3376
498
+ },
499
+ {
500
+ "epoch": 2.014218009478673,
501
+ "grad_norm": 0.00038110482273623347,
502
+ "learning_rate": 1.643957345971564e-05,
503
+ "loss": 0.0002,
504
+ "step": 3400
505
+ },
506
+ {
507
+ "epoch": 2.043838862559242,
508
+ "grad_norm": 0.00030082205194048584,
509
+ "learning_rate": 1.5945892575039495e-05,
510
+ "loss": 0.0,
511
+ "step": 3450
512
+ },
513
+ {
514
+ "epoch": 2.0734597156398102,
515
+ "grad_norm": 0.00030870226328261197,
516
+ "learning_rate": 1.545221169036335e-05,
517
+ "loss": 0.0,
518
+ "step": 3500
519
+ },
520
+ {
521
+ "epoch": 2.103080568720379,
522
+ "grad_norm": 0.00023404941020999104,
523
+ "learning_rate": 1.4958530805687204e-05,
524
+ "loss": 0.0001,
525
+ "step": 3550
526
+ },
527
+ {
528
+ "epoch": 2.132701421800948,
529
+ "grad_norm": 0.00021994848793838173,
530
+ "learning_rate": 1.4464849921011058e-05,
531
+ "loss": 0.0,
532
+ "step": 3600
533
+ },
534
+ {
535
+ "epoch": 2.1623222748815167,
536
+ "grad_norm": 0.0002600239240564406,
537
+ "learning_rate": 1.3971169036334913e-05,
538
+ "loss": 0.0,
539
+ "step": 3650
540
+ },
541
+ {
542
+ "epoch": 2.191943127962085,
543
+ "grad_norm": 0.00019250177138019353,
544
+ "learning_rate": 1.3477488151658769e-05,
545
+ "loss": 0.0,
546
+ "step": 3700
547
+ },
548
+ {
549
+ "epoch": 2.221563981042654,
550
+ "grad_norm": 0.00024143581686075777,
551
+ "learning_rate": 1.2983807266982623e-05,
552
+ "loss": 0.0,
553
+ "step": 3750
554
+ },
555
+ {
556
+ "epoch": 2.251184834123223,
557
+ "grad_norm": 0.00020565264276228845,
558
+ "learning_rate": 1.2490126382306478e-05,
559
+ "loss": 0.0,
560
+ "step": 3800
561
+ },
562
+ {
563
+ "epoch": 2.2808056872037916,
564
+ "grad_norm": 0.0002789797727018595,
565
+ "learning_rate": 1.1996445497630332e-05,
566
+ "loss": 0.0002,
567
+ "step": 3850
568
+ },
569
+ {
570
+ "epoch": 2.31042654028436,
571
+ "grad_norm": 0.0007835368160158396,
572
+ "learning_rate": 1.1502764612954187e-05,
573
+ "loss": 0.0007,
574
+ "step": 3900
575
+ },
576
+ {
577
+ "epoch": 2.340047393364929,
578
+ "grad_norm": 0.0004727982450276613,
579
+ "learning_rate": 1.1009083728278042e-05,
580
+ "loss": 0.0,
581
+ "step": 3950
582
+ },
583
+ {
584
+ "epoch": 2.3696682464454977,
585
+ "grad_norm": 0.0008073291974142194,
586
+ "learning_rate": 1.0515402843601896e-05,
587
+ "loss": 0.0,
588
+ "step": 4000
589
+ },
590
+ {
591
+ "epoch": 2.3992890995260665,
592
+ "grad_norm": 0.15108434855937958,
593
+ "learning_rate": 1.002172195892575e-05,
594
+ "loss": 0.0,
595
+ "step": 4050
596
+ },
597
+ {
598
+ "epoch": 2.428909952606635,
599
+ "grad_norm": 0.00033067440381273627,
600
+ "learning_rate": 9.528041074249605e-06,
601
+ "loss": 0.0,
602
+ "step": 4100
603
+ },
604
+ {
605
+ "epoch": 2.4585308056872037,
606
+ "grad_norm": 0.019667765125632286,
607
+ "learning_rate": 9.03436018957346e-06,
608
+ "loss": 0.0,
609
+ "step": 4150
610
+ },
611
+ {
612
+ "epoch": 2.4881516587677726,
613
+ "grad_norm": 0.000259611289948225,
614
+ "learning_rate": 8.540679304897314e-06,
615
+ "loss": 0.0,
616
+ "step": 4200
617
+ },
618
+ {
619
+ "epoch": 2.5177725118483414,
620
+ "grad_norm": 0.0002708205720409751,
621
+ "learning_rate": 8.046998420221169e-06,
622
+ "loss": 0.0003,
623
+ "step": 4250
624
+ },
625
+ {
626
+ "epoch": 2.5473933649289098,
627
+ "grad_norm": 0.0002382330858381465,
628
+ "learning_rate": 7.553317535545023e-06,
629
+ "loss": 0.0,
630
+ "step": 4300
631
+ },
632
+ {
633
+ "epoch": 2.5770142180094786,
634
+ "grad_norm": 0.0002609147340990603,
635
+ "learning_rate": 7.059636650868879e-06,
636
+ "loss": 0.0,
637
+ "step": 4350
638
+ },
639
+ {
640
+ "epoch": 2.6066350710900474,
641
+ "grad_norm": 0.00025002885377034545,
642
+ "learning_rate": 6.565955766192733e-06,
643
+ "loss": 0.0,
644
+ "step": 4400
645
+ },
646
+ {
647
+ "epoch": 2.6362559241706163,
648
+ "grad_norm": 0.00023832859005779028,
649
+ "learning_rate": 6.0722748815165886e-06,
650
+ "loss": 0.0,
651
+ "step": 4450
652
+ },
653
+ {
654
+ "epoch": 2.665876777251185,
655
+ "grad_norm": 0.0002076889795716852,
656
+ "learning_rate": 5.578593996840443e-06,
657
+ "loss": 0.0,
658
+ "step": 4500
659
+ },
660
+ {
661
+ "epoch": 2.6954976303317535,
662
+ "grad_norm": 0.0002478805836290121,
663
+ "learning_rate": 5.084913112164298e-06,
664
+ "loss": 0.0,
665
+ "step": 4550
666
+ },
667
+ {
668
+ "epoch": 2.7251184834123223,
669
+ "grad_norm": 0.00021155517606530339,
670
+ "learning_rate": 4.591232227488152e-06,
671
+ "loss": 0.0,
672
+ "step": 4600
673
+ },
674
+ {
675
+ "epoch": 2.754739336492891,
676
+ "grad_norm": 0.00021754855697508901,
677
+ "learning_rate": 4.097551342812007e-06,
678
+ "loss": 0.0,
679
+ "step": 4650
680
+ },
681
+ {
682
+ "epoch": 2.7843601895734595,
683
+ "grad_norm": 0.00020183408923912793,
684
+ "learning_rate": 3.6038704581358612e-06,
685
+ "loss": 0.0,
686
+ "step": 4700
687
+ },
688
+ {
689
+ "epoch": 2.8139810426540284,
690
+ "grad_norm": 0.00022289449407253414,
691
+ "learning_rate": 3.1101895734597158e-06,
692
+ "loss": 0.0,
693
+ "step": 4750
694
+ },
695
+ {
696
+ "epoch": 2.843601895734597,
697
+ "grad_norm": 0.007142237853258848,
698
+ "learning_rate": 2.6165086887835703e-06,
699
+ "loss": 0.0,
700
+ "step": 4800
701
+ },
702
+ {
703
+ "epoch": 2.873222748815166,
704
+ "grad_norm": 0.00019705097656697035,
705
+ "learning_rate": 2.122827804107425e-06,
706
+ "loss": 0.0,
707
+ "step": 4850
708
+ },
709
+ {
710
+ "epoch": 2.902843601895735,
711
+ "grad_norm": 0.00023452220193576068,
712
+ "learning_rate": 1.6291469194312798e-06,
713
+ "loss": 0.0001,
714
+ "step": 4900
715
+ },
716
+ {
717
+ "epoch": 2.9324644549763033,
718
+ "grad_norm": 0.000205856587854214,
719
+ "learning_rate": 1.1354660347551343e-06,
720
+ "loss": 0.0,
721
+ "step": 4950
722
+ },
723
+ {
724
+ "epoch": 2.962085308056872,
725
+ "grad_norm": 0.00020924191630911082,
726
+ "learning_rate": 6.41785150078989e-07,
727
+ "loss": 0.0,
728
+ "step": 5000
729
+ }
730
+ ],
731
+ "logging_steps": 50,
732
+ "max_steps": 5064,
733
+ "num_input_tokens_seen": 0,
734
+ "num_train_epochs": 3,
735
+ "save_steps": 500,
736
+ "stateful_callbacks": {
737
+ "TrainerControl": {
738
+ "args": {
739
+ "should_epoch_stop": false,
740
+ "should_evaluate": false,
741
+ "should_log": false,
742
+ "should_save": true,
743
+ "should_training_stop": false
744
+ },
745
+ "attributes": {}
746
+ }
747
+ },
748
+ "total_flos": 1246789065733344.0,
749
+ "train_batch_size": 8,
750
+ "trial_name": null,
751
+ "trial_params": null
752
+ }
checkpoint-5000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42eacd77743b7a41ad451c542aa07b5056fe7c7f890f7ab016bc148113f71f09
3
+ size 5713
checkpoint-5064/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
checkpoint-5064/config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DebertaV2ForTokenClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 1,
7
+ "dtype": "float32",
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2",
16
+ "3": "LABEL_3",
17
+ "4": "LABEL_4",
18
+ "5": "LABEL_5",
19
+ "6": "LABEL_6",
20
+ "7": "LABEL_7",
21
+ "8": "LABEL_8"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "LABEL_0": 0,
27
+ "LABEL_1": 1,
28
+ "LABEL_2": 2,
29
+ "LABEL_3": 3,
30
+ "LABEL_4": 4,
31
+ "LABEL_5": 5,
32
+ "LABEL_6": 6,
33
+ "LABEL_7": 7,
34
+ "LABEL_8": 8
35
+ },
36
+ "layer_norm_eps": 1e-07,
37
+ "legacy": true,
38
+ "max_position_embeddings": 512,
39
+ "max_relative_positions": -1,
40
+ "model_type": "deberta-v2",
41
+ "norm_rel_ebd": "layer_norm",
42
+ "num_attention_heads": 12,
43
+ "num_hidden_layers": 12,
44
+ "pad_token_id": 0,
45
+ "pooler_dropout": 0,
46
+ "pooler_hidden_act": "gelu",
47
+ "pooler_hidden_size": 768,
48
+ "pos_att_type": [
49
+ "p2c",
50
+ "c2p"
51
+ ],
52
+ "position_biased_input": false,
53
+ "position_buckets": 256,
54
+ "relative_attention": true,
55
+ "share_att_key": true,
56
+ "transformers_version": "4.56.1",
57
+ "type_vocab_size": 0,
58
+ "vocab_size": 128100
59
+ }
checkpoint-5064/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f29cefcbe4ebeab55797f5c52bcf7591e39877beed3a9ce01bde796777ba29a1
3
+ size 735378268
checkpoint-5064/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74a7035f474cc1cd56a5299ffc0cee20d9a1f579af144133f05cf3469fd5d967
3
+ size 1470878283
checkpoint-5064/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e4237637ed2a909ac55fe085c627ab99fc039d3c6aa9183495fa775e1f00ba6
3
+ size 14645
checkpoint-5064/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac8bf92429ffb94154ae048d975d1ba548e2690d1bb98a4ccbc355bf5d60771f
3
+ size 1383
checkpoint-5064/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a12cd4840f3c33f044bc06ba15cb1faedfb4c5136e557bf713cd04e8c9bf14b
3
+ size 1465
checkpoint-5064/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-5064/spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
checkpoint-5064/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-5064/tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "extra_special_tokens": {},
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "sp_model_kwargs": {},
55
+ "split_by_punct": false,
56
+ "tokenizer_class": "DebertaV2Tokenizer",
57
+ "unk_token": "[UNK]",
58
+ "vocab_type": "spm"
59
+ }
checkpoint-5064/trainer_state.json ADDED
@@ -0,0 +1,759 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 5064,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.02962085308056872,
14
+ "grad_norm": 0.0359644778072834,
15
+ "learning_rate": 4.951619273301738e-05,
16
+ "loss": 0.3566,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.05924170616113744,
21
+ "grad_norm": 0.045561712235212326,
22
+ "learning_rate": 4.902251184834124e-05,
23
+ "loss": 0.0019,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.08886255924170616,
28
+ "grad_norm": 0.011206220835447311,
29
+ "learning_rate": 4.852883096366509e-05,
30
+ "loss": 0.0017,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.11848341232227488,
35
+ "grad_norm": 0.008807787671685219,
36
+ "learning_rate": 4.8035150078988947e-05,
37
+ "loss": 0.0006,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.1481042654028436,
42
+ "grad_norm": 0.005796543322503567,
43
+ "learning_rate": 4.75414691943128e-05,
44
+ "loss": 0.0009,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 0.17772511848341233,
49
+ "grad_norm": 0.005227432586252689,
50
+ "learning_rate": 4.7047788309636656e-05,
51
+ "loss": 0.0006,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 0.20734597156398105,
56
+ "grad_norm": 0.003554289462044835,
57
+ "learning_rate": 4.655410742496051e-05,
58
+ "loss": 0.0005,
59
+ "step": 350
60
+ },
61
+ {
62
+ "epoch": 0.23696682464454977,
63
+ "grad_norm": 0.0033741986844688654,
64
+ "learning_rate": 4.6060426540284365e-05,
65
+ "loss": 0.0012,
66
+ "step": 400
67
+ },
68
+ {
69
+ "epoch": 0.2665876777251185,
70
+ "grad_norm": 0.002832002704963088,
71
+ "learning_rate": 4.556674565560822e-05,
72
+ "loss": 0.0002,
73
+ "step": 450
74
+ },
75
+ {
76
+ "epoch": 0.2962085308056872,
77
+ "grad_norm": 0.002275377744808793,
78
+ "learning_rate": 4.5073064770932074e-05,
79
+ "loss": 0.0007,
80
+ "step": 500
81
+ },
82
+ {
83
+ "epoch": 0.32582938388625593,
84
+ "grad_norm": 0.003911971114575863,
85
+ "learning_rate": 4.457938388625593e-05,
86
+ "loss": 0.0006,
87
+ "step": 550
88
+ },
89
+ {
90
+ "epoch": 0.35545023696682465,
91
+ "grad_norm": 0.006926015485078096,
92
+ "learning_rate": 4.408570300157978e-05,
93
+ "loss": 0.0014,
94
+ "step": 600
95
+ },
96
+ {
97
+ "epoch": 0.38507109004739337,
98
+ "grad_norm": 0.0027338722720742226,
99
+ "learning_rate": 4.359202211690364e-05,
100
+ "loss": 0.0008,
101
+ "step": 650
102
+ },
103
+ {
104
+ "epoch": 0.4146919431279621,
105
+ "grad_norm": 0.001827694708481431,
106
+ "learning_rate": 4.309834123222749e-05,
107
+ "loss": 0.0003,
108
+ "step": 700
109
+ },
110
+ {
111
+ "epoch": 0.4443127962085308,
112
+ "grad_norm": 0.0012653936864808202,
113
+ "learning_rate": 4.2604660347551346e-05,
114
+ "loss": 0.0001,
115
+ "step": 750
116
+ },
117
+ {
118
+ "epoch": 0.47393364928909953,
119
+ "grad_norm": 0.0022165332920849323,
120
+ "learning_rate": 4.21109794628752e-05,
121
+ "loss": 0.0004,
122
+ "step": 800
123
+ },
124
+ {
125
+ "epoch": 0.5035545023696683,
126
+ "grad_norm": 0.0063213687390089035,
127
+ "learning_rate": 4.1617298578199055e-05,
128
+ "loss": 0.0007,
129
+ "step": 850
130
+ },
131
+ {
132
+ "epoch": 0.533175355450237,
133
+ "grad_norm": 0.024515969678759575,
134
+ "learning_rate": 4.112361769352291e-05,
135
+ "loss": 0.001,
136
+ "step": 900
137
+ },
138
+ {
139
+ "epoch": 0.5627962085308057,
140
+ "grad_norm": 0.003376233857125044,
141
+ "learning_rate": 4.0629936808846765e-05,
142
+ "loss": 0.0005,
143
+ "step": 950
144
+ },
145
+ {
146
+ "epoch": 0.5924170616113744,
147
+ "grad_norm": 0.001513678696937859,
148
+ "learning_rate": 4.013625592417062e-05,
149
+ "loss": 0.0002,
150
+ "step": 1000
151
+ },
152
+ {
153
+ "epoch": 0.6220379146919431,
154
+ "grad_norm": 0.013340185396373272,
155
+ "learning_rate": 3.9642575039494474e-05,
156
+ "loss": 0.0004,
157
+ "step": 1050
158
+ },
159
+ {
160
+ "epoch": 0.6516587677725119,
161
+ "grad_norm": 0.0008107981411740184,
162
+ "learning_rate": 3.914889415481833e-05,
163
+ "loss": 0.0001,
164
+ "step": 1100
165
+ },
166
+ {
167
+ "epoch": 0.6812796208530806,
168
+ "grad_norm": 0.000826548261102289,
169
+ "learning_rate": 3.865521327014218e-05,
170
+ "loss": 0.0,
171
+ "step": 1150
172
+ },
173
+ {
174
+ "epoch": 0.7109004739336493,
175
+ "grad_norm": 0.0015754875494167209,
176
+ "learning_rate": 3.816153238546604e-05,
177
+ "loss": 0.0003,
178
+ "step": 1200
179
+ },
180
+ {
181
+ "epoch": 0.740521327014218,
182
+ "grad_norm": 0.0010875407606363297,
183
+ "learning_rate": 3.766785150078989e-05,
184
+ "loss": 0.0001,
185
+ "step": 1250
186
+ },
187
+ {
188
+ "epoch": 0.7701421800947867,
189
+ "grad_norm": 0.0013485795352607965,
190
+ "learning_rate": 3.7174170616113746e-05,
191
+ "loss": 0.0002,
192
+ "step": 1300
193
+ },
194
+ {
195
+ "epoch": 0.7997630331753555,
196
+ "grad_norm": 0.002195018110796809,
197
+ "learning_rate": 3.66804897314376e-05,
198
+ "loss": 0.0008,
199
+ "step": 1350
200
+ },
201
+ {
202
+ "epoch": 0.8293838862559242,
203
+ "grad_norm": 0.0013226654846221209,
204
+ "learning_rate": 3.6186808846761455e-05,
205
+ "loss": 0.0004,
206
+ "step": 1400
207
+ },
208
+ {
209
+ "epoch": 0.8590047393364929,
210
+ "grad_norm": 0.020256407558918,
211
+ "learning_rate": 3.569312796208531e-05,
212
+ "loss": 0.0011,
213
+ "step": 1450
214
+ },
215
+ {
216
+ "epoch": 0.8886255924170616,
217
+ "grad_norm": 0.0060112737119197845,
218
+ "learning_rate": 3.5199447077409164e-05,
219
+ "loss": 0.0003,
220
+ "step": 1500
221
+ },
222
+ {
223
+ "epoch": 0.9182464454976303,
224
+ "grad_norm": 0.0010298583656549454,
225
+ "learning_rate": 3.470576619273302e-05,
226
+ "loss": 0.0002,
227
+ "step": 1550
228
+ },
229
+ {
230
+ "epoch": 0.9478672985781991,
231
+ "grad_norm": 0.0008804717799648643,
232
+ "learning_rate": 3.4212085308056873e-05,
233
+ "loss": 0.0003,
234
+ "step": 1600
235
+ },
236
+ {
237
+ "epoch": 0.9774881516587678,
238
+ "grad_norm": 0.0007368926890194416,
239
+ "learning_rate": 3.371840442338073e-05,
240
+ "loss": 0.0002,
241
+ "step": 1650
242
+ },
243
+ {
244
+ "epoch": 1.0,
245
+ "eval_loss": 6.839788693469018e-05,
246
+ "eval_report": " precision recall f1-score support\n\nCERTIFICATION 1.00 1.00 1.00 1410\n EDUCATION 1.00 1.00 1.00 2241\n LANGUAGE 1.00 1.00 1.00 3014\n SKILL 1.00 1.00 1.00 3069\n\n micro avg 1.00 1.00 1.00 9734\n macro avg 1.00 1.00 1.00 9734\n weighted avg 1.00 1.00 1.00 9734\n",
247
+ "eval_runtime": 7.1833,
248
+ "eval_samples_per_second": 208.818,
249
+ "eval_steps_per_second": 26.172,
250
+ "step": 1688
251
+ },
252
+ {
253
+ "epoch": 1.0071090047393365,
254
+ "grad_norm": 0.0006786159938201308,
255
+ "learning_rate": 3.322472353870458e-05,
256
+ "loss": 0.0002,
257
+ "step": 1700
258
+ },
259
+ {
260
+ "epoch": 1.0367298578199051,
261
+ "grad_norm": 0.005513947457075119,
262
+ "learning_rate": 3.273104265402844e-05,
263
+ "loss": 0.0001,
264
+ "step": 1750
265
+ },
266
+ {
267
+ "epoch": 1.066350710900474,
268
+ "grad_norm": 0.000574503734242171,
269
+ "learning_rate": 3.223736176935229e-05,
270
+ "loss": 0.0001,
271
+ "step": 1800
272
+ },
273
+ {
274
+ "epoch": 1.0959715639810426,
275
+ "grad_norm": 0.004586311522871256,
276
+ "learning_rate": 3.1743680884676146e-05,
277
+ "loss": 0.0006,
278
+ "step": 1850
279
+ },
280
+ {
281
+ "epoch": 1.1255924170616114,
282
+ "grad_norm": 0.000738324539270252,
283
+ "learning_rate": 3.125e-05,
284
+ "loss": 0.0002,
285
+ "step": 1900
286
+ },
287
+ {
288
+ "epoch": 1.15521327014218,
289
+ "grad_norm": 0.0006399003323167562,
290
+ "learning_rate": 3.0756319115323855e-05,
291
+ "loss": 0.0001,
292
+ "step": 1950
293
+ },
294
+ {
295
+ "epoch": 1.1848341232227488,
296
+ "grad_norm": 0.0004596344952005893,
297
+ "learning_rate": 3.026263823064771e-05,
298
+ "loss": 0.0,
299
+ "step": 2000
300
+ },
301
+ {
302
+ "epoch": 1.2144549763033174,
303
+ "grad_norm": 0.0004429569817148149,
304
+ "learning_rate": 2.9768957345971564e-05,
305
+ "loss": 0.0001,
306
+ "step": 2050
307
+ },
308
+ {
309
+ "epoch": 1.2440758293838863,
310
+ "grad_norm": 0.0004196607042104006,
311
+ "learning_rate": 2.927527646129542e-05,
312
+ "loss": 0.0,
313
+ "step": 2100
314
+ },
315
+ {
316
+ "epoch": 1.2736966824644549,
317
+ "grad_norm": 0.0004485426179599017,
318
+ "learning_rate": 2.8781595576619273e-05,
319
+ "loss": 0.0,
320
+ "step": 2150
321
+ },
322
+ {
323
+ "epoch": 1.3033175355450237,
324
+ "grad_norm": 0.0005169134237803519,
325
+ "learning_rate": 2.8287914691943128e-05,
326
+ "loss": 0.0001,
327
+ "step": 2200
328
+ },
329
+ {
330
+ "epoch": 1.3329383886255926,
331
+ "grad_norm": 0.0005291880224831402,
332
+ "learning_rate": 2.7794233807266982e-05,
333
+ "loss": 0.0002,
334
+ "step": 2250
335
+ },
336
+ {
337
+ "epoch": 1.3625592417061612,
338
+ "grad_norm": 0.00048425907152704895,
339
+ "learning_rate": 2.7300552922590837e-05,
340
+ "loss": 0.0001,
341
+ "step": 2300
342
+ },
343
+ {
344
+ "epoch": 1.3921800947867298,
345
+ "grad_norm": 0.0004068867419846356,
346
+ "learning_rate": 2.6806872037914695e-05,
347
+ "loss": 0.0,
348
+ "step": 2350
349
+ },
350
+ {
351
+ "epoch": 1.4218009478672986,
352
+ "grad_norm": 0.0003516751166898757,
353
+ "learning_rate": 2.631319115323855e-05,
354
+ "loss": 0.0,
355
+ "step": 2400
356
+ },
357
+ {
358
+ "epoch": 1.4514218009478674,
359
+ "grad_norm": 0.0003432795056141913,
360
+ "learning_rate": 2.5819510268562404e-05,
361
+ "loss": 0.0,
362
+ "step": 2450
363
+ },
364
+ {
365
+ "epoch": 1.481042654028436,
366
+ "grad_norm": 0.00032765124342404306,
367
+ "learning_rate": 2.532582938388626e-05,
368
+ "loss": 0.0,
369
+ "step": 2500
370
+ },
371
+ {
372
+ "epoch": 1.5106635071090047,
373
+ "grad_norm": 0.00030620096367783844,
374
+ "learning_rate": 2.4832148499210113e-05,
375
+ "loss": 0.0,
376
+ "step": 2550
377
+ },
378
+ {
379
+ "epoch": 1.5402843601895735,
380
+ "grad_norm": 0.00032276054844260216,
381
+ "learning_rate": 2.4338467614533967e-05,
382
+ "loss": 0.0,
383
+ "step": 2600
384
+ },
385
+ {
386
+ "epoch": 1.5699052132701423,
387
+ "grad_norm": 0.0003284791891928762,
388
+ "learning_rate": 2.3844786729857822e-05,
389
+ "loss": 0.0,
390
+ "step": 2650
391
+ },
392
+ {
393
+ "epoch": 1.599526066350711,
394
+ "grad_norm": 0.0005517126410268247,
395
+ "learning_rate": 2.3351105845181677e-05,
396
+ "loss": 0.0001,
397
+ "step": 2700
398
+ },
399
+ {
400
+ "epoch": 1.6291469194312795,
401
+ "grad_norm": 0.0004335689009167254,
402
+ "learning_rate": 2.285742496050553e-05,
403
+ "loss": 0.0,
404
+ "step": 2750
405
+ },
406
+ {
407
+ "epoch": 1.6587677725118484,
408
+ "grad_norm": 0.00938709732145071,
409
+ "learning_rate": 2.2363744075829386e-05,
410
+ "loss": 0.0011,
411
+ "step": 2800
412
+ },
413
+ {
414
+ "epoch": 1.6883886255924172,
415
+ "grad_norm": 0.002625273773446679,
416
+ "learning_rate": 2.187006319115324e-05,
417
+ "loss": 0.0,
418
+ "step": 2850
419
+ },
420
+ {
421
+ "epoch": 1.7180094786729858,
422
+ "grad_norm": 0.00048340365174226463,
423
+ "learning_rate": 2.1376382306477095e-05,
424
+ "loss": 0.0,
425
+ "step": 2900
426
+ },
427
+ {
428
+ "epoch": 1.7476303317535544,
429
+ "grad_norm": 0.0035711589735001326,
430
+ "learning_rate": 2.088270142180095e-05,
431
+ "loss": 0.0005,
432
+ "step": 2950
433
+ },
434
+ {
435
+ "epoch": 1.7772511848341233,
436
+ "grad_norm": 0.0005380721995607018,
437
+ "learning_rate": 2.0389020537124804e-05,
438
+ "loss": 0.0001,
439
+ "step": 3000
440
+ },
441
+ {
442
+ "epoch": 1.806872037914692,
443
+ "grad_norm": 0.00039379362715408206,
444
+ "learning_rate": 1.9895339652448658e-05,
445
+ "loss": 0.0,
446
+ "step": 3050
447
+ },
448
+ {
449
+ "epoch": 1.8364928909952607,
450
+ "grad_norm": 0.00031137277255766094,
451
+ "learning_rate": 1.9401658767772513e-05,
452
+ "loss": 0.0001,
453
+ "step": 3100
454
+ },
455
+ {
456
+ "epoch": 1.8661137440758293,
457
+ "grad_norm": 0.00033859844552353024,
458
+ "learning_rate": 1.8907977883096367e-05,
459
+ "loss": 0.0003,
460
+ "step": 3150
461
+ },
462
+ {
463
+ "epoch": 1.8957345971563981,
464
+ "grad_norm": 0.0003177137696184218,
465
+ "learning_rate": 1.8414296998420222e-05,
466
+ "loss": 0.0,
467
+ "step": 3200
468
+ },
469
+ {
470
+ "epoch": 1.925355450236967,
471
+ "grad_norm": 0.5252463817596436,
472
+ "learning_rate": 1.7920616113744076e-05,
473
+ "loss": 0.0001,
474
+ "step": 3250
475
+ },
476
+ {
477
+ "epoch": 1.9549763033175356,
478
+ "grad_norm": 0.000578847888391465,
479
+ "learning_rate": 1.742693522906793e-05,
480
+ "loss": 0.0002,
481
+ "step": 3300
482
+ },
483
+ {
484
+ "epoch": 1.9845971563981042,
485
+ "grad_norm": 0.00031036767177283764,
486
+ "learning_rate": 1.6933254344391785e-05,
487
+ "loss": 0.0,
488
+ "step": 3350
489
+ },
490
+ {
491
+ "epoch": 2.0,
492
+ "eval_loss": 0.0002486561133991927,
493
+ "eval_report": " precision recall f1-score support\n\nCERTIFICATION 1.00 1.00 1.00 1410\n EDUCATION 1.00 1.00 1.00 2241\n LANGUAGE 1.00 1.00 1.00 3014\n SKILL 1.00 1.00 1.00 3069\n\n micro avg 1.00 1.00 1.00 9734\n macro avg 1.00 1.00 1.00 9734\n weighted avg 1.00 1.00 1.00 9734\n",
494
+ "eval_runtime": 7.0179,
495
+ "eval_samples_per_second": 213.738,
496
+ "eval_steps_per_second": 26.788,
497
+ "step": 3376
498
+ },
499
+ {
500
+ "epoch": 2.014218009478673,
501
+ "grad_norm": 0.00038110482273623347,
502
+ "learning_rate": 1.643957345971564e-05,
503
+ "loss": 0.0002,
504
+ "step": 3400
505
+ },
506
+ {
507
+ "epoch": 2.043838862559242,
508
+ "grad_norm": 0.00030082205194048584,
509
+ "learning_rate": 1.5945892575039495e-05,
510
+ "loss": 0.0,
511
+ "step": 3450
512
+ },
513
+ {
514
+ "epoch": 2.0734597156398102,
515
+ "grad_norm": 0.00030870226328261197,
516
+ "learning_rate": 1.545221169036335e-05,
517
+ "loss": 0.0,
518
+ "step": 3500
519
+ },
520
+ {
521
+ "epoch": 2.103080568720379,
522
+ "grad_norm": 0.00023404941020999104,
523
+ "learning_rate": 1.4958530805687204e-05,
524
+ "loss": 0.0001,
525
+ "step": 3550
526
+ },
527
+ {
528
+ "epoch": 2.132701421800948,
529
+ "grad_norm": 0.00021994848793838173,
530
+ "learning_rate": 1.4464849921011058e-05,
531
+ "loss": 0.0,
532
+ "step": 3600
533
+ },
534
+ {
535
+ "epoch": 2.1623222748815167,
536
+ "grad_norm": 0.0002600239240564406,
537
+ "learning_rate": 1.3971169036334913e-05,
538
+ "loss": 0.0,
539
+ "step": 3650
540
+ },
541
+ {
542
+ "epoch": 2.191943127962085,
543
+ "grad_norm": 0.00019250177138019353,
544
+ "learning_rate": 1.3477488151658769e-05,
545
+ "loss": 0.0,
546
+ "step": 3700
547
+ },
548
+ {
549
+ "epoch": 2.221563981042654,
550
+ "grad_norm": 0.00024143581686075777,
551
+ "learning_rate": 1.2983807266982623e-05,
552
+ "loss": 0.0,
553
+ "step": 3750
554
+ },
555
+ {
556
+ "epoch": 2.251184834123223,
557
+ "grad_norm": 0.00020565264276228845,
558
+ "learning_rate": 1.2490126382306478e-05,
559
+ "loss": 0.0,
560
+ "step": 3800
561
+ },
562
+ {
563
+ "epoch": 2.2808056872037916,
564
+ "grad_norm": 0.0002789797727018595,
565
+ "learning_rate": 1.1996445497630332e-05,
566
+ "loss": 0.0002,
567
+ "step": 3850
568
+ },
569
+ {
570
+ "epoch": 2.31042654028436,
571
+ "grad_norm": 0.0007835368160158396,
572
+ "learning_rate": 1.1502764612954187e-05,
573
+ "loss": 0.0007,
574
+ "step": 3900
575
+ },
576
+ {
577
+ "epoch": 2.340047393364929,
578
+ "grad_norm": 0.0004727982450276613,
579
+ "learning_rate": 1.1009083728278042e-05,
580
+ "loss": 0.0,
581
+ "step": 3950
582
+ },
583
+ {
584
+ "epoch": 2.3696682464454977,
585
+ "grad_norm": 0.0008073291974142194,
586
+ "learning_rate": 1.0515402843601896e-05,
587
+ "loss": 0.0,
588
+ "step": 4000
589
+ },
590
+ {
591
+ "epoch": 2.3992890995260665,
592
+ "grad_norm": 0.15108434855937958,
593
+ "learning_rate": 1.002172195892575e-05,
594
+ "loss": 0.0,
595
+ "step": 4050
596
+ },
597
+ {
598
+ "epoch": 2.428909952606635,
599
+ "grad_norm": 0.00033067440381273627,
600
+ "learning_rate": 9.528041074249605e-06,
601
+ "loss": 0.0,
602
+ "step": 4100
603
+ },
604
+ {
605
+ "epoch": 2.4585308056872037,
606
+ "grad_norm": 0.019667765125632286,
607
+ "learning_rate": 9.03436018957346e-06,
608
+ "loss": 0.0,
609
+ "step": 4150
610
+ },
611
+ {
612
+ "epoch": 2.4881516587677726,
613
+ "grad_norm": 0.000259611289948225,
614
+ "learning_rate": 8.540679304897314e-06,
615
+ "loss": 0.0,
616
+ "step": 4200
617
+ },
618
+ {
619
+ "epoch": 2.5177725118483414,
620
+ "grad_norm": 0.0002708205720409751,
621
+ "learning_rate": 8.046998420221169e-06,
622
+ "loss": 0.0003,
623
+ "step": 4250
624
+ },
625
+ {
626
+ "epoch": 2.5473933649289098,
627
+ "grad_norm": 0.0002382330858381465,
628
+ "learning_rate": 7.553317535545023e-06,
629
+ "loss": 0.0,
630
+ "step": 4300
631
+ },
632
+ {
633
+ "epoch": 2.5770142180094786,
634
+ "grad_norm": 0.0002609147340990603,
635
+ "learning_rate": 7.059636650868879e-06,
636
+ "loss": 0.0,
637
+ "step": 4350
638
+ },
639
+ {
640
+ "epoch": 2.6066350710900474,
641
+ "grad_norm": 0.00025002885377034545,
642
+ "learning_rate": 6.565955766192733e-06,
643
+ "loss": 0.0,
644
+ "step": 4400
645
+ },
646
+ {
647
+ "epoch": 2.6362559241706163,
648
+ "grad_norm": 0.00023832859005779028,
649
+ "learning_rate": 6.0722748815165886e-06,
650
+ "loss": 0.0,
651
+ "step": 4450
652
+ },
653
+ {
654
+ "epoch": 2.665876777251185,
655
+ "grad_norm": 0.0002076889795716852,
656
+ "learning_rate": 5.578593996840443e-06,
657
+ "loss": 0.0,
658
+ "step": 4500
659
+ },
660
+ {
661
+ "epoch": 2.6954976303317535,
662
+ "grad_norm": 0.0002478805836290121,
663
+ "learning_rate": 5.084913112164298e-06,
664
+ "loss": 0.0,
665
+ "step": 4550
666
+ },
667
+ {
668
+ "epoch": 2.7251184834123223,
669
+ "grad_norm": 0.00021155517606530339,
670
+ "learning_rate": 4.591232227488152e-06,
671
+ "loss": 0.0,
672
+ "step": 4600
673
+ },
674
+ {
675
+ "epoch": 2.754739336492891,
676
+ "grad_norm": 0.00021754855697508901,
677
+ "learning_rate": 4.097551342812007e-06,
678
+ "loss": 0.0,
679
+ "step": 4650
680
+ },
681
+ {
682
+ "epoch": 2.7843601895734595,
683
+ "grad_norm": 0.00020183408923912793,
684
+ "learning_rate": 3.6038704581358612e-06,
685
+ "loss": 0.0,
686
+ "step": 4700
687
+ },
688
+ {
689
+ "epoch": 2.8139810426540284,
690
+ "grad_norm": 0.00022289449407253414,
691
+ "learning_rate": 3.1101895734597158e-06,
692
+ "loss": 0.0,
693
+ "step": 4750
694
+ },
695
+ {
696
+ "epoch": 2.843601895734597,
697
+ "grad_norm": 0.007142237853258848,
698
+ "learning_rate": 2.6165086887835703e-06,
699
+ "loss": 0.0,
700
+ "step": 4800
701
+ },
702
+ {
703
+ "epoch": 2.873222748815166,
704
+ "grad_norm": 0.00019705097656697035,
705
+ "learning_rate": 2.122827804107425e-06,
706
+ "loss": 0.0,
707
+ "step": 4850
708
+ },
709
+ {
710
+ "epoch": 2.902843601895735,
711
+ "grad_norm": 0.00023452220193576068,
712
+ "learning_rate": 1.6291469194312798e-06,
713
+ "loss": 0.0001,
714
+ "step": 4900
715
+ },
716
+ {
717
+ "epoch": 2.9324644549763033,
718
+ "grad_norm": 0.000205856587854214,
719
+ "learning_rate": 1.1354660347551343e-06,
720
+ "loss": 0.0,
721
+ "step": 4950
722
+ },
723
+ {
724
+ "epoch": 2.962085308056872,
725
+ "grad_norm": 0.00020924191630911082,
726
+ "learning_rate": 6.41785150078989e-07,
727
+ "loss": 0.0,
728
+ "step": 5000
729
+ },
730
+ {
731
+ "epoch": 2.991706161137441,
732
+ "grad_norm": 0.00019217448425479233,
733
+ "learning_rate": 1.481042654028436e-07,
734
+ "loss": 0.0,
735
+ "step": 5050
736
+ }
737
+ ],
738
+ "logging_steps": 50,
739
+ "max_steps": 5064,
740
+ "num_input_tokens_seen": 0,
741
+ "num_train_epochs": 3,
742
+ "save_steps": 500,
743
+ "stateful_callbacks": {
744
+ "TrainerControl": {
745
+ "args": {
746
+ "should_epoch_stop": false,
747
+ "should_evaluate": false,
748
+ "should_log": false,
749
+ "should_save": true,
750
+ "should_training_stop": true
751
+ },
752
+ "attributes": {}
753
+ }
754
+ },
755
+ "total_flos": 1262694758161032.0,
756
+ "train_batch_size": 8,
757
+ "trial_name": null,
758
+ "trial_params": null
759
+ }
checkpoint-5064/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42eacd77743b7a41ad451c542aa07b5056fe7c7f890f7ab016bc148113f71f09
3
+ size 5713
config.json CHANGED
@@ -10,28 +10,28 @@
10
  "hidden_dropout_prob": 0.1,
11
  "hidden_size": 768,
12
  "id2label": {
13
- "0": "LABEL_0",
14
- "1": "LABEL_1",
15
- "2": "LABEL_2",
16
- "3": "LABEL_3",
17
- "4": "LABEL_4",
18
- "5": "LABEL_5",
19
- "6": "LABEL_6",
20
- "7": "LABEL_7",
21
- "8": "LABEL_8"
22
  },
23
  "initializer_range": 0.02,
24
  "intermediate_size": 3072,
25
  "label2id": {
26
- "LABEL_0": 0,
27
- "LABEL_1": 1,
28
- "LABEL_2": 2,
29
- "LABEL_3": 3,
30
- "LABEL_4": 4,
31
- "LABEL_5": 5,
32
- "LABEL_6": 6,
33
- "LABEL_7": 7,
34
- "LABEL_8": 8
35
  },
36
  "layer_norm_eps": 1e-07,
37
  "legacy": true,
 
10
  "hidden_dropout_prob": 0.1,
11
  "hidden_size": 768,
12
  "id2label": {
13
+ "0": "O",
14
+ "1": "B-EDUCATION",
15
+ "2": "I-EDUCATION",
16
+ "3": "B-SKILL",
17
+ "4": "I-SKILL",
18
+ "5": "B-CERTIFICATION",
19
+ "6": "I-CERTIFICATION",
20
+ "7": "B-LANGUAGE",
21
+ "8": "I-LANGUAGE"
22
  },
23
  "initializer_range": 0.02,
24
  "intermediate_size": 3072,
25
  "label2id": {
26
+ "B-CERTIFICATION": 5,
27
+ "B-EDUCATION": 1,
28
+ "B-LANGUAGE": 7,
29
+ "B-SKILL": 3,
30
+ "I-CERTIFICATION": 6,
31
+ "I-EDUCATION": 2,
32
+ "I-LANGUAGE": 8,
33
+ "I-SKILL": 4,
34
+ "O": 0
35
  },
36
  "layer_norm_eps": 1e-07,
37
  "legacy": true,
tokenizer.json CHANGED
@@ -1,11 +1,6 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 512,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
  "padding": null,
10
  "added_tokens": [
11
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42eacd77743b7a41ad451c542aa07b5056fe7c7f890f7ab016bc148113f71f09
3
+ size 5713