CocoRoF commited on
Commit
472c7ea
·
verified ·
1 Parent(s): 571da2e

Training in progress, step 1000, checkpoint

Browse files
last-checkpoint/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "dev7halo/ModernBERT-base-ko-test-v2",
3
+ "architectures": [
4
+ "ModernBERTSimCSE"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 50281,
9
+ "classifier_activation": "gelu",
10
+ "classifier_bias": false,
11
+ "classifier_dropout": 0.0,
12
+ "classifier_pooling": "mean",
13
+ "cls_token_id": 2,
14
+ "decoder_bias": true,
15
+ "deterministic_flash_attn": false,
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 50282,
18
+ "global_attn_every_n_layers": 3,
19
+ "global_rope_theta": 160000.0,
20
+ "gradient_checkpointing": false,
21
+ "hidden_activation": "gelu",
22
+ "hidden_size": 768,
23
+ "initializer_cutoff_factor": 2.0,
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 1152,
26
+ "layer_norm_eps": 1e-05,
27
+ "local_attention": 128,
28
+ "local_rope_theta": 10000.0,
29
+ "max_position_embeddings": 8192,
30
+ "mlp_bias": false,
31
+ "mlp_dropout": 0.0,
32
+ "model_type": "modernbert",
33
+ "norm_bias": false,
34
+ "norm_eps": 1e-05,
35
+ "num_attention_heads": 12,
36
+ "num_hidden_layers": 22,
37
+ "pad_token_id": 0,
38
+ "position_embedding_type": "absolute",
39
+ "reference_compile": false,
40
+ "sep_token_id": 3,
41
+ "sparse_pred_ignore_index": -100,
42
+ "sparse_prediction": false,
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.48.0.dev0",
45
+ "vocab_size": 50368
46
+ }
last-checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f130f0adb8d87b8bc0c4b41a9b09bd360f3e7d3ca43503ce7565fee2b353a89
3
+ size 598434152
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12db60090dcfa369719ae13a22a583e9466513a915f60cd6e6e01eb5f889bb42
3
+ size 1196955962
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34930968d5b280d50279d60ceb15eb6a032b914d70d039815be5221872d95cb7
3
+ size 14244
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9ffbd4b94e7a724dd90cd915b34618b812fc8c45b385da20eec131ccda80166
3
+ size 1000
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
last-checkpoint/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/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": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,797 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.46860356138706655,
5
+ "eval_steps": 250,
6
+ "global_step": 1000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.004686035613870665,
13
+ "grad_norm": 2.907787561416626,
14
+ "learning_rate": 9.997071227741332e-06,
15
+ "loss": 3.3815,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.00937207122774133,
20
+ "grad_norm": 2.2910118103027344,
21
+ "learning_rate": 9.994142455482663e-06,
22
+ "loss": 3.3605,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.014058106841611996,
27
+ "grad_norm": 2.791727066040039,
28
+ "learning_rate": 9.991213683223994e-06,
29
+ "loss": 3.3338,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.01874414245548266,
34
+ "grad_norm": 2.881253242492676,
35
+ "learning_rate": 9.988284910965324e-06,
36
+ "loss": 3.3047,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.023430178069353328,
41
+ "grad_norm": 3.5495920181274414,
42
+ "learning_rate": 9.985356138706655e-06,
43
+ "loss": 3.266,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.028116213683223992,
48
+ "grad_norm": 3.8195812702178955,
49
+ "learning_rate": 9.982427366447985e-06,
50
+ "loss": 3.2116,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.03280224929709466,
55
+ "grad_norm": 5.006792068481445,
56
+ "learning_rate": 9.979498594189316e-06,
57
+ "loss": 3.1271,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.03748828491096532,
62
+ "grad_norm": 5.206729412078857,
63
+ "learning_rate": 9.976569821930647e-06,
64
+ "loss": 3.0472,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.04217432052483599,
69
+ "grad_norm": 6.317724227905273,
70
+ "learning_rate": 9.973641049671978e-06,
71
+ "loss": 2.9458,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.046860356138706656,
76
+ "grad_norm": 7.30826997756958,
77
+ "learning_rate": 9.97071227741331e-06,
78
+ "loss": 2.9002,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.05154639175257732,
83
+ "grad_norm": 7.05161190032959,
84
+ "learning_rate": 9.96778350515464e-06,
85
+ "loss": 2.8379,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.056232427366447985,
90
+ "grad_norm": 12.389013290405273,
91
+ "learning_rate": 9.964854732895972e-06,
92
+ "loss": 2.7637,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.06091846298031865,
97
+ "grad_norm": 19.661762237548828,
98
+ "learning_rate": 9.961925960637301e-06,
99
+ "loss": 2.7413,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.06560449859418932,
104
+ "grad_norm": 7.9712018966674805,
105
+ "learning_rate": 9.958997188378632e-06,
106
+ "loss": 2.6953,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.07029053420805999,
111
+ "grad_norm": 44.79791259765625,
112
+ "learning_rate": 9.956068416119962e-06,
113
+ "loss": 2.6795,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.07497656982193064,
118
+ "grad_norm": 7.748485565185547,
119
+ "learning_rate": 9.953139643861293e-06,
120
+ "loss": 2.6179,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.07966260543580131,
125
+ "grad_norm": 7.135361194610596,
126
+ "learning_rate": 9.950210871602624e-06,
127
+ "loss": 2.5714,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.08434864104967198,
132
+ "grad_norm": 5.464244365692139,
133
+ "learning_rate": 9.947282099343956e-06,
134
+ "loss": 2.4817,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.08903467666354264,
139
+ "grad_norm": 10.304727554321289,
140
+ "learning_rate": 9.944353327085287e-06,
141
+ "loss": 2.3939,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.09372071227741331,
146
+ "grad_norm": 8.390380859375,
147
+ "learning_rate": 9.941424554826618e-06,
148
+ "loss": 2.3162,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.09840674789128398,
153
+ "grad_norm": 7.206277847290039,
154
+ "learning_rate": 9.938495782567949e-06,
155
+ "loss": 2.2413,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.10309278350515463,
160
+ "grad_norm": 10.72529411315918,
161
+ "learning_rate": 9.935567010309279e-06,
162
+ "loss": 2.1816,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.1077788191190253,
167
+ "grad_norm": 8.411327362060547,
168
+ "learning_rate": 9.93263823805061e-06,
169
+ "loss": 2.0204,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.11246485473289597,
174
+ "grad_norm": 9.118602752685547,
175
+ "learning_rate": 9.929709465791941e-06,
176
+ "loss": 1.9329,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.11715089034676664,
181
+ "grad_norm": 11.883502960205078,
182
+ "learning_rate": 9.92678069353327e-06,
183
+ "loss": 1.8041,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.11715089034676664,
188
+ "eval_loss": 0.20095524191856384,
189
+ "eval_pearson_cosine": 0.5629603652959432,
190
+ "eval_pearson_dot": 0.32442021258601983,
191
+ "eval_pearson_euclidean": 0.5948642130310873,
192
+ "eval_pearson_manhattan": 0.5931866084570743,
193
+ "eval_runtime": 46.3498,
194
+ "eval_samples_per_second": 32.363,
195
+ "eval_spearman_cosine": 0.5645428688364399,
196
+ "eval_spearman_dot": 0.3123519595505677,
197
+ "eval_spearman_euclidean": 0.5966715855304487,
198
+ "eval_spearman_manhattan": 0.5951499296436052,
199
+ "eval_steps_per_second": 32.363,
200
+ "step": 250
201
+ },
202
+ {
203
+ "epoch": 0.1218369259606373,
204
+ "grad_norm": 9.455839157104492,
205
+ "learning_rate": 9.923851921274602e-06,
206
+ "loss": 1.7175,
207
+ "step": 260
208
+ },
209
+ {
210
+ "epoch": 0.12652296157450796,
211
+ "grad_norm": 9.907763481140137,
212
+ "learning_rate": 9.920923149015933e-06,
213
+ "loss": 1.5752,
214
+ "step": 270
215
+ },
216
+ {
217
+ "epoch": 0.13120899718837864,
218
+ "grad_norm": 10.268372535705566,
219
+ "learning_rate": 9.917994376757264e-06,
220
+ "loss": 1.5905,
221
+ "step": 280
222
+ },
223
+ {
224
+ "epoch": 0.1358950328022493,
225
+ "grad_norm": 12.264440536499023,
226
+ "learning_rate": 9.915065604498595e-06,
227
+ "loss": 1.4994,
228
+ "step": 290
229
+ },
230
+ {
231
+ "epoch": 0.14058106841611998,
232
+ "grad_norm": 10.21927547454834,
233
+ "learning_rate": 9.912136832239926e-06,
234
+ "loss": 1.4741,
235
+ "step": 300
236
+ },
237
+ {
238
+ "epoch": 0.14526710402999063,
239
+ "grad_norm": 12.204063415527344,
240
+ "learning_rate": 9.909208059981256e-06,
241
+ "loss": 1.3685,
242
+ "step": 310
243
+ },
244
+ {
245
+ "epoch": 0.14995313964386128,
246
+ "grad_norm": 8.701486587524414,
247
+ "learning_rate": 9.906279287722587e-06,
248
+ "loss": 1.3407,
249
+ "step": 320
250
+ },
251
+ {
252
+ "epoch": 0.15463917525773196,
253
+ "grad_norm": 11.478012084960938,
254
+ "learning_rate": 9.903350515463918e-06,
255
+ "loss": 1.3996,
256
+ "step": 330
257
+ },
258
+ {
259
+ "epoch": 0.15932521087160262,
260
+ "grad_norm": 8.862137794494629,
261
+ "learning_rate": 9.90042174320525e-06,
262
+ "loss": 1.2921,
263
+ "step": 340
264
+ },
265
+ {
266
+ "epoch": 0.1640112464854733,
267
+ "grad_norm": 8.181413650512695,
268
+ "learning_rate": 9.897492970946579e-06,
269
+ "loss": 1.2948,
270
+ "step": 350
271
+ },
272
+ {
273
+ "epoch": 0.16869728209934395,
274
+ "grad_norm": 12.891910552978516,
275
+ "learning_rate": 9.89456419868791e-06,
276
+ "loss": 1.2444,
277
+ "step": 360
278
+ },
279
+ {
280
+ "epoch": 0.1733833177132146,
281
+ "grad_norm": 9.783638000488281,
282
+ "learning_rate": 9.891635426429241e-06,
283
+ "loss": 1.1765,
284
+ "step": 370
285
+ },
286
+ {
287
+ "epoch": 0.1780693533270853,
288
+ "grad_norm": 10.521812438964844,
289
+ "learning_rate": 9.888706654170573e-06,
290
+ "loss": 1.2163,
291
+ "step": 380
292
+ },
293
+ {
294
+ "epoch": 0.18275538894095594,
295
+ "grad_norm": 9.507091522216797,
296
+ "learning_rate": 9.885777881911904e-06,
297
+ "loss": 1.1555,
298
+ "step": 390
299
+ },
300
+ {
301
+ "epoch": 0.18744142455482662,
302
+ "grad_norm": 10.072102546691895,
303
+ "learning_rate": 9.882849109653235e-06,
304
+ "loss": 1.1631,
305
+ "step": 400
306
+ },
307
+ {
308
+ "epoch": 0.19212746016869728,
309
+ "grad_norm": 12.557927131652832,
310
+ "learning_rate": 9.879920337394564e-06,
311
+ "loss": 1.1319,
312
+ "step": 410
313
+ },
314
+ {
315
+ "epoch": 0.19681349578256796,
316
+ "grad_norm": 7.743768692016602,
317
+ "learning_rate": 9.876991565135896e-06,
318
+ "loss": 1.2022,
319
+ "step": 420
320
+ },
321
+ {
322
+ "epoch": 0.2014995313964386,
323
+ "grad_norm": 9.258079528808594,
324
+ "learning_rate": 9.874062792877227e-06,
325
+ "loss": 1.1219,
326
+ "step": 430
327
+ },
328
+ {
329
+ "epoch": 0.20618556701030927,
330
+ "grad_norm": 8.362629890441895,
331
+ "learning_rate": 9.871134020618558e-06,
332
+ "loss": 1.1138,
333
+ "step": 440
334
+ },
335
+ {
336
+ "epoch": 0.21087160262417995,
337
+ "grad_norm": 8.71789264678955,
338
+ "learning_rate": 9.868205248359888e-06,
339
+ "loss": 1.0473,
340
+ "step": 450
341
+ },
342
+ {
343
+ "epoch": 0.2155576382380506,
344
+ "grad_norm": 8.710640907287598,
345
+ "learning_rate": 9.865276476101219e-06,
346
+ "loss": 1.0933,
347
+ "step": 460
348
+ },
349
+ {
350
+ "epoch": 0.22024367385192128,
351
+ "grad_norm": 7.57949686050415,
352
+ "learning_rate": 9.86234770384255e-06,
353
+ "loss": 1.0429,
354
+ "step": 470
355
+ },
356
+ {
357
+ "epoch": 0.22492970946579194,
358
+ "grad_norm": 8.775091171264648,
359
+ "learning_rate": 9.859418931583881e-06,
360
+ "loss": 1.0406,
361
+ "step": 480
362
+ },
363
+ {
364
+ "epoch": 0.2296157450796626,
365
+ "grad_norm": 9.942752838134766,
366
+ "learning_rate": 9.856490159325212e-06,
367
+ "loss": 1.0526,
368
+ "step": 490
369
+ },
370
+ {
371
+ "epoch": 0.23430178069353327,
372
+ "grad_norm": 10.166437149047852,
373
+ "learning_rate": 9.853561387066542e-06,
374
+ "loss": 1.0265,
375
+ "step": 500
376
+ },
377
+ {
378
+ "epoch": 0.23430178069353327,
379
+ "eval_loss": 0.09848710149526596,
380
+ "eval_pearson_cosine": 0.7114527090607083,
381
+ "eval_pearson_dot": 0.5814656567702485,
382
+ "eval_pearson_euclidean": 0.7022168021213133,
383
+ "eval_pearson_manhattan": 0.7010309676073874,
384
+ "eval_runtime": 48.356,
385
+ "eval_samples_per_second": 31.02,
386
+ "eval_spearman_cosine": 0.7098203386273151,
387
+ "eval_spearman_dot": 0.5861254786395066,
388
+ "eval_spearman_euclidean": 0.7102590115372712,
389
+ "eval_spearman_manhattan": 0.7094011853041999,
390
+ "eval_steps_per_second": 31.02,
391
+ "step": 500
392
+ },
393
+ {
394
+ "epoch": 0.23898781630740393,
395
+ "grad_norm": 6.910321235656738,
396
+ "learning_rate": 9.850632614807873e-06,
397
+ "loss": 1.0267,
398
+ "step": 510
399
+ },
400
+ {
401
+ "epoch": 0.2436738519212746,
402
+ "grad_norm": 8.010503768920898,
403
+ "learning_rate": 9.847703842549204e-06,
404
+ "loss": 0.97,
405
+ "step": 520
406
+ },
407
+ {
408
+ "epoch": 0.24835988753514526,
409
+ "grad_norm": 8.340336799621582,
410
+ "learning_rate": 9.844775070290535e-06,
411
+ "loss": 0.9773,
412
+ "step": 530
413
+ },
414
+ {
415
+ "epoch": 0.2530459231490159,
416
+ "grad_norm": 6.75998592376709,
417
+ "learning_rate": 9.841846298031867e-06,
418
+ "loss": 0.9694,
419
+ "step": 540
420
+ },
421
+ {
422
+ "epoch": 0.25773195876288657,
423
+ "grad_norm": 6.592973709106445,
424
+ "learning_rate": 9.838917525773196e-06,
425
+ "loss": 0.9101,
426
+ "step": 550
427
+ },
428
+ {
429
+ "epoch": 0.2624179943767573,
430
+ "grad_norm": 8.13701343536377,
431
+ "learning_rate": 9.835988753514527e-06,
432
+ "loss": 0.9693,
433
+ "step": 560
434
+ },
435
+ {
436
+ "epoch": 0.26710402999062793,
437
+ "grad_norm": 10.256951332092285,
438
+ "learning_rate": 9.833059981255859e-06,
439
+ "loss": 0.9405,
440
+ "step": 570
441
+ },
442
+ {
443
+ "epoch": 0.2717900656044986,
444
+ "grad_norm": 9.521321296691895,
445
+ "learning_rate": 9.83013120899719e-06,
446
+ "loss": 0.8731,
447
+ "step": 580
448
+ },
449
+ {
450
+ "epoch": 0.27647610121836924,
451
+ "grad_norm": 7.164852142333984,
452
+ "learning_rate": 9.82720243673852e-06,
453
+ "loss": 0.9387,
454
+ "step": 590
455
+ },
456
+ {
457
+ "epoch": 0.28116213683223995,
458
+ "grad_norm": 8.326433181762695,
459
+ "learning_rate": 9.82427366447985e-06,
460
+ "loss": 0.8388,
461
+ "step": 600
462
+ },
463
+ {
464
+ "epoch": 0.2858481724461106,
465
+ "grad_norm": 8.819974899291992,
466
+ "learning_rate": 9.821344892221182e-06,
467
+ "loss": 0.9034,
468
+ "step": 610
469
+ },
470
+ {
471
+ "epoch": 0.29053420805998126,
472
+ "grad_norm": 6.0674052238464355,
473
+ "learning_rate": 9.818416119962513e-06,
474
+ "loss": 0.8225,
475
+ "step": 620
476
+ },
477
+ {
478
+ "epoch": 0.2952202436738519,
479
+ "grad_norm": 7.898690223693848,
480
+ "learning_rate": 9.815487347703844e-06,
481
+ "loss": 0.8916,
482
+ "step": 630
483
+ },
484
+ {
485
+ "epoch": 0.29990627928772257,
486
+ "grad_norm": 9.459305763244629,
487
+ "learning_rate": 9.812558575445175e-06,
488
+ "loss": 0.8771,
489
+ "step": 640
490
+ },
491
+ {
492
+ "epoch": 0.3045923149015933,
493
+ "grad_norm": 7.231110095977783,
494
+ "learning_rate": 9.809629803186505e-06,
495
+ "loss": 0.8575,
496
+ "step": 650
497
+ },
498
+ {
499
+ "epoch": 0.30927835051546393,
500
+ "grad_norm": 5.850890159606934,
501
+ "learning_rate": 9.806701030927836e-06,
502
+ "loss": 0.8294,
503
+ "step": 660
504
+ },
505
+ {
506
+ "epoch": 0.3139643861293346,
507
+ "grad_norm": 12.532159805297852,
508
+ "learning_rate": 9.803772258669167e-06,
509
+ "loss": 0.8745,
510
+ "step": 670
511
+ },
512
+ {
513
+ "epoch": 0.31865042174320524,
514
+ "grad_norm": 6.576635837554932,
515
+ "learning_rate": 9.800843486410497e-06,
516
+ "loss": 0.8167,
517
+ "step": 680
518
+ },
519
+ {
520
+ "epoch": 0.3233364573570759,
521
+ "grad_norm": 7.243174076080322,
522
+ "learning_rate": 9.797914714151828e-06,
523
+ "loss": 0.8886,
524
+ "step": 690
525
+ },
526
+ {
527
+ "epoch": 0.3280224929709466,
528
+ "grad_norm": 6.775111675262451,
529
+ "learning_rate": 9.794985941893159e-06,
530
+ "loss": 0.8205,
531
+ "step": 700
532
+ },
533
+ {
534
+ "epoch": 0.33270852858481725,
535
+ "grad_norm": 7.494016647338867,
536
+ "learning_rate": 9.79205716963449e-06,
537
+ "loss": 0.7778,
538
+ "step": 710
539
+ },
540
+ {
541
+ "epoch": 0.3373945641986879,
542
+ "grad_norm": 5.593213081359863,
543
+ "learning_rate": 9.789128397375821e-06,
544
+ "loss": 0.7875,
545
+ "step": 720
546
+ },
547
+ {
548
+ "epoch": 0.34208059981255856,
549
+ "grad_norm": 7.325387001037598,
550
+ "learning_rate": 9.786199625117153e-06,
551
+ "loss": 0.7839,
552
+ "step": 730
553
+ },
554
+ {
555
+ "epoch": 0.3467666354264292,
556
+ "grad_norm": 5.411241054534912,
557
+ "learning_rate": 9.783270852858484e-06,
558
+ "loss": 0.8363,
559
+ "step": 740
560
+ },
561
+ {
562
+ "epoch": 0.3514526710402999,
563
+ "grad_norm": 5.667125225067139,
564
+ "learning_rate": 9.780342080599813e-06,
565
+ "loss": 0.7904,
566
+ "step": 750
567
+ },
568
+ {
569
+ "epoch": 0.3514526710402999,
570
+ "eval_loss": 0.07609602808952332,
571
+ "eval_pearson_cosine": 0.7390127527190131,
572
+ "eval_pearson_dot": 0.6193519334256266,
573
+ "eval_pearson_euclidean": 0.7286540107637123,
574
+ "eval_pearson_manhattan": 0.7280163166143723,
575
+ "eval_runtime": 48.6286,
576
+ "eval_samples_per_second": 30.846,
577
+ "eval_spearman_cosine": 0.7392385981828663,
578
+ "eval_spearman_dot": 0.6275059521836013,
579
+ "eval_spearman_euclidean": 0.7379755721813188,
580
+ "eval_spearman_manhattan": 0.7372480627669395,
581
+ "eval_steps_per_second": 30.846,
582
+ "step": 750
583
+ },
584
+ {
585
+ "epoch": 0.3561387066541706,
586
+ "grad_norm": 5.931227207183838,
587
+ "learning_rate": 9.777413308341144e-06,
588
+ "loss": 0.7801,
589
+ "step": 760
590
+ },
591
+ {
592
+ "epoch": 0.36082474226804123,
593
+ "grad_norm": 5.550874710083008,
594
+ "learning_rate": 9.774484536082474e-06,
595
+ "loss": 0.7466,
596
+ "step": 770
597
+ },
598
+ {
599
+ "epoch": 0.3655107778819119,
600
+ "grad_norm": 5.67214298248291,
601
+ "learning_rate": 9.771555763823805e-06,
602
+ "loss": 0.7561,
603
+ "step": 780
604
+ },
605
+ {
606
+ "epoch": 0.3701968134957826,
607
+ "grad_norm": 5.121714115142822,
608
+ "learning_rate": 9.768626991565136e-06,
609
+ "loss": 0.7395,
610
+ "step": 790
611
+ },
612
+ {
613
+ "epoch": 0.37488284910965325,
614
+ "grad_norm": 4.957924842834473,
615
+ "learning_rate": 9.765698219306467e-06,
616
+ "loss": 0.7368,
617
+ "step": 800
618
+ },
619
+ {
620
+ "epoch": 0.3795688847235239,
621
+ "grad_norm": 6.30219030380249,
622
+ "learning_rate": 9.762769447047799e-06,
623
+ "loss": 0.8091,
624
+ "step": 810
625
+ },
626
+ {
627
+ "epoch": 0.38425492033739456,
628
+ "grad_norm": 6.518470287322998,
629
+ "learning_rate": 9.75984067478913e-06,
630
+ "loss": 0.7525,
631
+ "step": 820
632
+ },
633
+ {
634
+ "epoch": 0.3889409559512652,
635
+ "grad_norm": 6.101437568664551,
636
+ "learning_rate": 9.756911902530461e-06,
637
+ "loss": 0.7263,
638
+ "step": 830
639
+ },
640
+ {
641
+ "epoch": 0.3936269915651359,
642
+ "grad_norm": 5.428840160369873,
643
+ "learning_rate": 9.75398313027179e-06,
644
+ "loss": 0.7881,
645
+ "step": 840
646
+ },
647
+ {
648
+ "epoch": 0.3983130271790066,
649
+ "grad_norm": 7.170475482940674,
650
+ "learning_rate": 9.751054358013122e-06,
651
+ "loss": 0.7218,
652
+ "step": 850
653
+ },
654
+ {
655
+ "epoch": 0.4029990627928772,
656
+ "grad_norm": 6.153990745544434,
657
+ "learning_rate": 9.748125585754453e-06,
658
+ "loss": 0.748,
659
+ "step": 860
660
+ },
661
+ {
662
+ "epoch": 0.4076850984067479,
663
+ "grad_norm": 5.364086151123047,
664
+ "learning_rate": 9.745196813495782e-06,
665
+ "loss": 0.786,
666
+ "step": 870
667
+ },
668
+ {
669
+ "epoch": 0.41237113402061853,
670
+ "grad_norm": 5.541423797607422,
671
+ "learning_rate": 9.742268041237114e-06,
672
+ "loss": 0.7427,
673
+ "step": 880
674
+ },
675
+ {
676
+ "epoch": 0.41705716963448924,
677
+ "grad_norm": 5.1667022705078125,
678
+ "learning_rate": 9.739339268978445e-06,
679
+ "loss": 0.6918,
680
+ "step": 890
681
+ },
682
+ {
683
+ "epoch": 0.4217432052483599,
684
+ "grad_norm": 4.839612007141113,
685
+ "learning_rate": 9.736410496719776e-06,
686
+ "loss": 0.7056,
687
+ "step": 900
688
+ },
689
+ {
690
+ "epoch": 0.42642924086223055,
691
+ "grad_norm": 4.407963275909424,
692
+ "learning_rate": 9.733481724461107e-06,
693
+ "loss": 0.6313,
694
+ "step": 910
695
+ },
696
+ {
697
+ "epoch": 0.4311152764761012,
698
+ "grad_norm": 7.052595138549805,
699
+ "learning_rate": 9.730552952202438e-06,
700
+ "loss": 0.7489,
701
+ "step": 920
702
+ },
703
+ {
704
+ "epoch": 0.43580131208997186,
705
+ "grad_norm": 5.71290397644043,
706
+ "learning_rate": 9.727624179943768e-06,
707
+ "loss": 0.6578,
708
+ "step": 930
709
+ },
710
+ {
711
+ "epoch": 0.44048734770384257,
712
+ "grad_norm": 6.3575825691223145,
713
+ "learning_rate": 9.724695407685099e-06,
714
+ "loss": 0.6914,
715
+ "step": 940
716
+ },
717
+ {
718
+ "epoch": 0.4451733833177132,
719
+ "grad_norm": 5.223476886749268,
720
+ "learning_rate": 9.72176663542643e-06,
721
+ "loss": 0.6494,
722
+ "step": 950
723
+ },
724
+ {
725
+ "epoch": 0.4498594189315839,
726
+ "grad_norm": 6.220378398895264,
727
+ "learning_rate": 9.71883786316776e-06,
728
+ "loss": 0.6996,
729
+ "step": 960
730
+ },
731
+ {
732
+ "epoch": 0.45454545454545453,
733
+ "grad_norm": 6.475409507751465,
734
+ "learning_rate": 9.715909090909091e-06,
735
+ "loss": 0.721,
736
+ "step": 970
737
+ },
738
+ {
739
+ "epoch": 0.4592314901593252,
740
+ "grad_norm": 5.10095739364624,
741
+ "learning_rate": 9.712980318650422e-06,
742
+ "loss": 0.6734,
743
+ "step": 980
744
+ },
745
+ {
746
+ "epoch": 0.4639175257731959,
747
+ "grad_norm": 7.8438801765441895,
748
+ "learning_rate": 9.710051546391753e-06,
749
+ "loss": 0.7409,
750
+ "step": 990
751
+ },
752
+ {
753
+ "epoch": 0.46860356138706655,
754
+ "grad_norm": 5.446135997772217,
755
+ "learning_rate": 9.707122774133085e-06,
756
+ "loss": 0.6772,
757
+ "step": 1000
758
+ },
759
+ {
760
+ "epoch": 0.46860356138706655,
761
+ "eval_loss": 0.06938865035772324,
762
+ "eval_pearson_cosine": 0.7523242546763527,
763
+ "eval_pearson_dot": 0.6339033623348058,
764
+ "eval_pearson_euclidean": 0.7449881727323344,
765
+ "eval_pearson_manhattan": 0.7443626147120028,
766
+ "eval_runtime": 47.885,
767
+ "eval_samples_per_second": 31.325,
768
+ "eval_spearman_cosine": 0.7542578168613095,
769
+ "eval_spearman_dot": 0.6408093688850417,
770
+ "eval_spearman_euclidean": 0.7532432307302356,
771
+ "eval_spearman_manhattan": 0.7526380381288565,
772
+ "eval_steps_per_second": 31.325,
773
+ "step": 1000
774
+ }
775
+ ],
776
+ "logging_steps": 10,
777
+ "max_steps": 4268,
778
+ "num_input_tokens_seen": 0,
779
+ "num_train_epochs": 2,
780
+ "save_steps": 1000,
781
+ "stateful_callbacks": {
782
+ "TrainerControl": {
783
+ "args": {
784
+ "should_epoch_stop": false,
785
+ "should_evaluate": false,
786
+ "should_log": false,
787
+ "should_save": true,
788
+ "should_training_stop": false
789
+ },
790
+ "attributes": {}
791
+ }
792
+ },
793
+ "total_flos": 0.0,
794
+ "train_batch_size": 16,
795
+ "trial_name": null,
796
+ "trial_params": null
797
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:835e370164612fc33d7cfdf46af11a8006960745c8a6235c5705486ac7144766
3
+ size 5368
last-checkpoint/vocab.txt ADDED
The diff for this file is too large to render. See raw diff