akhooli commited on
Commit
0c59e0f
·
verified ·
1 Parent(s): 7571e21

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertForMaskedLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": null,
8
+ "classifier_activation": "gelu",
9
+ "classifier_bias": false,
10
+ "classifier_dropout": 0.0,
11
+ "classifier_pooling": "cls",
12
+ "cls_token_id": 3,
13
+ "decoder_bias": true,
14
+ "deterministic_flash_attn": false,
15
+ "embedding_dropout": 0.0,
16
+ "eos_token_id": null,
17
+ "global_attn_every_n_layers": 3,
18
+ "global_rope_theta": 10000,
19
+ "hidden_activation": "gelu",
20
+ "hidden_size": 768,
21
+ "initializer_cutoff_factor": 2.0,
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 1152,
24
+ "local_attention": 128,
25
+ "local_rope_theta": 10000.0,
26
+ "max_position_embeddings": 8192,
27
+ "mlp_bias": false,
28
+ "mlp_dropout": 0.0,
29
+ "model_type": "modernbert",
30
+ "norm_bias": false,
31
+ "norm_eps": 1e-05,
32
+ "num_attention_heads": 12,
33
+ "num_hidden_layers": 22,
34
+ "pad_token_id": 5,
35
+ "reference_compile": true,
36
+ "repad_logits_with_grad": false,
37
+ "sep_token_id": 4,
38
+ "sparse_pred_ignore_index": -100,
39
+ "sparse_prediction": false,
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.49.0",
42
+ "vocab_size": 50368
43
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ca80306252ecf491162c2fb625c5b77fe987d5af2c055b66d5972800c7ebe31
3
+ size 598635032
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dfd91fda551d8d152525e9a0b4cf6fb8dd2f50121bb1e8f35aff103c38ff353
3
+ size 1197357242
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:136123f8fa6859d05c048f5e61a9f9bd6302a6488c25427b150f9bfd4da0cfe2
3
+ size 14244
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d141efe0baa86e25f20b5829646320f96870d5fa7a8a540ff40ebacb665317e
3
+ size 988
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c51d9685f77178924176b796774f52a6429136227be8fc9cf1afe3480a0d6631
3
+ size 1064
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": true,
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<|padding|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<|endoftext|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[UNK]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[CLS]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[SEP]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "[PAD]",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "[MASK]",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ }
59
+ },
60
+ "clean_up_tokenization_spaces": true,
61
+ "cls_token": "[CLS]",
62
+ "extra_special_tokens": {},
63
+ "mask_token": "[MASK]",
64
+ "model_input_names": [
65
+ "input_ids",
66
+ "attention_mask"
67
+ ],
68
+ "model_max_length": 8192,
69
+ "pad_token": "[PAD]",
70
+ "sep_token": "[SEP]",
71
+ "tokenizer_class": "PreTrainedTokenizer",
72
+ "unk_token": "[UNK]"
73
+ }
trainer_state.json ADDED
@@ -0,0 +1,453 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.12977265992858178,
5
+ "eval_steps": 500,
6
+ "global_step": 60000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.002162877665476363,
13
+ "grad_norm": 2.268080472946167,
14
+ "learning_rate": 4.9945869519559514e-05,
15
+ "loss": 7.7847,
16
+ "step": 1000
17
+ },
18
+ {
19
+ "epoch": 0.004325755330952726,
20
+ "grad_norm": 2.551193952560425,
21
+ "learning_rate": 4.983760855867853e-05,
22
+ "loss": 5.9343,
23
+ "step": 2000
24
+ },
25
+ {
26
+ "epoch": 0.006488632996429089,
27
+ "grad_norm": 2.584500551223755,
28
+ "learning_rate": 4.972934759779754e-05,
29
+ "loss": 5.3418,
30
+ "step": 3000
31
+ },
32
+ {
33
+ "epoch": 0.008651510661905452,
34
+ "grad_norm": 2.7399814128875732,
35
+ "learning_rate": 4.962108663691656e-05,
36
+ "loss": 4.9453,
37
+ "step": 4000
38
+ },
39
+ {
40
+ "epoch": 0.010814388327381816,
41
+ "grad_norm": 2.7650134563446045,
42
+ "learning_rate": 4.9512825676035575e-05,
43
+ "loss": 4.6277,
44
+ "step": 5000
45
+ },
46
+ {
47
+ "epoch": 0.012977265992858178,
48
+ "grad_norm": 2.8655128479003906,
49
+ "learning_rate": 4.9404564715154586e-05,
50
+ "loss": 4.3648,
51
+ "step": 6000
52
+ },
53
+ {
54
+ "epoch": 0.015140143658334541,
55
+ "grad_norm": 2.8312480449676514,
56
+ "learning_rate": 4.92963037542736e-05,
57
+ "loss": 4.1441,
58
+ "step": 7000
59
+ },
60
+ {
61
+ "epoch": 0.017303021323810903,
62
+ "grad_norm": 2.842963218688965,
63
+ "learning_rate": 4.918804279339262e-05,
64
+ "loss": 3.9787,
65
+ "step": 8000
66
+ },
67
+ {
68
+ "epoch": 0.019465898989287266,
69
+ "grad_norm": 2.6685407161712646,
70
+ "learning_rate": 4.907978183251164e-05,
71
+ "loss": 3.8343,
72
+ "step": 9000
73
+ },
74
+ {
75
+ "epoch": 0.02162877665476363,
76
+ "grad_norm": 2.7094473838806152,
77
+ "learning_rate": 4.897152087163065e-05,
78
+ "loss": 3.7211,
79
+ "step": 10000
80
+ },
81
+ {
82
+ "epoch": 0.023791654320239993,
83
+ "grad_norm": 2.7870073318481445,
84
+ "learning_rate": 4.886336817171055e-05,
85
+ "loss": 3.6358,
86
+ "step": 11000
87
+ },
88
+ {
89
+ "epoch": 0.025954531985716355,
90
+ "grad_norm": 2.6066818237304688,
91
+ "learning_rate": 4.8755107210829566e-05,
92
+ "loss": 3.5526,
93
+ "step": 12000
94
+ },
95
+ {
96
+ "epoch": 0.028117409651192717,
97
+ "grad_norm": 2.8119983673095703,
98
+ "learning_rate": 4.864695451090946e-05,
99
+ "loss": 3.4758,
100
+ "step": 13000
101
+ },
102
+ {
103
+ "epoch": 0.030280287316669083,
104
+ "grad_norm": 2.7353262901306152,
105
+ "learning_rate": 4.853869355002847e-05,
106
+ "loss": 3.4134,
107
+ "step": 14000
108
+ },
109
+ {
110
+ "epoch": 0.032443164982145445,
111
+ "grad_norm": 2.6471846103668213,
112
+ "learning_rate": 4.843054085010837e-05,
113
+ "loss": 3.3547,
114
+ "step": 15000
115
+ },
116
+ {
117
+ "epoch": 0.03460604264762181,
118
+ "grad_norm": 2.67105770111084,
119
+ "learning_rate": 4.832227988922739e-05,
120
+ "loss": 3.3033,
121
+ "step": 16000
122
+ },
123
+ {
124
+ "epoch": 0.03676892031309817,
125
+ "grad_norm": 2.667982339859009,
126
+ "learning_rate": 4.8214127189307287e-05,
127
+ "loss": 3.2608,
128
+ "step": 17000
129
+ },
130
+ {
131
+ "epoch": 0.03893179797857453,
132
+ "grad_norm": 2.588027238845825,
133
+ "learning_rate": 4.81058662284263e-05,
134
+ "loss": 3.2199,
135
+ "step": 18000
136
+ },
137
+ {
138
+ "epoch": 0.0410946756440509,
139
+ "grad_norm": 2.650073289871216,
140
+ "learning_rate": 4.799771352850619e-05,
141
+ "loss": 3.1817,
142
+ "step": 19000
143
+ },
144
+ {
145
+ "epoch": 0.04325755330952726,
146
+ "grad_norm": 2.4354302883148193,
147
+ "learning_rate": 4.788945256762521e-05,
148
+ "loss": 3.1464,
149
+ "step": 20000
150
+ },
151
+ {
152
+ "epoch": 0.045420430975003624,
153
+ "grad_norm": 2.6227738857269287,
154
+ "learning_rate": 4.778129986770511e-05,
155
+ "loss": 3.1134,
156
+ "step": 21000
157
+ },
158
+ {
159
+ "epoch": 0.047583308640479986,
160
+ "grad_norm": 2.5212135314941406,
161
+ "learning_rate": 4.767303890682412e-05,
162
+ "loss": 3.08,
163
+ "step": 22000
164
+ },
165
+ {
166
+ "epoch": 0.04974618630595635,
167
+ "grad_norm": 2.4768059253692627,
168
+ "learning_rate": 4.756488620690402e-05,
169
+ "loss": 3.0511,
170
+ "step": 23000
171
+ },
172
+ {
173
+ "epoch": 0.05190906397143271,
174
+ "grad_norm": 2.5772910118103027,
175
+ "learning_rate": 4.7456625246023034e-05,
176
+ "loss": 3.0225,
177
+ "step": 24000
178
+ },
179
+ {
180
+ "epoch": 0.05407194163690907,
181
+ "grad_norm": 2.4655566215515137,
182
+ "learning_rate": 4.7348472546102937e-05,
183
+ "loss": 3.0053,
184
+ "step": 25000
185
+ },
186
+ {
187
+ "epoch": 0.056234819302385435,
188
+ "grad_norm": 2.432565212249756,
189
+ "learning_rate": 4.724021158522195e-05,
190
+ "loss": 2.9726,
191
+ "step": 26000
192
+ },
193
+ {
194
+ "epoch": 0.058397696967861804,
195
+ "grad_norm": 2.437964677810669,
196
+ "learning_rate": 4.7131950624340964e-05,
197
+ "loss": 2.9542,
198
+ "step": 27000
199
+ },
200
+ {
201
+ "epoch": 0.060560574633338166,
202
+ "grad_norm": 2.498307466506958,
203
+ "learning_rate": 4.702379792442086e-05,
204
+ "loss": 2.9373,
205
+ "step": 28000
206
+ },
207
+ {
208
+ "epoch": 0.06272345229881453,
209
+ "grad_norm": 2.3338165283203125,
210
+ "learning_rate": 4.6915536963539876e-05,
211
+ "loss": 2.9143,
212
+ "step": 29000
213
+ },
214
+ {
215
+ "epoch": 0.06488632996429089,
216
+ "grad_norm": 2.2597150802612305,
217
+ "learning_rate": 4.680738426361977e-05,
218
+ "loss": 2.8947,
219
+ "step": 30000
220
+ },
221
+ {
222
+ "epoch": 0.06704920762976725,
223
+ "grad_norm": 2.3500025272369385,
224
+ "learning_rate": 4.669912330273879e-05,
225
+ "loss": 2.8729,
226
+ "step": 31000
227
+ },
228
+ {
229
+ "epoch": 0.06921208529524361,
230
+ "grad_norm": 2.592963457107544,
231
+ "learning_rate": 4.6590970602818684e-05,
232
+ "loss": 2.8638,
233
+ "step": 32000
234
+ },
235
+ {
236
+ "epoch": 0.07137496296071998,
237
+ "grad_norm": 2.2916111946105957,
238
+ "learning_rate": 4.64827096419377e-05,
239
+ "loss": 2.8423,
240
+ "step": 33000
241
+ },
242
+ {
243
+ "epoch": 0.07353784062619634,
244
+ "grad_norm": 2.298884153366089,
245
+ "learning_rate": 4.63745569420176e-05,
246
+ "loss": 2.8258,
247
+ "step": 34000
248
+ },
249
+ {
250
+ "epoch": 0.0757007182916727,
251
+ "grad_norm": 2.2187180519104004,
252
+ "learning_rate": 4.6266295981136614e-05,
253
+ "loss": 2.8085,
254
+ "step": 35000
255
+ },
256
+ {
257
+ "epoch": 0.07786359595714906,
258
+ "grad_norm": 2.3649799823760986,
259
+ "learning_rate": 4.615814328121651e-05,
260
+ "loss": 2.7946,
261
+ "step": 36000
262
+ },
263
+ {
264
+ "epoch": 0.08002647362262542,
265
+ "grad_norm": 2.189671754837036,
266
+ "learning_rate": 4.6049882320335526e-05,
267
+ "loss": 2.7828,
268
+ "step": 37000
269
+ },
270
+ {
271
+ "epoch": 0.0821893512881018,
272
+ "grad_norm": 2.341826915740967,
273
+ "learning_rate": 4.594172962041542e-05,
274
+ "loss": 2.7706,
275
+ "step": 38000
276
+ },
277
+ {
278
+ "epoch": 0.08435222895357816,
279
+ "grad_norm": 2.3907382488250732,
280
+ "learning_rate": 4.583346865953443e-05,
281
+ "loss": 2.7548,
282
+ "step": 39000
283
+ },
284
+ {
285
+ "epoch": 0.08651510661905452,
286
+ "grad_norm": 2.2284059524536133,
287
+ "learning_rate": 4.5725315959614334e-05,
288
+ "loss": 2.7453,
289
+ "step": 40000
290
+ },
291
+ {
292
+ "epoch": 0.08867798428453089,
293
+ "grad_norm": 2.254753589630127,
294
+ "learning_rate": 4.561705499873335e-05,
295
+ "loss": 2.7335,
296
+ "step": 41000
297
+ },
298
+ {
299
+ "epoch": 0.09084086195000725,
300
+ "grad_norm": 2.2830395698547363,
301
+ "learning_rate": 4.550890229881325e-05,
302
+ "loss": 2.7188,
303
+ "step": 42000
304
+ },
305
+ {
306
+ "epoch": 0.09300373961548361,
307
+ "grad_norm": 2.2295284271240234,
308
+ "learning_rate": 4.540064133793226e-05,
309
+ "loss": 2.7066,
310
+ "step": 43000
311
+ },
312
+ {
313
+ "epoch": 0.09516661728095997,
314
+ "grad_norm": 2.177199602127075,
315
+ "learning_rate": 4.529248863801216e-05,
316
+ "loss": 2.6916,
317
+ "step": 44000
318
+ },
319
+ {
320
+ "epoch": 0.09732949494643633,
321
+ "grad_norm": 2.0382652282714844,
322
+ "learning_rate": 4.5184227677131176e-05,
323
+ "loss": 2.6852,
324
+ "step": 45000
325
+ },
326
+ {
327
+ "epoch": 0.0994923726119127,
328
+ "grad_norm": 2.240755319595337,
329
+ "learning_rate": 4.507607497721107e-05,
330
+ "loss": 2.6793,
331
+ "step": 46000
332
+ },
333
+ {
334
+ "epoch": 0.10165525027738906,
335
+ "grad_norm": 2.1940410137176514,
336
+ "learning_rate": 4.496781401633008e-05,
337
+ "loss": 2.6659,
338
+ "step": 47000
339
+ },
340
+ {
341
+ "epoch": 0.10381812794286542,
342
+ "grad_norm": 2.203796148300171,
343
+ "learning_rate": 4.4859661316409984e-05,
344
+ "loss": 2.6526,
345
+ "step": 48000
346
+ },
347
+ {
348
+ "epoch": 0.10598100560834178,
349
+ "grad_norm": 2.1186819076538086,
350
+ "learning_rate": 4.4751400355529e-05,
351
+ "loss": 2.6463,
352
+ "step": 49000
353
+ },
354
+ {
355
+ "epoch": 0.10814388327381814,
356
+ "grad_norm": 2.13010573387146,
357
+ "learning_rate": 4.46432476556089e-05,
358
+ "loss": 2.6403,
359
+ "step": 50000
360
+ },
361
+ {
362
+ "epoch": 0.11030676093929451,
363
+ "grad_norm": 2.1970157623291016,
364
+ "learning_rate": 4.4535094955688785e-05,
365
+ "loss": 2.6276,
366
+ "step": 51000
367
+ },
368
+ {
369
+ "epoch": 0.11246963860477087,
370
+ "grad_norm": 2.1742944717407227,
371
+ "learning_rate": 4.44268339948078e-05,
372
+ "loss": 2.6178,
373
+ "step": 52000
374
+ },
375
+ {
376
+ "epoch": 0.11463251627024724,
377
+ "grad_norm": 2.195935010910034,
378
+ "learning_rate": 4.4318681294887705e-05,
379
+ "loss": 2.6095,
380
+ "step": 53000
381
+ },
382
+ {
383
+ "epoch": 0.11679539393572361,
384
+ "grad_norm": 2.0977721214294434,
385
+ "learning_rate": 4.421042033400672e-05,
386
+ "loss": 2.6037,
387
+ "step": 54000
388
+ },
389
+ {
390
+ "epoch": 0.11895827160119997,
391
+ "grad_norm": 2.1214547157287598,
392
+ "learning_rate": 4.410215937312573e-05,
393
+ "loss": 2.5962,
394
+ "step": 55000
395
+ },
396
+ {
397
+ "epoch": 0.12112114926667633,
398
+ "grad_norm": 2.216897964477539,
399
+ "learning_rate": 4.399400667320563e-05,
400
+ "loss": 2.5881,
401
+ "step": 56000
402
+ },
403
+ {
404
+ "epoch": 0.1232840269321527,
405
+ "grad_norm": 2.1751599311828613,
406
+ "learning_rate": 4.3885745712324644e-05,
407
+ "loss": 2.5817,
408
+ "step": 57000
409
+ },
410
+ {
411
+ "epoch": 0.12544690459762906,
412
+ "grad_norm": 2.1866142749786377,
413
+ "learning_rate": 4.377748475144366e-05,
414
+ "loss": 2.5691,
415
+ "step": 58000
416
+ },
417
+ {
418
+ "epoch": 0.1276097822631054,
419
+ "grad_norm": 2.1192381381988525,
420
+ "learning_rate": 4.366933205152356e-05,
421
+ "loss": 2.5649,
422
+ "step": 59000
423
+ },
424
+ {
425
+ "epoch": 0.12977265992858178,
426
+ "grad_norm": 1.9748364686965942,
427
+ "learning_rate": 4.3561071090642574e-05,
428
+ "loss": 2.5535,
429
+ "step": 60000
430
+ }
431
+ ],
432
+ "logging_steps": 1000,
433
+ "max_steps": 462347,
434
+ "num_input_tokens_seen": 0,
435
+ "num_train_epochs": 1,
436
+ "save_steps": 10000,
437
+ "stateful_callbacks": {
438
+ "TrainerControl": {
439
+ "args": {
440
+ "should_epoch_stop": false,
441
+ "should_evaluate": false,
442
+ "should_log": false,
443
+ "should_save": true,
444
+ "should_training_stop": false
445
+ },
446
+ "attributes": {}
447
+ }
448
+ },
449
+ "total_flos": 1.30908615081984e+18,
450
+ "train_batch_size": 64,
451
+ "trial_name": null,
452
+ "trial_params": null
453
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b6d41263ff08360456e69ddad182f5fd2c333d98f562b278c707f6a008397b6
3
+ size 5240