tislamshuvo commited on
Commit
d85f89b
·
verified ·
1 Parent(s): 9e8600c

Initial model upload

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 0,
10
+ "head_dim": 64,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 576,
13
+ "initializer_range": 0.041666666666666664,
14
+ "intermediate_size": 1536,
15
+ "is_llama_config": true,
16
+ "max_position_embeddings": 8192,
17
+ "mlp_bias": false,
18
+ "model_type": "llama",
19
+ "num_attention_heads": 9,
20
+ "num_hidden_layers": 30,
21
+ "num_key_value_heads": 3,
22
+ "pad_token_id": 0,
23
+ "pretraining_tp": 1,
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_interleaved": false,
26
+ "rope_scaling": null,
27
+ "rope_theta": 100000,
28
+ "tie_word_embeddings": true,
29
+ "transformers_version": "4.56.2",
30
+ "use_cache": true,
31
+ "vocab_size": 97154
32
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": [
5
+ 0
6
+ ],
7
+ "pad_token_id": 0,
8
+ "transformers_version": "4.56.2"
9
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c2cfeaea47c6f35fff433cd46908d2b42e2223ef991fe548459b48543c5ca02
3
+ size 324358968
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69a02a5a60775fe23d4007addebf5b44d15d512bc933bacf2118f7e655fbb144
3
+ size 648889931
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
3
+ size 14645
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:476daabb4d46a00fb2f2d67cb5adab57c2e32b005871f042b95199db0f8b4eca
3
+ size 1465
special_tokens_map.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|eot_id|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|begin_of_text|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": {
19
+ "content": "<|endoftext|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "eos_token": {
26
+ "content": "<|endoftext|>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "pad_token": "<|endoftext|>",
33
+ "unk_token": {
34
+ "content": "<|endoftext|>",
35
+ "lstrip": false,
36
+ "normalized": false,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ }
40
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd747a4bed02fc295c3b037e4927c5265ad11534971b316e1db71b09ab15b4e0
3
+ size 12340639
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
trainer_state.json ADDED
@@ -0,0 +1,874 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.0648249186987478,
6
+ "eval_steps": 500,
7
+ "global_step": 6000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0005402076558228983,
14
+ "grad_norm": 4.3125,
15
+ "learning_rate": 1.7644940583363342e-06,
16
+ "loss": 1.7943,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.0010804153116457966,
21
+ "grad_norm": 4.28125,
22
+ "learning_rate": 3.5649981994958587e-06,
23
+ "loss": 1.7796,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.001620622967468695,
28
+ "grad_norm": 3.640625,
29
+ "learning_rate": 5.365502340655383e-06,
30
+ "loss": 1.7311,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.002160830623291593,
35
+ "grad_norm": 1.390625,
36
+ "learning_rate": 7.166006481814909e-06,
37
+ "loss": 1.7021,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.0027010382791144917,
42
+ "grad_norm": 2.890625,
43
+ "learning_rate": 8.966510622974434e-06,
44
+ "loss": 1.7806,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 0.00324124593493739,
49
+ "grad_norm": 1.15625,
50
+ "learning_rate": 1.0767014764133958e-05,
51
+ "loss": 1.7074,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 0.003781453590760288,
56
+ "grad_norm": 0.5390625,
57
+ "learning_rate": 1.2567518905293481e-05,
58
+ "loss": 1.6765,
59
+ "step": 350
60
+ },
61
+ {
62
+ "epoch": 0.004321661246583186,
63
+ "grad_norm": 1.078125,
64
+ "learning_rate": 1.4368023046453008e-05,
65
+ "loss": 1.6671,
66
+ "step": 400
67
+ },
68
+ {
69
+ "epoch": 0.004861868902406085,
70
+ "grad_norm": 0.455078125,
71
+ "learning_rate": 1.6168527187612533e-05,
72
+ "loss": 1.6235,
73
+ "step": 450
74
+ },
75
+ {
76
+ "epoch": 0.0054020765582289835,
77
+ "grad_norm": 0.2890625,
78
+ "learning_rate": 1.7969031328772056e-05,
79
+ "loss": 1.6529,
80
+ "step": 500
81
+ },
82
+ {
83
+ "epoch": 0.005942284214051881,
84
+ "grad_norm": 0.345703125,
85
+ "learning_rate": 1.9769535469931582e-05,
86
+ "loss": 1.559,
87
+ "step": 550
88
+ },
89
+ {
90
+ "epoch": 0.00648249186987478,
91
+ "grad_norm": 0.306640625,
92
+ "learning_rate": 2.1570039611091105e-05,
93
+ "loss": 1.5842,
94
+ "step": 600
95
+ },
96
+ {
97
+ "epoch": 0.007022699525697678,
98
+ "grad_norm": 0.359375,
99
+ "learning_rate": 2.337054375225063e-05,
100
+ "loss": 1.5504,
101
+ "step": 650
102
+ },
103
+ {
104
+ "epoch": 0.007562907181520576,
105
+ "grad_norm": 0.30859375,
106
+ "learning_rate": 2.5171047893410155e-05,
107
+ "loss": 1.5611,
108
+ "step": 700
109
+ },
110
+ {
111
+ "epoch": 0.008103114837343476,
112
+ "grad_norm": 0.91015625,
113
+ "learning_rate": 2.697155203456968e-05,
114
+ "loss": 1.5447,
115
+ "step": 750
116
+ },
117
+ {
118
+ "epoch": 0.008643322493166372,
119
+ "grad_norm": 0.359375,
120
+ "learning_rate": 2.8772056175729207e-05,
121
+ "loss": 1.546,
122
+ "step": 800
123
+ },
124
+ {
125
+ "epoch": 0.009183530148989271,
126
+ "grad_norm": 0.328125,
127
+ "learning_rate": 3.057256031688873e-05,
128
+ "loss": 1.5344,
129
+ "step": 850
130
+ },
131
+ {
132
+ "epoch": 0.00972373780481217,
133
+ "grad_norm": 0.29296875,
134
+ "learning_rate": 3.237306445804826e-05,
135
+ "loss": 1.4914,
136
+ "step": 900
137
+ },
138
+ {
139
+ "epoch": 0.010263945460635068,
140
+ "grad_norm": 0.29296875,
141
+ "learning_rate": 3.4173568599207777e-05,
142
+ "loss": 1.559,
143
+ "step": 950
144
+ },
145
+ {
146
+ "epoch": 0.010804153116457967,
147
+ "grad_norm": 0.283203125,
148
+ "learning_rate": 3.59740727403673e-05,
149
+ "loss": 1.485,
150
+ "step": 1000
151
+ },
152
+ {
153
+ "epoch": 0.011344360772280866,
154
+ "grad_norm": 0.263671875,
155
+ "learning_rate": 3.777457688152683e-05,
156
+ "loss": 1.4972,
157
+ "step": 1050
158
+ },
159
+ {
160
+ "epoch": 0.011884568428103762,
161
+ "grad_norm": 0.439453125,
162
+ "learning_rate": 3.9575081022686356e-05,
163
+ "loss": 1.45,
164
+ "step": 1100
165
+ },
166
+ {
167
+ "epoch": 0.012424776083926661,
168
+ "grad_norm": 0.3046875,
169
+ "learning_rate": 4.137558516384588e-05,
170
+ "loss": 1.4232,
171
+ "step": 1150
172
+ },
173
+ {
174
+ "epoch": 0.01296498373974956,
175
+ "grad_norm": 0.35546875,
176
+ "learning_rate": 4.31760893050054e-05,
177
+ "loss": 1.4098,
178
+ "step": 1200
179
+ },
180
+ {
181
+ "epoch": 0.013505191395572458,
182
+ "grad_norm": 0.330078125,
183
+ "learning_rate": 4.497659344616493e-05,
184
+ "loss": 1.3447,
185
+ "step": 1250
186
+ },
187
+ {
188
+ "epoch": 0.014045399051395357,
189
+ "grad_norm": 0.31640625,
190
+ "learning_rate": 4.6777097587324455e-05,
191
+ "loss": 1.35,
192
+ "step": 1300
193
+ },
194
+ {
195
+ "epoch": 0.014585606707218255,
196
+ "grad_norm": 0.37109375,
197
+ "learning_rate": 4.857760172848398e-05,
198
+ "loss": 1.3509,
199
+ "step": 1350
200
+ },
201
+ {
202
+ "epoch": 0.015125814363041152,
203
+ "grad_norm": 0.3515625,
204
+ "learning_rate": 5.03781058696435e-05,
205
+ "loss": 1.3161,
206
+ "step": 1400
207
+ },
208
+ {
209
+ "epoch": 0.01566602201886405,
210
+ "grad_norm": 0.27734375,
211
+ "learning_rate": 5.2178610010803034e-05,
212
+ "loss": 1.3277,
213
+ "step": 1450
214
+ },
215
+ {
216
+ "epoch": 0.01620622967468695,
217
+ "grad_norm": 0.37890625,
218
+ "learning_rate": 5.3979114151962554e-05,
219
+ "loss": 1.2814,
220
+ "step": 1500
221
+ },
222
+ {
223
+ "epoch": 0.016746437330509848,
224
+ "grad_norm": 0.31640625,
225
+ "learning_rate": 5.577961829312208e-05,
226
+ "loss": 1.2944,
227
+ "step": 1550
228
+ },
229
+ {
230
+ "epoch": 0.017286644986332745,
231
+ "grad_norm": 0.32421875,
232
+ "learning_rate": 5.75801224342816e-05,
233
+ "loss": 1.2714,
234
+ "step": 1600
235
+ },
236
+ {
237
+ "epoch": 0.017826852642155645,
238
+ "grad_norm": 0.3203125,
239
+ "learning_rate": 5.9380626575441126e-05,
240
+ "loss": 1.2847,
241
+ "step": 1650
242
+ },
243
+ {
244
+ "epoch": 0.018367060297978542,
245
+ "grad_norm": 0.390625,
246
+ "learning_rate": 6.118113071660065e-05,
247
+ "loss": 1.2828,
248
+ "step": 1700
249
+ },
250
+ {
251
+ "epoch": 0.018907267953801443,
252
+ "grad_norm": 0.33984375,
253
+ "learning_rate": 6.298163485776018e-05,
254
+ "loss": 1.252,
255
+ "step": 1750
256
+ },
257
+ {
258
+ "epoch": 0.01944747560962434,
259
+ "grad_norm": 0.35546875,
260
+ "learning_rate": 6.47821389989197e-05,
261
+ "loss": 1.2659,
262
+ "step": 1800
263
+ },
264
+ {
265
+ "epoch": 0.019987683265447236,
266
+ "grad_norm": 0.375,
267
+ "learning_rate": 6.658264314007923e-05,
268
+ "loss": 1.2429,
269
+ "step": 1850
270
+ },
271
+ {
272
+ "epoch": 0.020527890921270137,
273
+ "grad_norm": 0.357421875,
274
+ "learning_rate": 6.838314728123874e-05,
275
+ "loss": 1.2492,
276
+ "step": 1900
277
+ },
278
+ {
279
+ "epoch": 0.021068098577093033,
280
+ "grad_norm": 0.39453125,
281
+ "learning_rate": 7.018365142239827e-05,
282
+ "loss": 1.2083,
283
+ "step": 1950
284
+ },
285
+ {
286
+ "epoch": 0.021608306232915934,
287
+ "grad_norm": 0.3515625,
288
+ "learning_rate": 7.19841555635578e-05,
289
+ "loss": 1.2459,
290
+ "step": 2000
291
+ },
292
+ {
293
+ "epoch": 0.02214851388873883,
294
+ "grad_norm": 0.35546875,
295
+ "learning_rate": 7.378465970471732e-05,
296
+ "loss": 1.2101,
297
+ "step": 2050
298
+ },
299
+ {
300
+ "epoch": 0.02268872154456173,
301
+ "grad_norm": 0.34765625,
302
+ "learning_rate": 7.558516384587685e-05,
303
+ "loss": 1.1946,
304
+ "step": 2100
305
+ },
306
+ {
307
+ "epoch": 0.023228929200384628,
308
+ "grad_norm": 0.3671875,
309
+ "learning_rate": 7.738566798703636e-05,
310
+ "loss": 1.2097,
311
+ "step": 2150
312
+ },
313
+ {
314
+ "epoch": 0.023769136856207525,
315
+ "grad_norm": 0.400390625,
316
+ "learning_rate": 7.91861721281959e-05,
317
+ "loss": 1.1788,
318
+ "step": 2200
319
+ },
320
+ {
321
+ "epoch": 0.024309344512030425,
322
+ "grad_norm": 0.419921875,
323
+ "learning_rate": 8.098667626935542e-05,
324
+ "loss": 1.1804,
325
+ "step": 2250
326
+ },
327
+ {
328
+ "epoch": 0.024849552167853322,
329
+ "grad_norm": 0.419921875,
330
+ "learning_rate": 8.278718041051496e-05,
331
+ "loss": 1.2001,
332
+ "step": 2300
333
+ },
334
+ {
335
+ "epoch": 0.025389759823676222,
336
+ "grad_norm": 0.3828125,
337
+ "learning_rate": 8.458768455167447e-05,
338
+ "loss": 1.181,
339
+ "step": 2350
340
+ },
341
+ {
342
+ "epoch": 0.02592996747949912,
343
+ "grad_norm": 0.408203125,
344
+ "learning_rate": 8.6388188692834e-05,
345
+ "loss": 1.1763,
346
+ "step": 2400
347
+ },
348
+ {
349
+ "epoch": 0.02647017513532202,
350
+ "grad_norm": 0.431640625,
351
+ "learning_rate": 8.818869283399352e-05,
352
+ "loss": 1.1643,
353
+ "step": 2450
354
+ },
355
+ {
356
+ "epoch": 0.027010382791144916,
357
+ "grad_norm": 0.412109375,
358
+ "learning_rate": 8.998919697515305e-05,
359
+ "loss": 1.1801,
360
+ "step": 2500
361
+ },
362
+ {
363
+ "epoch": 0.027550590446967813,
364
+ "grad_norm": 0.42578125,
365
+ "learning_rate": 9.178970111631257e-05,
366
+ "loss": 1.1554,
367
+ "step": 2550
368
+ },
369
+ {
370
+ "epoch": 0.028090798102790714,
371
+ "grad_norm": 0.435546875,
372
+ "learning_rate": 9.35902052574721e-05,
373
+ "loss": 1.1682,
374
+ "step": 2600
375
+ },
376
+ {
377
+ "epoch": 0.02863100575861361,
378
+ "grad_norm": 0.400390625,
379
+ "learning_rate": 9.539070939863161e-05,
380
+ "loss": 1.1518,
381
+ "step": 2650
382
+ },
383
+ {
384
+ "epoch": 0.02917121341443651,
385
+ "grad_norm": 0.43359375,
386
+ "learning_rate": 9.719121353979115e-05,
387
+ "loss": 1.1331,
388
+ "step": 2700
389
+ },
390
+ {
391
+ "epoch": 0.029711421070259408,
392
+ "grad_norm": 0.44140625,
393
+ "learning_rate": 9.899171768095067e-05,
394
+ "loss": 1.1256,
395
+ "step": 2750
396
+ },
397
+ {
398
+ "epoch": 0.030251628726082305,
399
+ "grad_norm": 0.474609375,
400
+ "learning_rate": 0.00010079222182211019,
401
+ "loss": 1.1367,
402
+ "step": 2800
403
+ },
404
+ {
405
+ "epoch": 0.030791836381905205,
406
+ "grad_norm": 0.4765625,
407
+ "learning_rate": 0.00010259272596326972,
408
+ "loss": 1.1206,
409
+ "step": 2850
410
+ },
411
+ {
412
+ "epoch": 0.0313320440377281,
413
+ "grad_norm": 0.396484375,
414
+ "learning_rate": 0.00010439323010442925,
415
+ "loss": 1.1086,
416
+ "step": 2900
417
+ },
418
+ {
419
+ "epoch": 0.031872251693551,
420
+ "grad_norm": 0.451171875,
421
+ "learning_rate": 0.00010619373424558876,
422
+ "loss": 1.1455,
423
+ "step": 2950
424
+ },
425
+ {
426
+ "epoch": 0.0324124593493739,
427
+ "grad_norm": 0.5390625,
428
+ "learning_rate": 0.0001079942383867483,
429
+ "loss": 1.1079,
430
+ "step": 3000
431
+ },
432
+ {
433
+ "epoch": 0.0329526670051968,
434
+ "grad_norm": 0.46875,
435
+ "learning_rate": 0.00010979474252790783,
436
+ "loss": 1.0991,
437
+ "step": 3050
438
+ },
439
+ {
440
+ "epoch": 0.033492874661019696,
441
+ "grad_norm": 0.453125,
442
+ "learning_rate": 0.00011159524666906735,
443
+ "loss": 1.1154,
444
+ "step": 3100
445
+ },
446
+ {
447
+ "epoch": 0.03403308231684259,
448
+ "grad_norm": 0.439453125,
449
+ "learning_rate": 0.00011339575081022686,
450
+ "loss": 1.1002,
451
+ "step": 3150
452
+ },
453
+ {
454
+ "epoch": 0.03457328997266549,
455
+ "grad_norm": 0.462890625,
456
+ "learning_rate": 0.00011519625495138639,
457
+ "loss": 1.0997,
458
+ "step": 3200
459
+ },
460
+ {
461
+ "epoch": 0.035113497628488394,
462
+ "grad_norm": 0.412109375,
463
+ "learning_rate": 0.00011699675909254593,
464
+ "loss": 1.0754,
465
+ "step": 3250
466
+ },
467
+ {
468
+ "epoch": 0.03565370528431129,
469
+ "grad_norm": 0.486328125,
470
+ "learning_rate": 0.00011879726323370543,
471
+ "loss": 1.0933,
472
+ "step": 3300
473
+ },
474
+ {
475
+ "epoch": 0.03619391294013419,
476
+ "grad_norm": 0.408203125,
477
+ "learning_rate": 0.00012059776737486497,
478
+ "loss": 1.0764,
479
+ "step": 3350
480
+ },
481
+ {
482
+ "epoch": 0.036734120595957084,
483
+ "grad_norm": 0.453125,
484
+ "learning_rate": 0.0001223982715160245,
485
+ "loss": 1.1249,
486
+ "step": 3400
487
+ },
488
+ {
489
+ "epoch": 0.03727432825177998,
490
+ "grad_norm": 0.40234375,
491
+ "learning_rate": 0.000124198775657184,
492
+ "loss": 1.0746,
493
+ "step": 3450
494
+ },
495
+ {
496
+ "epoch": 0.037814535907602885,
497
+ "grad_norm": 0.51953125,
498
+ "learning_rate": 0.00012599927979834355,
499
+ "loss": 1.0747,
500
+ "step": 3500
501
+ },
502
+ {
503
+ "epoch": 0.03835474356342578,
504
+ "grad_norm": 0.44140625,
505
+ "learning_rate": 0.00012779978393950308,
506
+ "loss": 1.0814,
507
+ "step": 3550
508
+ },
509
+ {
510
+ "epoch": 0.03889495121924868,
511
+ "grad_norm": 0.5,
512
+ "learning_rate": 0.0001296002880806626,
513
+ "loss": 1.064,
514
+ "step": 3600
515
+ },
516
+ {
517
+ "epoch": 0.039435158875071576,
518
+ "grad_norm": 0.4453125,
519
+ "learning_rate": 0.0001314007922218221,
520
+ "loss": 1.0867,
521
+ "step": 3650
522
+ },
523
+ {
524
+ "epoch": 0.03997536653089447,
525
+ "grad_norm": 0.4296875,
526
+ "learning_rate": 0.00013320129636298166,
527
+ "loss": 1.066,
528
+ "step": 3700
529
+ },
530
+ {
531
+ "epoch": 0.040515574186717376,
532
+ "grad_norm": 0.51953125,
533
+ "learning_rate": 0.00013500180050414118,
534
+ "loss": 1.0721,
535
+ "step": 3750
536
+ },
537
+ {
538
+ "epoch": 0.04105578184254027,
539
+ "grad_norm": 0.482421875,
540
+ "learning_rate": 0.00013680230464530068,
541
+ "loss": 1.0518,
542
+ "step": 3800
543
+ },
544
+ {
545
+ "epoch": 0.04159598949836317,
546
+ "grad_norm": 0.466796875,
547
+ "learning_rate": 0.0001386028087864602,
548
+ "loss": 1.0495,
549
+ "step": 3850
550
+ },
551
+ {
552
+ "epoch": 0.04213619715418607,
553
+ "grad_norm": 0.39453125,
554
+ "learning_rate": 0.00014040331292761973,
555
+ "loss": 1.0292,
556
+ "step": 3900
557
+ },
558
+ {
559
+ "epoch": 0.04267640481000897,
560
+ "grad_norm": 0.4375,
561
+ "learning_rate": 0.00014220381706877926,
562
+ "loss": 1.031,
563
+ "step": 3950
564
+ },
565
+ {
566
+ "epoch": 0.04321661246583187,
567
+ "grad_norm": 0.48828125,
568
+ "learning_rate": 0.0001440043212099388,
569
+ "loss": 1.026,
570
+ "step": 4000
571
+ },
572
+ {
573
+ "epoch": 0.043756820121654764,
574
+ "grad_norm": 0.46875,
575
+ "learning_rate": 0.0001458048253510983,
576
+ "loss": 1.0372,
577
+ "step": 4050
578
+ },
579
+ {
580
+ "epoch": 0.04429702777747766,
581
+ "grad_norm": 0.396484375,
582
+ "learning_rate": 0.00014760532949225784,
583
+ "loss": 1.0388,
584
+ "step": 4100
585
+ },
586
+ {
587
+ "epoch": 0.04483723543330056,
588
+ "grad_norm": 0.4296875,
589
+ "learning_rate": 0.00014940583363341737,
590
+ "loss": 1.0258,
591
+ "step": 4150
592
+ },
593
+ {
594
+ "epoch": 0.04537744308912346,
595
+ "grad_norm": 0.478515625,
596
+ "learning_rate": 0.0001512063377745769,
597
+ "loss": 1.0111,
598
+ "step": 4200
599
+ },
600
+ {
601
+ "epoch": 0.04591765074494636,
602
+ "grad_norm": 0.46484375,
603
+ "learning_rate": 0.00015300684191573642,
604
+ "loss": 1.0316,
605
+ "step": 4250
606
+ },
607
+ {
608
+ "epoch": 0.046457858400769256,
609
+ "grad_norm": 0.5546875,
610
+ "learning_rate": 0.00015480734605689592,
611
+ "loss": 1.0375,
612
+ "step": 4300
613
+ },
614
+ {
615
+ "epoch": 0.04699806605659215,
616
+ "grad_norm": 0.408203125,
617
+ "learning_rate": 0.00015660785019805547,
618
+ "loss": 1.037,
619
+ "step": 4350
620
+ },
621
+ {
622
+ "epoch": 0.04753827371241505,
623
+ "grad_norm": 0.458984375,
624
+ "learning_rate": 0.000158408354339215,
625
+ "loss": 1.0172,
626
+ "step": 4400
627
+ },
628
+ {
629
+ "epoch": 0.04807848136823795,
630
+ "grad_norm": 0.455078125,
631
+ "learning_rate": 0.0001602088584803745,
632
+ "loss": 1.0482,
633
+ "step": 4450
634
+ },
635
+ {
636
+ "epoch": 0.04861868902406085,
637
+ "grad_norm": 0.451171875,
638
+ "learning_rate": 0.00016200936262153402,
639
+ "loss": 1.0072,
640
+ "step": 4500
641
+ },
642
+ {
643
+ "epoch": 0.04915889667988375,
644
+ "grad_norm": 0.63671875,
645
+ "learning_rate": 0.00016380986676269358,
646
+ "loss": 0.9988,
647
+ "step": 4550
648
+ },
649
+ {
650
+ "epoch": 0.049699104335706644,
651
+ "grad_norm": 0.42578125,
652
+ "learning_rate": 0.0001656103709038531,
653
+ "loss": 0.9998,
654
+ "step": 4600
655
+ },
656
+ {
657
+ "epoch": 0.05023931199152954,
658
+ "grad_norm": 0.5234375,
659
+ "learning_rate": 0.0001674108750450126,
660
+ "loss": 1.0084,
661
+ "step": 4650
662
+ },
663
+ {
664
+ "epoch": 0.050779519647352445,
665
+ "grad_norm": 0.498046875,
666
+ "learning_rate": 0.00016921137918617213,
667
+ "loss": 1.0152,
668
+ "step": 4700
669
+ },
670
+ {
671
+ "epoch": 0.05131972730317534,
672
+ "grad_norm": 0.48046875,
673
+ "learning_rate": 0.00017101188332733166,
674
+ "loss": 0.982,
675
+ "step": 4750
676
+ },
677
+ {
678
+ "epoch": 0.05185993495899824,
679
+ "grad_norm": 0.53515625,
680
+ "learning_rate": 0.00017281238746849118,
681
+ "loss": 1.0199,
682
+ "step": 4800
683
+ },
684
+ {
685
+ "epoch": 0.052400142614821135,
686
+ "grad_norm": 0.48828125,
687
+ "learning_rate": 0.0001746128916096507,
688
+ "loss": 1.0044,
689
+ "step": 4850
690
+ },
691
+ {
692
+ "epoch": 0.05294035027064404,
693
+ "grad_norm": 0.5078125,
694
+ "learning_rate": 0.00017641339575081024,
695
+ "loss": 0.9955,
696
+ "step": 4900
697
+ },
698
+ {
699
+ "epoch": 0.053480557926466936,
700
+ "grad_norm": 0.498046875,
701
+ "learning_rate": 0.00017821389989196976,
702
+ "loss": 0.9803,
703
+ "step": 4950
704
+ },
705
+ {
706
+ "epoch": 0.05402076558228983,
707
+ "grad_norm": 0.443359375,
708
+ "learning_rate": 0.0001800144040331293,
709
+ "loss": 1.0071,
710
+ "step": 5000
711
+ },
712
+ {
713
+ "epoch": 0.05456097323811273,
714
+ "grad_norm": 0.447265625,
715
+ "learning_rate": 0.00018181490817428881,
716
+ "loss": 0.9752,
717
+ "step": 5050
718
+ },
719
+ {
720
+ "epoch": 0.055101180893935627,
721
+ "grad_norm": 0.474609375,
722
+ "learning_rate": 0.00018361541231544834,
723
+ "loss": 0.9567,
724
+ "step": 5100
725
+ },
726
+ {
727
+ "epoch": 0.05564138854975853,
728
+ "grad_norm": 0.6171875,
729
+ "learning_rate": 0.00018541591645660784,
730
+ "loss": 0.9918,
731
+ "step": 5150
732
+ },
733
+ {
734
+ "epoch": 0.05618159620558143,
735
+ "grad_norm": 0.458984375,
736
+ "learning_rate": 0.0001872164205977674,
737
+ "loss": 0.9632,
738
+ "step": 5200
739
+ },
740
+ {
741
+ "epoch": 0.056721803861404324,
742
+ "grad_norm": 0.46484375,
743
+ "learning_rate": 0.00018901692473892692,
744
+ "loss": 0.9607,
745
+ "step": 5250
746
+ },
747
+ {
748
+ "epoch": 0.05726201151722722,
749
+ "grad_norm": 0.51171875,
750
+ "learning_rate": 0.00019081742888008642,
751
+ "loss": 0.96,
752
+ "step": 5300
753
+ },
754
+ {
755
+ "epoch": 0.05780221917305012,
756
+ "grad_norm": 0.474609375,
757
+ "learning_rate": 0.00019261793302124595,
758
+ "loss": 0.9752,
759
+ "step": 5350
760
+ },
761
+ {
762
+ "epoch": 0.05834242682887302,
763
+ "grad_norm": 0.45703125,
764
+ "learning_rate": 0.0001944184371624055,
765
+ "loss": 0.9782,
766
+ "step": 5400
767
+ },
768
+ {
769
+ "epoch": 0.05888263448469592,
770
+ "grad_norm": 0.498046875,
771
+ "learning_rate": 0.00019621894130356503,
772
+ "loss": 0.956,
773
+ "step": 5450
774
+ },
775
+ {
776
+ "epoch": 0.059422842140518815,
777
+ "grad_norm": 0.466796875,
778
+ "learning_rate": 0.00019801944544472453,
779
+ "loss": 0.9549,
780
+ "step": 5500
781
+ },
782
+ {
783
+ "epoch": 0.05996304979634171,
784
+ "grad_norm": 0.6171875,
785
+ "learning_rate": 0.00019981994958588405,
786
+ "loss": 0.9739,
787
+ "step": 5550
788
+ },
789
+ {
790
+ "epoch": 0.06050325745216461,
791
+ "grad_norm": 0.4765625,
792
+ "learning_rate": 0.00019999996900614756,
793
+ "loss": 0.9687,
794
+ "step": 5600
795
+ },
796
+ {
797
+ "epoch": 0.06104346510798751,
798
+ "grad_norm": 0.6171875,
799
+ "learning_rate": 0.0001999998618669291,
800
+ "loss": 0.97,
801
+ "step": 5650
802
+ },
803
+ {
804
+ "epoch": 0.06158367276381041,
805
+ "grad_norm": 0.451171875,
806
+ "learning_rate": 0.00019999967819978658,
807
+ "loss": 0.9493,
808
+ "step": 5700
809
+ },
810
+ {
811
+ "epoch": 0.06212388041963331,
812
+ "grad_norm": 0.447265625,
813
+ "learning_rate": 0.00019999941800486043,
814
+ "loss": 0.9411,
815
+ "step": 5750
816
+ },
817
+ {
818
+ "epoch": 0.0626640880754562,
819
+ "grad_norm": 0.640625,
820
+ "learning_rate": 0.00019999908128234985,
821
+ "loss": 0.9662,
822
+ "step": 5800
823
+ },
824
+ {
825
+ "epoch": 0.0632042957312791,
826
+ "grad_norm": 0.443359375,
827
+ "learning_rate": 0.0001999986680325125,
828
+ "loss": 0.9541,
829
+ "step": 5850
830
+ },
831
+ {
832
+ "epoch": 0.063744503387102,
833
+ "grad_norm": 0.44921875,
834
+ "learning_rate": 0.00019999817825566463,
835
+ "loss": 0.9312,
836
+ "step": 5900
837
+ },
838
+ {
839
+ "epoch": 0.0642847110429249,
840
+ "grad_norm": 0.45703125,
841
+ "learning_rate": 0.00019999761195218106,
842
+ "loss": 0.9492,
843
+ "step": 5950
844
+ },
845
+ {
846
+ "epoch": 0.0648249186987478,
847
+ "grad_norm": 0.466796875,
848
+ "learning_rate": 0.00019999696912249515,
849
+ "loss": 0.9508,
850
+ "step": 6000
851
+ }
852
+ ],
853
+ "logging_steps": 50,
854
+ "max_steps": 185114,
855
+ "num_input_tokens_seen": 0,
856
+ "num_train_epochs": 2,
857
+ "save_steps": 1000,
858
+ "stateful_callbacks": {
859
+ "TrainerControl": {
860
+ "args": {
861
+ "should_epoch_stop": false,
862
+ "should_evaluate": false,
863
+ "should_log": false,
864
+ "should_save": true,
865
+ "should_training_stop": false
866
+ },
867
+ "attributes": {}
868
+ }
869
+ },
870
+ "total_flos": 5.01130777853952e+17,
871
+ "train_batch_size": 8,
872
+ "trial_name": null,
873
+ "trial_params": null
874
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5348b2922954d15fa86c4d96d8f315f6b452c178eb542034ad6cc49b8b430335
3
+ size 5841
vocab.json ADDED
The diff for this file is too large to render. See raw diff