muxdev commited on
Commit
65d69de
·
verified ·
1 Parent(s): 96d02f2

Upload 11 files

Browse files
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "add_cross_attention": false,
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "dtype": "float32",
10
+ "embd_pdrop": 0.1,
11
+ "eos_token_id": 50256,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 1024,
16
+ "n_embd": 768,
17
+ "n_head": 12,
18
+ "n_inner": null,
19
+ "n_layer": 12,
20
+ "n_positions": 1024,
21
+ "name": "Lumin Alpha-100",
22
+ "pad_token_id": null,
23
+ "reorder_and_upcast_attn": false,
24
+ "resid_pdrop": 0.1,
25
+ "scale_attn_by_inverse_layer_idx": false,
26
+ "scale_attn_weights": true,
27
+ "summary_activation": null,
28
+ "summary_first_dropout": 0.1,
29
+ "summary_proj_to_labels": true,
30
+ "summary_type": "cls_index",
31
+ "summary_use_proj": true,
32
+ "tie_word_embeddings": true,
33
+ "transformers_version": "5.0.0",
34
+ "use_cache": false,
35
+ "vocab_size": 50258
36
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "transformers_version": "5.0.0",
8
+ "use_cache": true
9
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bcb5e06ec55cf339bf62a047a6f4cc85dc2a7e2bf6602da36dbb6f6c2db0922
3
+ size 497777280
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc1ad8224fa17c7a08344ef7767b9dd53cea985ddaf0b938b72b3865a0230ccc
3
+ size 995650955
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22ce081b3261b95a64ec4332ae1de5b74222eb033c00d6782045d3d87d1e100e
3
+ size 14645
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82ad8990572ad11a824b7db276c8af49c179ca7e7724b4e6906cd0ae480a80a8
3
+ size 1383
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:644e3826492e0199f95f4d6b5fb3d6db6067e2bdad6c66909988fc86684ffa9e
3
+ size 1465
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "eos_token": "<|endoftext|>",
6
+ "errors": "replace",
7
+ "is_local": false,
8
+ "model_max_length": 1024,
9
+ "pad_token": "<|pad|>",
10
+ "tokenizer_class": "GPT2Tokenizer",
11
+ "unk_token": "<|endoftext|>"
12
+ }
trainer_state.json ADDED
@@ -0,0 +1,734 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
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": 0.01,
14
+ "grad_norm": 2.332974433898926,
15
+ "learning_rate": 1.9804000000000002e-05,
16
+ "loss": 9.66635009765625,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.02,
21
+ "grad_norm": 1.6665964126586914,
22
+ "learning_rate": 1.9604e-05,
23
+ "loss": 8.088862915039062,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.03,
28
+ "grad_norm": 2.068279504776001,
29
+ "learning_rate": 1.9404e-05,
30
+ "loss": 7.215781860351562,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.04,
35
+ "grad_norm": 1.76992666721344,
36
+ "learning_rate": 1.9204e-05,
37
+ "loss": 6.690926513671875,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.05,
42
+ "grad_norm": 1.480324149131775,
43
+ "learning_rate": 1.9004000000000003e-05,
44
+ "loss": 6.430185546875,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 0.06,
49
+ "grad_norm": 1.1323567628860474,
50
+ "learning_rate": 1.8804e-05,
51
+ "loss": 6.076779174804687,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 0.07,
56
+ "grad_norm": 1.248739242553711,
57
+ "learning_rate": 1.8604000000000003e-05,
58
+ "loss": 6.090475463867188,
59
+ "step": 350
60
+ },
61
+ {
62
+ "epoch": 0.08,
63
+ "grad_norm": 1.2340136766433716,
64
+ "learning_rate": 1.8404000000000002e-05,
65
+ "loss": 6.04998046875,
66
+ "step": 400
67
+ },
68
+ {
69
+ "epoch": 0.09,
70
+ "grad_norm": 1.1271188259124756,
71
+ "learning_rate": 1.8204e-05,
72
+ "loss": 5.8744744873046875,
73
+ "step": 450
74
+ },
75
+ {
76
+ "epoch": 0.1,
77
+ "grad_norm": 1.7444993257522583,
78
+ "learning_rate": 1.8004000000000002e-05,
79
+ "loss": 5.79928466796875,
80
+ "step": 500
81
+ },
82
+ {
83
+ "epoch": 0.11,
84
+ "grad_norm": 1.294396162033081,
85
+ "learning_rate": 1.7804e-05,
86
+ "loss": 5.830994873046875,
87
+ "step": 550
88
+ },
89
+ {
90
+ "epoch": 0.12,
91
+ "grad_norm": 1.1351591348648071,
92
+ "learning_rate": 1.7604e-05,
93
+ "loss": 5.764346313476563,
94
+ "step": 600
95
+ },
96
+ {
97
+ "epoch": 0.13,
98
+ "grad_norm": 1.6005209684371948,
99
+ "learning_rate": 1.7404e-05,
100
+ "loss": 5.688011474609375,
101
+ "step": 650
102
+ },
103
+ {
104
+ "epoch": 0.14,
105
+ "grad_norm": 1.3918774127960205,
106
+ "learning_rate": 1.7204e-05,
107
+ "loss": 5.67168212890625,
108
+ "step": 700
109
+ },
110
+ {
111
+ "epoch": 0.15,
112
+ "grad_norm": 1.0998594760894775,
113
+ "learning_rate": 1.7004000000000002e-05,
114
+ "loss": 5.563177490234375,
115
+ "step": 750
116
+ },
117
+ {
118
+ "epoch": 0.16,
119
+ "grad_norm": 1.2702234983444214,
120
+ "learning_rate": 1.6804e-05,
121
+ "loss": 5.638896484375,
122
+ "step": 800
123
+ },
124
+ {
125
+ "epoch": 0.17,
126
+ "grad_norm": 1.2025340795516968,
127
+ "learning_rate": 1.6604000000000002e-05,
128
+ "loss": 5.447022705078125,
129
+ "step": 850
130
+ },
131
+ {
132
+ "epoch": 0.18,
133
+ "grad_norm": 1.0838000774383545,
134
+ "learning_rate": 1.6404e-05,
135
+ "loss": 5.563392944335938,
136
+ "step": 900
137
+ },
138
+ {
139
+ "epoch": 0.19,
140
+ "grad_norm": 1.6105167865753174,
141
+ "learning_rate": 1.6204000000000003e-05,
142
+ "loss": 5.441434326171875,
143
+ "step": 950
144
+ },
145
+ {
146
+ "epoch": 0.2,
147
+ "grad_norm": 1.195156455039978,
148
+ "learning_rate": 1.6004e-05,
149
+ "loss": 5.535233154296875,
150
+ "step": 1000
151
+ },
152
+ {
153
+ "epoch": 0.21,
154
+ "grad_norm": 1.3313252925872803,
155
+ "learning_rate": 1.5804000000000003e-05,
156
+ "loss": 5.4950341796875,
157
+ "step": 1050
158
+ },
159
+ {
160
+ "epoch": 0.22,
161
+ "grad_norm": 1.2405613660812378,
162
+ "learning_rate": 1.5604000000000002e-05,
163
+ "loss": 5.525492553710937,
164
+ "step": 1100
165
+ },
166
+ {
167
+ "epoch": 0.23,
168
+ "grad_norm": 1.3697841167449951,
169
+ "learning_rate": 1.5404e-05,
170
+ "loss": 5.394120483398438,
171
+ "step": 1150
172
+ },
173
+ {
174
+ "epoch": 0.24,
175
+ "grad_norm": 1.6689515113830566,
176
+ "learning_rate": 1.5204e-05,
177
+ "loss": 5.42336181640625,
178
+ "step": 1200
179
+ },
180
+ {
181
+ "epoch": 0.25,
182
+ "grad_norm": 1.6169382333755493,
183
+ "learning_rate": 1.5004e-05,
184
+ "loss": 5.263718872070313,
185
+ "step": 1250
186
+ },
187
+ {
188
+ "epoch": 0.26,
189
+ "grad_norm": 1.3931348323822021,
190
+ "learning_rate": 1.4804000000000001e-05,
191
+ "loss": 5.332710571289063,
192
+ "step": 1300
193
+ },
194
+ {
195
+ "epoch": 0.27,
196
+ "grad_norm": 1.3986672163009644,
197
+ "learning_rate": 1.4604000000000001e-05,
198
+ "loss": 5.300538330078125,
199
+ "step": 1350
200
+ },
201
+ {
202
+ "epoch": 0.28,
203
+ "grad_norm": 1.2856848239898682,
204
+ "learning_rate": 1.4404e-05,
205
+ "loss": 5.265980834960938,
206
+ "step": 1400
207
+ },
208
+ {
209
+ "epoch": 0.29,
210
+ "grad_norm": 1.4729372262954712,
211
+ "learning_rate": 1.4204000000000002e-05,
212
+ "loss": 5.241402587890625,
213
+ "step": 1450
214
+ },
215
+ {
216
+ "epoch": 0.3,
217
+ "grad_norm": 1.5896576642990112,
218
+ "learning_rate": 1.4004000000000002e-05,
219
+ "loss": 5.286559448242188,
220
+ "step": 1500
221
+ },
222
+ {
223
+ "epoch": 0.31,
224
+ "grad_norm": 1.5870860815048218,
225
+ "learning_rate": 1.3804000000000002e-05,
226
+ "loss": 5.2646923828125,
227
+ "step": 1550
228
+ },
229
+ {
230
+ "epoch": 0.32,
231
+ "grad_norm": 1.9024347066879272,
232
+ "learning_rate": 1.3604000000000002e-05,
233
+ "loss": 5.213834838867188,
234
+ "step": 1600
235
+ },
236
+ {
237
+ "epoch": 0.33,
238
+ "grad_norm": 1.545648217201233,
239
+ "learning_rate": 1.3404e-05,
240
+ "loss": 5.284638671875,
241
+ "step": 1650
242
+ },
243
+ {
244
+ "epoch": 0.34,
245
+ "grad_norm": 1.7494972944259644,
246
+ "learning_rate": 1.3204000000000001e-05,
247
+ "loss": 5.29470703125,
248
+ "step": 1700
249
+ },
250
+ {
251
+ "epoch": 0.35,
252
+ "grad_norm": 1.534767746925354,
253
+ "learning_rate": 1.3004000000000001e-05,
254
+ "loss": 5.17380126953125,
255
+ "step": 1750
256
+ },
257
+ {
258
+ "epoch": 0.36,
259
+ "grad_norm": 1.9378814697265625,
260
+ "learning_rate": 1.2804000000000001e-05,
261
+ "loss": 5.2462841796875,
262
+ "step": 1800
263
+ },
264
+ {
265
+ "epoch": 0.37,
266
+ "grad_norm": 1.7414913177490234,
267
+ "learning_rate": 1.2604e-05,
268
+ "loss": 5.184336547851562,
269
+ "step": 1850
270
+ },
271
+ {
272
+ "epoch": 0.38,
273
+ "grad_norm": 1.312013030052185,
274
+ "learning_rate": 1.2404e-05,
275
+ "loss": 5.2285107421875,
276
+ "step": 1900
277
+ },
278
+ {
279
+ "epoch": 0.39,
280
+ "grad_norm": 2.7188756465911865,
281
+ "learning_rate": 1.2204e-05,
282
+ "loss": 5.183685302734375,
283
+ "step": 1950
284
+ },
285
+ {
286
+ "epoch": 0.4,
287
+ "grad_norm": 1.5776464939117432,
288
+ "learning_rate": 1.2004e-05,
289
+ "loss": 5.212086181640625,
290
+ "step": 2000
291
+ },
292
+ {
293
+ "epoch": 0.41,
294
+ "grad_norm": 1.8002684116363525,
295
+ "learning_rate": 1.1803999999999999e-05,
296
+ "loss": 5.187786865234375,
297
+ "step": 2050
298
+ },
299
+ {
300
+ "epoch": 0.42,
301
+ "grad_norm": 1.690958023071289,
302
+ "learning_rate": 1.1604000000000003e-05,
303
+ "loss": 5.070486145019531,
304
+ "step": 2100
305
+ },
306
+ {
307
+ "epoch": 0.43,
308
+ "grad_norm": 1.566103219985962,
309
+ "learning_rate": 1.1404000000000001e-05,
310
+ "loss": 5.091676330566406,
311
+ "step": 2150
312
+ },
313
+ {
314
+ "epoch": 0.44,
315
+ "grad_norm": 1.6997359991073608,
316
+ "learning_rate": 1.1204000000000001e-05,
317
+ "loss": 5.151467895507812,
318
+ "step": 2200
319
+ },
320
+ {
321
+ "epoch": 0.45,
322
+ "grad_norm": 1.4722249507904053,
323
+ "learning_rate": 1.1004000000000002e-05,
324
+ "loss": 5.095538024902344,
325
+ "step": 2250
326
+ },
327
+ {
328
+ "epoch": 0.46,
329
+ "grad_norm": 1.7524068355560303,
330
+ "learning_rate": 1.0804000000000002e-05,
331
+ "loss": 5.041690673828125,
332
+ "step": 2300
333
+ },
334
+ {
335
+ "epoch": 0.47,
336
+ "grad_norm": 1.56508207321167,
337
+ "learning_rate": 1.0604e-05,
338
+ "loss": 5.047481689453125,
339
+ "step": 2350
340
+ },
341
+ {
342
+ "epoch": 0.48,
343
+ "grad_norm": 1.5206327438354492,
344
+ "learning_rate": 1.0404e-05,
345
+ "loss": 5.138922119140625,
346
+ "step": 2400
347
+ },
348
+ {
349
+ "epoch": 0.49,
350
+ "grad_norm": 1.7860289812088013,
351
+ "learning_rate": 1.0204000000000001e-05,
352
+ "loss": 5.1789208984375,
353
+ "step": 2450
354
+ },
355
+ {
356
+ "epoch": 0.5,
357
+ "grad_norm": 1.762772798538208,
358
+ "learning_rate": 1.0004000000000001e-05,
359
+ "loss": 4.9995901489257815,
360
+ "step": 2500
361
+ },
362
+ {
363
+ "epoch": 0.51,
364
+ "grad_norm": 1.9011698961257935,
365
+ "learning_rate": 9.804000000000001e-06,
366
+ "loss": 5.030536804199219,
367
+ "step": 2550
368
+ },
369
+ {
370
+ "epoch": 0.52,
371
+ "grad_norm": 1.7511317729949951,
372
+ "learning_rate": 9.604000000000002e-06,
373
+ "loss": 5.054608459472656,
374
+ "step": 2600
375
+ },
376
+ {
377
+ "epoch": 0.53,
378
+ "grad_norm": 1.454971194267273,
379
+ "learning_rate": 9.404e-06,
380
+ "loss": 5.037495422363281,
381
+ "step": 2650
382
+ },
383
+ {
384
+ "epoch": 0.54,
385
+ "grad_norm": 1.5396337509155273,
386
+ "learning_rate": 9.204e-06,
387
+ "loss": 5.031622314453125,
388
+ "step": 2700
389
+ },
390
+ {
391
+ "epoch": 0.55,
392
+ "grad_norm": 1.467636227607727,
393
+ "learning_rate": 9.004e-06,
394
+ "loss": 5.0833673095703125,
395
+ "step": 2750
396
+ },
397
+ {
398
+ "epoch": 0.56,
399
+ "grad_norm": 1.5613443851470947,
400
+ "learning_rate": 8.804e-06,
401
+ "loss": 4.928188171386719,
402
+ "step": 2800
403
+ },
404
+ {
405
+ "epoch": 0.57,
406
+ "grad_norm": 1.7963453531265259,
407
+ "learning_rate": 8.604000000000001e-06,
408
+ "loss": 5.066728515625,
409
+ "step": 2850
410
+ },
411
+ {
412
+ "epoch": 0.58,
413
+ "grad_norm": 1.9899804592132568,
414
+ "learning_rate": 8.404000000000001e-06,
415
+ "loss": 4.9547052001953125,
416
+ "step": 2900
417
+ },
418
+ {
419
+ "epoch": 0.59,
420
+ "grad_norm": 1.502890944480896,
421
+ "learning_rate": 8.204000000000001e-06,
422
+ "loss": 5.096377868652343,
423
+ "step": 2950
424
+ },
425
+ {
426
+ "epoch": 0.6,
427
+ "grad_norm": 1.554468035697937,
428
+ "learning_rate": 8.004e-06,
429
+ "loss": 5.010852966308594,
430
+ "step": 3000
431
+ },
432
+ {
433
+ "epoch": 0.61,
434
+ "grad_norm": 1.768509030342102,
435
+ "learning_rate": 7.804e-06,
436
+ "loss": 4.954717102050782,
437
+ "step": 3050
438
+ },
439
+ {
440
+ "epoch": 0.62,
441
+ "grad_norm": 1.5894496440887451,
442
+ "learning_rate": 7.604e-06,
443
+ "loss": 4.946051025390625,
444
+ "step": 3100
445
+ },
446
+ {
447
+ "epoch": 0.63,
448
+ "grad_norm": 1.7610846757888794,
449
+ "learning_rate": 7.404e-06,
450
+ "loss": 4.855561828613281,
451
+ "step": 3150
452
+ },
453
+ {
454
+ "epoch": 0.64,
455
+ "grad_norm": 1.7571163177490234,
456
+ "learning_rate": 7.204000000000001e-06,
457
+ "loss": 4.930430297851562,
458
+ "step": 3200
459
+ },
460
+ {
461
+ "epoch": 0.65,
462
+ "grad_norm": 1.6853914260864258,
463
+ "learning_rate": 7.004000000000001e-06,
464
+ "loss": 4.855824584960938,
465
+ "step": 3250
466
+ },
467
+ {
468
+ "epoch": 0.66,
469
+ "grad_norm": 1.4607149362564087,
470
+ "learning_rate": 6.804e-06,
471
+ "loss": 5.078975524902344,
472
+ "step": 3300
473
+ },
474
+ {
475
+ "epoch": 0.67,
476
+ "grad_norm": 1.9196784496307373,
477
+ "learning_rate": 6.604000000000001e-06,
478
+ "loss": 4.9388720703125,
479
+ "step": 3350
480
+ },
481
+ {
482
+ "epoch": 0.68,
483
+ "grad_norm": 1.8639936447143555,
484
+ "learning_rate": 6.404e-06,
485
+ "loss": 4.99400146484375,
486
+ "step": 3400
487
+ },
488
+ {
489
+ "epoch": 0.69,
490
+ "grad_norm": 1.7838945388793945,
491
+ "learning_rate": 6.204e-06,
492
+ "loss": 4.887441101074219,
493
+ "step": 3450
494
+ },
495
+ {
496
+ "epoch": 0.7,
497
+ "grad_norm": 1.659825086593628,
498
+ "learning_rate": 6.004000000000001e-06,
499
+ "loss": 4.677823181152344,
500
+ "step": 3500
501
+ },
502
+ {
503
+ "epoch": 0.71,
504
+ "grad_norm": 1.4775367975234985,
505
+ "learning_rate": 5.804000000000001e-06,
506
+ "loss": 4.8725653076171875,
507
+ "step": 3550
508
+ },
509
+ {
510
+ "epoch": 0.72,
511
+ "grad_norm": 1.4383823871612549,
512
+ "learning_rate": 5.604000000000001e-06,
513
+ "loss": 4.973861389160156,
514
+ "step": 3600
515
+ },
516
+ {
517
+ "epoch": 0.73,
518
+ "grad_norm": 1.7640321254730225,
519
+ "learning_rate": 5.404e-06,
520
+ "loss": 4.926856994628906,
521
+ "step": 3650
522
+ },
523
+ {
524
+ "epoch": 0.74,
525
+ "grad_norm": 1.3515348434448242,
526
+ "learning_rate": 5.2040000000000005e-06,
527
+ "loss": 4.904393005371094,
528
+ "step": 3700
529
+ },
530
+ {
531
+ "epoch": 0.75,
532
+ "grad_norm": 1.3852506875991821,
533
+ "learning_rate": 5.004e-06,
534
+ "loss": 4.93823486328125,
535
+ "step": 3750
536
+ },
537
+ {
538
+ "epoch": 0.76,
539
+ "grad_norm": 1.5573221445083618,
540
+ "learning_rate": 4.804e-06,
541
+ "loss": 4.901606140136718,
542
+ "step": 3800
543
+ },
544
+ {
545
+ "epoch": 0.77,
546
+ "grad_norm": 1.7575520277023315,
547
+ "learning_rate": 4.604e-06,
548
+ "loss": 4.8115087890625,
549
+ "step": 3850
550
+ },
551
+ {
552
+ "epoch": 0.78,
553
+ "grad_norm": 1.5037921667099,
554
+ "learning_rate": 4.4040000000000005e-06,
555
+ "loss": 4.910712890625,
556
+ "step": 3900
557
+ },
558
+ {
559
+ "epoch": 0.79,
560
+ "grad_norm": 2.2725980281829834,
561
+ "learning_rate": 4.204e-06,
562
+ "loss": 4.771448364257813,
563
+ "step": 3950
564
+ },
565
+ {
566
+ "epoch": 0.8,
567
+ "grad_norm": 1.4463030099868774,
568
+ "learning_rate": 4.004e-06,
569
+ "loss": 4.809368286132813,
570
+ "step": 4000
571
+ },
572
+ {
573
+ "epoch": 0.81,
574
+ "grad_norm": 1.726515293121338,
575
+ "learning_rate": 3.8040000000000003e-06,
576
+ "loss": 4.944158935546875,
577
+ "step": 4050
578
+ },
579
+ {
580
+ "epoch": 0.82,
581
+ "grad_norm": 1.6566334962844849,
582
+ "learning_rate": 3.604e-06,
583
+ "loss": 4.9215576171875,
584
+ "step": 4100
585
+ },
586
+ {
587
+ "epoch": 0.83,
588
+ "grad_norm": 1.5525240898132324,
589
+ "learning_rate": 3.404e-06,
590
+ "loss": 4.8733984375,
591
+ "step": 4150
592
+ },
593
+ {
594
+ "epoch": 0.84,
595
+ "grad_norm": 1.4844027757644653,
596
+ "learning_rate": 3.2040000000000006e-06,
597
+ "loss": 4.825590515136719,
598
+ "step": 4200
599
+ },
600
+ {
601
+ "epoch": 0.85,
602
+ "grad_norm": 1.5394399166107178,
603
+ "learning_rate": 3.0040000000000004e-06,
604
+ "loss": 4.887457580566406,
605
+ "step": 4250
606
+ },
607
+ {
608
+ "epoch": 0.86,
609
+ "grad_norm": 1.463205099105835,
610
+ "learning_rate": 2.804e-06,
611
+ "loss": 4.960470275878906,
612
+ "step": 4300
613
+ },
614
+ {
615
+ "epoch": 0.87,
616
+ "grad_norm": 1.674668550491333,
617
+ "learning_rate": 2.6040000000000004e-06,
618
+ "loss": 4.964275207519531,
619
+ "step": 4350
620
+ },
621
+ {
622
+ "epoch": 0.88,
623
+ "grad_norm": 1.597741723060608,
624
+ "learning_rate": 2.404e-06,
625
+ "loss": 4.844057312011719,
626
+ "step": 4400
627
+ },
628
+ {
629
+ "epoch": 0.89,
630
+ "grad_norm": 1.4939367771148682,
631
+ "learning_rate": 2.2040000000000004e-06,
632
+ "loss": 4.818087463378906,
633
+ "step": 4450
634
+ },
635
+ {
636
+ "epoch": 0.9,
637
+ "grad_norm": 1.5718450546264648,
638
+ "learning_rate": 2.004e-06,
639
+ "loss": 4.905419006347656,
640
+ "step": 4500
641
+ },
642
+ {
643
+ "epoch": 0.91,
644
+ "grad_norm": 1.5969394445419312,
645
+ "learning_rate": 1.8040000000000002e-06,
646
+ "loss": 4.818899230957031,
647
+ "step": 4550
648
+ },
649
+ {
650
+ "epoch": 0.92,
651
+ "grad_norm": 1.6721904277801514,
652
+ "learning_rate": 1.604e-06,
653
+ "loss": 4.901571044921875,
654
+ "step": 4600
655
+ },
656
+ {
657
+ "epoch": 0.93,
658
+ "grad_norm": 1.3588262796401978,
659
+ "learning_rate": 1.404e-06,
660
+ "loss": 4.869562377929688,
661
+ "step": 4650
662
+ },
663
+ {
664
+ "epoch": 0.94,
665
+ "grad_norm": 1.6911239624023438,
666
+ "learning_rate": 1.204e-06,
667
+ "loss": 4.782047729492188,
668
+ "step": 4700
669
+ },
670
+ {
671
+ "epoch": 0.95,
672
+ "grad_norm": 1.359279990196228,
673
+ "learning_rate": 1.004e-06,
674
+ "loss": 4.815296936035156,
675
+ "step": 4750
676
+ },
677
+ {
678
+ "epoch": 0.96,
679
+ "grad_norm": 1.4526113271713257,
680
+ "learning_rate": 8.04e-07,
681
+ "loss": 4.827503051757812,
682
+ "step": 4800
683
+ },
684
+ {
685
+ "epoch": 0.97,
686
+ "grad_norm": 1.6256376504898071,
687
+ "learning_rate": 6.040000000000001e-07,
688
+ "loss": 4.810068359375,
689
+ "step": 4850
690
+ },
691
+ {
692
+ "epoch": 0.98,
693
+ "grad_norm": 1.2820252180099487,
694
+ "learning_rate": 4.04e-07,
695
+ "loss": 4.8670956420898435,
696
+ "step": 4900
697
+ },
698
+ {
699
+ "epoch": 0.99,
700
+ "grad_norm": 1.3670392036437988,
701
+ "learning_rate": 2.0400000000000003e-07,
702
+ "loss": 4.911158447265625,
703
+ "step": 4950
704
+ },
705
+ {
706
+ "epoch": 1.0,
707
+ "grad_norm": 1.4537466764450073,
708
+ "learning_rate": 4e-09,
709
+ "loss": 4.827361145019531,
710
+ "step": 5000
711
+ }
712
+ ],
713
+ "logging_steps": 50,
714
+ "max_steps": 5000,
715
+ "num_input_tokens_seen": 0,
716
+ "num_train_epochs": 1,
717
+ "save_steps": 500,
718
+ "stateful_callbacks": {
719
+ "TrainerControl": {
720
+ "args": {
721
+ "should_epoch_stop": false,
722
+ "should_evaluate": false,
723
+ "should_log": false,
724
+ "should_save": true,
725
+ "should_training_stop": true
726
+ },
727
+ "attributes": {}
728
+ }
729
+ },
730
+ "total_flos": 2.090336256e+16,
731
+ "train_batch_size": 2,
732
+ "trial_name": null,
733
+ "trial_params": null
734
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30527db78841562abfff3f36b89fad8921976f4bb8369289bfe5c14856912d67
3
+ size 5137