TinyPixel commited on
Commit
fa167dc
1 Parent(s): 9df55f0

Upload folder using huggingface_hub

Browse files
adapter_config.json CHANGED
@@ -19,10 +19,10 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
- "query_key_value",
23
  "dense_h_to_4h",
24
  "dense_4h_to_h",
25
- "dense"
26
  ],
27
  "task_type": "CAUSAL_LM",
28
  "use_rslora": false
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
+ "dense",
23
  "dense_h_to_4h",
24
  "dense_4h_to_h",
25
+ "query_key_value"
26
  ],
27
  "task_type": "CAUSAL_LM",
28
  "use_rslora": false
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78671cff9d3d469914f3eb2d167c737aa6cc70f611534e82c140624b1d8cabea
3
  size 134235712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8551ab343ef5e8756f53d7454de355fbf4b3367bec32cd436fb2109f4cb2b96
3
  size 134235712
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:acd30d14f8b142894f0998e147031f021f807282127debd24edbf18c6c5a3921
3
  size 268514874
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0761fd66f7e9f27517b9cdc385248f873232decf6233d679c16ce939ed446c6d
3
  size 268514874
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6055acff3008c750d0114c2c3bf07b24308bcfe96bb48724f0b78d4c3dc5b6d2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a273e635a3dbe6f12de8531b896d85c09b670ee924a5c5d5c034c9f1e364651e
3
  size 14244
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:393139604afddfb6660b2e3c4a2918802f1119180d7aaa0f39ebae93c8bd7d80
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b371ae767212827ffe8a91587d7467c4f40f93812413ed6571b08320a4c26332
3
  size 1064
special_tokens_map.json CHANGED
@@ -1,4 +1,20 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "bos_token": {
3
  "content": "<|endoftext|>",
4
  "lstrip": false,
@@ -14,7 +30,7 @@
14
  "single_word": false
15
  },
16
  "pad_token": {
17
- "content": "[PAD]",
18
  "lstrip": false,
19
  "normalized": false,
20
  "rstrip": false,
 
1
  {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|prompter|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|assistant|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
  "bos_token": {
19
  "content": "<|endoftext|>",
20
  "lstrip": false,
 
30
  "single_word": false
31
  },
32
  "pad_token": {
33
+ "content": "<|padding|>",
34
  "lstrip": false,
35
  "normalized": false,
36
  "rstrip": false,
tokenizer.json CHANGED
@@ -235,7 +235,16 @@
235
  },
236
  {
237
  "id": 50277,
238
- "content": "[PAD]",
 
 
 
 
 
 
 
 
 
239
  "single_word": false,
240
  "lstrip": false,
241
  "rstrip": false,
 
235
  },
236
  {
237
  "id": 50277,
238
+ "content": "<|prompter|>",
239
+ "single_word": false,
240
+ "lstrip": false,
241
+ "rstrip": false,
242
+ "normalized": false,
243
+ "special": true
244
+ },
245
+ {
246
+ "id": 50278,
247
+ "content": "<|assistant|>",
248
  "single_word": false,
249
  "lstrip": false,
250
  "rstrip": false,
tokenizer_config.json CHANGED
@@ -202,7 +202,15 @@
202
  "special": false
203
  },
204
  "50277": {
205
- "content": "[PAD]",
 
 
 
 
 
 
 
 
206
  "lstrip": false,
207
  "normalized": false,
208
  "rstrip": false,
@@ -210,11 +218,15 @@
210
  "special": true
211
  }
212
  },
 
 
 
 
213
  "bos_token": "<|endoftext|>",
214
  "clean_up_tokenization_spaces": true,
215
  "eos_token": "<|endoftext|>",
216
  "model_max_length": 1000000000000000019884624838656,
217
- "pad_token": "[PAD]",
218
  "tokenizer_class": "GPTNeoXTokenizer",
219
  "unk_token": "<|endoftext|>"
220
  }
 
202
  "special": false
203
  },
204
  "50277": {
205
+ "content": "<|prompter|>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "50278": {
213
+ "content": "<|assistant|>",
214
  "lstrip": false,
215
  "normalized": false,
216
  "rstrip": false,
 
218
  "special": true
219
  }
220
  },
221
+ "additional_special_tokens": [
222
+ "<|prompter|>",
223
+ "<|assistant|>"
224
+ ],
225
  "bos_token": "<|endoftext|>",
226
  "clean_up_tokenization_spaces": true,
227
  "eos_token": "<|endoftext|>",
228
  "model_max_length": 1000000000000000019884624838656,
229
+ "pad_token": "<|padding|>",
230
  "tokenizer_class": "GPTNeoXTokenizer",
231
  "unk_token": "<|endoftext|>"
232
  }
trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 2.953846153846154,
5
  "eval_steps": 500,
6
- "global_step": 144,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -11,442 +11,154 @@
11
  {
12
  "epoch": 0.04,
13
  "learning_rate": 0.0002,
14
- "loss": 2.2923,
15
  "step": 2
16
  },
17
  {
18
  "epoch": 0.08,
19
  "learning_rate": 0.0002,
20
- "loss": 2.4944,
21
  "step": 4
22
  },
23
  {
24
  "epoch": 0.12,
25
  "learning_rate": 0.0002,
26
- "loss": 2.5643,
27
  "step": 6
28
  },
29
  {
30
  "epoch": 0.16,
31
  "learning_rate": 0.0002,
32
- "loss": 2.5449,
33
  "step": 8
34
  },
35
  {
36
  "epoch": 0.21,
37
  "learning_rate": 0.0002,
38
- "loss": 2.5427,
39
  "step": 10
40
  },
41
  {
42
  "epoch": 0.25,
43
  "learning_rate": 0.0002,
44
- "loss": 2.8026,
45
  "step": 12
46
  },
47
  {
48
  "epoch": 0.29,
49
  "learning_rate": 0.0002,
50
- "loss": 2.2733,
51
  "step": 14
52
  },
53
  {
54
  "epoch": 0.33,
55
  "learning_rate": 0.0002,
56
- "loss": 2.3667,
57
  "step": 16
58
  },
59
  {
60
  "epoch": 0.37,
61
  "learning_rate": 0.0002,
62
- "loss": 2.633,
63
  "step": 18
64
  },
65
  {
66
  "epoch": 0.41,
67
  "learning_rate": 0.0002,
68
- "loss": 2.4816,
69
  "step": 20
70
  },
71
  {
72
  "epoch": 0.45,
73
  "learning_rate": 0.0002,
74
- "loss": 2.6263,
75
  "step": 22
76
  },
77
  {
78
  "epoch": 0.49,
79
  "learning_rate": 0.0002,
80
- "loss": 2.5695,
81
  "step": 24
82
  },
83
  {
84
  "epoch": 0.53,
85
  "learning_rate": 0.0002,
86
- "loss": 2.223,
87
  "step": 26
88
  },
89
  {
90
  "epoch": 0.57,
91
  "learning_rate": 0.0002,
92
- "loss": 2.261,
93
  "step": 28
94
  },
95
  {
96
  "epoch": 0.62,
97
  "learning_rate": 0.0002,
98
- "loss": 2.3568,
99
  "step": 30
100
  },
101
  {
102
  "epoch": 0.66,
103
  "learning_rate": 0.0002,
104
- "loss": 2.6185,
105
  "step": 32
106
  },
107
  {
108
  "epoch": 0.7,
109
  "learning_rate": 0.0002,
110
- "loss": 2.5005,
111
  "step": 34
112
  },
113
  {
114
  "epoch": 0.74,
115
  "learning_rate": 0.0002,
116
- "loss": 2.7505,
117
  "step": 36
118
  },
119
  {
120
  "epoch": 0.78,
121
  "learning_rate": 0.0002,
122
- "loss": 2.1988,
123
  "step": 38
124
  },
125
  {
126
  "epoch": 0.82,
127
  "learning_rate": 0.0002,
128
- "loss": 2.1159,
129
  "step": 40
130
  },
131
  {
132
  "epoch": 0.86,
133
  "learning_rate": 0.0002,
134
- "loss": 2.4971,
135
  "step": 42
136
  },
137
  {
138
  "epoch": 0.9,
139
  "learning_rate": 0.0002,
140
- "loss": 2.5058,
141
  "step": 44
142
  },
143
  {
144
  "epoch": 0.94,
145
  "learning_rate": 0.0002,
146
- "loss": 2.5139,
147
  "step": 46
148
  },
149
  {
150
  "epoch": 0.98,
151
  "learning_rate": 0.0002,
152
- "loss": 2.4968,
153
  "step": 48
154
- },
155
- {
156
- "epoch": 1.03,
157
- "learning_rate": 0.0002,
158
- "loss": 2.2284,
159
- "step": 50
160
- },
161
- {
162
- "epoch": 1.07,
163
- "learning_rate": 0.0002,
164
- "loss": 2.2673,
165
- "step": 52
166
- },
167
- {
168
- "epoch": 1.11,
169
- "learning_rate": 0.0002,
170
- "loss": 2.3655,
171
- "step": 54
172
- },
173
- {
174
- "epoch": 1.15,
175
- "learning_rate": 0.0002,
176
- "loss": 2.2416,
177
- "step": 56
178
- },
179
- {
180
- "epoch": 1.19,
181
- "learning_rate": 0.0002,
182
- "loss": 2.3234,
183
- "step": 58
184
- },
185
- {
186
- "epoch": 1.23,
187
- "learning_rate": 0.0002,
188
- "loss": 2.42,
189
- "step": 60
190
- },
191
- {
192
- "epoch": 1.27,
193
- "learning_rate": 0.0002,
194
- "loss": 2.2975,
195
- "step": 62
196
- },
197
- {
198
- "epoch": 1.31,
199
- "learning_rate": 0.0002,
200
- "loss": 2.1622,
201
- "step": 64
202
- },
203
- {
204
- "epoch": 1.35,
205
- "learning_rate": 0.0002,
206
- "loss": 2.4531,
207
- "step": 66
208
- },
209
- {
210
- "epoch": 1.39,
211
- "learning_rate": 0.0002,
212
- "loss": 2.5373,
213
- "step": 68
214
- },
215
- {
216
- "epoch": 1.44,
217
- "learning_rate": 0.0002,
218
- "loss": 2.47,
219
- "step": 70
220
- },
221
- {
222
- "epoch": 1.48,
223
- "learning_rate": 0.0002,
224
- "loss": 2.4924,
225
- "step": 72
226
- },
227
- {
228
- "epoch": 1.52,
229
- "learning_rate": 0.0002,
230
- "loss": 2.2274,
231
- "step": 74
232
- },
233
- {
234
- "epoch": 1.56,
235
- "learning_rate": 0.0002,
236
- "loss": 2.2213,
237
- "step": 76
238
- },
239
- {
240
- "epoch": 1.6,
241
- "learning_rate": 0.0002,
242
- "loss": 2.2334,
243
- "step": 78
244
- },
245
- {
246
- "epoch": 1.64,
247
- "learning_rate": 0.0002,
248
- "loss": 2.3033,
249
- "step": 80
250
- },
251
- {
252
- "epoch": 1.68,
253
- "learning_rate": 0.0002,
254
- "loss": 2.3899,
255
- "step": 82
256
- },
257
- {
258
- "epoch": 1.72,
259
- "learning_rate": 0.0002,
260
- "loss": 2.3991,
261
- "step": 84
262
- },
263
- {
264
- "epoch": 1.76,
265
- "learning_rate": 0.0002,
266
- "loss": 2.1522,
267
- "step": 86
268
- },
269
- {
270
- "epoch": 1.81,
271
- "learning_rate": 0.0002,
272
- "loss": 2.343,
273
- "step": 88
274
- },
275
- {
276
- "epoch": 1.85,
277
- "learning_rate": 0.0002,
278
- "loss": 2.4061,
279
- "step": 90
280
- },
281
- {
282
- "epoch": 1.89,
283
- "learning_rate": 0.0002,
284
- "loss": 2.4116,
285
- "step": 92
286
- },
287
- {
288
- "epoch": 1.93,
289
- "learning_rate": 0.0002,
290
- "loss": 2.4976,
291
- "step": 94
292
- },
293
- {
294
- "epoch": 1.97,
295
- "learning_rate": 0.0002,
296
- "loss": 2.4427,
297
- "step": 96
298
- },
299
- {
300
- "epoch": 2.01,
301
- "learning_rate": 0.0002,
302
- "loss": 2.4328,
303
- "step": 98
304
- },
305
- {
306
- "epoch": 2.05,
307
- "learning_rate": 0.0002,
308
- "loss": 2.1793,
309
- "step": 100
310
- },
311
- {
312
- "epoch": 2.09,
313
- "learning_rate": 0.0002,
314
- "loss": 2.3683,
315
- "step": 102
316
- },
317
- {
318
- "epoch": 2.13,
319
- "learning_rate": 0.0002,
320
- "loss": 2.5376,
321
- "step": 104
322
- },
323
- {
324
- "epoch": 2.17,
325
- "learning_rate": 0.0002,
326
- "loss": 2.1945,
327
- "step": 106
328
- },
329
- {
330
- "epoch": 2.22,
331
- "learning_rate": 0.0002,
332
- "loss": 2.1629,
333
- "step": 108
334
- },
335
- {
336
- "epoch": 2.26,
337
- "learning_rate": 0.0002,
338
- "loss": 2.1191,
339
- "step": 110
340
- },
341
- {
342
- "epoch": 2.3,
343
- "learning_rate": 0.0002,
344
- "loss": 2.1457,
345
- "step": 112
346
- },
347
- {
348
- "epoch": 2.34,
349
- "learning_rate": 0.0002,
350
- "loss": 2.2078,
351
- "step": 114
352
- },
353
- {
354
- "epoch": 2.38,
355
- "learning_rate": 0.0002,
356
- "loss": 2.4336,
357
- "step": 116
358
- },
359
- {
360
- "epoch": 2.42,
361
- "learning_rate": 0.0002,
362
- "loss": 2.4243,
363
- "step": 118
364
- },
365
- {
366
- "epoch": 2.46,
367
- "learning_rate": 0.0002,
368
- "loss": 2.3391,
369
- "step": 120
370
- },
371
- {
372
- "epoch": 2.5,
373
- "learning_rate": 0.0002,
374
- "loss": 2.0758,
375
- "step": 122
376
- },
377
- {
378
- "epoch": 2.54,
379
- "learning_rate": 0.0002,
380
- "loss": 2.2001,
381
- "step": 124
382
- },
383
- {
384
- "epoch": 2.58,
385
- "learning_rate": 0.0002,
386
- "loss": 2.2007,
387
- "step": 126
388
- },
389
- {
390
- "epoch": 2.63,
391
- "learning_rate": 0.0002,
392
- "loss": 2.3695,
393
- "step": 128
394
- },
395
- {
396
- "epoch": 2.67,
397
- "learning_rate": 0.0002,
398
- "loss": 2.3721,
399
- "step": 130
400
- },
401
- {
402
- "epoch": 2.71,
403
- "learning_rate": 0.0002,
404
- "loss": 2.2898,
405
- "step": 132
406
- },
407
- {
408
- "epoch": 2.75,
409
- "learning_rate": 0.0002,
410
- "loss": 1.9498,
411
- "step": 134
412
- },
413
- {
414
- "epoch": 2.79,
415
- "learning_rate": 0.0002,
416
- "loss": 2.187,
417
- "step": 136
418
- },
419
- {
420
- "epoch": 2.83,
421
- "learning_rate": 0.0002,
422
- "loss": 2.0774,
423
- "step": 138
424
- },
425
- {
426
- "epoch": 2.87,
427
- "learning_rate": 0.0002,
428
- "loss": 2.3311,
429
- "step": 140
430
- },
431
- {
432
- "epoch": 2.91,
433
- "learning_rate": 0.0002,
434
- "loss": 2.3446,
435
- "step": 142
436
- },
437
- {
438
- "epoch": 2.95,
439
- "learning_rate": 0.0002,
440
- "loss": 2.3359,
441
- "step": 144
442
  }
443
  ],
444
  "logging_steps": 2,
445
- "max_steps": 144,
446
  "num_input_tokens_seen": 0,
447
- "num_train_epochs": 3,
448
  "save_steps": 500,
449
- "total_flos": 6200486723076096.0,
450
  "train_batch_size": 1,
451
  "trial_name": null,
452
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.9846153846153847,
5
  "eval_steps": 500,
6
+ "global_step": 48,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
11
  {
12
  "epoch": 0.04,
13
  "learning_rate": 0.0002,
14
+ "loss": 2.2836,
15
  "step": 2
16
  },
17
  {
18
  "epoch": 0.08,
19
  "learning_rate": 0.0002,
20
+ "loss": 2.4552,
21
  "step": 4
22
  },
23
  {
24
  "epoch": 0.12,
25
  "learning_rate": 0.0002,
26
+ "loss": 2.7222,
27
  "step": 6
28
  },
29
  {
30
  "epoch": 0.16,
31
  "learning_rate": 0.0002,
32
+ "loss": 2.6656,
33
  "step": 8
34
  },
35
  {
36
  "epoch": 0.21,
37
  "learning_rate": 0.0002,
38
+ "loss": 2.6016,
39
  "step": 10
40
  },
41
  {
42
  "epoch": 0.25,
43
  "learning_rate": 0.0002,
44
+ "loss": 3.1001,
45
  "step": 12
46
  },
47
  {
48
  "epoch": 0.29,
49
  "learning_rate": 0.0002,
50
+ "loss": 2.2399,
51
  "step": 14
52
  },
53
  {
54
  "epoch": 0.33,
55
  "learning_rate": 0.0002,
56
+ "loss": 2.3808,
57
  "step": 16
58
  },
59
  {
60
  "epoch": 0.37,
61
  "learning_rate": 0.0002,
62
+ "loss": 2.412,
63
  "step": 18
64
  },
65
  {
66
  "epoch": 0.41,
67
  "learning_rate": 0.0002,
68
+ "loss": 2.5426,
69
  "step": 20
70
  },
71
  {
72
  "epoch": 0.45,
73
  "learning_rate": 0.0002,
74
+ "loss": 2.7169,
75
  "step": 22
76
  },
77
  {
78
  "epoch": 0.49,
79
  "learning_rate": 0.0002,
80
+ "loss": 2.9043,
81
  "step": 24
82
  },
83
  {
84
  "epoch": 0.53,
85
  "learning_rate": 0.0002,
86
+ "loss": 2.1974,
87
  "step": 26
88
  },
89
  {
90
  "epoch": 0.57,
91
  "learning_rate": 0.0002,
92
+ "loss": 2.4357,
93
  "step": 28
94
  },
95
  {
96
  "epoch": 0.62,
97
  "learning_rate": 0.0002,
98
+ "loss": 2.6253,
99
  "step": 30
100
  },
101
  {
102
  "epoch": 0.66,
103
  "learning_rate": 0.0002,
104
+ "loss": 2.7215,
105
  "step": 32
106
  },
107
  {
108
  "epoch": 0.7,
109
  "learning_rate": 0.0002,
110
+ "loss": 2.5237,
111
  "step": 34
112
  },
113
  {
114
  "epoch": 0.74,
115
  "learning_rate": 0.0002,
116
+ "loss": 3.1991,
117
  "step": 36
118
  },
119
  {
120
  "epoch": 0.78,
121
  "learning_rate": 0.0002,
122
+ "loss": 2.4282,
123
  "step": 38
124
  },
125
  {
126
  "epoch": 0.82,
127
  "learning_rate": 0.0002,
128
+ "loss": 2.2196,
129
  "step": 40
130
  },
131
  {
132
  "epoch": 0.86,
133
  "learning_rate": 0.0002,
134
+ "loss": 2.6197,
135
  "step": 42
136
  },
137
  {
138
  "epoch": 0.9,
139
  "learning_rate": 0.0002,
140
+ "loss": 2.4451,
141
  "step": 44
142
  },
143
  {
144
  "epoch": 0.94,
145
  "learning_rate": 0.0002,
146
+ "loss": 2.5496,
147
  "step": 46
148
  },
149
  {
150
  "epoch": 0.98,
151
  "learning_rate": 0.0002,
152
+ "loss": 2.8388,
153
  "step": 48
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
154
  }
155
  ],
156
  "logging_steps": 2,
157
+ "max_steps": 48,
158
  "num_input_tokens_seen": 0,
159
+ "num_train_epochs": 1,
160
  "save_steps": 500,
161
+ "total_flos": 2046020741603328.0,
162
  "train_batch_size": 1,
163
  "trial_name": null,
164
  "trial_params": null
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cad143bc0726c99f5ae973d329c4029448ed469f25c4a6fc7ff427bbece32cca
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05d4bf44e2f3fa9eef10818d2ac256b26d0eae9c331d6b54985e765c04f7baf9
3
  size 4728