appvoid commited on
Commit
6e4677d
1 Parent(s): bc164ee

Upload folder using huggingface_hub

Browse files
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "[BOS]": 32001,
3
+ "[EOS]": 32002,
4
+ "[PAD]": 32000
5
+ }
checkpoint-1125/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "appvoid/arco-mini-run-1",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "head_dim": 96,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 1536,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "max_position_embeddings": 2048,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 8,
19
+ "num_hidden_layers": 8,
20
+ "num_key_value_heads": 8,
21
+ "pad_token_id": 0,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": null,
25
+ "rope_theta": 100000,
26
+ "sliding_window": null,
27
+ "tie_word_embeddings": false,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.45.1",
30
+ "use_cache": true,
31
+ "vocab_size": 32003
32
+ }
checkpoint-1125/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.45.1"
7
+ }
checkpoint-1125/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4024c4aadb2e62c407bbdfab16c42185d8a15fd785e51ba94bb7453386d53b5c
3
+ size 997345472
checkpoint-1125/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb94bee85e941ab8323d67a608d7bbc68ab9b15534e02b79448cd10d8d16daf6
3
+ size 1994737722
checkpoint-1125/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
3
+ size 14244
checkpoint-1125/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10a5c0903aa41376be2e7e08598d576931d26fb1dedc7d0c5140f9d591e1debc
3
+ size 1064
checkpoint-1125/trainer_state.json ADDED
@@ -0,0 +1,817 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 5000,
6
+ "global_step": 1125,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.008888888888888889,
13
+ "grad_norm": 0.392131507396698,
14
+ "learning_rate": 2.0000000000000003e-06,
15
+ "loss": 2.3156,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.017777777777777778,
20
+ "grad_norm": 0.6833685636520386,
21
+ "learning_rate": 4.000000000000001e-06,
22
+ "loss": 2.5258,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.02666666666666667,
27
+ "grad_norm": 0.4975835978984833,
28
+ "learning_rate": 6e-06,
29
+ "loss": 2.5274,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.035555555555555556,
34
+ "grad_norm": 0.47904446721076965,
35
+ "learning_rate": 8.000000000000001e-06,
36
+ "loss": 2.2199,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.044444444444444446,
41
+ "grad_norm": 0.5792201161384583,
42
+ "learning_rate": 1e-05,
43
+ "loss": 2.3423,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.05333333333333334,
48
+ "grad_norm": 0.48581650853157043,
49
+ "learning_rate": 1.2e-05,
50
+ "loss": 2.3571,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.06222222222222222,
55
+ "grad_norm": 0.4770135283470154,
56
+ "learning_rate": 1.4000000000000001e-05,
57
+ "loss": 2.4415,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.07111111111111111,
62
+ "grad_norm": 0.6430277824401855,
63
+ "learning_rate": 1.6000000000000003e-05,
64
+ "loss": 2.5717,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.08,
69
+ "grad_norm": 0.5969924926757812,
70
+ "learning_rate": 1.8e-05,
71
+ "loss": 2.2712,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.08888888888888889,
76
+ "grad_norm": 0.5458263754844666,
77
+ "learning_rate": 2e-05,
78
+ "loss": 2.1937,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.09777777777777778,
83
+ "grad_norm": 0.49687811732292175,
84
+ "learning_rate": 2.2000000000000003e-05,
85
+ "loss": 2.3534,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.10666666666666667,
90
+ "grad_norm": 0.5264276266098022,
91
+ "learning_rate": 2.4e-05,
92
+ "loss": 2.3235,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.11555555555555555,
97
+ "grad_norm": 0.6222357749938965,
98
+ "learning_rate": 2.6000000000000002e-05,
99
+ "loss": 2.484,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.12444444444444444,
104
+ "grad_norm": 0.5594074130058289,
105
+ "learning_rate": 2.8000000000000003e-05,
106
+ "loss": 2.3924,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.13333333333333333,
111
+ "grad_norm": 0.5403823852539062,
112
+ "learning_rate": 3e-05,
113
+ "loss": 2.043,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.14222222222222222,
118
+ "grad_norm": 0.8265597820281982,
119
+ "learning_rate": 3.2000000000000005e-05,
120
+ "loss": 2.4271,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.1511111111111111,
125
+ "grad_norm": 0.4910406172275543,
126
+ "learning_rate": 3.4000000000000007e-05,
127
+ "loss": 2.2711,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.16,
132
+ "grad_norm": 0.6300191283226013,
133
+ "learning_rate": 3.6e-05,
134
+ "loss": 2.4088,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.1688888888888889,
139
+ "grad_norm": 0.9516507387161255,
140
+ "learning_rate": 3.8e-05,
141
+ "loss": 2.2007,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.17777777777777778,
146
+ "grad_norm": 0.6081224679946899,
147
+ "learning_rate": 4e-05,
148
+ "loss": 2.2574,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.18666666666666668,
153
+ "grad_norm": 0.670280396938324,
154
+ "learning_rate": 4.2e-05,
155
+ "loss": 2.1538,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.19555555555555557,
160
+ "grad_norm": 0.5967269539833069,
161
+ "learning_rate": 4.4000000000000006e-05,
162
+ "loss": 2.3559,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.20444444444444446,
167
+ "grad_norm": 0.6861779093742371,
168
+ "learning_rate": 4.600000000000001e-05,
169
+ "loss": 2.2649,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.21333333333333335,
174
+ "grad_norm": 0.7942169308662415,
175
+ "learning_rate": 4.8e-05,
176
+ "loss": 2.4453,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.2222222222222222,
181
+ "grad_norm": 0.686896562576294,
182
+ "learning_rate": 5e-05,
183
+ "loss": 2.272,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.2311111111111111,
188
+ "grad_norm": 0.6957288980484009,
189
+ "learning_rate": 5.2000000000000004e-05,
190
+ "loss": 2.2378,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.24,
195
+ "grad_norm": 0.5659416317939758,
196
+ "learning_rate": 5.4000000000000005e-05,
197
+ "loss": 2.2169,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.24888888888888888,
202
+ "grad_norm": 0.6357027292251587,
203
+ "learning_rate": 5.6000000000000006e-05,
204
+ "loss": 2.3081,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.2577777777777778,
209
+ "grad_norm": 0.561445951461792,
210
+ "learning_rate": 5.8e-05,
211
+ "loss": 2.3665,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.26666666666666666,
216
+ "grad_norm": 0.8563527464866638,
217
+ "learning_rate": 6e-05,
218
+ "loss": 2.2106,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.27555555555555555,
223
+ "grad_norm": 0.7866883873939514,
224
+ "learning_rate": 6.2e-05,
225
+ "loss": 2.0944,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.28444444444444444,
230
+ "grad_norm": 0.9338068962097168,
231
+ "learning_rate": 6.400000000000001e-05,
232
+ "loss": 2.2693,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.29333333333333333,
237
+ "grad_norm": 0.7246842384338379,
238
+ "learning_rate": 6.6e-05,
239
+ "loss": 2.2881,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.3022222222222222,
244
+ "grad_norm": 1.0052026510238647,
245
+ "learning_rate": 6.800000000000001e-05,
246
+ "loss": 2.3067,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.3111111111111111,
251
+ "grad_norm": 0.6183302998542786,
252
+ "learning_rate": 7e-05,
253
+ "loss": 2.3916,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.32,
258
+ "grad_norm": 0.7271236777305603,
259
+ "learning_rate": 7.2e-05,
260
+ "loss": 2.4863,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.3288888888888889,
265
+ "grad_norm": 0.8021159768104553,
266
+ "learning_rate": 7.4e-05,
267
+ "loss": 2.5189,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.3377777777777778,
272
+ "grad_norm": 0.670994758605957,
273
+ "learning_rate": 7.6e-05,
274
+ "loss": 2.299,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.3466666666666667,
279
+ "grad_norm": 0.6826931238174438,
280
+ "learning_rate": 7.800000000000001e-05,
281
+ "loss": 2.2439,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.35555555555555557,
286
+ "grad_norm": 0.6512673497200012,
287
+ "learning_rate": 8e-05,
288
+ "loss": 2.2511,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.36444444444444446,
293
+ "grad_norm": 0.6105847358703613,
294
+ "learning_rate": 8.2e-05,
295
+ "loss": 2.2597,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.37333333333333335,
300
+ "grad_norm": 0.7471911907196045,
301
+ "learning_rate": 8.4e-05,
302
+ "loss": 2.3652,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.38222222222222224,
307
+ "grad_norm": 0.6970444321632385,
308
+ "learning_rate": 8.6e-05,
309
+ "loss": 2.3259,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.39111111111111113,
314
+ "grad_norm": 0.6674960255622864,
315
+ "learning_rate": 8.800000000000001e-05,
316
+ "loss": 2.3558,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.4,
321
+ "grad_norm": 0.7472724318504333,
322
+ "learning_rate": 9e-05,
323
+ "loss": 2.2086,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.4088888888888889,
328
+ "grad_norm": 0.7264606356620789,
329
+ "learning_rate": 9.200000000000001e-05,
330
+ "loss": 2.084,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.4177777777777778,
335
+ "grad_norm": 0.6516128182411194,
336
+ "learning_rate": 9.4e-05,
337
+ "loss": 2.0929,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.4266666666666667,
342
+ "grad_norm": 0.8081138134002686,
343
+ "learning_rate": 9.6e-05,
344
+ "loss": 2.1653,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.43555555555555553,
349
+ "grad_norm": 0.8400042653083801,
350
+ "learning_rate": 9.8e-05,
351
+ "loss": 2.3939,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.4444444444444444,
356
+ "grad_norm": 0.4789764881134033,
357
+ "learning_rate": 0.0001,
358
+ "loss": 2.2763,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.4533333333333333,
363
+ "grad_norm": 0.7314158082008362,
364
+ "learning_rate": 9.84e-05,
365
+ "loss": 2.3742,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.4622222222222222,
370
+ "grad_norm": 0.5646970272064209,
371
+ "learning_rate": 9.680000000000001e-05,
372
+ "loss": 2.1478,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.4711111111111111,
377
+ "grad_norm": 0.4644782841205597,
378
+ "learning_rate": 9.52e-05,
379
+ "loss": 2.2953,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.48,
384
+ "grad_norm": 0.6332143545150757,
385
+ "learning_rate": 9.360000000000001e-05,
386
+ "loss": 2.2399,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.4888888888888889,
391
+ "grad_norm": 0.706084668636322,
392
+ "learning_rate": 9.200000000000001e-05,
393
+ "loss": 2.2324,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.49777777777777776,
398
+ "grad_norm": 0.6272305250167847,
399
+ "learning_rate": 9.04e-05,
400
+ "loss": 2.2321,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.5066666666666667,
405
+ "grad_norm": 0.5707433223724365,
406
+ "learning_rate": 8.88e-05,
407
+ "loss": 2.2092,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.5155555555555555,
412
+ "grad_norm": 0.660696268081665,
413
+ "learning_rate": 8.72e-05,
414
+ "loss": 1.9807,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.5244444444444445,
419
+ "grad_norm": 0.5993101000785828,
420
+ "learning_rate": 8.560000000000001e-05,
421
+ "loss": 1.9566,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 0.5333333333333333,
426
+ "grad_norm": 0.5725361704826355,
427
+ "learning_rate": 8.4e-05,
428
+ "loss": 2.1722,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 0.5422222222222223,
433
+ "grad_norm": 0.651642918586731,
434
+ "learning_rate": 8.24e-05,
435
+ "loss": 2.1262,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 0.5511111111111111,
440
+ "grad_norm": 0.5352093577384949,
441
+ "learning_rate": 8.080000000000001e-05,
442
+ "loss": 2.1979,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 0.56,
447
+ "grad_norm": 0.5744340419769287,
448
+ "learning_rate": 7.920000000000001e-05,
449
+ "loss": 2.0399,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 0.5688888888888889,
454
+ "grad_norm": 0.6103332042694092,
455
+ "learning_rate": 7.76e-05,
456
+ "loss": 2.2209,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 0.5777777777777777,
461
+ "grad_norm": 0.6434329152107239,
462
+ "learning_rate": 7.6e-05,
463
+ "loss": 2.379,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 0.5866666666666667,
468
+ "grad_norm": 0.5661439299583435,
469
+ "learning_rate": 7.44e-05,
470
+ "loss": 2.1698,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 0.5955555555555555,
475
+ "grad_norm": 0.5890876054763794,
476
+ "learning_rate": 7.280000000000001e-05,
477
+ "loss": 2.058,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 0.6044444444444445,
482
+ "grad_norm": 0.4725685715675354,
483
+ "learning_rate": 7.12e-05,
484
+ "loss": 2.0658,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 0.6133333333333333,
489
+ "grad_norm": 0.6357767581939697,
490
+ "learning_rate": 6.96e-05,
491
+ "loss": 2.1107,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 0.6222222222222222,
496
+ "grad_norm": 0.6726393699645996,
497
+ "learning_rate": 6.800000000000001e-05,
498
+ "loss": 2.1904,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 0.6311111111111111,
503
+ "grad_norm": 0.5009137392044067,
504
+ "learning_rate": 6.64e-05,
505
+ "loss": 2.0765,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 0.64,
510
+ "grad_norm": 0.7313541173934937,
511
+ "learning_rate": 6.48e-05,
512
+ "loss": 2.3566,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 0.6488888888888888,
517
+ "grad_norm": 0.7757258415222168,
518
+ "learning_rate": 6.32e-05,
519
+ "loss": 2.2077,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 0.6577777777777778,
524
+ "grad_norm": 0.5176954865455627,
525
+ "learning_rate": 6.16e-05,
526
+ "loss": 2.1287,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 0.6666666666666666,
531
+ "grad_norm": 0.6251640915870667,
532
+ "learning_rate": 6e-05,
533
+ "loss": 2.1726,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 0.6755555555555556,
538
+ "grad_norm": 0.5190748572349548,
539
+ "learning_rate": 5.8399999999999997e-05,
540
+ "loss": 2.1528,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 0.6844444444444444,
545
+ "grad_norm": 0.6299232840538025,
546
+ "learning_rate": 5.68e-05,
547
+ "loss": 1.9734,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 0.6933333333333334,
552
+ "grad_norm": 0.6707553863525391,
553
+ "learning_rate": 5.520000000000001e-05,
554
+ "loss": 1.9959,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 0.7022222222222222,
559
+ "grad_norm": 0.5231025815010071,
560
+ "learning_rate": 5.360000000000001e-05,
561
+ "loss": 2.0261,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 0.7111111111111111,
566
+ "grad_norm": 0.489175021648407,
567
+ "learning_rate": 5.2000000000000004e-05,
568
+ "loss": 2.1987,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 0.72,
573
+ "grad_norm": 0.6425113677978516,
574
+ "learning_rate": 5.0400000000000005e-05,
575
+ "loss": 2.0759,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 0.7288888888888889,
580
+ "grad_norm": 0.6148718595504761,
581
+ "learning_rate": 4.88e-05,
582
+ "loss": 2.158,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 0.7377777777777778,
587
+ "grad_norm": 0.7482603192329407,
588
+ "learning_rate": 4.72e-05,
589
+ "loss": 1.9579,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 0.7466666666666667,
594
+ "grad_norm": 0.5650503039360046,
595
+ "learning_rate": 4.5600000000000004e-05,
596
+ "loss": 2.1253,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 0.7555555555555555,
601
+ "grad_norm": 0.6965321898460388,
602
+ "learning_rate": 4.4000000000000006e-05,
603
+ "loss": 2.1034,
604
+ "step": 850
605
+ },
606
+ {
607
+ "epoch": 0.7644444444444445,
608
+ "grad_norm": 0.5848603844642639,
609
+ "learning_rate": 4.24e-05,
610
+ "loss": 2.0139,
611
+ "step": 860
612
+ },
613
+ {
614
+ "epoch": 0.7733333333333333,
615
+ "grad_norm": 0.566116988658905,
616
+ "learning_rate": 4.08e-05,
617
+ "loss": 2.0551,
618
+ "step": 870
619
+ },
620
+ {
621
+ "epoch": 0.7822222222222223,
622
+ "grad_norm": 0.5044224858283997,
623
+ "learning_rate": 3.9200000000000004e-05,
624
+ "loss": 1.9789,
625
+ "step": 880
626
+ },
627
+ {
628
+ "epoch": 0.7911111111111111,
629
+ "grad_norm": 0.566875159740448,
630
+ "learning_rate": 3.76e-05,
631
+ "loss": 2.3283,
632
+ "step": 890
633
+ },
634
+ {
635
+ "epoch": 0.8,
636
+ "grad_norm": 0.5149425268173218,
637
+ "learning_rate": 3.6e-05,
638
+ "loss": 1.9651,
639
+ "step": 900
640
+ },
641
+ {
642
+ "epoch": 0.8088888888888889,
643
+ "grad_norm": 0.5834816694259644,
644
+ "learning_rate": 3.4399999999999996e-05,
645
+ "loss": 1.9825,
646
+ "step": 910
647
+ },
648
+ {
649
+ "epoch": 0.8177777777777778,
650
+ "grad_norm": 0.7403817772865295,
651
+ "learning_rate": 3.2800000000000004e-05,
652
+ "loss": 2.0542,
653
+ "step": 920
654
+ },
655
+ {
656
+ "epoch": 0.8266666666666667,
657
+ "grad_norm": 0.6044632792472839,
658
+ "learning_rate": 3.12e-05,
659
+ "loss": 2.2774,
660
+ "step": 930
661
+ },
662
+ {
663
+ "epoch": 0.8355555555555556,
664
+ "grad_norm": 0.6258851885795593,
665
+ "learning_rate": 2.96e-05,
666
+ "loss": 2.1449,
667
+ "step": 940
668
+ },
669
+ {
670
+ "epoch": 0.8444444444444444,
671
+ "grad_norm": 0.6421411037445068,
672
+ "learning_rate": 2.8000000000000003e-05,
673
+ "loss": 2.0822,
674
+ "step": 950
675
+ },
676
+ {
677
+ "epoch": 0.8533333333333334,
678
+ "grad_norm": 0.34951749444007874,
679
+ "learning_rate": 2.64e-05,
680
+ "loss": 1.9521,
681
+ "step": 960
682
+ },
683
+ {
684
+ "epoch": 0.8622222222222222,
685
+ "grad_norm": 0.5875269770622253,
686
+ "learning_rate": 2.48e-05,
687
+ "loss": 2.0813,
688
+ "step": 970
689
+ },
690
+ {
691
+ "epoch": 0.8711111111111111,
692
+ "grad_norm": 0.5003840327262878,
693
+ "learning_rate": 2.32e-05,
694
+ "loss": 1.9155,
695
+ "step": 980
696
+ },
697
+ {
698
+ "epoch": 0.88,
699
+ "grad_norm": 0.4974331259727478,
700
+ "learning_rate": 2.16e-05,
701
+ "loss": 2.0593,
702
+ "step": 990
703
+ },
704
+ {
705
+ "epoch": 0.8888888888888888,
706
+ "grad_norm": 0.505962610244751,
707
+ "learning_rate": 2e-05,
708
+ "loss": 2.0306,
709
+ "step": 1000
710
+ },
711
+ {
712
+ "epoch": 0.8977777777777778,
713
+ "grad_norm": 0.5298508405685425,
714
+ "learning_rate": 1.84e-05,
715
+ "loss": 2.136,
716
+ "step": 1010
717
+ },
718
+ {
719
+ "epoch": 0.9066666666666666,
720
+ "grad_norm": 0.4652698338031769,
721
+ "learning_rate": 1.6800000000000002e-05,
722
+ "loss": 1.9021,
723
+ "step": 1020
724
+ },
725
+ {
726
+ "epoch": 0.9155555555555556,
727
+ "grad_norm": 0.5339078307151794,
728
+ "learning_rate": 1.52e-05,
729
+ "loss": 2.0262,
730
+ "step": 1030
731
+ },
732
+ {
733
+ "epoch": 0.9244444444444444,
734
+ "grad_norm": 0.5623987317085266,
735
+ "learning_rate": 1.3600000000000002e-05,
736
+ "loss": 1.8597,
737
+ "step": 1040
738
+ },
739
+ {
740
+ "epoch": 0.9333333333333333,
741
+ "grad_norm": 0.689896285533905,
742
+ "learning_rate": 1.2e-05,
743
+ "loss": 2.1377,
744
+ "step": 1050
745
+ },
746
+ {
747
+ "epoch": 0.9422222222222222,
748
+ "grad_norm": 0.460510790348053,
749
+ "learning_rate": 1.04e-05,
750
+ "loss": 1.889,
751
+ "step": 1060
752
+ },
753
+ {
754
+ "epoch": 0.9511111111111111,
755
+ "grad_norm": 0.5239367485046387,
756
+ "learning_rate": 8.8e-06,
757
+ "loss": 2.1753,
758
+ "step": 1070
759
+ },
760
+ {
761
+ "epoch": 0.96,
762
+ "grad_norm": 0.5576533079147339,
763
+ "learning_rate": 7.2e-06,
764
+ "loss": 2.1375,
765
+ "step": 1080
766
+ },
767
+ {
768
+ "epoch": 0.9688888888888889,
769
+ "grad_norm": 0.5585991144180298,
770
+ "learning_rate": 5.600000000000001e-06,
771
+ "loss": 1.9434,
772
+ "step": 1090
773
+ },
774
+ {
775
+ "epoch": 0.9777777777777777,
776
+ "grad_norm": 0.5961203575134277,
777
+ "learning_rate": 4.000000000000001e-06,
778
+ "loss": 2.0194,
779
+ "step": 1100
780
+ },
781
+ {
782
+ "epoch": 0.9866666666666667,
783
+ "grad_norm": 0.6022922396659851,
784
+ "learning_rate": 2.4000000000000003e-06,
785
+ "loss": 1.9679,
786
+ "step": 1110
787
+ },
788
+ {
789
+ "epoch": 0.9955555555555555,
790
+ "grad_norm": 0.4506663382053375,
791
+ "learning_rate": 8.000000000000001e-07,
792
+ "loss": 2.1243,
793
+ "step": 1120
794
+ }
795
+ ],
796
+ "logging_steps": 10,
797
+ "max_steps": 1125,
798
+ "num_input_tokens_seen": 0,
799
+ "num_train_epochs": 1,
800
+ "save_steps": 5000,
801
+ "stateful_callbacks": {
802
+ "TrainerControl": {
803
+ "args": {
804
+ "should_epoch_stop": false,
805
+ "should_evaluate": false,
806
+ "should_log": false,
807
+ "should_save": true,
808
+ "should_training_stop": true
809
+ },
810
+ "attributes": {}
811
+ }
812
+ },
813
+ "total_flos": 4.4276096434176e+16,
814
+ "train_batch_size": 4,
815
+ "trial_name": null,
816
+ "trial_params": null
817
+ }
checkpoint-1125/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:025897f889b908ecd0d79f6bd2dc98c903d5a1682861bea4facbf95618948d99
3
+ size 5176
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "appvoid/arco-mini-run-1",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "head_dim": 96,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 1536,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "max_position_embeddings": 2048,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 8,
19
+ "num_hidden_layers": 8,
20
+ "num_key_value_heads": 8,
21
+ "pad_token_id": 0,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": null,
25
+ "rope_theta": 100000,
26
+ "sliding_window": null,
27
+ "tie_word_embeddings": false,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.45.1",
30
+ "use_cache": true,
31
+ "vocab_size": 32003
32
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.45.1"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4024c4aadb2e62c407bbdfab16c42185d8a15fd785e51ba94bb7453386d53b5c
3
+ size 997345472
special_tokens_map.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[BOS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[EOS]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "pad_token": {
24
+ "content": "[PAD]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "sep_token": {
31
+ "content": "</s>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "unk_token": {
38
+ "content": "<unk>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ }
44
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "32000": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "[BOS]",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "[EOS]",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ }
54
+ },
55
+ "additional_special_tokens": [],
56
+ "bos_token": "[BOS]",
57
+ "clean_up_tokenization_spaces": false,
58
+ "cls_token": "</s>",
59
+ "eos_token": "[EOS]",
60
+ "legacy": true,
61
+ "model_max_length": 1000000000000000019884624838656,
62
+ "pad_token": "[PAD]",
63
+ "sep_token": "</s>",
64
+ "sp_model_kwargs": {},
65
+ "spaces_between_special_tokens": false,
66
+ "tokenizer_class": "LlamaTokenizer",
67
+ "unk_token": "<unk>",
68
+ "use_default_system_prompt": false
69
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:025897f889b908ecd0d79f6bd2dc98c903d5a1682861bea4facbf95618948d99
3
+ size 5176