CodeIsAbstract commited on
Commit
667e68a
·
verified ·
1 Parent(s): 964da49

Upload fine-tuned model

Browse files
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": [
9
+ 128001,
10
+ 128008,
11
+ 128009
12
+ ],
13
+ "head_dim": 64,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 2048,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 8192,
18
+ "max_position_embeddings": 131072,
19
+ "mlp_bias": false,
20
+ "model_type": "llama",
21
+ "num_attention_heads": 32,
22
+ "num_hidden_layers": 16,
23
+ "num_key_value_heads": 8,
24
+ "pad_token_id": 128256,
25
+ "pretraining_tp": 1,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_scaling": {
28
+ "factor": 32.0,
29
+ "high_freq_factor": 4.0,
30
+ "low_freq_factor": 1.0,
31
+ "original_max_position_embeddings": 8192,
32
+ "rope_type": "llama3"
33
+ },
34
+ "rope_theta": 500000.0,
35
+ "tie_word_embeddings": true,
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.51.3",
38
+ "use_cache": true,
39
+ "vocab_size": 128257
40
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.51.3"
12
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:781e5b94c9bf4769641e2448927ed87da02abbf9a7852c02c002314ed396af6d
3
+ size 4943282520
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e58bfa0abf4b4fbd62b7518ad650459402902dc50b159e553c1e5ca9d9532b81
3
+ size 2510813050
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9899ccda7f0d8d9511991180b93aab508ce6e8489de708c88ad1188e7e1d90d6
3
+ size 14244
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1401337c015c8773efe530395608b16ca9aca28c1f96dd6f56880cfc23b56090
3
+ size 988
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8104f4614023e4a3a7725dd956b72be95ff427616ef159691de7ca2115e47aee
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,922 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.4384283660757067,
6
+ "eval_steps": 200,
7
+ "global_step": 1200,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.011978917105893628,
14
+ "grad_norm": Infinity,
15
+ "learning_rate": 4e-07,
16
+ "loss": 94.1331,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.023957834211787255,
21
+ "grad_norm": 616.6350708007812,
22
+ "learning_rate": 1.9999995539071857e-06,
23
+ "loss": 13.5081,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.035936751317680884,
28
+ "grad_norm": 1712.5594482421875,
29
+ "learning_rate": 1.9999460232510422e-06,
30
+ "loss": 44.8754,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.04791566842357451,
35
+ "grad_norm": 0.8271563053131104,
36
+ "learning_rate": 1.9998032795044213e-06,
37
+ "loss": 31.7079,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.059894585529468136,
42
+ "grad_norm": 0.7399762868881226,
43
+ "learning_rate": 1.9995713354026208e-06,
44
+ "loss": 14.6654,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.07187350263536177,
49
+ "grad_norm": 4523.66748046875,
50
+ "learning_rate": 1.999250211639208e-06,
51
+ "loss": 15.7606,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.08385241974125539,
56
+ "grad_norm": 2372.1298828125,
57
+ "learning_rate": 1.998839936864172e-06,
58
+ "loss": 29.1475,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.09583133684714902,
63
+ "grad_norm": 525.8820190429688,
64
+ "learning_rate": 1.9983405476813705e-06,
65
+ "loss": 30.3939,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.10781025395304264,
70
+ "grad_norm": 622.8740844726562,
71
+ "learning_rate": 1.9977520886452595e-06,
72
+ "loss": 25.0045,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.11978917105893627,
77
+ "grad_norm": 393.3197326660156,
78
+ "learning_rate": 1.997074612256923e-06,
79
+ "loss": 10.3827,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.1317680881648299,
84
+ "grad_norm": 1076.3707275390625,
85
+ "learning_rate": 1.996308178959385e-06,
86
+ "loss": 35.8152,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.14374700527072354,
91
+ "grad_norm": 0.5970665812492371,
92
+ "learning_rate": 1.99545285713222e-06,
93
+ "loss": 18.8117,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.15572592237661714,
98
+ "grad_norm": 1666.3372802734375,
99
+ "learning_rate": 1.9945087230854505e-06,
100
+ "loss": 35.409,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.16770483948251078,
105
+ "grad_norm": 454.6666564941406,
106
+ "learning_rate": 1.9934758610527393e-06,
107
+ "loss": 26.721,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.1796837565884044,
112
+ "grad_norm": 0.6310660243034363,
113
+ "learning_rate": 1.9923543631838743e-06,
114
+ "loss": 29.0184,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.19166267369429804,
119
+ "grad_norm": 1460.1695556640625,
120
+ "learning_rate": 1.991144329536547e-06,
121
+ "loss": 32.6666,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.20364159080019167,
126
+ "grad_norm": 1623.7030029296875,
127
+ "learning_rate": 1.989845868067426e-06,
128
+ "loss": 22.361,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.21562050790608528,
133
+ "grad_norm": 0.2606387734413147,
134
+ "learning_rate": 1.9884590946225245e-06,
135
+ "loss": 26.8546,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.2275994250119789,
140
+ "grad_norm": 2438.140869140625,
141
+ "learning_rate": 1.986984132926866e-06,
142
+ "loss": 22.4338,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.23957834211787254,
147
+ "grad_norm": 457.811767578125,
148
+ "learning_rate": 1.985421114573445e-06,
149
+ "loss": 38.06,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.23957834211787254,
154
+ "eval_loss": 7.858267307281494,
155
+ "eval_runtime": 239.5749,
156
+ "eval_samples_per_second": 6.219,
157
+ "eval_steps_per_second": 3.11,
158
+ "step": 200
159
+ },
160
+ {
161
+ "epoch": 0.25155725922376615,
162
+ "grad_norm": 3668.065673828125,
163
+ "learning_rate": 1.983770179011485e-06,
164
+ "loss": 36.1835,
165
+ "step": 210
166
+ },
167
+ {
168
+ "epoch": 0.2635361763296598,
169
+ "grad_norm": 0.26454946398735046,
170
+ "learning_rate": 1.9820314735340013e-06,
171
+ "loss": 36.229,
172
+ "step": 220
173
+ },
174
+ {
175
+ "epoch": 0.2755150934355534,
176
+ "grad_norm": 0.4162730872631073,
177
+ "learning_rate": 1.9802051532646555e-06,
178
+ "loss": 32.5845,
179
+ "step": 230
180
+ },
181
+ {
182
+ "epoch": 0.2874940105414471,
183
+ "grad_norm": 0.15878209471702576,
184
+ "learning_rate": 1.9782913811439183e-06,
185
+ "loss": 15.8691,
186
+ "step": 240
187
+ },
188
+ {
189
+ "epoch": 0.2994729276473407,
190
+ "grad_norm": 210.30516052246094,
191
+ "learning_rate": 1.9762903279145307e-06,
192
+ "loss": 21.8668,
193
+ "step": 250
194
+ },
195
+ {
196
+ "epoch": 0.3114518447532343,
197
+ "grad_norm": 0.31922483444213867,
198
+ "learning_rate": 1.974202172106272e-06,
199
+ "loss": 19.8604,
200
+ "step": 260
201
+ },
202
+ {
203
+ "epoch": 0.32343076185912795,
204
+ "grad_norm": 166.21446228027344,
205
+ "learning_rate": 1.9720271000200323e-06,
206
+ "loss": 19.3605,
207
+ "step": 270
208
+ },
209
+ {
210
+ "epoch": 0.33540967896502155,
211
+ "grad_norm": 1452.038330078125,
212
+ "learning_rate": 1.9697653057111875e-06,
213
+ "loss": 33.3646,
214
+ "step": 280
215
+ },
216
+ {
217
+ "epoch": 0.3473885960709152,
218
+ "grad_norm": 0.4086947739124298,
219
+ "learning_rate": 1.967416990972291e-06,
220
+ "loss": 15.2998,
221
+ "step": 290
222
+ },
223
+ {
224
+ "epoch": 0.3593675131768088,
225
+ "grad_norm": 1385.362548828125,
226
+ "learning_rate": 1.964982365315066e-06,
227
+ "loss": 16.0225,
228
+ "step": 300
229
+ },
230
+ {
231
+ "epoch": 0.3713464302827024,
232
+ "grad_norm": 189.06552124023438,
233
+ "learning_rate": 1.9624616459517164e-06,
234
+ "loss": 33.4549,
235
+ "step": 310
236
+ },
237
+ {
238
+ "epoch": 0.3833253473885961,
239
+ "grad_norm": 1255.678466796875,
240
+ "learning_rate": 1.959855057775546e-06,
241
+ "loss": 33.8802,
242
+ "step": 320
243
+ },
244
+ {
245
+ "epoch": 0.3953042644944897,
246
+ "grad_norm": 1233.65673828125,
247
+ "learning_rate": 1.9571628333408937e-06,
248
+ "loss": 33.1002,
249
+ "step": 330
250
+ },
251
+ {
252
+ "epoch": 0.40728318160038335,
253
+ "grad_norm": 162.6513671875,
254
+ "learning_rate": 1.954385212842387e-06,
255
+ "loss": 28.827,
256
+ "step": 340
257
+ },
258
+ {
259
+ "epoch": 0.41926209870627695,
260
+ "grad_norm": 2140.404296875,
261
+ "learning_rate": 1.9515224440935103e-06,
262
+ "loss": 16.8164,
263
+ "step": 350
264
+ },
265
+ {
266
+ "epoch": 0.43124101581217056,
267
+ "grad_norm": 0.2348758578300476,
268
+ "learning_rate": 1.948574782504498e-06,
269
+ "loss": 11.385,
270
+ "step": 360
271
+ },
272
+ {
273
+ "epoch": 0.4432199329180642,
274
+ "grad_norm": 0.24031803011894226,
275
+ "learning_rate": 1.9455424910595442e-06,
276
+ "loss": 12.6478,
277
+ "step": 370
278
+ },
279
+ {
280
+ "epoch": 0.4551988500239578,
281
+ "grad_norm": 992.0042114257812,
282
+ "learning_rate": 1.942425840293343e-06,
283
+ "loss": 17.7328,
284
+ "step": 380
285
+ },
286
+ {
287
+ "epoch": 0.4671777671298515,
288
+ "grad_norm": 1306.5712890625,
289
+ "learning_rate": 1.939225108266951e-06,
290
+ "loss": 30.8945,
291
+ "step": 390
292
+ },
293
+ {
294
+ "epoch": 0.4791566842357451,
295
+ "grad_norm": 0.18838146328926086,
296
+ "learning_rate": 1.9359405805429763e-06,
297
+ "loss": 12.8307,
298
+ "step": 400
299
+ },
300
+ {
301
+ "epoch": 0.4791566842357451,
302
+ "eval_loss": 5.787263870239258,
303
+ "eval_runtime": 237.9568,
304
+ "eval_samples_per_second": 6.262,
305
+ "eval_steps_per_second": 3.131,
306
+ "step": 400
307
+ },
308
+ {
309
+ "epoch": 0.4911356013416387,
310
+ "grad_norm": 0.2591519057750702,
311
+ "learning_rate": 1.932572550160106e-06,
312
+ "loss": 30.1815,
313
+ "step": 410
314
+ },
315
+ {
316
+ "epoch": 0.5031145184475323,
317
+ "grad_norm": 1008.1605224609375,
318
+ "learning_rate": 1.9291213176069584e-06,
319
+ "loss": 15.7189,
320
+ "step": 420
321
+ },
322
+ {
323
+ "epoch": 0.515093435553426,
324
+ "grad_norm": 347.5401306152344,
325
+ "learning_rate": 1.9255871907952756e-06,
326
+ "loss": 18.0663,
327
+ "step": 430
328
+ },
329
+ {
330
+ "epoch": 0.5270723526593196,
331
+ "grad_norm": 480.1645812988281,
332
+ "learning_rate": 1.921970485032452e-06,
333
+ "loss": 18.3552,
334
+ "step": 440
335
+ },
336
+ {
337
+ "epoch": 0.5390512697652132,
338
+ "grad_norm": 0.502577543258667,
339
+ "learning_rate": 1.918271522993403e-06,
340
+ "loss": 9.8206,
341
+ "step": 450
342
+ },
343
+ {
344
+ "epoch": 0.5510301868711068,
345
+ "grad_norm": 181.82675170898438,
346
+ "learning_rate": 1.914490634691777e-06,
347
+ "loss": 22.7731,
348
+ "step": 460
349
+ },
350
+ {
351
+ "epoch": 0.5630091039770004,
352
+ "grad_norm": 1757.3203125,
353
+ "learning_rate": 1.9106281574505113e-06,
354
+ "loss": 42.1869,
355
+ "step": 470
356
+ },
357
+ {
358
+ "epoch": 0.5749880210828942,
359
+ "grad_norm": 0.3148007392883301,
360
+ "learning_rate": 1.9066844358717384e-06,
361
+ "loss": 10.479,
362
+ "step": 480
363
+ },
364
+ {
365
+ "epoch": 0.5869669381887878,
366
+ "grad_norm": 0.43468308448791504,
367
+ "learning_rate": 1.90265982180604e-06,
368
+ "loss": 25.0078,
369
+ "step": 490
370
+ },
371
+ {
372
+ "epoch": 0.5989458552946814,
373
+ "grad_norm": 428.818359375,
374
+ "learning_rate": 1.8985546743210556e-06,
375
+ "loss": 17.2799,
376
+ "step": 500
377
+ },
378
+ {
379
+ "epoch": 0.610924772400575,
380
+ "grad_norm": 826.046630859375,
381
+ "learning_rate": 1.894369359669449e-06,
382
+ "loss": 22.2318,
383
+ "step": 510
384
+ },
385
+ {
386
+ "epoch": 0.6229036895064686,
387
+ "grad_norm": 1385.6824951171875,
388
+ "learning_rate": 1.8901042512562298e-06,
389
+ "loss": 23.271,
390
+ "step": 520
391
+ },
392
+ {
393
+ "epoch": 0.6348826066123623,
394
+ "grad_norm": 1433.165771484375,
395
+ "learning_rate": 1.8857597296054402e-06,
396
+ "loss": 15.2536,
397
+ "step": 530
398
+ },
399
+ {
400
+ "epoch": 0.6468615237182559,
401
+ "grad_norm": 1745.93115234375,
402
+ "learning_rate": 1.8813361823262054e-06,
403
+ "loss": 25.0982,
404
+ "step": 540
405
+ },
406
+ {
407
+ "epoch": 0.6588404408241495,
408
+ "grad_norm": 1039.310302734375,
409
+ "learning_rate": 1.8768340040781511e-06,
410
+ "loss": 30.7892,
411
+ "step": 550
412
+ },
413
+ {
414
+ "epoch": 0.6708193579300431,
415
+ "grad_norm": 310.6319274902344,
416
+ "learning_rate": 1.8722535965361946e-06,
417
+ "loss": 7.1616,
418
+ "step": 560
419
+ },
420
+ {
421
+ "epoch": 0.6827982750359367,
422
+ "grad_norm": 356.1474304199219,
423
+ "learning_rate": 1.8675953683547053e-06,
424
+ "loss": 18.7229,
425
+ "step": 570
426
+ },
427
+ {
428
+ "epoch": 0.6947771921418304,
429
+ "grad_norm": 145.14263916015625,
430
+ "learning_rate": 1.8628597351310482e-06,
431
+ "loss": 17.1177,
432
+ "step": 580
433
+ },
434
+ {
435
+ "epoch": 0.706756109247724,
436
+ "grad_norm": 989.70654296875,
437
+ "learning_rate": 1.8580471193685044e-06,
438
+ "loss": 20.149,
439
+ "step": 590
440
+ },
441
+ {
442
+ "epoch": 0.7187350263536176,
443
+ "grad_norm": 1277.737548828125,
444
+ "learning_rate": 1.853157950438575e-06,
445
+ "loss": 13.4416,
446
+ "step": 600
447
+ },
448
+ {
449
+ "epoch": 0.7187350263536176,
450
+ "eval_loss": 5.8129730224609375,
451
+ "eval_runtime": 239.911,
452
+ "eval_samples_per_second": 6.211,
453
+ "eval_steps_per_second": 3.105,
454
+ "step": 600
455
+ },
456
+ {
457
+ "epoch": 0.7307139434595112,
458
+ "grad_norm": 446.188232421875,
459
+ "learning_rate": 1.8481926645426752e-06,
460
+ "loss": 18.3421,
461
+ "step": 610
462
+ },
463
+ {
464
+ "epoch": 0.7426928605654048,
465
+ "grad_norm": 0.44947949051856995,
466
+ "learning_rate": 1.8431517046732154e-06,
467
+ "loss": 18.8154,
468
+ "step": 620
469
+ },
470
+ {
471
+ "epoch": 0.7546717776712986,
472
+ "grad_norm": 224.2598876953125,
473
+ "learning_rate": 1.8380355205740811e-06,
474
+ "loss": 19.2502,
475
+ "step": 630
476
+ },
477
+ {
478
+ "epoch": 0.7666506947771922,
479
+ "grad_norm": 0.3780662715435028,
480
+ "learning_rate": 1.8328445687005049e-06,
481
+ "loss": 17.2432,
482
+ "step": 640
483
+ },
484
+ {
485
+ "epoch": 0.7786296118830858,
486
+ "grad_norm": 0.4702111482620239,
487
+ "learning_rate": 1.8275793121783438e-06,
488
+ "loss": 26.5332,
489
+ "step": 650
490
+ },
491
+ {
492
+ "epoch": 0.7906085289889794,
493
+ "grad_norm": 0.27338534593582153,
494
+ "learning_rate": 1.8222402207627605e-06,
495
+ "loss": 9.9615,
496
+ "step": 660
497
+ },
498
+ {
499
+ "epoch": 0.802587446094873,
500
+ "grad_norm": 2576.7802734375,
501
+ "learning_rate": 1.8168277707963116e-06,
502
+ "loss": 28.2978,
503
+ "step": 670
504
+ },
505
+ {
506
+ "epoch": 0.8145663632007667,
507
+ "grad_norm": 171.48802185058594,
508
+ "learning_rate": 1.8113424451664507e-06,
509
+ "loss": 21.4006,
510
+ "step": 680
511
+ },
512
+ {
513
+ "epoch": 0.8265452803066603,
514
+ "grad_norm": 228.12960815429688,
515
+ "learning_rate": 1.805784733262445e-06,
516
+ "loss": 16.6388,
517
+ "step": 690
518
+ },
519
+ {
520
+ "epoch": 0.8385241974125539,
521
+ "grad_norm": 250.2900390625,
522
+ "learning_rate": 1.8001551309317136e-06,
523
+ "loss": 12.3178,
524
+ "step": 700
525
+ },
526
+ {
527
+ "epoch": 0.8505031145184475,
528
+ "grad_norm": 0.25326794385910034,
529
+ "learning_rate": 1.7944541404355888e-06,
530
+ "loss": 15.9896,
531
+ "step": 710
532
+ },
533
+ {
534
+ "epoch": 0.8624820316243411,
535
+ "grad_norm": 614.1929321289062,
536
+ "learning_rate": 1.7886822704045063e-06,
537
+ "loss": 21.2252,
538
+ "step": 720
539
+ },
540
+ {
541
+ "epoch": 0.8744609487302348,
542
+ "grad_norm": 0.3262430429458618,
543
+ "learning_rate": 1.782840035792625e-06,
544
+ "loss": 17.6816,
545
+ "step": 730
546
+ },
547
+ {
548
+ "epoch": 0.8864398658361284,
549
+ "grad_norm": 0.4543621242046356,
550
+ "learning_rate": 1.7769279578318837e-06,
551
+ "loss": 11.1479,
552
+ "step": 740
553
+ },
554
+ {
555
+ "epoch": 0.898418782942022,
556
+ "grad_norm": 317.15899658203125,
557
+ "learning_rate": 1.7709465639854994e-06,
558
+ "loss": 12.7186,
559
+ "step": 750
560
+ },
561
+ {
562
+ "epoch": 0.9103977000479156,
563
+ "grad_norm": 735.1277465820312,
564
+ "learning_rate": 1.7648963879009074e-06,
565
+ "loss": 24.4749,
566
+ "step": 760
567
+ },
568
+ {
569
+ "epoch": 0.9223766171538093,
570
+ "grad_norm": 259.2248840332031,
571
+ "learning_rate": 1.7587779693621494e-06,
572
+ "loss": 13.9466,
573
+ "step": 770
574
+ },
575
+ {
576
+ "epoch": 0.934355534259703,
577
+ "grad_norm": 0.48265841603279114,
578
+ "learning_rate": 1.752591854241717e-06,
579
+ "loss": 10.1343,
580
+ "step": 780
581
+ },
582
+ {
583
+ "epoch": 0.9463344513655966,
584
+ "grad_norm": 281.167236328125,
585
+ "learning_rate": 1.7463385944518482e-06,
586
+ "loss": 8.1786,
587
+ "step": 790
588
+ },
589
+ {
590
+ "epoch": 0.9583133684714902,
591
+ "grad_norm": 143.92201232910156,
592
+ "learning_rate": 1.7400187478952888e-06,
593
+ "loss": 30.3769,
594
+ "step": 800
595
+ },
596
+ {
597
+ "epoch": 0.9583133684714902,
598
+ "eval_loss": 5.779825687408447,
599
+ "eval_runtime": 239.5089,
600
+ "eval_samples_per_second": 6.221,
601
+ "eval_steps_per_second": 3.111,
602
+ "step": 800
603
+ },
604
+ {
605
+ "epoch": 0.9702922855773838,
606
+ "grad_norm": 787.3501586914062,
607
+ "learning_rate": 1.733632878415515e-06,
608
+ "loss": 18.6365,
609
+ "step": 810
610
+ },
611
+ {
612
+ "epoch": 0.9822712026832774,
613
+ "grad_norm": 1132.944580078125,
614
+ "learning_rate": 1.7271815557464313e-06,
615
+ "loss": 14.7469,
616
+ "step": 820
617
+ },
618
+ {
619
+ "epoch": 0.9942501197891711,
620
+ "grad_norm": 1053.750244140625,
621
+ "learning_rate": 1.7206653554615384e-06,
622
+ "loss": 25.2116,
623
+ "step": 830
624
+ },
625
+ {
626
+ "epoch": 1.0071873502635362,
627
+ "grad_norm": 1744.1956787109375,
628
+ "learning_rate": 1.7140848589225819e-06,
629
+ "loss": 12.9715,
630
+ "step": 840
631
+ },
632
+ {
633
+ "epoch": 1.0191662673694297,
634
+ "grad_norm": 0.658488392829895,
635
+ "learning_rate": 1.7074406532276843e-06,
636
+ "loss": 15.2876,
637
+ "step": 850
638
+ },
639
+ {
640
+ "epoch": 1.0311451844753234,
641
+ "grad_norm": 935.2374877929688,
642
+ "learning_rate": 1.700733331158966e-06,
643
+ "loss": 15.3804,
644
+ "step": 860
645
+ },
646
+ {
647
+ "epoch": 1.0431241015812172,
648
+ "grad_norm": 1073.8214111328125,
649
+ "learning_rate": 1.693963491129658e-06,
650
+ "loss": 9.6525,
651
+ "step": 870
652
+ },
653
+ {
654
+ "epoch": 1.0551030186871106,
655
+ "grad_norm": 1496.8275146484375,
656
+ "learning_rate": 1.6871317371307128e-06,
657
+ "loss": 11.7977,
658
+ "step": 880
659
+ },
660
+ {
661
+ "epoch": 1.0670819357930044,
662
+ "grad_norm": 1174.0115966796875,
663
+ "learning_rate": 1.6802386786769173e-06,
664
+ "loss": 11.7103,
665
+ "step": 890
666
+ },
667
+ {
668
+ "epoch": 1.0790608528988979,
669
+ "grad_norm": 0.169984370470047,
670
+ "learning_rate": 1.6732849307525148e-06,
671
+ "loss": 17.5266,
672
+ "step": 900
673
+ },
674
+ {
675
+ "epoch": 1.0910397700047916,
676
+ "grad_norm": 315.50323486328125,
677
+ "learning_rate": 1.6662711137563345e-06,
678
+ "loss": 13.7159,
679
+ "step": 910
680
+ },
681
+ {
682
+ "epoch": 1.1030186871106853,
683
+ "grad_norm": 1578.7376708984375,
684
+ "learning_rate": 1.6591978534464428e-06,
685
+ "loss": 24.5682,
686
+ "step": 920
687
+ },
688
+ {
689
+ "epoch": 1.1149976042165788,
690
+ "grad_norm": 741.6873779296875,
691
+ "learning_rate": 1.652065780884315e-06,
692
+ "loss": 21.1884,
693
+ "step": 930
694
+ },
695
+ {
696
+ "epoch": 1.1269765213224725,
697
+ "grad_norm": 0.4323195517063141,
698
+ "learning_rate": 1.6448755323785313e-06,
699
+ "loss": 4.4746,
700
+ "step": 940
701
+ },
702
+ {
703
+ "epoch": 1.138955438428366,
704
+ "grad_norm": 0.26412129402160645,
705
+ "learning_rate": 1.6376277494280085e-06,
706
+ "loss": 10.954,
707
+ "step": 950
708
+ },
709
+ {
710
+ "epoch": 1.1509343555342597,
711
+ "grad_norm": 0.3975050449371338,
712
+ "learning_rate": 1.6303230786647652e-06,
713
+ "loss": 7.8232,
714
+ "step": 960
715
+ },
716
+ {
717
+ "epoch": 1.1629132726401532,
718
+ "grad_norm": 1786.0848388671875,
719
+ "learning_rate": 1.622962171796233e-06,
720
+ "loss": 15.7735,
721
+ "step": 970
722
+ },
723
+ {
724
+ "epoch": 1.174892189746047,
725
+ "grad_norm": 0.31270813941955566,
726
+ "learning_rate": 1.6155456855471099e-06,
727
+ "loss": 12.1594,
728
+ "step": 980
729
+ },
730
+ {
731
+ "epoch": 1.1868711068519406,
732
+ "grad_norm": 369.54388427734375,
733
+ "learning_rate": 1.6080742816007699e-06,
734
+ "loss": 14.8824,
735
+ "step": 990
736
+ },
737
+ {
738
+ "epoch": 1.1988500239578341,
739
+ "grad_norm": 1238.604736328125,
740
+ "learning_rate": 1.6005486265402297e-06,
741
+ "loss": 28.347,
742
+ "step": 1000
743
+ },
744
+ {
745
+ "epoch": 1.1988500239578341,
746
+ "eval_loss": 5.866006374359131,
747
+ "eval_runtime": 240.6875,
748
+ "eval_samples_per_second": 6.191,
749
+ "eval_steps_per_second": 3.095,
750
+ "step": 1000
751
+ },
752
+ {
753
+ "epoch": 1.2108289410637278,
754
+ "grad_norm": 767.6785888671875,
755
+ "learning_rate": 1.5929693917886763e-06,
756
+ "loss": 10.1278,
757
+ "step": 1010
758
+ },
759
+ {
760
+ "epoch": 1.2228078581696216,
761
+ "grad_norm": 206.80807495117188,
762
+ "learning_rate": 1.585337253549564e-06,
763
+ "loss": 15.3151,
764
+ "step": 1020
765
+ },
766
+ {
767
+ "epoch": 1.234786775275515,
768
+ "grad_norm": 1851.927490234375,
769
+ "learning_rate": 1.577652892746287e-06,
770
+ "loss": 27.8078,
771
+ "step": 1030
772
+ },
773
+ {
774
+ "epoch": 1.2467656923814088,
775
+ "grad_norm": 196.03907775878906,
776
+ "learning_rate": 1.5699169949614256e-06,
777
+ "loss": 16.0873,
778
+ "step": 1040
779
+ },
780
+ {
781
+ "epoch": 1.2587446094873023,
782
+ "grad_norm": 1514.0220947265625,
783
+ "learning_rate": 1.5621302503755832e-06,
784
+ "loss": 18.1552,
785
+ "step": 1050
786
+ },
787
+ {
788
+ "epoch": 1.270723526593196,
789
+ "grad_norm": 0.2465379238128662,
790
+ "learning_rate": 1.5542933537058072e-06,
791
+ "loss": 15.3595,
792
+ "step": 1060
793
+ },
794
+ {
795
+ "epoch": 1.2827024436990895,
796
+ "grad_norm": 1181.0020751953125,
797
+ "learning_rate": 1.5464070041436097e-06,
798
+ "loss": 9.0312,
799
+ "step": 1070
800
+ },
801
+ {
802
+ "epoch": 1.2946813608049832,
803
+ "grad_norm": 234.97207641601562,
804
+ "learning_rate": 1.538471905292585e-06,
805
+ "loss": 10.9891,
806
+ "step": 1080
807
+ },
808
+ {
809
+ "epoch": 1.306660277910877,
810
+ "grad_norm": NaN,
811
+ "learning_rate": 1.5304887651056396e-06,
812
+ "loss": 17.0111,
813
+ "step": 1090
814
+ },
815
+ {
816
+ "epoch": 1.3186391950167704,
817
+ "grad_norm": 189.0157928466797,
818
+ "learning_rate": 1.5232634521732122e-06,
819
+ "loss": 9.3152,
820
+ "step": 1100
821
+ },
822
+ {
823
+ "epoch": 1.3306181121226641,
824
+ "grad_norm": 0.5336930751800537,
825
+ "learning_rate": 1.515190999157904e-06,
826
+ "loss": 20.7567,
827
+ "step": 1110
828
+ },
829
+ {
830
+ "epoch": 1.3425970292285578,
831
+ "grad_norm": 2664.725830078125,
832
+ "learning_rate": 1.5070725818803735e-06,
833
+ "loss": 11.0421,
834
+ "step": 1120
835
+ },
836
+ {
837
+ "epoch": 1.3545759463344513,
838
+ "grad_norm": 0.2817501425743103,
839
+ "learning_rate": 1.498908924648811e-06,
840
+ "loss": 12.3921,
841
+ "step": 1130
842
+ },
843
+ {
844
+ "epoch": 1.366554863440345,
845
+ "grad_norm": 166.9059295654297,
846
+ "learning_rate": 1.4907007558076216e-06,
847
+ "loss": 11.9341,
848
+ "step": 1140
849
+ },
850
+ {
851
+ "epoch": 1.3785337805462385,
852
+ "grad_norm": 275.1123352050781,
853
+ "learning_rate": 1.4824488076724433e-06,
854
+ "loss": 13.0555,
855
+ "step": 1150
856
+ },
857
+ {
858
+ "epoch": 1.3905126976521323,
859
+ "grad_norm": 0.3370044231414795,
860
+ "learning_rate": 1.4741538164648097e-06,
861
+ "loss": 25.3636,
862
+ "step": 1160
863
+ },
864
+ {
865
+ "epoch": 1.4024916147580258,
866
+ "grad_norm": 190.51695251464844,
867
+ "learning_rate": 1.4658165222464686e-06,
868
+ "loss": 13.6367,
869
+ "step": 1170
870
+ },
871
+ {
872
+ "epoch": 1.4144705318639195,
873
+ "grad_norm": 166.0221710205078,
874
+ "learning_rate": 1.4574376688533532e-06,
875
+ "loss": 9.6226,
876
+ "step": 1180
877
+ },
878
+ {
879
+ "epoch": 1.4264494489698132,
880
+ "grad_norm": 1424.2623291015625,
881
+ "learning_rate": 1.4490180038292192e-06,
882
+ "loss": 13.0517,
883
+ "step": 1190
884
+ },
885
+ {
886
+ "epoch": 1.4384283660757067,
887
+ "grad_norm": 528.625244140625,
888
+ "learning_rate": 1.4405582783589513e-06,
889
+ "loss": 24.365,
890
+ "step": 1200
891
+ },
892
+ {
893
+ "epoch": 1.4384283660757067,
894
+ "eval_loss": 5.900476455688477,
895
+ "eval_runtime": 238.5443,
896
+ "eval_samples_per_second": 6.246,
897
+ "eval_steps_per_second": 3.123,
898
+ "step": 1200
899
+ }
900
+ ],
901
+ "logging_steps": 10,
902
+ "max_steps": 3336,
903
+ "num_input_tokens_seen": 0,
904
+ "num_train_epochs": 4,
905
+ "save_steps": 300,
906
+ "stateful_callbacks": {
907
+ "TrainerControl": {
908
+ "args": {
909
+ "should_epoch_stop": false,
910
+ "should_evaluate": false,
911
+ "should_log": false,
912
+ "should_save": true,
913
+ "should_training_stop": false
914
+ },
915
+ "attributes": {}
916
+ }
917
+ },
918
+ "total_flos": 2.8713596241523507e+17,
919
+ "train_batch_size": 2,
920
+ "trial_name": null,
921
+ "trial_params": null
922
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5f7d272736c2cbc32a5e558e83d24a1d14057e79f2859a67b11974fde7f79dc
3
+ size 5368