amazingvince commited on
Commit
be8c094
1 Parent(s): 7291735

Training in progress, epoch 0

Browse files
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "amazingvince/Not-WizardLM-2-7B",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 10000.0,
20
+ "sliding_window": 4096,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.39.3",
24
+ "use_cache": false,
25
+ "vocab_size": 32000
26
+ }
model/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74c40d3b78c24420a9b0febae51d8241050c3c02bce66cbac5f07f2985350804
3
+ size 4943162336
model/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b1c2ce10ac84a1d587254efccfe368e5c58b6cc315bd111d376b1e582c5c9d7
3
+ size 4999819336
model/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8be4b77e7f7bcb220ae89294175854009d2b5d98009dca36cb2aec2fab545d9e
3
+ size 4540516344
model_2/.ipynb_checkpoints/Untitled-checkpoint.ipynb ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "cells": [],
3
+ "metadata": {},
4
+ "nbformat": 4,
5
+ "nbformat_minor": 5
6
+ }
model_2/.ipynb_checkpoints/trainer_state-checkpoint.json ADDED
@@ -0,0 +1,921 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.973977695167286,
5
+ "eval_steps": 500,
6
+ "global_step": 300,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.05,
13
+ "grad_norm": 2144.0,
14
+ "learning_rate": 8.333333333333333e-07,
15
+ "logits/chosen": -2.582127094268799,
16
+ "logits/rejected": -2.6067237854003906,
17
+ "logps/chosen": -1126.8817138671875,
18
+ "logps/rejected": -1078.447509765625,
19
+ "loss": 0.6576,
20
+ "rewards/accuracies": 0.42500001192092896,
21
+ "rewards/chosen": 0.08093704283237457,
22
+ "rewards/margins": 0.09326125681400299,
23
+ "rewards/rejected": -0.012324221432209015,
24
+ "step": 5
25
+ },
26
+ {
27
+ "epoch": 0.1,
28
+ "grad_norm": 504.0,
29
+ "learning_rate": 1.6666666666666667e-06,
30
+ "logits/chosen": -2.340122699737549,
31
+ "logits/rejected": -2.652778387069702,
32
+ "logps/chosen": -1099.25048828125,
33
+ "logps/rejected": -1232.9901123046875,
34
+ "loss": 0.2009,
35
+ "rewards/accuracies": 0.925000011920929,
36
+ "rewards/chosen": 1.4397642612457275,
37
+ "rewards/margins": 2.55800461769104,
38
+ "rewards/rejected": -1.1182401180267334,
39
+ "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.15,
43
+ "grad_norm": 36.0,
44
+ "learning_rate": 2.5e-06,
45
+ "logits/chosen": -2.513775110244751,
46
+ "logits/rejected": -2.662311315536499,
47
+ "logps/chosen": -990.4671020507812,
48
+ "logps/rejected": -1043.4093017578125,
49
+ "loss": 0.0709,
50
+ "rewards/accuracies": 1.0,
51
+ "rewards/chosen": 2.9243946075439453,
52
+ "rewards/margins": 6.777369499206543,
53
+ "rewards/rejected": -3.8529744148254395,
54
+ "step": 15
55
+ },
56
+ {
57
+ "epoch": 0.2,
58
+ "grad_norm": 3.703125,
59
+ "learning_rate": 3.3333333333333333e-06,
60
+ "logits/chosen": -2.4629788398742676,
61
+ "logits/rejected": -2.802347183227539,
62
+ "logps/chosen": -1008.41064453125,
63
+ "logps/rejected": -1297.322265625,
64
+ "loss": 0.0009,
65
+ "rewards/accuracies": 1.0,
66
+ "rewards/chosen": 8.369072914123535,
67
+ "rewards/margins": 15.539718627929688,
68
+ "rewards/rejected": -7.170646667480469,
69
+ "step": 20
70
+ },
71
+ {
72
+ "epoch": 0.25,
73
+ "grad_norm": 0.000362396240234375,
74
+ "learning_rate": 4.166666666666667e-06,
75
+ "logits/chosen": -2.5417537689208984,
76
+ "logits/rejected": -2.6880087852478027,
77
+ "logps/chosen": -926.39892578125,
78
+ "logps/rejected": -1187.432861328125,
79
+ "loss": 0.0002,
80
+ "rewards/accuracies": 1.0,
81
+ "rewards/chosen": 10.67939281463623,
82
+ "rewards/margins": 24.91078758239746,
83
+ "rewards/rejected": -14.23139476776123,
84
+ "step": 25
85
+ },
86
+ {
87
+ "epoch": 0.3,
88
+ "grad_norm": 0.048095703125,
89
+ "learning_rate": 5e-06,
90
+ "logits/chosen": -2.577080249786377,
91
+ "logits/rejected": -2.733059883117676,
92
+ "logps/chosen": -908.2595825195312,
93
+ "logps/rejected": -1309.6556396484375,
94
+ "loss": 0.0,
95
+ "rewards/accuracies": 1.0,
96
+ "rewards/chosen": 8.903298377990723,
97
+ "rewards/margins": 34.511558532714844,
98
+ "rewards/rejected": -25.608257293701172,
99
+ "step": 30
100
+ },
101
+ {
102
+ "epoch": 0.35,
103
+ "grad_norm": 4.0978193283081055e-07,
104
+ "learning_rate": 4.995770395678171e-06,
105
+ "logits/chosen": -2.651310920715332,
106
+ "logits/rejected": -2.6355812549591064,
107
+ "logps/chosen": -873.0777587890625,
108
+ "logps/rejected": -1328.905517578125,
109
+ "loss": 0.0,
110
+ "rewards/accuracies": 1.0,
111
+ "rewards/chosen": 11.599026679992676,
112
+ "rewards/margins": 44.44927215576172,
113
+ "rewards/rejected": -32.850250244140625,
114
+ "step": 35
115
+ },
116
+ {
117
+ "epoch": 0.4,
118
+ "grad_norm": 0.055908203125,
119
+ "learning_rate": 4.983095894354858e-06,
120
+ "logits/chosen": -2.5453743934631348,
121
+ "logits/rejected": -2.668313503265381,
122
+ "logps/chosen": -1026.492919921875,
123
+ "logps/rejected": -1623.9166259765625,
124
+ "loss": 0.0061,
125
+ "rewards/accuracies": 1.0,
126
+ "rewards/chosen": 12.174985885620117,
127
+ "rewards/margins": 48.78560256958008,
128
+ "rewards/rejected": -36.610618591308594,
129
+ "step": 40
130
+ },
131
+ {
132
+ "epoch": 0.45,
133
+ "grad_norm": 0.0002899169921875,
134
+ "learning_rate": 4.962019382530521e-06,
135
+ "logits/chosen": -2.688816785812378,
136
+ "logits/rejected": -2.8246970176696777,
137
+ "logps/chosen": -866.5418090820312,
138
+ "logps/rejected": -1398.448974609375,
139
+ "loss": 0.0001,
140
+ "rewards/accuracies": 1.0,
141
+ "rewards/chosen": 15.687978744506836,
142
+ "rewards/margins": 49.26004409790039,
143
+ "rewards/rejected": -33.57206344604492,
144
+ "step": 45
145
+ },
146
+ {
147
+ "epoch": 0.5,
148
+ "grad_norm": 3.448803909122944e-09,
149
+ "learning_rate": 4.93261217644956e-06,
150
+ "logits/chosen": -2.555048704147339,
151
+ "logits/rejected": -2.771728515625,
152
+ "logps/chosen": -826.4230346679688,
153
+ "logps/rejected": -1372.0035400390625,
154
+ "loss": 0.0,
155
+ "rewards/accuracies": 1.0,
156
+ "rewards/chosen": 14.595741271972656,
157
+ "rewards/margins": 46.010047912597656,
158
+ "rewards/rejected": -31.414306640625,
159
+ "step": 50
160
+ },
161
+ {
162
+ "epoch": 0.55,
163
+ "grad_norm": 14.5,
164
+ "learning_rate": 4.894973780788722e-06,
165
+ "logits/chosen": -2.570012331008911,
166
+ "logits/rejected": -2.613524913787842,
167
+ "logps/chosen": -867.3160400390625,
168
+ "logps/rejected": -1359.3463134765625,
169
+ "loss": 0.0006,
170
+ "rewards/accuracies": 1.0,
171
+ "rewards/chosen": 16.941835403442383,
172
+ "rewards/margins": 41.53192901611328,
173
+ "rewards/rejected": -24.590087890625,
174
+ "step": 55
175
+ },
176
+ {
177
+ "epoch": 0.59,
178
+ "grad_norm": 7.420778274536133e-06,
179
+ "learning_rate": 4.849231551964771e-06,
180
+ "logits/chosen": -2.6153066158294678,
181
+ "logits/rejected": -2.857034206390381,
182
+ "logps/chosen": -774.2218627929688,
183
+ "logps/rejected": -1181.09619140625,
184
+ "loss": 0.0001,
185
+ "rewards/accuracies": 1.0,
186
+ "rewards/chosen": 21.74435043334961,
187
+ "rewards/margins": 31.659595489501953,
188
+ "rewards/rejected": -9.915243148803711,
189
+ "step": 60
190
+ },
191
+ {
192
+ "epoch": 0.64,
193
+ "grad_norm": 0.00081634521484375,
194
+ "learning_rate": 4.7955402672006855e-06,
195
+ "logits/chosen": -2.738781690597534,
196
+ "logits/rejected": -2.8861005306243896,
197
+ "logps/chosen": -704.155517578125,
198
+ "logps/rejected": -1052.4534912109375,
199
+ "loss": 0.0002,
200
+ "rewards/accuracies": 1.0,
201
+ "rewards/chosen": 25.42382049560547,
202
+ "rewards/margins": 30.588428497314453,
203
+ "rewards/rejected": -5.164605617523193,
204
+ "step": 65
205
+ },
206
+ {
207
+ "epoch": 0.69,
208
+ "grad_norm": 1.555308699607849e-07,
209
+ "learning_rate": 4.734081600808531e-06,
210
+ "logits/chosen": -2.744210720062256,
211
+ "logits/rejected": -2.9681973457336426,
212
+ "logps/chosen": -755.2449340820312,
213
+ "logps/rejected": -1124.8590087890625,
214
+ "loss": 0.0,
215
+ "rewards/accuracies": 1.0,
216
+ "rewards/chosen": 26.51047706604004,
217
+ "rewards/margins": 34.19602966308594,
218
+ "rewards/rejected": -7.685556888580322,
219
+ "step": 70
220
+ },
221
+ {
222
+ "epoch": 0.74,
223
+ "grad_norm": 0.0208740234375,
224
+ "learning_rate": 4.665063509461098e-06,
225
+ "logits/chosen": -2.6066527366638184,
226
+ "logits/rejected": -2.763363838195801,
227
+ "logps/chosen": -718.3406982421875,
228
+ "logps/rejected": -1171.5050048828125,
229
+ "loss": 0.0001,
230
+ "rewards/accuracies": 1.0,
231
+ "rewards/chosen": 23.655757904052734,
232
+ "rewards/margins": 39.56992721557617,
233
+ "rewards/rejected": -15.914169311523438,
234
+ "step": 75
235
+ },
236
+ {
237
+ "epoch": 0.79,
238
+ "grad_norm": 2.0605511963367462e-08,
239
+ "learning_rate": 4.588719528532342e-06,
240
+ "logits/chosen": -2.6591174602508545,
241
+ "logits/rejected": -2.818765640258789,
242
+ "logps/chosen": -713.7478637695312,
243
+ "logps/rejected": -1214.9329833984375,
244
+ "loss": 0.0178,
245
+ "rewards/accuracies": 0.9750000238418579,
246
+ "rewards/chosen": 25.415401458740234,
247
+ "rewards/margins": 46.337589263916016,
248
+ "rewards/rejected": -20.922182083129883,
249
+ "step": 80
250
+ },
251
+ {
252
+ "epoch": 0.84,
253
+ "grad_norm": 8.866190910339355e-07,
254
+ "learning_rate": 4.50530798188761e-06,
255
+ "logits/chosen": -2.592603921890259,
256
+ "logits/rejected": -2.5666003227233887,
257
+ "logps/chosen": -672.0972900390625,
258
+ "logps/rejected": -1153.8974609375,
259
+ "loss": 0.0,
260
+ "rewards/accuracies": 1.0,
261
+ "rewards/chosen": 21.85224151611328,
262
+ "rewards/margins": 44.60143280029297,
263
+ "rewards/rejected": -22.749195098876953,
264
+ "step": 85
265
+ },
266
+ {
267
+ "epoch": 0.89,
268
+ "grad_norm": 0.0032501220703125,
269
+ "learning_rate": 4.415111107797445e-06,
270
+ "logits/chosen": -2.5358242988586426,
271
+ "logits/rejected": -2.7607996463775635,
272
+ "logps/chosen": -837.4728393554688,
273
+ "logps/rejected": -1421.790771484375,
274
+ "loss": 0.0,
275
+ "rewards/accuracies": 1.0,
276
+ "rewards/chosen": 21.30091667175293,
277
+ "rewards/margins": 51.24127197265625,
278
+ "rewards/rejected": -29.94034767150879,
279
+ "step": 90
280
+ },
281
+ {
282
+ "epoch": 0.94,
283
+ "grad_norm": 0.00067901611328125,
284
+ "learning_rate": 4.318434103932622e-06,
285
+ "logits/chosen": -2.5782151222229004,
286
+ "logits/rejected": -2.708712339401245,
287
+ "logps/chosen": -784.4146728515625,
288
+ "logps/rejected": -1424.0408935546875,
289
+ "loss": 0.0,
290
+ "rewards/accuracies": 1.0,
291
+ "rewards/chosen": 24.907550811767578,
292
+ "rewards/margins": 59.107765197753906,
293
+ "rewards/rejected": -34.20021438598633,
294
+ "step": 95
295
+ },
296
+ {
297
+ "epoch": 0.99,
298
+ "grad_norm": 1.0652001947164536e-08,
299
+ "learning_rate": 4.215604094671835e-06,
300
+ "logits/chosen": -2.598839044570923,
301
+ "logits/rejected": -2.6679890155792236,
302
+ "logps/chosen": -733.5455322265625,
303
+ "logps/rejected": -1301.297119140625,
304
+ "loss": 0.0,
305
+ "rewards/accuracies": 1.0,
306
+ "rewards/chosen": 27.65069007873535,
307
+ "rewards/margins": 55.6466178894043,
308
+ "rewards/rejected": -27.995929718017578,
309
+ "step": 100
310
+ },
311
+ {
312
+ "epoch": 1.04,
313
+ "grad_norm": 3.073364496231079e-08,
314
+ "learning_rate": 4.106969024216348e-06,
315
+ "logits/chosen": -2.4979000091552734,
316
+ "logits/rejected": -2.702669620513916,
317
+ "logps/chosen": -800.4815673828125,
318
+ "logps/rejected": -1545.734130859375,
319
+ "loss": 0.0,
320
+ "rewards/accuracies": 1.0,
321
+ "rewards/chosen": 28.3299503326416,
322
+ "rewards/margins": 66.7006607055664,
323
+ "rewards/rejected": -38.37070846557617,
324
+ "step": 105
325
+ },
326
+ {
327
+ "epoch": 1.09,
328
+ "grad_norm": 1.1980533599853516e-05,
329
+ "learning_rate": 3.992896479256966e-06,
330
+ "logits/chosen": -2.5696396827697754,
331
+ "logits/rejected": -2.6518044471740723,
332
+ "logps/chosen": -811.0010986328125,
333
+ "logps/rejected": -1455.451904296875,
334
+ "loss": 0.0,
335
+ "rewards/accuracies": 1.0,
336
+ "rewards/chosen": 24.791704177856445,
337
+ "rewards/margins": 59.291259765625,
338
+ "rewards/rejected": -34.49955749511719,
339
+ "step": 110
340
+ },
341
+ {
342
+ "epoch": 1.14,
343
+ "grad_norm": 1.178705133497715e-09,
344
+ "learning_rate": 3.8737724451770155e-06,
345
+ "logits/chosen": -2.480198383331299,
346
+ "logits/rejected": -2.7152700424194336,
347
+ "logps/chosen": -748.87255859375,
348
+ "logps/rejected": -1521.2923583984375,
349
+ "loss": 0.0,
350
+ "rewards/accuracies": 1.0,
351
+ "rewards/chosen": 24.639190673828125,
352
+ "rewards/margins": 62.03853225708008,
353
+ "rewards/rejected": -37.39933395385742,
354
+ "step": 115
355
+ },
356
+ {
357
+ "epoch": 1.19,
358
+ "grad_norm": 1.7508864402770996e-07,
359
+ "learning_rate": 3.7500000000000005e-06,
360
+ "logits/chosen": -2.5954699516296387,
361
+ "logits/rejected": -2.7862911224365234,
362
+ "logps/chosen": -828.2017822265625,
363
+ "logps/rejected": -1500.0533447265625,
364
+ "loss": 0.0,
365
+ "rewards/accuracies": 1.0,
366
+ "rewards/chosen": 24.49906349182129,
367
+ "rewards/margins": 57.625587463378906,
368
+ "rewards/rejected": -33.12652587890625,
369
+ "step": 120
370
+ },
371
+ {
372
+ "epoch": 1.24,
373
+ "grad_norm": 2.9921531677246094e-05,
374
+ "learning_rate": 3.621997950501156e-06,
375
+ "logits/chosen": -2.5512304306030273,
376
+ "logits/rejected": -2.5572822093963623,
377
+ "logps/chosen": -721.7669067382812,
378
+ "logps/rejected": -1303.0982666015625,
379
+ "loss": 0.0,
380
+ "rewards/accuracies": 1.0,
381
+ "rewards/chosen": 24.202795028686523,
382
+ "rewards/margins": 57.88828659057617,
383
+ "rewards/rejected": -33.68549346923828,
384
+ "step": 125
385
+ },
386
+ {
387
+ "epoch": 1.29,
388
+ "grad_norm": 1.0477378964424133e-09,
389
+ "learning_rate": 3.4901994150978926e-06,
390
+ "logits/chosen": -2.5931153297424316,
391
+ "logits/rejected": -2.693915843963623,
392
+ "logps/chosen": -727.4300537109375,
393
+ "logps/rejected": -1358.4566650390625,
394
+ "loss": 0.0,
395
+ "rewards/accuracies": 1.0,
396
+ "rewards/chosen": 24.488115310668945,
397
+ "rewards/margins": 57.87506866455078,
398
+ "rewards/rejected": -33.38694763183594,
399
+ "step": 130
400
+ },
401
+ {
402
+ "epoch": 1.34,
403
+ "grad_norm": 0.0002765655517578125,
404
+ "learning_rate": 3.3550503583141726e-06,
405
+ "logits/chosen": -2.6825664043426514,
406
+ "logits/rejected": -2.786104679107666,
407
+ "logps/chosen": -796.1810302734375,
408
+ "logps/rejected": -1376.611328125,
409
+ "loss": 0.0,
410
+ "rewards/accuracies": 1.0,
411
+ "rewards/chosen": 25.74446678161621,
412
+ "rewards/margins": 58.13447189331055,
413
+ "rewards/rejected": -32.39000701904297,
414
+ "step": 135
415
+ },
416
+ {
417
+ "epoch": 1.39,
418
+ "grad_norm": 5.030632019042969e-05,
419
+ "learning_rate": 3.217008081777726e-06,
420
+ "logits/chosen": -2.5538275241851807,
421
+ "logits/rejected": -2.7200071811676025,
422
+ "logps/chosen": -782.6590576171875,
423
+ "logps/rejected": -1443.415283203125,
424
+ "loss": 0.0,
425
+ "rewards/accuracies": 1.0,
426
+ "rewards/chosen": 27.598276138305664,
427
+ "rewards/margins": 58.656410217285156,
428
+ "rewards/rejected": -31.05812644958496,
429
+ "step": 140
430
+ },
431
+ {
432
+ "epoch": 1.44,
433
+ "grad_norm": 3.6209821701049805e-06,
434
+ "learning_rate": 3.0765396768561005e-06,
435
+ "logits/chosen": -2.6117515563964844,
436
+ "logits/rejected": -2.74174165725708,
437
+ "logps/chosen": -670.0432739257812,
438
+ "logps/rejected": -1294.08642578125,
439
+ "loss": 0.0,
440
+ "rewards/accuracies": 1.0,
441
+ "rewards/chosen": 26.823715209960938,
442
+ "rewards/margins": 60.58592987060547,
443
+ "rewards/rejected": -33.76221466064453,
444
+ "step": 145
445
+ },
446
+ {
447
+ "epoch": 1.49,
448
+ "grad_norm": 1.1932570487260818e-09,
449
+ "learning_rate": 2.9341204441673267e-06,
450
+ "logits/chosen": -2.6705422401428223,
451
+ "logits/rejected": -2.7561261653900146,
452
+ "logps/chosen": -830.1842041015625,
453
+ "logps/rejected": -1481.5352783203125,
454
+ "loss": 0.0,
455
+ "rewards/accuracies": 1.0,
456
+ "rewards/chosen": 24.070798873901367,
457
+ "rewards/margins": 62.027305603027344,
458
+ "rewards/rejected": -37.956504821777344,
459
+ "step": 150
460
+ },
461
+ {
462
+ "epoch": 1.54,
463
+ "grad_norm": 7.927417755126953e-06,
464
+ "learning_rate": 2.7902322853130758e-06,
465
+ "logits/chosen": -2.5545754432678223,
466
+ "logits/rejected": -2.740570068359375,
467
+ "logps/chosen": -853.0714111328125,
468
+ "logps/rejected": -1508.432373046875,
469
+ "loss": 0.0,
470
+ "rewards/accuracies": 1.0,
471
+ "rewards/chosen": 25.61324119567871,
472
+ "rewards/margins": 58.5531120300293,
473
+ "rewards/rejected": -32.93987274169922,
474
+ "step": 155
475
+ },
476
+ {
477
+ "epoch": 1.59,
478
+ "grad_norm": 1.5178830414797062e-16,
479
+ "learning_rate": 2.6453620722761897e-06,
480
+ "logits/chosen": -2.5684103965759277,
481
+ "logits/rejected": -2.6356844902038574,
482
+ "logps/chosen": -695.0123291015625,
483
+ "logps/rejected": -1333.6201171875,
484
+ "loss": 0.0,
485
+ "rewards/accuracies": 1.0,
486
+ "rewards/chosen": 26.32758140563965,
487
+ "rewards/margins": 56.49725341796875,
488
+ "rewards/rejected": -30.169677734375,
489
+ "step": 160
490
+ },
491
+ {
492
+ "epoch": 1.64,
493
+ "grad_norm": 4.0512531995773315e-08,
494
+ "learning_rate": 2.5e-06,
495
+ "logits/chosen": -2.6028122901916504,
496
+ "logits/rejected": -2.621495246887207,
497
+ "logps/chosen": -689.859130859375,
498
+ "logps/rejected": -1285.8802490234375,
499
+ "loss": 0.0,
500
+ "rewards/accuracies": 1.0,
501
+ "rewards/chosen": 26.484960556030273,
502
+ "rewards/margins": 60.581703186035156,
503
+ "rewards/rejected": -34.09674835205078,
504
+ "step": 165
505
+ },
506
+ {
507
+ "epoch": 1.69,
508
+ "grad_norm": 5.811452865600586e-07,
509
+ "learning_rate": 2.3546379277238107e-06,
510
+ "logits/chosen": -2.5608181953430176,
511
+ "logits/rejected": -2.633148431777954,
512
+ "logps/chosen": -689.5059204101562,
513
+ "logps/rejected": -1259.192138671875,
514
+ "loss": 0.0,
515
+ "rewards/accuracies": 1.0,
516
+ "rewards/chosen": 24.118501663208008,
517
+ "rewards/margins": 56.985939025878906,
518
+ "rewards/rejected": -32.86743927001953,
519
+ "step": 170
520
+ },
521
+ {
522
+ "epoch": 1.73,
523
+ "grad_norm": 2.637505531311035e-06,
524
+ "learning_rate": 2.2097677146869242e-06,
525
+ "logits/chosen": -2.5463547706604004,
526
+ "logits/rejected": -2.6621968746185303,
527
+ "logps/chosen": -845.2557373046875,
528
+ "logps/rejected": -1509.9571533203125,
529
+ "loss": 0.0,
530
+ "rewards/accuracies": 1.0,
531
+ "rewards/chosen": 20.753326416015625,
532
+ "rewards/margins": 60.85497283935547,
533
+ "rewards/rejected": -40.101646423339844,
534
+ "step": 175
535
+ },
536
+ {
537
+ "epoch": 1.78,
538
+ "grad_norm": 2.8033131371785203e-15,
539
+ "learning_rate": 2.0658795558326745e-06,
540
+ "logits/chosen": -2.5142176151275635,
541
+ "logits/rejected": -2.800828456878662,
542
+ "logps/chosen": -768.0780029296875,
543
+ "logps/rejected": -1504.419677734375,
544
+ "loss": 0.0,
545
+ "rewards/accuracies": 1.0,
546
+ "rewards/chosen": 26.789424896240234,
547
+ "rewards/margins": 65.28126525878906,
548
+ "rewards/rejected": -38.49182891845703,
549
+ "step": 180
550
+ },
551
+ {
552
+ "epoch": 1.83,
553
+ "grad_norm": 7.450580596923828e-06,
554
+ "learning_rate": 1.9234603231439e-06,
555
+ "logits/chosen": -2.5999841690063477,
556
+ "logits/rejected": -2.785568952560425,
557
+ "logps/chosen": -742.1795654296875,
558
+ "logps/rejected": -1414.2978515625,
559
+ "loss": 0.0,
560
+ "rewards/accuracies": 1.0,
561
+ "rewards/chosen": 26.651920318603516,
562
+ "rewards/margins": 61.58074951171875,
563
+ "rewards/rejected": -34.92882537841797,
564
+ "step": 185
565
+ },
566
+ {
567
+ "epoch": 1.88,
568
+ "grad_norm": 3.841705620288849e-08,
569
+ "learning_rate": 1.7829919182222752e-06,
570
+ "logits/chosen": -2.735452175140381,
571
+ "logits/rejected": -2.7289414405822754,
572
+ "logps/chosen": -814.5637817382812,
573
+ "logps/rejected": -1430.7174072265625,
574
+ "loss": 0.0,
575
+ "rewards/accuracies": 1.0,
576
+ "rewards/chosen": 28.13421630859375,
577
+ "rewards/margins": 61.936744689941406,
578
+ "rewards/rejected": -33.802528381347656,
579
+ "step": 190
580
+ },
581
+ {
582
+ "epoch": 1.93,
583
+ "grad_norm": 6.892264536872972e-13,
584
+ "learning_rate": 1.6449496416858285e-06,
585
+ "logits/chosen": -2.515446186065674,
586
+ "logits/rejected": -2.742518663406372,
587
+ "logps/chosen": -745.94970703125,
588
+ "logps/rejected": -1403.6351318359375,
589
+ "loss": 0.0,
590
+ "rewards/accuracies": 1.0,
591
+ "rewards/chosen": 26.278427124023438,
592
+ "rewards/margins": 64.49276733398438,
593
+ "rewards/rejected": -38.21433639526367,
594
+ "step": 195
595
+ },
596
+ {
597
+ "epoch": 1.98,
598
+ "grad_norm": 1.1757947504520416e-08,
599
+ "learning_rate": 1.509800584902108e-06,
600
+ "logits/chosen": -2.478830575942993,
601
+ "logits/rejected": -2.7162294387817383,
602
+ "logps/chosen": -780.1927490234375,
603
+ "logps/rejected": -1506.2659912109375,
604
+ "loss": 0.0,
605
+ "rewards/accuracies": 1.0,
606
+ "rewards/chosen": 26.495025634765625,
607
+ "rewards/margins": 63.679115295410156,
608
+ "rewards/rejected": -37.184085845947266,
609
+ "step": 200
610
+ },
611
+ {
612
+ "epoch": 2.03,
613
+ "grad_norm": 1.519918441772461e-05,
614
+ "learning_rate": 1.3780020494988447e-06,
615
+ "logits/chosen": -2.5534565448760986,
616
+ "logits/rejected": -2.703151226043701,
617
+ "logps/chosen": -684.3609619140625,
618
+ "logps/rejected": -1303.3043212890625,
619
+ "loss": 0.0,
620
+ "rewards/accuracies": 1.0,
621
+ "rewards/chosen": 23.173385620117188,
622
+ "rewards/margins": 54.865631103515625,
623
+ "rewards/rejected": -31.692245483398438,
624
+ "step": 205
625
+ },
626
+ {
627
+ "epoch": 2.08,
628
+ "grad_norm": 0.0001277923583984375,
629
+ "learning_rate": 1.2500000000000007e-06,
630
+ "logits/chosen": -2.566140651702881,
631
+ "logits/rejected": -2.703296661376953,
632
+ "logps/chosen": -764.0347290039062,
633
+ "logps/rejected": -1441.303955078125,
634
+ "loss": 0.0,
635
+ "rewards/accuracies": 1.0,
636
+ "rewards/chosen": 25.557802200317383,
637
+ "rewards/margins": 61.8077392578125,
638
+ "rewards/rejected": -36.249942779541016,
639
+ "step": 210
640
+ },
641
+ {
642
+ "epoch": 2.13,
643
+ "grad_norm": 3.110617399215698e-07,
644
+ "learning_rate": 1.1262275548229852e-06,
645
+ "logits/chosen": -2.577171564102173,
646
+ "logits/rejected": -2.6875264644622803,
647
+ "logps/chosen": -733.8834228515625,
648
+ "logps/rejected": -1341.32763671875,
649
+ "loss": 0.0,
650
+ "rewards/accuracies": 1.0,
651
+ "rewards/chosen": 23.420785903930664,
652
+ "rewards/margins": 59.020118713378906,
653
+ "rewards/rejected": -35.59933090209961,
654
+ "step": 215
655
+ },
656
+ {
657
+ "epoch": 2.18,
658
+ "grad_norm": 1.8917489796876907e-09,
659
+ "learning_rate": 1.0071035207430352e-06,
660
+ "logits/chosen": -2.5544378757476807,
661
+ "logits/rejected": -2.641348361968994,
662
+ "logps/chosen": -771.989013671875,
663
+ "logps/rejected": -1348.832275390625,
664
+ "loss": 0.0,
665
+ "rewards/accuracies": 1.0,
666
+ "rewards/chosen": 24.312747955322266,
667
+ "rewards/margins": 58.93672561645508,
668
+ "rewards/rejected": -34.62397003173828,
669
+ "step": 220
670
+ },
671
+ {
672
+ "epoch": 2.23,
673
+ "grad_norm": 8.221832104027271e-10,
674
+ "learning_rate": 8.930309757836517e-07,
675
+ "logits/chosen": -2.6528477668762207,
676
+ "logits/rejected": -2.757702350616455,
677
+ "logps/chosen": -788.48828125,
678
+ "logps/rejected": -1497.994140625,
679
+ "loss": 0.0,
680
+ "rewards/accuracies": 1.0,
681
+ "rewards/chosen": 24.537336349487305,
682
+ "rewards/margins": 68.33438110351562,
683
+ "rewards/rejected": -43.79704284667969,
684
+ "step": 225
685
+ },
686
+ {
687
+ "epoch": 2.28,
688
+ "grad_norm": 0.000446319580078125,
689
+ "learning_rate": 7.843959053281663e-07,
690
+ "logits/chosen": -2.631401777267456,
691
+ "logits/rejected": -2.7087044715881348,
692
+ "logps/chosen": -811.6467895507812,
693
+ "logps/rejected": -1447.6087646484375,
694
+ "loss": 0.0,
695
+ "rewards/accuracies": 1.0,
696
+ "rewards/chosen": 25.546356201171875,
697
+ "rewards/margins": 62.1228141784668,
698
+ "rewards/rejected": -36.576454162597656,
699
+ "step": 230
700
+ },
701
+ {
702
+ "epoch": 2.33,
703
+ "grad_norm": 0.001556396484375,
704
+ "learning_rate": 6.815658960673782e-07,
705
+ "logits/chosen": -2.496450901031494,
706
+ "logits/rejected": -2.640903949737549,
707
+ "logps/chosen": -756.075439453125,
708
+ "logps/rejected": -1518.998046875,
709
+ "loss": 0.0,
710
+ "rewards/accuracies": 1.0,
711
+ "rewards/chosen": 22.391010284423828,
712
+ "rewards/margins": 63.806968688964844,
713
+ "rewards/rejected": -41.41596603393555,
714
+ "step": 235
715
+ },
716
+ {
717
+ "epoch": 2.38,
718
+ "grad_norm": 3.361701965332031e-05,
719
+ "learning_rate": 5.848888922025553e-07,
720
+ "logits/chosen": -2.5900871753692627,
721
+ "logits/rejected": -2.6478281021118164,
722
+ "logps/chosen": -654.4774780273438,
723
+ "logps/rejected": -1188.7408447265625,
724
+ "loss": 0.0,
725
+ "rewards/accuracies": 1.0,
726
+ "rewards/chosen": 25.036846160888672,
727
+ "rewards/margins": 53.53025436401367,
728
+ "rewards/rejected": -28.493408203125,
729
+ "step": 240
730
+ },
731
+ {
732
+ "epoch": 2.43,
733
+ "grad_norm": 2.1191226551309228e-10,
734
+ "learning_rate": 4.946920181123904e-07,
735
+ "logits/chosen": -2.509355068206787,
736
+ "logits/rejected": -2.687610149383545,
737
+ "logps/chosen": -787.9483642578125,
738
+ "logps/rejected": -1455.489013671875,
739
+ "loss": 0.0,
740
+ "rewards/accuracies": 1.0,
741
+ "rewards/chosen": 23.417675018310547,
742
+ "rewards/margins": 57.781227111816406,
743
+ "rewards/rejected": -34.363548278808594,
744
+ "step": 245
745
+ },
746
+ {
747
+ "epoch": 2.48,
748
+ "grad_norm": 1.210719347000122e-08,
749
+ "learning_rate": 4.1128047146765936e-07,
750
+ "logits/chosen": -2.5654799938201904,
751
+ "logits/rejected": -2.7495007514953613,
752
+ "logps/chosen": -880.7611083984375,
753
+ "logps/rejected": -1492.9364013671875,
754
+ "loss": 0.0,
755
+ "rewards/accuracies": 1.0,
756
+ "rewards/chosen": 26.42355728149414,
757
+ "rewards/margins": 58.61255645751953,
758
+ "rewards/rejected": -32.188995361328125,
759
+ "step": 250
760
+ },
761
+ {
762
+ "epoch": 2.53,
763
+ "grad_norm": 3.552713678800501e-12,
764
+ "learning_rate": 3.3493649053890325e-07,
765
+ "logits/chosen": -2.5684847831726074,
766
+ "logits/rejected": -2.7665956020355225,
767
+ "logps/chosen": -717.5662231445312,
768
+ "logps/rejected": -1405.523681640625,
769
+ "loss": 0.0,
770
+ "rewards/accuracies": 1.0,
771
+ "rewards/chosen": 25.795669555664062,
772
+ "rewards/margins": 55.92620849609375,
773
+ "rewards/rejected": -30.130529403686523,
774
+ "step": 255
775
+ },
776
+ {
777
+ "epoch": 2.58,
778
+ "grad_norm": 4.1470733097570545e-18,
779
+ "learning_rate": 2.6591839919146963e-07,
780
+ "logits/chosen": -2.5511410236358643,
781
+ "logits/rejected": -2.642638921737671,
782
+ "logps/chosen": -770.4322509765625,
783
+ "logps/rejected": -1513.5374755859375,
784
+ "loss": 0.0,
785
+ "rewards/accuracies": 1.0,
786
+ "rewards/chosen": 26.562414169311523,
787
+ "rewards/margins": 67.80595397949219,
788
+ "rewards/rejected": -41.24353790283203,
789
+ "step": 260
790
+ },
791
+ {
792
+ "epoch": 2.63,
793
+ "grad_norm": 2.775341272354126e-07,
794
+ "learning_rate": 2.044597327993153e-07,
795
+ "logits/chosen": -2.5555355548858643,
796
+ "logits/rejected": -2.715888738632202,
797
+ "logps/chosen": -807.5404052734375,
798
+ "logps/rejected": -1584.75927734375,
799
+ "loss": 0.0,
800
+ "rewards/accuracies": 1.0,
801
+ "rewards/chosen": 25.03497886657715,
802
+ "rewards/margins": 64.63668823242188,
803
+ "rewards/rejected": -39.601707458496094,
804
+ "step": 265
805
+ },
806
+ {
807
+ "epoch": 2.68,
808
+ "grad_norm": 4.007461029686965e-12,
809
+ "learning_rate": 1.507684480352292e-07,
810
+ "logits/chosen": -2.597036123275757,
811
+ "logits/rejected": -2.643857479095459,
812
+ "logps/chosen": -831.2688598632812,
813
+ "logps/rejected": -1632.8023681640625,
814
+ "loss": 0.0,
815
+ "rewards/accuracies": 1.0,
816
+ "rewards/chosen": 24.538908004760742,
817
+ "rewards/margins": 74.41605377197266,
818
+ "rewards/rejected": -49.87714385986328,
819
+ "step": 270
820
+ },
821
+ {
822
+ "epoch": 2.73,
823
+ "grad_norm": 4.172325134277344e-05,
824
+ "learning_rate": 1.0502621921127776e-07,
825
+ "logits/chosen": -2.5798580646514893,
826
+ "logits/rejected": -2.7736194133758545,
827
+ "logps/chosen": -767.0318603515625,
828
+ "logps/rejected": -1508.767822265625,
829
+ "loss": 0.0,
830
+ "rewards/accuracies": 1.0,
831
+ "rewards/chosen": 25.648067474365234,
832
+ "rewards/margins": 66.6827163696289,
833
+ "rewards/rejected": -41.034645080566406,
834
+ "step": 275
835
+ },
836
+ {
837
+ "epoch": 2.78,
838
+ "grad_norm": 1.9818544387817383e-06,
839
+ "learning_rate": 6.738782355044048e-08,
840
+ "logits/chosen": -2.5585246086120605,
841
+ "logits/rejected": -2.666764736175537,
842
+ "logps/chosen": -772.8341064453125,
843
+ "logps/rejected": -1421.703857421875,
844
+ "loss": 0.0,
845
+ "rewards/accuracies": 1.0,
846
+ "rewards/chosen": 27.29400634765625,
847
+ "rewards/margins": 63.170677185058594,
848
+ "rewards/rejected": -35.87666702270508,
849
+ "step": 280
850
+ },
851
+ {
852
+ "epoch": 2.83,
853
+ "grad_norm": 1.2631062418222427e-08,
854
+ "learning_rate": 3.798061746947995e-08,
855
+ "logits/chosen": -2.512103319168091,
856
+ "logits/rejected": -2.690737009048462,
857
+ "logps/chosen": -810.3479614257812,
858
+ "logps/rejected": -1493.773193359375,
859
+ "loss": 0.0,
860
+ "rewards/accuracies": 1.0,
861
+ "rewards/chosen": 22.784202575683594,
862
+ "rewards/margins": 61.64385223388672,
863
+ "rewards/rejected": -38.859649658203125,
864
+ "step": 285
865
+ },
866
+ {
867
+ "epoch": 2.87,
868
+ "grad_norm": 8.009374141693115e-08,
869
+ "learning_rate": 1.6904105645142443e-08,
870
+ "logits/chosen": -2.618516445159912,
871
+ "logits/rejected": -2.7000651359558105,
872
+ "logps/chosen": -769.9617309570312,
873
+ "logps/rejected": -1351.812255859375,
874
+ "loss": 0.0,
875
+ "rewards/accuracies": 1.0,
876
+ "rewards/chosen": 25.189565658569336,
877
+ "rewards/margins": 57.4492073059082,
878
+ "rewards/rejected": -32.259639739990234,
879
+ "step": 290
880
+ },
881
+ {
882
+ "epoch": 2.92,
883
+ "grad_norm": 9.324138683375338e-17,
884
+ "learning_rate": 4.229604321829561e-09,
885
+ "logits/chosen": -2.5340938568115234,
886
+ "logits/rejected": -2.880659818649292,
887
+ "logps/chosen": -801.6094970703125,
888
+ "logps/rejected": -1518.06201171875,
889
+ "loss": 0.0,
890
+ "rewards/accuracies": 1.0,
891
+ "rewards/chosen": 26.99312400817871,
892
+ "rewards/margins": 64.31195068359375,
893
+ "rewards/rejected": -37.3188362121582,
894
+ "step": 295
895
+ },
896
+ {
897
+ "epoch": 2.97,
898
+ "grad_norm": 3.241002559661865e-07,
899
+ "learning_rate": 0.0,
900
+ "logits/chosen": -2.616868019104004,
901
+ "logits/rejected": -2.702866792678833,
902
+ "logps/chosen": -725.1414184570312,
903
+ "logps/rejected": -1320.96435546875,
904
+ "loss": 0.0,
905
+ "rewards/accuracies": 1.0,
906
+ "rewards/chosen": 25.64286231994629,
907
+ "rewards/margins": 60.58977508544922,
908
+ "rewards/rejected": -34.94690704345703,
909
+ "step": 300
910
+ }
911
+ ],
912
+ "logging_steps": 5,
913
+ "max_steps": 300,
914
+ "num_input_tokens_seen": 0,
915
+ "num_train_epochs": 3,
916
+ "save_steps": 500,
917
+ "total_flos": 0.0,
918
+ "train_batch_size": 1,
919
+ "trial_name": null,
920
+ "trial_params": null
921
+ }
model_2/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "amazingvince/Not-WizardLM-2-7B",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 10000.0,
20
+ "sliding_window": 4096,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.39.3",
24
+ "use_cache": false,
25
+ "vocab_size": 32000
26
+ }
model_2/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.39.3"
6
+ }
model_2/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74c40d3b78c24420a9b0febae51d8241050c3c02bce66cbac5f07f2985350804
3
+ size 4943162336
model_2/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b1c2ce10ac84a1d587254efccfe368e5c58b6cc315bd111d376b1e582c5c9d7
3
+ size 4999819336
model_2/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8be4b77e7f7bcb220ae89294175854009d2b5d98009dca36cb2aec2fab545d9e
3
+ size 4540516344
model_2/model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 14483464192
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00003-of-00003.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
296
+ "model.norm.weight": "model-00003-of-00003.safetensors"
297
+ }
298
+ }
model_2/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
model_2/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
model_2/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
model_2/tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
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
+ },
31
+ "additional_special_tokens": [],
32
+ "bos_token": "<s>",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 8192,
37
+ "pad_token": "<unk>",
38
+ "padding_side": "right",
39
+ "sp_model_kwargs": {},
40
+ "spaces_between_special_tokens": false,
41
+ "tokenizer_class": "LlamaTokenizer",
42
+ "unk_token": "<unk>",
43
+ "use_default_system_prompt": false
44
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
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 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
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
+ },
31
+ "additional_special_tokens": [],
32
+ "bos_token": "<s>",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 8192,
37
+ "pad_token": "<unk>",
38
+ "padding_side": "right",
39
+ "sp_model_kwargs": {},
40
+ "spaces_between_special_tokens": false,
41
+ "tokenizer_class": "LlamaTokenizer",
42
+ "unk_token": "<unk>",
43
+ "use_default_system_prompt": false
44
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc09ac89945631b1006df504d6c8ff040c9e2495df1e150512b149d59a452f16
3
+ size 4795