DrNicefellow commited on
Commit
51d00ce
1 Parent(s): 0619a9b

Upload 8 files

Browse files
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MistralForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 2048,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 3072,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "mistral",
14
+ "num_attention_heads": 32,
15
+ "num_hidden_layers": 24,
16
+ "num_key_value_heads": 4,
17
+ "rms_norm_eps": 1e-06,
18
+ "rope_theta": 10000.0,
19
+ "sliding_window": 4096,
20
+ "tie_word_embeddings": false,
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.38.0.dev0",
23
+ "use_cache": true,
24
+ "vocab_size": 32000
25
+ }
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": "4.38.0.dev0"
6
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:feb3ebd1c38b4cd67fca60fa98369cd5dd6e7f0aa61df8b8d7b8f76bbf1e944d
3
+ size 6485383922
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9729807e0d8c76a161a6543bde55f092f5e326209174713a6b8462aa39a4f1a
3
+ size 3242672438
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed4469ec40e4593037923b5178b7e3c952f5960695b9ce4051f18c2c66aa4726
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,351 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.19465014879922485,
5
+ "eval_steps": 100000000,
6
+ "global_step": 27000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "learning_rate": 1.0000000000000001e-07,
14
+ "loss": 10.7586,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.0,
19
+ "learning_rate": 5e-05,
20
+ "loss": 6.5292,
21
+ "step": 500
22
+ },
23
+ {
24
+ "epoch": 0.01,
25
+ "learning_rate": 4.99998214600225e-05,
26
+ "loss": 4.7262,
27
+ "step": 1000
28
+ },
29
+ {
30
+ "epoch": 0.01,
31
+ "learning_rate": 4.9999285842640105e-05,
32
+ "loss": 4.1997,
33
+ "step": 1500
34
+ },
35
+ {
36
+ "epoch": 0.01,
37
+ "learning_rate": 4.999839315550315e-05,
38
+ "loss": 3.8892,
39
+ "step": 2000
40
+ },
41
+ {
42
+ "epoch": 0.02,
43
+ "learning_rate": 4.9997143411362066e-05,
44
+ "loss": 3.6618,
45
+ "step": 2500
46
+ },
47
+ {
48
+ "epoch": 0.02,
49
+ "learning_rate": 4.9995536628067196e-05,
50
+ "loss": 3.5132,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 0.03,
55
+ "learning_rate": 4.9993572828568536e-05,
56
+ "loss": 3.4092,
57
+ "step": 3500
58
+ },
59
+ {
60
+ "epoch": 0.03,
61
+ "learning_rate": 4.999125204091544e-05,
62
+ "loss": 3.3295,
63
+ "step": 4000
64
+ },
65
+ {
66
+ "epoch": 0.03,
67
+ "learning_rate": 4.998857429825615e-05,
68
+ "loss": 3.2596,
69
+ "step": 4500
70
+ },
71
+ {
72
+ "epoch": 0.04,
73
+ "learning_rate": 4.9985539638837424e-05,
74
+ "loss": 3.2068,
75
+ "step": 5000
76
+ },
77
+ {
78
+ "epoch": 0.04,
79
+ "learning_rate": 4.998214810600389e-05,
80
+ "loss": 3.163,
81
+ "step": 5500
82
+ },
83
+ {
84
+ "epoch": 0.04,
85
+ "learning_rate": 4.997839974819749e-05,
86
+ "loss": 3.1256,
87
+ "step": 6000
88
+ },
89
+ {
90
+ "epoch": 0.05,
91
+ "learning_rate": 4.997429461895675e-05,
92
+ "loss": 3.0844,
93
+ "step": 6500
94
+ },
95
+ {
96
+ "epoch": 0.05,
97
+ "learning_rate": 4.996983277691606e-05,
98
+ "loss": 3.0541,
99
+ "step": 7000
100
+ },
101
+ {
102
+ "epoch": 0.05,
103
+ "learning_rate": 4.996501428580478e-05,
104
+ "loss": 3.0293,
105
+ "step": 7500
106
+ },
107
+ {
108
+ "epoch": 0.06,
109
+ "learning_rate": 4.995983921444638e-05,
110
+ "loss": 2.999,
111
+ "step": 8000
112
+ },
113
+ {
114
+ "epoch": 0.06,
115
+ "learning_rate": 4.9954307636757434e-05,
116
+ "loss": 2.9744,
117
+ "step": 8500
118
+ },
119
+ {
120
+ "epoch": 0.06,
121
+ "learning_rate": 4.994841963174656e-05,
122
+ "loss": 2.9525,
123
+ "step": 9000
124
+ },
125
+ {
126
+ "epoch": 0.07,
127
+ "learning_rate": 4.9942175283513294e-05,
128
+ "loss": 2.9321,
129
+ "step": 9500
130
+ },
131
+ {
132
+ "epoch": 0.07,
133
+ "learning_rate": 4.993557468124691e-05,
134
+ "loss": 2.9237,
135
+ "step": 10000
136
+ },
137
+ {
138
+ "epoch": 0.08,
139
+ "learning_rate": 4.9928617919225106e-05,
140
+ "loss": 2.9021,
141
+ "step": 10500
142
+ },
143
+ {
144
+ "epoch": 0.08,
145
+ "learning_rate": 4.99213050968127e-05,
146
+ "loss": 2.8766,
147
+ "step": 11000
148
+ },
149
+ {
150
+ "epoch": 0.08,
151
+ "learning_rate": 4.991363631846019e-05,
152
+ "loss": 2.8691,
153
+ "step": 11500
154
+ },
155
+ {
156
+ "epoch": 0.09,
157
+ "learning_rate": 4.990561169370224e-05,
158
+ "loss": 2.8531,
159
+ "step": 12000
160
+ },
161
+ {
162
+ "epoch": 0.09,
163
+ "learning_rate": 4.989723133715618e-05,
164
+ "loss": 2.8366,
165
+ "step": 12500
166
+ },
167
+ {
168
+ "epoch": 0.09,
169
+ "learning_rate": 4.988849536852028e-05,
170
+ "loss": 2.8265,
171
+ "step": 13000
172
+ },
173
+ {
174
+ "epoch": 0.1,
175
+ "learning_rate": 4.987940391257212e-05,
176
+ "loss": 2.8099,
177
+ "step": 13500
178
+ },
179
+ {
180
+ "epoch": 0.1,
181
+ "learning_rate": 4.986995709916677e-05,
182
+ "loss": 2.8009,
183
+ "step": 14000
184
+ },
185
+ {
186
+ "epoch": 0.1,
187
+ "learning_rate": 4.9860155063234944e-05,
188
+ "loss": 2.7881,
189
+ "step": 14500
190
+ },
191
+ {
192
+ "epoch": 0.11,
193
+ "learning_rate": 4.9849997944781055e-05,
194
+ "loss": 2.7794,
195
+ "step": 15000
196
+ },
197
+ {
198
+ "epoch": 0.11,
199
+ "learning_rate": 4.9839485888881235e-05,
200
+ "loss": 2.7674,
201
+ "step": 15500
202
+ },
203
+ {
204
+ "epoch": 0.12,
205
+ "learning_rate": 4.982861904568127e-05,
206
+ "loss": 2.7559,
207
+ "step": 16000
208
+ },
209
+ {
210
+ "epoch": 0.12,
211
+ "learning_rate": 4.981739757039443e-05,
212
+ "loss": 2.7455,
213
+ "step": 16500
214
+ },
215
+ {
216
+ "epoch": 0.12,
217
+ "learning_rate": 4.9805821623299285e-05,
218
+ "loss": 2.7351,
219
+ "step": 17000
220
+ },
221
+ {
222
+ "epoch": 0.13,
223
+ "learning_rate": 4.979389136973737e-05,
224
+ "loss": 2.7317,
225
+ "step": 17500
226
+ },
227
+ {
228
+ "epoch": 0.13,
229
+ "learning_rate": 4.978160698011085e-05,
230
+ "loss": 2.7192,
231
+ "step": 18000
232
+ },
233
+ {
234
+ "epoch": 0.13,
235
+ "learning_rate": 4.976896862988012e-05,
236
+ "loss": 2.709,
237
+ "step": 18500
238
+ },
239
+ {
240
+ "epoch": 0.14,
241
+ "learning_rate": 4.975597649956122e-05,
242
+ "loss": 2.7043,
243
+ "step": 19000
244
+ },
245
+ {
246
+ "epoch": 0.14,
247
+ "learning_rate": 4.974263077472334e-05,
248
+ "loss": 2.6954,
249
+ "step": 19500
250
+ },
251
+ {
252
+ "epoch": 0.14,
253
+ "learning_rate": 4.97289316459861e-05,
254
+ "loss": 2.6905,
255
+ "step": 20000
256
+ },
257
+ {
258
+ "epoch": 0.15,
259
+ "learning_rate": 4.9714879309016874e-05,
260
+ "loss": 2.6782,
261
+ "step": 20500
262
+ },
263
+ {
264
+ "epoch": 0.15,
265
+ "learning_rate": 4.970047396452798e-05,
266
+ "loss": 2.6751,
267
+ "step": 21000
268
+ },
269
+ {
270
+ "epoch": 0.15,
271
+ "learning_rate": 4.968571581827381e-05,
272
+ "loss": 2.6659,
273
+ "step": 21500
274
+ },
275
+ {
276
+ "epoch": 0.16,
277
+ "learning_rate": 4.9670605081047886e-05,
278
+ "loss": 2.6594,
279
+ "step": 22000
280
+ },
281
+ {
282
+ "epoch": 0.16,
283
+ "learning_rate": 4.9655141968679866e-05,
284
+ "loss": 2.6553,
285
+ "step": 22500
286
+ },
287
+ {
288
+ "epoch": 0.17,
289
+ "learning_rate": 4.963932670203245e-05,
290
+ "loss": 2.6499,
291
+ "step": 23000
292
+ },
293
+ {
294
+ "epoch": 0.17,
295
+ "learning_rate": 4.962315950699822e-05,
296
+ "loss": 2.6391,
297
+ "step": 23500
298
+ },
299
+ {
300
+ "epoch": 0.17,
301
+ "learning_rate": 4.960664061449643e-05,
302
+ "loss": 2.6313,
303
+ "step": 24000
304
+ },
305
+ {
306
+ "epoch": 0.18,
307
+ "learning_rate": 4.958977026046971e-05,
308
+ "loss": 2.6318,
309
+ "step": 24500
310
+ },
311
+ {
312
+ "epoch": 0.18,
313
+ "learning_rate": 4.957254868588065e-05,
314
+ "loss": 2.6275,
315
+ "step": 25000
316
+ },
317
+ {
318
+ "epoch": 0.18,
319
+ "learning_rate": 4.955497613670842e-05,
320
+ "loss": 2.6192,
321
+ "step": 25500
322
+ },
323
+ {
324
+ "epoch": 0.19,
325
+ "learning_rate": 4.953705286394522e-05,
326
+ "loss": 2.6153,
327
+ "step": 26000
328
+ },
329
+ {
330
+ "epoch": 0.19,
331
+ "learning_rate": 4.9518779123592705e-05,
332
+ "loss": 2.6102,
333
+ "step": 26500
334
+ },
335
+ {
336
+ "epoch": 0.19,
337
+ "learning_rate": 4.9500155176658345e-05,
338
+ "loss": 2.601,
339
+ "step": 27000
340
+ }
341
+ ],
342
+ "logging_steps": 500,
343
+ "max_steps": 416130,
344
+ "num_input_tokens_seen": 0,
345
+ "num_train_epochs": 3,
346
+ "save_steps": 3000,
347
+ "total_flos": 9.888432390144e+18,
348
+ "train_batch_size": 16,
349
+ "trial_name": null,
350
+ "trial_params": null
351
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9d0d01338b60b1be222619b79ea3b0ae2fdbdadaf777c837223a484daa9c2b4
3
+ size 4728