Azamorn commited on
Commit
04af1da
1 Parent(s): e81ff75

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_fn": "swish",
4
+ "architectures": [
5
+ "RetNetForCausalLM"
6
+ ],
7
+ "decoder_embed_dim": 1280,
8
+ "decoder_ffn_embed_dim": 2560,
9
+ "decoder_layers": 12,
10
+ "decoder_normalize_before": true,
11
+ "decoder_retention_heads": 8,
12
+ "decoder_value_embed_dim": 2560,
13
+ "deepnorm": false,
14
+ "drop_path_rate": 0.0,
15
+ "dropout": 0.0,
16
+ "eos_token_id": 50256,
17
+ "forward_impl": "parallel",
18
+ "initializer_range": 0.02,
19
+ "is_decoder": true,
20
+ "layernorm_embedding": true,
21
+ "layernorm_eps": 1e-06,
22
+ "model_type": "retnet",
23
+ "no_scale_embedding": false,
24
+ "output_retentions": false,
25
+ "pad_token_id": 50256,
26
+ "recurrent_chunk_size": 512,
27
+ "subln": true,
28
+ "tie_word_embeddings": false,
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.36.2",
31
+ "unk_token_id": 50256,
32
+ "use_cache": true,
33
+ "use_ffn_rms_norm": false,
34
+ "use_glu": true,
35
+ "use_lm_decay": false,
36
+ "vocab_size": 50257,
37
+ "z_loss_coeff": 0.0
38
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": 50256,
4
+ "pad_token_id": 50256,
5
+ "transformers_version": "4.36.2"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c158b28744f13168b014d5cf922deca9738e6809ab54db7e8affc8232fcb3974
3
+ size 1615784368
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9332add6073f65b7e3a08cc193bb303da7205dba8c332784ee758e46bc804da6
3
+ size 3231643962
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 sha256:45925f2efb7989009db479896dcd4dc450d8b946cbe8f7080ca846dee0a898df
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": true,
15
+ "eos_token": "<|endoftext|>",
16
+ "model_max_length": 16384,
17
+ "pad_token": "<|endoftext|>",
18
+ "tokenizer_class": "GPT2Tokenizer",
19
+ "unk_token": "<|endoftext|>"
20
+ }
trainer_state.json ADDED
@@ -0,0 +1,1221 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.2,
5
+ "eval_steps": 500,
6
+ "global_step": 1000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "learning_rate": 0.0004993997599039616,
14
+ "loss": 9.442,
15
+ "step": 5
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 0.0004987995198079231,
20
+ "loss": 6.4069,
21
+ "step": 10
22
+ },
23
+ {
24
+ "epoch": 0.02,
25
+ "learning_rate": 0.0004981992797118848,
26
+ "loss": 5.2241,
27
+ "step": 15
28
+ },
29
+ {
30
+ "epoch": 0.02,
31
+ "learning_rate": 0.0004975990396158463,
32
+ "loss": 4.6629,
33
+ "step": 20
34
+ },
35
+ {
36
+ "epoch": 0.03,
37
+ "learning_rate": 0.0004969987995198079,
38
+ "loss": 4.4599,
39
+ "step": 25
40
+ },
41
+ {
42
+ "epoch": 0.04,
43
+ "learning_rate": 0.0004963985594237695,
44
+ "loss": 4.4699,
45
+ "step": 30
46
+ },
47
+ {
48
+ "epoch": 0.04,
49
+ "learning_rate": 0.0004957983193277311,
50
+ "loss": 4.328,
51
+ "step": 35
52
+ },
53
+ {
54
+ "epoch": 0.05,
55
+ "learning_rate": 0.0004951980792316927,
56
+ "loss": 4.2845,
57
+ "step": 40
58
+ },
59
+ {
60
+ "epoch": 0.05,
61
+ "learning_rate": 0.0004945978391356542,
62
+ "loss": 4.2205,
63
+ "step": 45
64
+ },
65
+ {
66
+ "epoch": 0.06,
67
+ "learning_rate": 0.0004939975990396158,
68
+ "loss": 4.1616,
69
+ "step": 50
70
+ },
71
+ {
72
+ "epoch": 0.07,
73
+ "learning_rate": 0.0004933973589435775,
74
+ "loss": 4.1001,
75
+ "step": 55
76
+ },
77
+ {
78
+ "epoch": 0.07,
79
+ "learning_rate": 0.000492797118847539,
80
+ "loss": 4.051,
81
+ "step": 60
82
+ },
83
+ {
84
+ "epoch": 0.08,
85
+ "learning_rate": 0.0004921968787515006,
86
+ "loss": 3.9317,
87
+ "step": 65
88
+ },
89
+ {
90
+ "epoch": 0.08,
91
+ "learning_rate": 0.0004915966386554621,
92
+ "loss": 3.9395,
93
+ "step": 70
94
+ },
95
+ {
96
+ "epoch": 0.09,
97
+ "learning_rate": 0.0004909963985594238,
98
+ "loss": 3.892,
99
+ "step": 75
100
+ },
101
+ {
102
+ "epoch": 0.1,
103
+ "learning_rate": 0.0004903961584633854,
104
+ "loss": 3.7325,
105
+ "step": 80
106
+ },
107
+ {
108
+ "epoch": 0.1,
109
+ "learning_rate": 0.0004897959183673469,
110
+ "loss": 3.735,
111
+ "step": 85
112
+ },
113
+ {
114
+ "epoch": 0.11,
115
+ "learning_rate": 0.0004891956782713085,
116
+ "loss": 3.6928,
117
+ "step": 90
118
+ },
119
+ {
120
+ "epoch": 0.11,
121
+ "learning_rate": 0.0004885954381752701,
122
+ "loss": 3.7048,
123
+ "step": 95
124
+ },
125
+ {
126
+ "epoch": 0.12,
127
+ "learning_rate": 0.0004879951980792317,
128
+ "loss": 3.5304,
129
+ "step": 100
130
+ },
131
+ {
132
+ "epoch": 0.13,
133
+ "learning_rate": 0.00048739495798319325,
134
+ "loss": 3.565,
135
+ "step": 105
136
+ },
137
+ {
138
+ "epoch": 0.13,
139
+ "learning_rate": 0.00048679471788715486,
140
+ "loss": 3.6801,
141
+ "step": 110
142
+ },
143
+ {
144
+ "epoch": 0.14,
145
+ "learning_rate": 0.00048619447779111647,
146
+ "loss": 3.5079,
147
+ "step": 115
148
+ },
149
+ {
150
+ "epoch": 0.14,
151
+ "learning_rate": 0.00048559423769507803,
152
+ "loss": 3.5053,
153
+ "step": 120
154
+ },
155
+ {
156
+ "epoch": 0.15,
157
+ "learning_rate": 0.00048499399759903964,
158
+ "loss": 3.35,
159
+ "step": 125
160
+ },
161
+ {
162
+ "epoch": 0.16,
163
+ "learning_rate": 0.0004843937575030012,
164
+ "loss": 3.4045,
165
+ "step": 130
166
+ },
167
+ {
168
+ "epoch": 0.16,
169
+ "learning_rate": 0.0004837935174069628,
170
+ "loss": 3.3187,
171
+ "step": 135
172
+ },
173
+ {
174
+ "epoch": 0.17,
175
+ "learning_rate": 0.00048319327731092437,
176
+ "loss": 3.3906,
177
+ "step": 140
178
+ },
179
+ {
180
+ "epoch": 0.17,
181
+ "learning_rate": 0.000482593037214886,
182
+ "loss": 3.3228,
183
+ "step": 145
184
+ },
185
+ {
186
+ "epoch": 0.18,
187
+ "learning_rate": 0.00048199279711884753,
188
+ "loss": 3.297,
189
+ "step": 150
190
+ },
191
+ {
192
+ "epoch": 0.19,
193
+ "learning_rate": 0.00048139255702280915,
194
+ "loss": 3.3078,
195
+ "step": 155
196
+ },
197
+ {
198
+ "epoch": 0.19,
199
+ "learning_rate": 0.0004807923169267707,
200
+ "loss": 3.312,
201
+ "step": 160
202
+ },
203
+ {
204
+ "epoch": 0.2,
205
+ "learning_rate": 0.0004801920768307323,
206
+ "loss": 3.3131,
207
+ "step": 165
208
+ },
209
+ {
210
+ "epoch": 0.2,
211
+ "learning_rate": 0.00047959183673469387,
212
+ "loss": 3.2012,
213
+ "step": 170
214
+ },
215
+ {
216
+ "epoch": 0.21,
217
+ "learning_rate": 0.0004789915966386555,
218
+ "loss": 3.2605,
219
+ "step": 175
220
+ },
221
+ {
222
+ "epoch": 0.22,
223
+ "learning_rate": 0.00047839135654261704,
224
+ "loss": 3.1821,
225
+ "step": 180
226
+ },
227
+ {
228
+ "epoch": 0.22,
229
+ "learning_rate": 0.00047779111644657865,
230
+ "loss": 3.1836,
231
+ "step": 185
232
+ },
233
+ {
234
+ "epoch": 0.23,
235
+ "learning_rate": 0.0004771908763505402,
236
+ "loss": 3.1439,
237
+ "step": 190
238
+ },
239
+ {
240
+ "epoch": 0.23,
241
+ "learning_rate": 0.0004765906362545018,
242
+ "loss": 3.1493,
243
+ "step": 195
244
+ },
245
+ {
246
+ "epoch": 0.24,
247
+ "learning_rate": 0.0004759903961584634,
248
+ "loss": 3.0728,
249
+ "step": 200
250
+ },
251
+ {
252
+ "epoch": 0.25,
253
+ "learning_rate": 0.000475390156062425,
254
+ "loss": 3.1574,
255
+ "step": 205
256
+ },
257
+ {
258
+ "epoch": 0.25,
259
+ "learning_rate": 0.00047478991596638654,
260
+ "loss": 3.1272,
261
+ "step": 210
262
+ },
263
+ {
264
+ "epoch": 0.26,
265
+ "learning_rate": 0.00047418967587034816,
266
+ "loss": 3.0083,
267
+ "step": 215
268
+ },
269
+ {
270
+ "epoch": 0.26,
271
+ "learning_rate": 0.00047358943577430977,
272
+ "loss": 3.0536,
273
+ "step": 220
274
+ },
275
+ {
276
+ "epoch": 0.27,
277
+ "learning_rate": 0.0004729891956782713,
278
+ "loss": 3.0536,
279
+ "step": 225
280
+ },
281
+ {
282
+ "epoch": 0.28,
283
+ "learning_rate": 0.0004723889555822329,
284
+ "loss": 3.0091,
285
+ "step": 230
286
+ },
287
+ {
288
+ "epoch": 0.28,
289
+ "learning_rate": 0.0004717887154861945,
290
+ "loss": 3.0709,
291
+ "step": 235
292
+ },
293
+ {
294
+ "epoch": 0.29,
295
+ "learning_rate": 0.0004711884753901561,
296
+ "loss": 2.9084,
297
+ "step": 240
298
+ },
299
+ {
300
+ "epoch": 0.29,
301
+ "learning_rate": 0.00047058823529411766,
302
+ "loss": 2.9807,
303
+ "step": 245
304
+ },
305
+ {
306
+ "epoch": 0.3,
307
+ "learning_rate": 0.0004699879951980792,
308
+ "loss": 2.9563,
309
+ "step": 250
310
+ },
311
+ {
312
+ "epoch": 0.31,
313
+ "learning_rate": 0.00046938775510204083,
314
+ "loss": 2.9508,
315
+ "step": 255
316
+ },
317
+ {
318
+ "epoch": 0.31,
319
+ "learning_rate": 0.00046878751500600244,
320
+ "loss": 2.9896,
321
+ "step": 260
322
+ },
323
+ {
324
+ "epoch": 0.32,
325
+ "learning_rate": 0.000468187274909964,
326
+ "loss": 2.8946,
327
+ "step": 265
328
+ },
329
+ {
330
+ "epoch": 0.32,
331
+ "learning_rate": 0.00046758703481392555,
332
+ "loss": 2.9081,
333
+ "step": 270
334
+ },
335
+ {
336
+ "epoch": 0.33,
337
+ "learning_rate": 0.00046698679471788716,
338
+ "loss": 2.8824,
339
+ "step": 275
340
+ },
341
+ {
342
+ "epoch": 0.34,
343
+ "learning_rate": 0.0004663865546218488,
344
+ "loss": 2.9004,
345
+ "step": 280
346
+ },
347
+ {
348
+ "epoch": 0.34,
349
+ "learning_rate": 0.00046578631452581033,
350
+ "loss": 2.8155,
351
+ "step": 285
352
+ },
353
+ {
354
+ "epoch": 0.35,
355
+ "learning_rate": 0.0004651860744297719,
356
+ "loss": 2.8921,
357
+ "step": 290
358
+ },
359
+ {
360
+ "epoch": 0.35,
361
+ "learning_rate": 0.0004645858343337335,
362
+ "loss": 2.8942,
363
+ "step": 295
364
+ },
365
+ {
366
+ "epoch": 0.36,
367
+ "learning_rate": 0.0004639855942376951,
368
+ "loss": 2.8331,
369
+ "step": 300
370
+ },
371
+ {
372
+ "epoch": 0.37,
373
+ "learning_rate": 0.00046338535414165667,
374
+ "loss": 2.9032,
375
+ "step": 305
376
+ },
377
+ {
378
+ "epoch": 0.37,
379
+ "learning_rate": 0.0004627851140456182,
380
+ "loss": 2.8443,
381
+ "step": 310
382
+ },
383
+ {
384
+ "epoch": 0.38,
385
+ "learning_rate": 0.00046218487394957984,
386
+ "loss": 2.9231,
387
+ "step": 315
388
+ },
389
+ {
390
+ "epoch": 0.38,
391
+ "learning_rate": 0.00046158463385354145,
392
+ "loss": 2.8204,
393
+ "step": 320
394
+ },
395
+ {
396
+ "epoch": 0.39,
397
+ "learning_rate": 0.000460984393757503,
398
+ "loss": 2.8024,
399
+ "step": 325
400
+ },
401
+ {
402
+ "epoch": 0.4,
403
+ "learning_rate": 0.00046038415366146456,
404
+ "loss": 2.8511,
405
+ "step": 330
406
+ },
407
+ {
408
+ "epoch": 0.4,
409
+ "learning_rate": 0.00045978391356542623,
410
+ "loss": 2.7767,
411
+ "step": 335
412
+ },
413
+ {
414
+ "epoch": 0.41,
415
+ "learning_rate": 0.0004591836734693878,
416
+ "loss": 2.7563,
417
+ "step": 340
418
+ },
419
+ {
420
+ "epoch": 0.41,
421
+ "learning_rate": 0.00045858343337334934,
422
+ "loss": 2.8491,
423
+ "step": 345
424
+ },
425
+ {
426
+ "epoch": 0.42,
427
+ "learning_rate": 0.0004579831932773109,
428
+ "loss": 2.8621,
429
+ "step": 350
430
+ },
431
+ {
432
+ "epoch": 0.43,
433
+ "learning_rate": 0.00045738295318127257,
434
+ "loss": 2.7985,
435
+ "step": 355
436
+ },
437
+ {
438
+ "epoch": 0.43,
439
+ "learning_rate": 0.0004567827130852341,
440
+ "loss": 2.8162,
441
+ "step": 360
442
+ },
443
+ {
444
+ "epoch": 0.44,
445
+ "learning_rate": 0.0004561824729891957,
446
+ "loss": 2.7087,
447
+ "step": 365
448
+ },
449
+ {
450
+ "epoch": 0.44,
451
+ "learning_rate": 0.00045558223289315724,
452
+ "loss": 2.7947,
453
+ "step": 370
454
+ },
455
+ {
456
+ "epoch": 0.45,
457
+ "learning_rate": 0.0004549819927971189,
458
+ "loss": 2.7413,
459
+ "step": 375
460
+ },
461
+ {
462
+ "epoch": 0.46,
463
+ "learning_rate": 0.00045438175270108046,
464
+ "loss": 2.7319,
465
+ "step": 380
466
+ },
467
+ {
468
+ "epoch": 0.46,
469
+ "learning_rate": 0.000453781512605042,
470
+ "loss": 2.8137,
471
+ "step": 385
472
+ },
473
+ {
474
+ "epoch": 0.47,
475
+ "learning_rate": 0.00045318127250900357,
476
+ "loss": 2.7292,
477
+ "step": 390
478
+ },
479
+ {
480
+ "epoch": 0.47,
481
+ "learning_rate": 0.00045258103241296524,
482
+ "loss": 2.8123,
483
+ "step": 395
484
+ },
485
+ {
486
+ "epoch": 0.48,
487
+ "learning_rate": 0.0004519807923169268,
488
+ "loss": 2.7721,
489
+ "step": 400
490
+ },
491
+ {
492
+ "epoch": 0.49,
493
+ "learning_rate": 0.00045138055222088835,
494
+ "loss": 2.7073,
495
+ "step": 405
496
+ },
497
+ {
498
+ "epoch": 0.49,
499
+ "learning_rate": 0.0004507803121248499,
500
+ "loss": 2.6707,
501
+ "step": 410
502
+ },
503
+ {
504
+ "epoch": 0.5,
505
+ "learning_rate": 0.0004501800720288116,
506
+ "loss": 2.6422,
507
+ "step": 415
508
+ },
509
+ {
510
+ "epoch": 0.5,
511
+ "learning_rate": 0.00044957983193277313,
512
+ "loss": 2.7066,
513
+ "step": 420
514
+ },
515
+ {
516
+ "epoch": 0.51,
517
+ "learning_rate": 0.0004489795918367347,
518
+ "loss": 2.6398,
519
+ "step": 425
520
+ },
521
+ {
522
+ "epoch": 0.52,
523
+ "learning_rate": 0.0004483793517406963,
524
+ "loss": 2.7323,
525
+ "step": 430
526
+ },
527
+ {
528
+ "epoch": 0.52,
529
+ "learning_rate": 0.0004477791116446579,
530
+ "loss": 2.695,
531
+ "step": 435
532
+ },
533
+ {
534
+ "epoch": 0.53,
535
+ "learning_rate": 0.00044717887154861947,
536
+ "loss": 2.6634,
537
+ "step": 440
538
+ },
539
+ {
540
+ "epoch": 0.53,
541
+ "learning_rate": 0.000446578631452581,
542
+ "loss": 2.6284,
543
+ "step": 445
544
+ },
545
+ {
546
+ "epoch": 0.54,
547
+ "learning_rate": 0.00044597839135654264,
548
+ "loss": 2.7046,
549
+ "step": 450
550
+ },
551
+ {
552
+ "epoch": 0.55,
553
+ "learning_rate": 0.00044537815126050425,
554
+ "loss": 2.7038,
555
+ "step": 455
556
+ },
557
+ {
558
+ "epoch": 0.55,
559
+ "learning_rate": 0.0004447779111644658,
560
+ "loss": 2.6489,
561
+ "step": 460
562
+ },
563
+ {
564
+ "epoch": 0.56,
565
+ "learning_rate": 0.00044417767106842736,
566
+ "loss": 2.6162,
567
+ "step": 465
568
+ },
569
+ {
570
+ "epoch": 0.56,
571
+ "learning_rate": 0.000443577430972389,
572
+ "loss": 2.6625,
573
+ "step": 470
574
+ },
575
+ {
576
+ "epoch": 0.57,
577
+ "learning_rate": 0.00044297719087635053,
578
+ "loss": 2.6046,
579
+ "step": 475
580
+ },
581
+ {
582
+ "epoch": 0.58,
583
+ "learning_rate": 0.00044237695078031214,
584
+ "loss": 2.6556,
585
+ "step": 480
586
+ },
587
+ {
588
+ "epoch": 0.58,
589
+ "learning_rate": 0.0004417767106842737,
590
+ "loss": 2.5762,
591
+ "step": 485
592
+ },
593
+ {
594
+ "epoch": 0.59,
595
+ "learning_rate": 0.0004411764705882353,
596
+ "loss": 2.6441,
597
+ "step": 490
598
+ },
599
+ {
600
+ "epoch": 0.59,
601
+ "learning_rate": 0.00044057623049219687,
602
+ "loss": 2.6731,
603
+ "step": 495
604
+ },
605
+ {
606
+ "epoch": 0.6,
607
+ "learning_rate": 0.0004399759903961585,
608
+ "loss": 2.5839,
609
+ "step": 500
610
+ },
611
+ {
612
+ "epoch": 0.61,
613
+ "learning_rate": 0.00043937575030012003,
614
+ "loss": 2.5429,
615
+ "step": 505
616
+ },
617
+ {
618
+ "epoch": 0.61,
619
+ "learning_rate": 0.00043877551020408165,
620
+ "loss": 2.5735,
621
+ "step": 510
622
+ },
623
+ {
624
+ "epoch": 0.62,
625
+ "learning_rate": 0.0004381752701080432,
626
+ "loss": 2.561,
627
+ "step": 515
628
+ },
629
+ {
630
+ "epoch": 0.62,
631
+ "learning_rate": 0.0004375750300120048,
632
+ "loss": 2.5553,
633
+ "step": 520
634
+ },
635
+ {
636
+ "epoch": 0.63,
637
+ "learning_rate": 0.00043697478991596637,
638
+ "loss": 2.5196,
639
+ "step": 525
640
+ },
641
+ {
642
+ "epoch": 0.64,
643
+ "learning_rate": 0.000436374549819928,
644
+ "loss": 2.5371,
645
+ "step": 530
646
+ },
647
+ {
648
+ "epoch": 0.64,
649
+ "learning_rate": 0.00043577430972388954,
650
+ "loss": 2.4678,
651
+ "step": 535
652
+ },
653
+ {
654
+ "epoch": 0.65,
655
+ "learning_rate": 0.00043517406962785115,
656
+ "loss": 2.5223,
657
+ "step": 540
658
+ },
659
+ {
660
+ "epoch": 0.65,
661
+ "learning_rate": 0.00043457382953181276,
662
+ "loss": 2.5111,
663
+ "step": 545
664
+ },
665
+ {
666
+ "epoch": 0.66,
667
+ "learning_rate": 0.0004339735894357743,
668
+ "loss": 2.5562,
669
+ "step": 550
670
+ },
671
+ {
672
+ "epoch": 0.67,
673
+ "learning_rate": 0.0004333733493397359,
674
+ "loss": 2.5992,
675
+ "step": 555
676
+ },
677
+ {
678
+ "epoch": 0.67,
679
+ "learning_rate": 0.0004327731092436975,
680
+ "loss": 2.5308,
681
+ "step": 560
682
+ },
683
+ {
684
+ "epoch": 0.68,
685
+ "learning_rate": 0.0004321728691476591,
686
+ "loss": 2.5141,
687
+ "step": 565
688
+ },
689
+ {
690
+ "epoch": 0.68,
691
+ "learning_rate": 0.00043157262905162066,
692
+ "loss": 2.5755,
693
+ "step": 570
694
+ },
695
+ {
696
+ "epoch": 0.69,
697
+ "learning_rate": 0.0004309723889555822,
698
+ "loss": 2.5723,
699
+ "step": 575
700
+ },
701
+ {
702
+ "epoch": 0.7,
703
+ "learning_rate": 0.0004303721488595438,
704
+ "loss": 2.4098,
705
+ "step": 580
706
+ },
707
+ {
708
+ "epoch": 0.7,
709
+ "learning_rate": 0.00042977190876350544,
710
+ "loss": 2.5296,
711
+ "step": 585
712
+ },
713
+ {
714
+ "epoch": 0.71,
715
+ "learning_rate": 0.000429171668667467,
716
+ "loss": 2.547,
717
+ "step": 590
718
+ },
719
+ {
720
+ "epoch": 0.71,
721
+ "learning_rate": 0.00042857142857142855,
722
+ "loss": 2.4059,
723
+ "step": 595
724
+ },
725
+ {
726
+ "epoch": 0.72,
727
+ "learning_rate": 0.00042797118847539016,
728
+ "loss": 2.4101,
729
+ "step": 600
730
+ },
731
+ {
732
+ "epoch": 0.73,
733
+ "learning_rate": 0.00042737094837935177,
734
+ "loss": 2.5301,
735
+ "step": 605
736
+ },
737
+ {
738
+ "epoch": 0.73,
739
+ "learning_rate": 0.00042677070828331333,
740
+ "loss": 2.4837,
741
+ "step": 610
742
+ },
743
+ {
744
+ "epoch": 0.74,
745
+ "learning_rate": 0.0004261704681872749,
746
+ "loss": 2.5095,
747
+ "step": 615
748
+ },
749
+ {
750
+ "epoch": 0.74,
751
+ "learning_rate": 0.0004255702280912365,
752
+ "loss": 2.4423,
753
+ "step": 620
754
+ },
755
+ {
756
+ "epoch": 0.75,
757
+ "learning_rate": 0.0004249699879951981,
758
+ "loss": 2.4299,
759
+ "step": 625
760
+ },
761
+ {
762
+ "epoch": 0.76,
763
+ "learning_rate": 0.00042436974789915967,
764
+ "loss": 2.487,
765
+ "step": 630
766
+ },
767
+ {
768
+ "epoch": 0.76,
769
+ "learning_rate": 0.0004237695078031212,
770
+ "loss": 2.4534,
771
+ "step": 635
772
+ },
773
+ {
774
+ "epoch": 0.77,
775
+ "learning_rate": 0.0004231692677070829,
776
+ "loss": 2.4706,
777
+ "step": 640
778
+ },
779
+ {
780
+ "epoch": 0.77,
781
+ "learning_rate": 0.00042256902761104444,
782
+ "loss": 2.4558,
783
+ "step": 645
784
+ },
785
+ {
786
+ "epoch": 0.78,
787
+ "learning_rate": 0.000421968787515006,
788
+ "loss": 2.4226,
789
+ "step": 650
790
+ },
791
+ {
792
+ "epoch": 0.79,
793
+ "learning_rate": 0.00042136854741896756,
794
+ "loss": 2.4443,
795
+ "step": 655
796
+ },
797
+ {
798
+ "epoch": 0.79,
799
+ "learning_rate": 0.0004207683073229292,
800
+ "loss": 2.4487,
801
+ "step": 660
802
+ },
803
+ {
804
+ "epoch": 0.8,
805
+ "learning_rate": 0.0004201680672268908,
806
+ "loss": 2.4283,
807
+ "step": 665
808
+ },
809
+ {
810
+ "epoch": 0.8,
811
+ "learning_rate": 0.00041956782713085234,
812
+ "loss": 2.4918,
813
+ "step": 670
814
+ },
815
+ {
816
+ "epoch": 0.81,
817
+ "learning_rate": 0.0004189675870348139,
818
+ "loss": 2.4895,
819
+ "step": 675
820
+ },
821
+ {
822
+ "epoch": 0.82,
823
+ "learning_rate": 0.00041836734693877556,
824
+ "loss": 2.4296,
825
+ "step": 680
826
+ },
827
+ {
828
+ "epoch": 0.82,
829
+ "learning_rate": 0.0004177671068427371,
830
+ "loss": 2.4259,
831
+ "step": 685
832
+ },
833
+ {
834
+ "epoch": 0.83,
835
+ "learning_rate": 0.0004171668667466987,
836
+ "loss": 2.4956,
837
+ "step": 690
838
+ },
839
+ {
840
+ "epoch": 0.83,
841
+ "learning_rate": 0.00041656662665066023,
842
+ "loss": 2.4708,
843
+ "step": 695
844
+ },
845
+ {
846
+ "epoch": 0.84,
847
+ "learning_rate": 0.0004159663865546219,
848
+ "loss": 2.4078,
849
+ "step": 700
850
+ },
851
+ {
852
+ "epoch": 0.85,
853
+ "learning_rate": 0.00041536614645858345,
854
+ "loss": 2.4024,
855
+ "step": 705
856
+ },
857
+ {
858
+ "epoch": 0.85,
859
+ "learning_rate": 0.000414765906362545,
860
+ "loss": 2.3847,
861
+ "step": 710
862
+ },
863
+ {
864
+ "epoch": 0.86,
865
+ "learning_rate": 0.00041416566626650657,
866
+ "loss": 2.361,
867
+ "step": 715
868
+ },
869
+ {
870
+ "epoch": 0.86,
871
+ "learning_rate": 0.00041356542617046823,
872
+ "loss": 2.4494,
873
+ "step": 720
874
+ },
875
+ {
876
+ "epoch": 0.87,
877
+ "learning_rate": 0.0004129651860744298,
878
+ "loss": 2.4495,
879
+ "step": 725
880
+ },
881
+ {
882
+ "epoch": 0.88,
883
+ "learning_rate": 0.00041236494597839135,
884
+ "loss": 2.431,
885
+ "step": 730
886
+ },
887
+ {
888
+ "epoch": 0.88,
889
+ "learning_rate": 0.0004117647058823529,
890
+ "loss": 2.4143,
891
+ "step": 735
892
+ },
893
+ {
894
+ "epoch": 0.89,
895
+ "learning_rate": 0.00041116446578631457,
896
+ "loss": 2.3522,
897
+ "step": 740
898
+ },
899
+ {
900
+ "epoch": 0.89,
901
+ "learning_rate": 0.00041056422569027613,
902
+ "loss": 2.4095,
903
+ "step": 745
904
+ },
905
+ {
906
+ "epoch": 0.9,
907
+ "learning_rate": 0.0004099639855942377,
908
+ "loss": 2.3399,
909
+ "step": 750
910
+ },
911
+ {
912
+ "epoch": 0.91,
913
+ "learning_rate": 0.0004093637454981993,
914
+ "loss": 2.3234,
915
+ "step": 755
916
+ },
917
+ {
918
+ "epoch": 0.91,
919
+ "learning_rate": 0.0004087635054021609,
920
+ "loss": 2.3904,
921
+ "step": 760
922
+ },
923
+ {
924
+ "epoch": 0.92,
925
+ "learning_rate": 0.00040816326530612246,
926
+ "loss": 2.3691,
927
+ "step": 765
928
+ },
929
+ {
930
+ "epoch": 0.92,
931
+ "learning_rate": 0.000407563025210084,
932
+ "loss": 2.3312,
933
+ "step": 770
934
+ },
935
+ {
936
+ "epoch": 0.93,
937
+ "learning_rate": 0.00040696278511404563,
938
+ "loss": 2.3323,
939
+ "step": 775
940
+ },
941
+ {
942
+ "epoch": 0.94,
943
+ "learning_rate": 0.00040636254501800724,
944
+ "loss": 2.3701,
945
+ "step": 780
946
+ },
947
+ {
948
+ "epoch": 0.94,
949
+ "learning_rate": 0.0004057623049219688,
950
+ "loss": 2.433,
951
+ "step": 785
952
+ },
953
+ {
954
+ "epoch": 0.95,
955
+ "learning_rate": 0.00040516206482593036,
956
+ "loss": 2.3172,
957
+ "step": 790
958
+ },
959
+ {
960
+ "epoch": 0.95,
961
+ "learning_rate": 0.00040456182472989197,
962
+ "loss": 2.3529,
963
+ "step": 795
964
+ },
965
+ {
966
+ "epoch": 0.96,
967
+ "learning_rate": 0.0004039615846338536,
968
+ "loss": 2.4238,
969
+ "step": 800
970
+ },
971
+ {
972
+ "epoch": 0.97,
973
+ "learning_rate": 0.00040336134453781514,
974
+ "loss": 2.3834,
975
+ "step": 805
976
+ },
977
+ {
978
+ "epoch": 0.97,
979
+ "learning_rate": 0.0004027611044417767,
980
+ "loss": 2.2364,
981
+ "step": 810
982
+ },
983
+ {
984
+ "epoch": 0.98,
985
+ "learning_rate": 0.0004021608643457383,
986
+ "loss": 2.3618,
987
+ "step": 815
988
+ },
989
+ {
990
+ "epoch": 0.98,
991
+ "learning_rate": 0.0004015606242496999,
992
+ "loss": 2.3188,
993
+ "step": 820
994
+ },
995
+ {
996
+ "epoch": 0.99,
997
+ "learning_rate": 0.0004009603841536615,
998
+ "loss": 2.3659,
999
+ "step": 825
1000
+ },
1001
+ {
1002
+ "epoch": 1.0,
1003
+ "learning_rate": 0.00040036014405762303,
1004
+ "loss": 2.3043,
1005
+ "step": 830
1006
+ },
1007
+ {
1008
+ "epoch": 1.0,
1009
+ "learning_rate": 0.00039975990396158464,
1010
+ "loss": 2.299,
1011
+ "step": 835
1012
+ },
1013
+ {
1014
+ "epoch": 1.01,
1015
+ "learning_rate": 0.00039915966386554625,
1016
+ "loss": 2.1782,
1017
+ "step": 840
1018
+ },
1019
+ {
1020
+ "epoch": 1.01,
1021
+ "learning_rate": 0.0003985594237695078,
1022
+ "loss": 2.1026,
1023
+ "step": 845
1024
+ },
1025
+ {
1026
+ "epoch": 1.02,
1027
+ "learning_rate": 0.00039795918367346937,
1028
+ "loss": 2.1629,
1029
+ "step": 850
1030
+ },
1031
+ {
1032
+ "epoch": 1.03,
1033
+ "learning_rate": 0.000397358943577431,
1034
+ "loss": 2.1208,
1035
+ "step": 855
1036
+ },
1037
+ {
1038
+ "epoch": 1.03,
1039
+ "learning_rate": 0.0003967587034813926,
1040
+ "loss": 2.0706,
1041
+ "step": 860
1042
+ },
1043
+ {
1044
+ "epoch": 1.04,
1045
+ "learning_rate": 0.00039615846338535415,
1046
+ "loss": 2.0824,
1047
+ "step": 865
1048
+ },
1049
+ {
1050
+ "epoch": 1.04,
1051
+ "learning_rate": 0.00039555822328931576,
1052
+ "loss": 2.1032,
1053
+ "step": 870
1054
+ },
1055
+ {
1056
+ "epoch": 1.05,
1057
+ "learning_rate": 0.0003949579831932773,
1058
+ "loss": 2.1157,
1059
+ "step": 875
1060
+ },
1061
+ {
1062
+ "epoch": 1.06,
1063
+ "learning_rate": 0.0003943577430972389,
1064
+ "loss": 2.072,
1065
+ "step": 880
1066
+ },
1067
+ {
1068
+ "epoch": 1.06,
1069
+ "learning_rate": 0.0003937575030012005,
1070
+ "loss": 2.1275,
1071
+ "step": 885
1072
+ },
1073
+ {
1074
+ "epoch": 1.07,
1075
+ "learning_rate": 0.0003931572629051621,
1076
+ "loss": 2.0514,
1077
+ "step": 890
1078
+ },
1079
+ {
1080
+ "epoch": 1.07,
1081
+ "learning_rate": 0.00039255702280912365,
1082
+ "loss": 2.0643,
1083
+ "step": 895
1084
+ },
1085
+ {
1086
+ "epoch": 1.08,
1087
+ "learning_rate": 0.00039195678271308526,
1088
+ "loss": 2.1485,
1089
+ "step": 900
1090
+ },
1091
+ {
1092
+ "epoch": 1.09,
1093
+ "learning_rate": 0.0003913565426170468,
1094
+ "loss": 2.0773,
1095
+ "step": 905
1096
+ },
1097
+ {
1098
+ "epoch": 1.09,
1099
+ "learning_rate": 0.00039075630252100843,
1100
+ "loss": 2.0944,
1101
+ "step": 910
1102
+ },
1103
+ {
1104
+ "epoch": 1.1,
1105
+ "learning_rate": 0.00039015606242497,
1106
+ "loss": 2.1342,
1107
+ "step": 915
1108
+ },
1109
+ {
1110
+ "epoch": 1.1,
1111
+ "learning_rate": 0.0003895558223289316,
1112
+ "loss": 2.0535,
1113
+ "step": 920
1114
+ },
1115
+ {
1116
+ "epoch": 1.11,
1117
+ "learning_rate": 0.00038895558223289316,
1118
+ "loss": 2.0487,
1119
+ "step": 925
1120
+ },
1121
+ {
1122
+ "epoch": 1.12,
1123
+ "learning_rate": 0.00038835534213685477,
1124
+ "loss": 2.0567,
1125
+ "step": 930
1126
+ },
1127
+ {
1128
+ "epoch": 1.12,
1129
+ "learning_rate": 0.0003877551020408163,
1130
+ "loss": 2.0674,
1131
+ "step": 935
1132
+ },
1133
+ {
1134
+ "epoch": 1.13,
1135
+ "learning_rate": 0.0003871548619447779,
1136
+ "loss": 2.103,
1137
+ "step": 940
1138
+ },
1139
+ {
1140
+ "epoch": 1.13,
1141
+ "learning_rate": 0.0003865546218487395,
1142
+ "loss": 2.0839,
1143
+ "step": 945
1144
+ },
1145
+ {
1146
+ "epoch": 1.14,
1147
+ "learning_rate": 0.0003859543817527011,
1148
+ "loss": 2.1078,
1149
+ "step": 950
1150
+ },
1151
+ {
1152
+ "epoch": 1.15,
1153
+ "learning_rate": 0.00038535414165666266,
1154
+ "loss": 2.1217,
1155
+ "step": 955
1156
+ },
1157
+ {
1158
+ "epoch": 1.15,
1159
+ "learning_rate": 0.0003847539015606242,
1160
+ "loss": 2.1457,
1161
+ "step": 960
1162
+ },
1163
+ {
1164
+ "epoch": 1.16,
1165
+ "learning_rate": 0.0003841536614645859,
1166
+ "loss": 2.0889,
1167
+ "step": 965
1168
+ },
1169
+ {
1170
+ "epoch": 1.16,
1171
+ "learning_rate": 0.00038355342136854744,
1172
+ "loss": 2.0706,
1173
+ "step": 970
1174
+ },
1175
+ {
1176
+ "epoch": 1.17,
1177
+ "learning_rate": 0.000382953181272509,
1178
+ "loss": 2.1443,
1179
+ "step": 975
1180
+ },
1181
+ {
1182
+ "epoch": 1.18,
1183
+ "learning_rate": 0.00038235294117647055,
1184
+ "loss": 2.1191,
1185
+ "step": 980
1186
+ },
1187
+ {
1188
+ "epoch": 1.18,
1189
+ "learning_rate": 0.0003817527010804322,
1190
+ "loss": 2.0608,
1191
+ "step": 985
1192
+ },
1193
+ {
1194
+ "epoch": 1.19,
1195
+ "learning_rate": 0.0003811524609843938,
1196
+ "loss": 2.0786,
1197
+ "step": 990
1198
+ },
1199
+ {
1200
+ "epoch": 1.19,
1201
+ "learning_rate": 0.00038055222088835533,
1202
+ "loss": 2.1455,
1203
+ "step": 995
1204
+ },
1205
+ {
1206
+ "epoch": 1.2,
1207
+ "learning_rate": 0.0003799519807923169,
1208
+ "loss": 1.9875,
1209
+ "step": 1000
1210
+ }
1211
+ ],
1212
+ "logging_steps": 5,
1213
+ "max_steps": 4165,
1214
+ "num_input_tokens_seen": 0,
1215
+ "num_train_epochs": 5,
1216
+ "save_steps": 500,
1217
+ "total_flos": 1.974401690333184e+16,
1218
+ "train_batch_size": 8,
1219
+ "trial_name": null,
1220
+ "trial_params": null
1221
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d6deb1eafa027b91462fa7419537cd914f3ff433e6b11d5c2fb7dd39a0cf167
3
+ size 4728
vocab.json ADDED
The diff for this file is too large to render. See raw diff