cc8055 commited on
Commit
e3c0feb
1 Parent(s): 322079a

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+ ### Framework versions
7
+
8
+
9
+ - PEFT 0.4.0
adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 32,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": [
13
+ "lm_head",
14
+ "embed_tokens"
15
+ ],
16
+ "peft_type": "LORA",
17
+ "r": 16,
18
+ "revision": null,
19
+ "target_modules": [
20
+ "down_proj",
21
+ "v_proj",
22
+ "up_proj",
23
+ "o_proj",
24
+ "k_proj",
25
+ "q_proj",
26
+ "gate_proj"
27
+ ],
28
+ "task_type": "CAUSAL_LM"
29
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c744eafecaaf55147e6628443212e9711adfb14ca2335c0abf08945bdf5e542
3
+ size 574861797
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 2048,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 5632,
13
+ "max_position_embeddings": 2048,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 22,
17
+ "num_key_value_heads": 4,
18
+ "pad_token_id": 0,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 10000.0,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.31.0",
26
+ "use_cache": true,
27
+ "vocab_size": 32000
28
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.31.0"
7
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:558fa852852ca3c3250751f2e007bf8015f51576131a4ad45786bc0b61d2c041
3
+ size 1149761349
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cd5805c7d55c4dcdf3bf2c6d78f62236b12982c2c76a0575d80a1b6b411357f
3
+ size 2200174918
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4de687af4226e77e0ff27366f3e146212de674fcc112a9ea0522214b762a3ce8
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:569564bc75dd59306cdd8f3d6844c442e81406f9ac70e338f477bac99cee6643
3
+ size 627
trainer_state.json ADDED
@@ -0,0 +1,1216 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "global_step": 20000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.01,
12
+ "learning_rate": 0.0002,
13
+ "loss": 1.8051,
14
+ "step": 100
15
+ },
16
+ {
17
+ "epoch": 0.01,
18
+ "learning_rate": 0.0002,
19
+ "loss": 1.7655,
20
+ "step": 200
21
+ },
22
+ {
23
+ "epoch": 0.01,
24
+ "learning_rate": 0.0002,
25
+ "loss": 1.7675,
26
+ "step": 300
27
+ },
28
+ {
29
+ "epoch": 0.02,
30
+ "learning_rate": 0.0002,
31
+ "loss": 1.7158,
32
+ "step": 400
33
+ },
34
+ {
35
+ "epoch": 0.03,
36
+ "learning_rate": 0.0002,
37
+ "loss": 1.7021,
38
+ "step": 500
39
+ },
40
+ {
41
+ "epoch": 0.03,
42
+ "learning_rate": 0.0002,
43
+ "loss": 1.6921,
44
+ "step": 600
45
+ },
46
+ {
47
+ "epoch": 0.04,
48
+ "learning_rate": 0.0002,
49
+ "loss": 1.7088,
50
+ "step": 700
51
+ },
52
+ {
53
+ "epoch": 0.04,
54
+ "learning_rate": 0.0002,
55
+ "loss": 1.6985,
56
+ "step": 800
57
+ },
58
+ {
59
+ "epoch": 0.04,
60
+ "learning_rate": 0.0002,
61
+ "loss": 1.6791,
62
+ "step": 900
63
+ },
64
+ {
65
+ "epoch": 0.05,
66
+ "learning_rate": 0.0002,
67
+ "loss": 1.6797,
68
+ "step": 1000
69
+ },
70
+ {
71
+ "epoch": 0.06,
72
+ "learning_rate": 0.0002,
73
+ "loss": 1.6752,
74
+ "step": 1100
75
+ },
76
+ {
77
+ "epoch": 0.06,
78
+ "learning_rate": 0.0002,
79
+ "loss": 1.6761,
80
+ "step": 1200
81
+ },
82
+ {
83
+ "epoch": 0.07,
84
+ "learning_rate": 0.0002,
85
+ "loss": 1.6278,
86
+ "step": 1300
87
+ },
88
+ {
89
+ "epoch": 0.07,
90
+ "learning_rate": 0.0002,
91
+ "loss": 1.6576,
92
+ "step": 1400
93
+ },
94
+ {
95
+ "epoch": 0.07,
96
+ "learning_rate": 0.0002,
97
+ "loss": 1.6409,
98
+ "step": 1500
99
+ },
100
+ {
101
+ "epoch": 0.08,
102
+ "learning_rate": 0.0002,
103
+ "loss": 1.6454,
104
+ "step": 1600
105
+ },
106
+ {
107
+ "epoch": 0.09,
108
+ "learning_rate": 0.0002,
109
+ "loss": 1.5936,
110
+ "step": 1700
111
+ },
112
+ {
113
+ "epoch": 0.09,
114
+ "learning_rate": 0.0002,
115
+ "loss": 1.621,
116
+ "step": 1800
117
+ },
118
+ {
119
+ "epoch": 0.1,
120
+ "learning_rate": 0.0002,
121
+ "loss": 1.6192,
122
+ "step": 1900
123
+ },
124
+ {
125
+ "epoch": 0.1,
126
+ "learning_rate": 0.0002,
127
+ "loss": 1.5758,
128
+ "step": 2000
129
+ },
130
+ {
131
+ "epoch": 0.1,
132
+ "learning_rate": 0.0002,
133
+ "loss": 1.6007,
134
+ "step": 2100
135
+ },
136
+ {
137
+ "epoch": 0.11,
138
+ "learning_rate": 0.0002,
139
+ "loss": 1.5688,
140
+ "step": 2200
141
+ },
142
+ {
143
+ "epoch": 0.12,
144
+ "learning_rate": 0.0002,
145
+ "loss": 1.5973,
146
+ "step": 2300
147
+ },
148
+ {
149
+ "epoch": 0.12,
150
+ "learning_rate": 0.0002,
151
+ "loss": 1.5517,
152
+ "step": 2400
153
+ },
154
+ {
155
+ "epoch": 0.12,
156
+ "learning_rate": 0.0002,
157
+ "loss": 1.5694,
158
+ "step": 2500
159
+ },
160
+ {
161
+ "epoch": 0.13,
162
+ "learning_rate": 0.0002,
163
+ "loss": 1.5177,
164
+ "step": 2600
165
+ },
166
+ {
167
+ "epoch": 0.14,
168
+ "learning_rate": 0.0002,
169
+ "loss": 1.5637,
170
+ "step": 2700
171
+ },
172
+ {
173
+ "epoch": 0.14,
174
+ "learning_rate": 0.0002,
175
+ "loss": 1.5593,
176
+ "step": 2800
177
+ },
178
+ {
179
+ "epoch": 0.14,
180
+ "learning_rate": 0.0002,
181
+ "loss": 1.5087,
182
+ "step": 2900
183
+ },
184
+ {
185
+ "epoch": 0.15,
186
+ "learning_rate": 0.0002,
187
+ "loss": 1.5299,
188
+ "step": 3000
189
+ },
190
+ {
191
+ "epoch": 0.15,
192
+ "learning_rate": 0.0002,
193
+ "loss": 1.5264,
194
+ "step": 3100
195
+ },
196
+ {
197
+ "epoch": 0.16,
198
+ "learning_rate": 0.0002,
199
+ "loss": 1.5103,
200
+ "step": 3200
201
+ },
202
+ {
203
+ "epoch": 0.17,
204
+ "learning_rate": 0.0002,
205
+ "loss": 1.5064,
206
+ "step": 3300
207
+ },
208
+ {
209
+ "epoch": 0.17,
210
+ "learning_rate": 0.0002,
211
+ "loss": 1.5014,
212
+ "step": 3400
213
+ },
214
+ {
215
+ "epoch": 0.17,
216
+ "learning_rate": 0.0002,
217
+ "loss": 1.5104,
218
+ "step": 3500
219
+ },
220
+ {
221
+ "epoch": 0.18,
222
+ "learning_rate": 0.0002,
223
+ "loss": 1.4832,
224
+ "step": 3600
225
+ },
226
+ {
227
+ "epoch": 0.18,
228
+ "learning_rate": 0.0002,
229
+ "loss": 1.5121,
230
+ "step": 3700
231
+ },
232
+ {
233
+ "epoch": 0.19,
234
+ "learning_rate": 0.0002,
235
+ "loss": 1.4547,
236
+ "step": 3800
237
+ },
238
+ {
239
+ "epoch": 0.2,
240
+ "learning_rate": 0.0002,
241
+ "loss": 1.4498,
242
+ "step": 3900
243
+ },
244
+ {
245
+ "epoch": 0.2,
246
+ "learning_rate": 0.0002,
247
+ "loss": 1.4706,
248
+ "step": 4000
249
+ },
250
+ {
251
+ "epoch": 0.2,
252
+ "learning_rate": 0.0002,
253
+ "loss": 1.4534,
254
+ "step": 4100
255
+ },
256
+ {
257
+ "epoch": 0.21,
258
+ "learning_rate": 0.0002,
259
+ "loss": 1.4664,
260
+ "step": 4200
261
+ },
262
+ {
263
+ "epoch": 0.21,
264
+ "learning_rate": 0.0002,
265
+ "loss": 1.4408,
266
+ "step": 4300
267
+ },
268
+ {
269
+ "epoch": 0.22,
270
+ "learning_rate": 0.0002,
271
+ "loss": 1.4809,
272
+ "step": 4400
273
+ },
274
+ {
275
+ "epoch": 0.23,
276
+ "learning_rate": 0.0002,
277
+ "loss": 1.4656,
278
+ "step": 4500
279
+ },
280
+ {
281
+ "epoch": 0.23,
282
+ "learning_rate": 0.0002,
283
+ "loss": 1.4435,
284
+ "step": 4600
285
+ },
286
+ {
287
+ "epoch": 0.23,
288
+ "learning_rate": 0.0002,
289
+ "loss": 1.4093,
290
+ "step": 4700
291
+ },
292
+ {
293
+ "epoch": 0.24,
294
+ "learning_rate": 0.0002,
295
+ "loss": 1.4241,
296
+ "step": 4800
297
+ },
298
+ {
299
+ "epoch": 0.24,
300
+ "learning_rate": 0.0002,
301
+ "loss": 1.439,
302
+ "step": 4900
303
+ },
304
+ {
305
+ "epoch": 0.25,
306
+ "learning_rate": 0.0002,
307
+ "loss": 1.3942,
308
+ "step": 5000
309
+ },
310
+ {
311
+ "epoch": 0.26,
312
+ "learning_rate": 0.0002,
313
+ "loss": 1.4163,
314
+ "step": 5100
315
+ },
316
+ {
317
+ "epoch": 0.26,
318
+ "learning_rate": 0.0002,
319
+ "loss": 1.4359,
320
+ "step": 5200
321
+ },
322
+ {
323
+ "epoch": 0.27,
324
+ "learning_rate": 0.0002,
325
+ "loss": 1.4112,
326
+ "step": 5300
327
+ },
328
+ {
329
+ "epoch": 0.27,
330
+ "learning_rate": 0.0002,
331
+ "loss": 1.4354,
332
+ "step": 5400
333
+ },
334
+ {
335
+ "epoch": 0.28,
336
+ "learning_rate": 0.0002,
337
+ "loss": 1.4081,
338
+ "step": 5500
339
+ },
340
+ {
341
+ "epoch": 0.28,
342
+ "learning_rate": 0.0002,
343
+ "loss": 1.3576,
344
+ "step": 5600
345
+ },
346
+ {
347
+ "epoch": 0.28,
348
+ "learning_rate": 0.0002,
349
+ "loss": 1.4104,
350
+ "step": 5700
351
+ },
352
+ {
353
+ "epoch": 0.29,
354
+ "learning_rate": 0.0002,
355
+ "loss": 1.3598,
356
+ "step": 5800
357
+ },
358
+ {
359
+ "epoch": 0.29,
360
+ "learning_rate": 0.0002,
361
+ "loss": 1.4263,
362
+ "step": 5900
363
+ },
364
+ {
365
+ "epoch": 0.3,
366
+ "learning_rate": 0.0002,
367
+ "loss": 1.371,
368
+ "step": 6000
369
+ },
370
+ {
371
+ "epoch": 0.3,
372
+ "learning_rate": 0.0002,
373
+ "loss": 1.3493,
374
+ "step": 6100
375
+ },
376
+ {
377
+ "epoch": 0.31,
378
+ "learning_rate": 0.0002,
379
+ "loss": 1.396,
380
+ "step": 6200
381
+ },
382
+ {
383
+ "epoch": 0.32,
384
+ "learning_rate": 0.0002,
385
+ "loss": 1.387,
386
+ "step": 6300
387
+ },
388
+ {
389
+ "epoch": 0.32,
390
+ "learning_rate": 0.0002,
391
+ "loss": 1.3604,
392
+ "step": 6400
393
+ },
394
+ {
395
+ "epoch": 0.33,
396
+ "learning_rate": 0.0002,
397
+ "loss": 1.3396,
398
+ "step": 6500
399
+ },
400
+ {
401
+ "epoch": 0.33,
402
+ "learning_rate": 0.0002,
403
+ "loss": 1.3333,
404
+ "step": 6600
405
+ },
406
+ {
407
+ "epoch": 0.34,
408
+ "learning_rate": 0.0002,
409
+ "loss": 1.3497,
410
+ "step": 6700
411
+ },
412
+ {
413
+ "epoch": 0.34,
414
+ "learning_rate": 0.0002,
415
+ "loss": 1.3387,
416
+ "step": 6800
417
+ },
418
+ {
419
+ "epoch": 0.34,
420
+ "learning_rate": 0.0002,
421
+ "loss": 1.3431,
422
+ "step": 6900
423
+ },
424
+ {
425
+ "epoch": 0.35,
426
+ "learning_rate": 0.0002,
427
+ "loss": 1.3469,
428
+ "step": 7000
429
+ },
430
+ {
431
+ "epoch": 0.35,
432
+ "learning_rate": 0.0002,
433
+ "loss": 1.3268,
434
+ "step": 7100
435
+ },
436
+ {
437
+ "epoch": 0.36,
438
+ "learning_rate": 0.0002,
439
+ "loss": 1.3166,
440
+ "step": 7200
441
+ },
442
+ {
443
+ "epoch": 0.36,
444
+ "learning_rate": 0.0002,
445
+ "loss": 1.3069,
446
+ "step": 7300
447
+ },
448
+ {
449
+ "epoch": 0.37,
450
+ "learning_rate": 0.0002,
451
+ "loss": 1.3503,
452
+ "step": 7400
453
+ },
454
+ {
455
+ "epoch": 0.38,
456
+ "learning_rate": 0.0002,
457
+ "loss": 1.3374,
458
+ "step": 7500
459
+ },
460
+ {
461
+ "epoch": 0.38,
462
+ "learning_rate": 0.0002,
463
+ "loss": 1.3348,
464
+ "step": 7600
465
+ },
466
+ {
467
+ "epoch": 0.39,
468
+ "learning_rate": 0.0002,
469
+ "loss": 1.3306,
470
+ "step": 7700
471
+ },
472
+ {
473
+ "epoch": 0.39,
474
+ "learning_rate": 0.0002,
475
+ "loss": 1.3174,
476
+ "step": 7800
477
+ },
478
+ {
479
+ "epoch": 0.4,
480
+ "learning_rate": 0.0002,
481
+ "loss": 1.2756,
482
+ "step": 7900
483
+ },
484
+ {
485
+ "epoch": 0.4,
486
+ "learning_rate": 0.0002,
487
+ "loss": 1.298,
488
+ "step": 8000
489
+ },
490
+ {
491
+ "epoch": 0.41,
492
+ "learning_rate": 0.0002,
493
+ "loss": 1.2558,
494
+ "step": 8100
495
+ },
496
+ {
497
+ "epoch": 0.41,
498
+ "learning_rate": 0.0002,
499
+ "loss": 1.2841,
500
+ "step": 8200
501
+ },
502
+ {
503
+ "epoch": 0.41,
504
+ "learning_rate": 0.0002,
505
+ "loss": 1.2717,
506
+ "step": 8300
507
+ },
508
+ {
509
+ "epoch": 0.42,
510
+ "learning_rate": 0.0002,
511
+ "loss": 1.3095,
512
+ "step": 8400
513
+ },
514
+ {
515
+ "epoch": 0.42,
516
+ "learning_rate": 0.0002,
517
+ "loss": 1.2651,
518
+ "step": 8500
519
+ },
520
+ {
521
+ "epoch": 0.43,
522
+ "learning_rate": 0.0002,
523
+ "loss": 1.2514,
524
+ "step": 8600
525
+ },
526
+ {
527
+ "epoch": 0.43,
528
+ "learning_rate": 0.0002,
529
+ "loss": 1.251,
530
+ "step": 8700
531
+ },
532
+ {
533
+ "epoch": 0.44,
534
+ "learning_rate": 0.0002,
535
+ "loss": 1.2891,
536
+ "step": 8800
537
+ },
538
+ {
539
+ "epoch": 0.45,
540
+ "learning_rate": 0.0002,
541
+ "loss": 1.2787,
542
+ "step": 8900
543
+ },
544
+ {
545
+ "epoch": 0.45,
546
+ "learning_rate": 0.0002,
547
+ "loss": 1.2872,
548
+ "step": 9000
549
+ },
550
+ {
551
+ "epoch": 0.46,
552
+ "learning_rate": 0.0002,
553
+ "loss": 1.2401,
554
+ "step": 9100
555
+ },
556
+ {
557
+ "epoch": 0.46,
558
+ "learning_rate": 0.0002,
559
+ "loss": 1.2464,
560
+ "step": 9200
561
+ },
562
+ {
563
+ "epoch": 0.47,
564
+ "learning_rate": 0.0002,
565
+ "loss": 1.2558,
566
+ "step": 9300
567
+ },
568
+ {
569
+ "epoch": 0.47,
570
+ "learning_rate": 0.0002,
571
+ "loss": 1.2351,
572
+ "step": 9400
573
+ },
574
+ {
575
+ "epoch": 0.47,
576
+ "learning_rate": 0.0002,
577
+ "loss": 1.2528,
578
+ "step": 9500
579
+ },
580
+ {
581
+ "epoch": 0.48,
582
+ "learning_rate": 0.0002,
583
+ "loss": 1.2324,
584
+ "step": 9600
585
+ },
586
+ {
587
+ "epoch": 0.48,
588
+ "learning_rate": 0.0002,
589
+ "loss": 1.2067,
590
+ "step": 9700
591
+ },
592
+ {
593
+ "epoch": 0.49,
594
+ "learning_rate": 0.0002,
595
+ "loss": 1.223,
596
+ "step": 9800
597
+ },
598
+ {
599
+ "epoch": 0.49,
600
+ "learning_rate": 0.0002,
601
+ "loss": 1.2198,
602
+ "step": 9900
603
+ },
604
+ {
605
+ "epoch": 0.5,
606
+ "learning_rate": 0.0002,
607
+ "loss": 1.2219,
608
+ "step": 10000
609
+ },
610
+ {
611
+ "epoch": 0.51,
612
+ "learning_rate": 0.0002,
613
+ "loss": 1.1942,
614
+ "step": 10100
615
+ },
616
+ {
617
+ "epoch": 0.51,
618
+ "learning_rate": 0.0002,
619
+ "loss": 1.2175,
620
+ "step": 10200
621
+ },
622
+ {
623
+ "epoch": 0.52,
624
+ "learning_rate": 0.0002,
625
+ "loss": 1.1902,
626
+ "step": 10300
627
+ },
628
+ {
629
+ "epoch": 0.52,
630
+ "learning_rate": 0.0002,
631
+ "loss": 1.1868,
632
+ "step": 10400
633
+ },
634
+ {
635
+ "epoch": 0.53,
636
+ "learning_rate": 0.0002,
637
+ "loss": 1.2066,
638
+ "step": 10500
639
+ },
640
+ {
641
+ "epoch": 0.53,
642
+ "learning_rate": 0.0002,
643
+ "loss": 1.183,
644
+ "step": 10600
645
+ },
646
+ {
647
+ "epoch": 0.54,
648
+ "learning_rate": 0.0002,
649
+ "loss": 1.1652,
650
+ "step": 10700
651
+ },
652
+ {
653
+ "epoch": 0.54,
654
+ "learning_rate": 0.0002,
655
+ "loss": 1.1789,
656
+ "step": 10800
657
+ },
658
+ {
659
+ "epoch": 0.55,
660
+ "learning_rate": 0.0002,
661
+ "loss": 1.1821,
662
+ "step": 10900
663
+ },
664
+ {
665
+ "epoch": 0.55,
666
+ "learning_rate": 0.0002,
667
+ "loss": 1.1542,
668
+ "step": 11000
669
+ },
670
+ {
671
+ "epoch": 0.56,
672
+ "learning_rate": 0.0002,
673
+ "loss": 1.1606,
674
+ "step": 11100
675
+ },
676
+ {
677
+ "epoch": 0.56,
678
+ "learning_rate": 0.0002,
679
+ "loss": 1.2044,
680
+ "step": 11200
681
+ },
682
+ {
683
+ "epoch": 0.56,
684
+ "learning_rate": 0.0002,
685
+ "loss": 1.1583,
686
+ "step": 11300
687
+ },
688
+ {
689
+ "epoch": 0.57,
690
+ "learning_rate": 0.0002,
691
+ "loss": 1.2191,
692
+ "step": 11400
693
+ },
694
+ {
695
+ "epoch": 0.57,
696
+ "learning_rate": 0.0002,
697
+ "loss": 1.1519,
698
+ "step": 11500
699
+ },
700
+ {
701
+ "epoch": 0.58,
702
+ "learning_rate": 0.0002,
703
+ "loss": 1.1523,
704
+ "step": 11600
705
+ },
706
+ {
707
+ "epoch": 0.58,
708
+ "learning_rate": 0.0002,
709
+ "loss": 1.1948,
710
+ "step": 11700
711
+ },
712
+ {
713
+ "epoch": 0.59,
714
+ "learning_rate": 0.0002,
715
+ "loss": 1.1603,
716
+ "step": 11800
717
+ },
718
+ {
719
+ "epoch": 0.59,
720
+ "learning_rate": 0.0002,
721
+ "loss": 1.1601,
722
+ "step": 11900
723
+ },
724
+ {
725
+ "epoch": 0.6,
726
+ "learning_rate": 0.0002,
727
+ "loss": 1.1245,
728
+ "step": 12000
729
+ },
730
+ {
731
+ "epoch": 0.6,
732
+ "learning_rate": 0.0002,
733
+ "loss": 1.1801,
734
+ "step": 12100
735
+ },
736
+ {
737
+ "epoch": 0.61,
738
+ "learning_rate": 0.0002,
739
+ "loss": 1.1747,
740
+ "step": 12200
741
+ },
742
+ {
743
+ "epoch": 0.61,
744
+ "learning_rate": 0.0002,
745
+ "loss": 1.1694,
746
+ "step": 12300
747
+ },
748
+ {
749
+ "epoch": 0.62,
750
+ "learning_rate": 0.0002,
751
+ "loss": 1.1405,
752
+ "step": 12400
753
+ },
754
+ {
755
+ "epoch": 0.62,
756
+ "learning_rate": 0.0002,
757
+ "loss": 1.1568,
758
+ "step": 12500
759
+ },
760
+ {
761
+ "epoch": 0.63,
762
+ "learning_rate": 0.0002,
763
+ "loss": 1.1642,
764
+ "step": 12600
765
+ },
766
+ {
767
+ "epoch": 0.64,
768
+ "learning_rate": 0.0002,
769
+ "loss": 1.1422,
770
+ "step": 12700
771
+ },
772
+ {
773
+ "epoch": 0.64,
774
+ "learning_rate": 0.0002,
775
+ "loss": 1.0952,
776
+ "step": 12800
777
+ },
778
+ {
779
+ "epoch": 0.65,
780
+ "learning_rate": 0.0002,
781
+ "loss": 1.1208,
782
+ "step": 12900
783
+ },
784
+ {
785
+ "epoch": 0.65,
786
+ "learning_rate": 0.0002,
787
+ "loss": 1.1284,
788
+ "step": 13000
789
+ },
790
+ {
791
+ "epoch": 0.66,
792
+ "learning_rate": 0.0002,
793
+ "loss": 1.1416,
794
+ "step": 13100
795
+ },
796
+ {
797
+ "epoch": 0.66,
798
+ "learning_rate": 0.0002,
799
+ "loss": 1.1485,
800
+ "step": 13200
801
+ },
802
+ {
803
+ "epoch": 0.67,
804
+ "learning_rate": 0.0002,
805
+ "loss": 1.1013,
806
+ "step": 13300
807
+ },
808
+ {
809
+ "epoch": 0.67,
810
+ "learning_rate": 0.0002,
811
+ "loss": 1.1042,
812
+ "step": 13400
813
+ },
814
+ {
815
+ "epoch": 0.68,
816
+ "learning_rate": 0.0002,
817
+ "loss": 1.0657,
818
+ "step": 13500
819
+ },
820
+ {
821
+ "epoch": 0.68,
822
+ "learning_rate": 0.0002,
823
+ "loss": 1.0916,
824
+ "step": 13600
825
+ },
826
+ {
827
+ "epoch": 0.69,
828
+ "learning_rate": 0.0002,
829
+ "loss": 1.102,
830
+ "step": 13700
831
+ },
832
+ {
833
+ "epoch": 0.69,
834
+ "learning_rate": 0.0002,
835
+ "loss": 1.1345,
836
+ "step": 13800
837
+ },
838
+ {
839
+ "epoch": 0.69,
840
+ "learning_rate": 0.0002,
841
+ "loss": 1.1131,
842
+ "step": 13900
843
+ },
844
+ {
845
+ "epoch": 0.7,
846
+ "learning_rate": 0.0002,
847
+ "loss": 1.115,
848
+ "step": 14000
849
+ },
850
+ {
851
+ "epoch": 0.7,
852
+ "learning_rate": 0.0002,
853
+ "loss": 1.0934,
854
+ "step": 14100
855
+ },
856
+ {
857
+ "epoch": 0.71,
858
+ "learning_rate": 0.0002,
859
+ "loss": 1.0929,
860
+ "step": 14200
861
+ },
862
+ {
863
+ "epoch": 0.71,
864
+ "learning_rate": 0.0002,
865
+ "loss": 1.1246,
866
+ "step": 14300
867
+ },
868
+ {
869
+ "epoch": 0.72,
870
+ "learning_rate": 0.0002,
871
+ "loss": 1.1284,
872
+ "step": 14400
873
+ },
874
+ {
875
+ "epoch": 0.72,
876
+ "learning_rate": 0.0002,
877
+ "loss": 1.0908,
878
+ "step": 14500
879
+ },
880
+ {
881
+ "epoch": 0.73,
882
+ "learning_rate": 0.0002,
883
+ "loss": 1.104,
884
+ "step": 14600
885
+ },
886
+ {
887
+ "epoch": 0.73,
888
+ "learning_rate": 0.0002,
889
+ "loss": 1.0935,
890
+ "step": 14700
891
+ },
892
+ {
893
+ "epoch": 0.74,
894
+ "learning_rate": 0.0002,
895
+ "loss": 1.125,
896
+ "step": 14800
897
+ },
898
+ {
899
+ "epoch": 0.74,
900
+ "learning_rate": 0.0002,
901
+ "loss": 1.093,
902
+ "step": 14900
903
+ },
904
+ {
905
+ "epoch": 0.75,
906
+ "learning_rate": 0.0002,
907
+ "loss": 1.0783,
908
+ "step": 15000
909
+ },
910
+ {
911
+ "epoch": 0.76,
912
+ "learning_rate": 0.0002,
913
+ "loss": 1.0933,
914
+ "step": 15100
915
+ },
916
+ {
917
+ "epoch": 0.76,
918
+ "learning_rate": 0.0002,
919
+ "loss": 1.0803,
920
+ "step": 15200
921
+ },
922
+ {
923
+ "epoch": 0.77,
924
+ "learning_rate": 0.0002,
925
+ "loss": 1.1047,
926
+ "step": 15300
927
+ },
928
+ {
929
+ "epoch": 0.77,
930
+ "learning_rate": 0.0002,
931
+ "loss": 1.0661,
932
+ "step": 15400
933
+ },
934
+ {
935
+ "epoch": 0.78,
936
+ "learning_rate": 0.0002,
937
+ "loss": 1.0404,
938
+ "step": 15500
939
+ },
940
+ {
941
+ "epoch": 0.78,
942
+ "learning_rate": 0.0002,
943
+ "loss": 1.0883,
944
+ "step": 15600
945
+ },
946
+ {
947
+ "epoch": 0.79,
948
+ "learning_rate": 0.0002,
949
+ "loss": 1.0613,
950
+ "step": 15700
951
+ },
952
+ {
953
+ "epoch": 0.79,
954
+ "learning_rate": 0.0002,
955
+ "loss": 1.0591,
956
+ "step": 15800
957
+ },
958
+ {
959
+ "epoch": 0.8,
960
+ "learning_rate": 0.0002,
961
+ "loss": 1.0712,
962
+ "step": 15900
963
+ },
964
+ {
965
+ "epoch": 0.8,
966
+ "learning_rate": 0.0002,
967
+ "loss": 1.0551,
968
+ "step": 16000
969
+ },
970
+ {
971
+ "epoch": 0.81,
972
+ "learning_rate": 0.0002,
973
+ "loss": 1.042,
974
+ "step": 16100
975
+ },
976
+ {
977
+ "epoch": 0.81,
978
+ "learning_rate": 0.0002,
979
+ "loss": 1.0873,
980
+ "step": 16200
981
+ },
982
+ {
983
+ "epoch": 0.81,
984
+ "learning_rate": 0.0002,
985
+ "loss": 1.0212,
986
+ "step": 16300
987
+ },
988
+ {
989
+ "epoch": 0.82,
990
+ "learning_rate": 0.0002,
991
+ "loss": 1.0706,
992
+ "step": 16400
993
+ },
994
+ {
995
+ "epoch": 0.82,
996
+ "learning_rate": 0.0002,
997
+ "loss": 1.0268,
998
+ "step": 16500
999
+ },
1000
+ {
1001
+ "epoch": 0.83,
1002
+ "learning_rate": 0.0002,
1003
+ "loss": 1.0624,
1004
+ "step": 16600
1005
+ },
1006
+ {
1007
+ "epoch": 0.83,
1008
+ "learning_rate": 0.0002,
1009
+ "loss": 1.0172,
1010
+ "step": 16700
1011
+ },
1012
+ {
1013
+ "epoch": 0.84,
1014
+ "learning_rate": 0.0002,
1015
+ "loss": 1.0391,
1016
+ "step": 16800
1017
+ },
1018
+ {
1019
+ "epoch": 0.84,
1020
+ "learning_rate": 0.0002,
1021
+ "loss": 1.0386,
1022
+ "step": 16900
1023
+ },
1024
+ {
1025
+ "epoch": 0.85,
1026
+ "learning_rate": 0.0002,
1027
+ "loss": 1.0418,
1028
+ "step": 17000
1029
+ },
1030
+ {
1031
+ "epoch": 0.85,
1032
+ "learning_rate": 0.0002,
1033
+ "loss": 1.0722,
1034
+ "step": 17100
1035
+ },
1036
+ {
1037
+ "epoch": 0.86,
1038
+ "learning_rate": 0.0002,
1039
+ "loss": 1.0623,
1040
+ "step": 17200
1041
+ },
1042
+ {
1043
+ "epoch": 0.86,
1044
+ "learning_rate": 0.0002,
1045
+ "loss": 1.0313,
1046
+ "step": 17300
1047
+ },
1048
+ {
1049
+ "epoch": 0.87,
1050
+ "learning_rate": 0.0002,
1051
+ "loss": 1.0032,
1052
+ "step": 17400
1053
+ },
1054
+ {
1055
+ "epoch": 0.88,
1056
+ "learning_rate": 0.0002,
1057
+ "loss": 1.0141,
1058
+ "step": 17500
1059
+ },
1060
+ {
1061
+ "epoch": 0.88,
1062
+ "learning_rate": 0.0002,
1063
+ "loss": 1.0268,
1064
+ "step": 17600
1065
+ },
1066
+ {
1067
+ "epoch": 0.89,
1068
+ "learning_rate": 0.0002,
1069
+ "loss": 1.0475,
1070
+ "step": 17700
1071
+ },
1072
+ {
1073
+ "epoch": 0.89,
1074
+ "learning_rate": 0.0002,
1075
+ "loss": 1.0664,
1076
+ "step": 17800
1077
+ },
1078
+ {
1079
+ "epoch": 0.9,
1080
+ "learning_rate": 0.0002,
1081
+ "loss": 1.0096,
1082
+ "step": 17900
1083
+ },
1084
+ {
1085
+ "epoch": 0.9,
1086
+ "learning_rate": 0.0002,
1087
+ "loss": 1.0158,
1088
+ "step": 18000
1089
+ },
1090
+ {
1091
+ "epoch": 0.91,
1092
+ "learning_rate": 0.0002,
1093
+ "loss": 1.0472,
1094
+ "step": 18100
1095
+ },
1096
+ {
1097
+ "epoch": 0.91,
1098
+ "learning_rate": 0.0002,
1099
+ "loss": 1.0588,
1100
+ "step": 18200
1101
+ },
1102
+ {
1103
+ "epoch": 0.92,
1104
+ "learning_rate": 0.0002,
1105
+ "loss": 1.0205,
1106
+ "step": 18300
1107
+ },
1108
+ {
1109
+ "epoch": 0.92,
1110
+ "learning_rate": 0.0002,
1111
+ "loss": 1.0078,
1112
+ "step": 18400
1113
+ },
1114
+ {
1115
+ "epoch": 0.93,
1116
+ "learning_rate": 0.0002,
1117
+ "loss": 1.0085,
1118
+ "step": 18500
1119
+ },
1120
+ {
1121
+ "epoch": 0.93,
1122
+ "learning_rate": 0.0002,
1123
+ "loss": 1.0189,
1124
+ "step": 18600
1125
+ },
1126
+ {
1127
+ "epoch": 0.94,
1128
+ "learning_rate": 0.0002,
1129
+ "loss": 1.0223,
1130
+ "step": 18700
1131
+ },
1132
+ {
1133
+ "epoch": 0.94,
1134
+ "learning_rate": 0.0002,
1135
+ "loss": 0.9967,
1136
+ "step": 18800
1137
+ },
1138
+ {
1139
+ "epoch": 0.94,
1140
+ "learning_rate": 0.0002,
1141
+ "loss": 0.9659,
1142
+ "step": 18900
1143
+ },
1144
+ {
1145
+ "epoch": 0.95,
1146
+ "learning_rate": 0.0002,
1147
+ "loss": 1.0014,
1148
+ "step": 19000
1149
+ },
1150
+ {
1151
+ "epoch": 0.95,
1152
+ "learning_rate": 0.0002,
1153
+ "loss": 1.0076,
1154
+ "step": 19100
1155
+ },
1156
+ {
1157
+ "epoch": 0.96,
1158
+ "learning_rate": 0.0002,
1159
+ "loss": 1.0119,
1160
+ "step": 19200
1161
+ },
1162
+ {
1163
+ "epoch": 0.96,
1164
+ "learning_rate": 0.0002,
1165
+ "loss": 1.0287,
1166
+ "step": 19300
1167
+ },
1168
+ {
1169
+ "epoch": 0.97,
1170
+ "learning_rate": 0.0002,
1171
+ "loss": 0.99,
1172
+ "step": 19400
1173
+ },
1174
+ {
1175
+ "epoch": 0.97,
1176
+ "learning_rate": 0.0002,
1177
+ "loss": 1.0108,
1178
+ "step": 19500
1179
+ },
1180
+ {
1181
+ "epoch": 0.98,
1182
+ "learning_rate": 0.0002,
1183
+ "loss": 0.9991,
1184
+ "step": 19600
1185
+ },
1186
+ {
1187
+ "epoch": 0.98,
1188
+ "learning_rate": 0.0002,
1189
+ "loss": 0.9656,
1190
+ "step": 19700
1191
+ },
1192
+ {
1193
+ "epoch": 0.99,
1194
+ "learning_rate": 0.0002,
1195
+ "loss": 0.9977,
1196
+ "step": 19800
1197
+ },
1198
+ {
1199
+ "epoch": 0.99,
1200
+ "learning_rate": 0.0002,
1201
+ "loss": 0.9915,
1202
+ "step": 19900
1203
+ },
1204
+ {
1205
+ "epoch": 1.0,
1206
+ "learning_rate": 0.0002,
1207
+ "loss": 0.9808,
1208
+ "step": 20000
1209
+ }
1210
+ ],
1211
+ "max_steps": 20000,
1212
+ "num_train_epochs": 1,
1213
+ "total_flos": 3.5798846029020365e+17,
1214
+ "trial_name": null,
1215
+ "trial_params": null
1216
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f66b9f75b074121766a488dc1e84a52f1f3f59f68245829a9e02cd3e60ae4306
3
+ size 3899