bimabk commited on
Commit
035cfa7
·
verified ·
1 Parent(s): 5a03260

Upload task output 8ca8a9ea-9ae3-4938-9713-015819984d61

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "<|PAD_TOKEN|>": 151646,
3
+ "<|endoftext|>": 151643,
4
+ "<|im_end|>": 151645,
5
+ "<|im_start|>": 151644
6
+ }
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151643,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 1536,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 8960,
12
+ "max_position_embeddings": 131072,
13
+ "max_window_layers": 28,
14
+ "model_type": "qwen2",
15
+ "num_attention_heads": 12,
16
+ "num_hidden_layers": 28,
17
+ "num_key_value_heads": 2,
18
+ "pad_token_id": 151646,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": null,
21
+ "rope_theta": 1000000.0,
22
+ "sliding_window": null,
23
+ "tie_word_embeddings": true,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.51.3",
26
+ "unsloth_version": "2024.9",
27
+ "use_cache": false,
28
+ "use_sliding_window": false,
29
+ "vocab_size": 151936
30
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": 151643,
4
+ "max_length": 131072,
5
+ "max_new_tokens": 2048,
6
+ "pad_token_id": 151646,
7
+ "transformers_version": "4.51.3"
8
+ }
loss.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ 444,0.5516598224639893
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 sha256:836ac6098e81d72e0e259bb77d370116ead4af95bea1be23f8d56a09d97f7aff
3
+ size 3087467144
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": {
14
+ "content": "<|PAD_TOKEN|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ }
20
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9479047c22047670077878de944c696032b1a81049beeb6e99fbda7fb93e395a
3
+ size 11418456
tokenizer_config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "151646": {
29
+ "content": "<|PAD_TOKEN|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ }
36
+ },
37
+ "additional_special_tokens": [
38
+ "<|im_start|>",
39
+ "<|im_end|>"
40
+ ],
41
+ "bos_token": null,
42
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
43
+ "clean_up_tokenization_spaces": false,
44
+ "eos_token": "<|endoftext|>",
45
+ "errors": "replace",
46
+ "extra_special_tokens": {},
47
+ "model_max_length": 32768,
48
+ "pad_token": "<|PAD_TOKEN|>",
49
+ "padding_side": "left",
50
+ "split_special_tokens": false,
51
+ "tokenizer_class": "Qwen2Tokenizer",
52
+ "unk_token": null
53
+ }
trainer_state.json ADDED
@@ -0,0 +1,674 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.9910313901345291,
6
+ "eval_steps": 500,
7
+ "global_step": 444,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.02242152466367713,
14
+ "grad_norm": 1.8046875,
15
+ "learning_rate": 3.225012776176047e-05,
16
+ "loss": 0.8841,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.04484304932735426,
21
+ "grad_norm": 1.2890625,
22
+ "learning_rate": 7.256278746396105e-05,
23
+ "loss": 0.703,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.06726457399103139,
28
+ "grad_norm": 1.4375,
29
+ "learning_rate": 0.00011287544716616165,
30
+ "loss": 0.6704,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.08968609865470852,
35
+ "grad_norm": 1.7578125,
36
+ "learning_rate": 0.00015318810686836223,
37
+ "loss": 0.6641,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.11210762331838565,
42
+ "grad_norm": 0.95703125,
43
+ "learning_rate": 0.00019350076657056282,
44
+ "loss": 0.6811,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.13452914798206278,
49
+ "grad_norm": 1.6953125,
50
+ "learning_rate": 0.00023381342627276343,
51
+ "loss": 0.662,
52
+ "step": 30
53
+ },
54
+ {
55
+ "epoch": 0.15695067264573992,
56
+ "grad_norm": 1.515625,
57
+ "learning_rate": 0.000274126085974964,
58
+ "loss": 0.6823,
59
+ "step": 35
60
+ },
61
+ {
62
+ "epoch": 0.17937219730941703,
63
+ "grad_norm": 8.1875,
64
+ "learning_rate": 0.0002821678320668541,
65
+ "loss": 0.9132,
66
+ "step": 40
67
+ },
68
+ {
69
+ "epoch": 0.20179372197309417,
70
+ "grad_norm": 1.6484375,
71
+ "learning_rate": 0.00028208340355189316,
72
+ "loss": 0.9479,
73
+ "step": 45
74
+ },
75
+ {
76
+ "epoch": 0.2242152466367713,
77
+ "grad_norm": 1.390625,
78
+ "learning_rate": 0.00028193408503878413,
79
+ "loss": 0.7504,
80
+ "step": 50
81
+ },
82
+ {
83
+ "epoch": 0.24663677130044842,
84
+ "grad_norm": 1.109375,
85
+ "learning_rate": 0.00028171996818179184,
86
+ "loss": 0.7178,
87
+ "step": 55
88
+ },
89
+ {
90
+ "epoch": 0.26905829596412556,
91
+ "grad_norm": 0.765625,
92
+ "learning_rate": 0.00028144118440951647,
93
+ "loss": 0.7022,
94
+ "step": 60
95
+ },
96
+ {
97
+ "epoch": 0.2914798206278027,
98
+ "grad_norm": 0.63671875,
99
+ "learning_rate": 0.00028109790484422007,
100
+ "loss": 0.6894,
101
+ "step": 65
102
+ },
103
+ {
104
+ "epoch": 0.31390134529147984,
105
+ "grad_norm": 0.671875,
106
+ "learning_rate": 0.0002806903401967889,
107
+ "loss": 0.6873,
108
+ "step": 70
109
+ },
110
+ {
111
+ "epoch": 0.336322869955157,
112
+ "grad_norm": 0.61328125,
113
+ "learning_rate": 0.0002802187406373956,
114
+ "loss": 0.6881,
115
+ "step": 75
116
+ },
117
+ {
118
+ "epoch": 0.35874439461883406,
119
+ "grad_norm": 0.546875,
120
+ "learning_rate": 0.0002796833956419402,
121
+ "loss": 0.6827,
122
+ "step": 80
123
+ },
124
+ {
125
+ "epoch": 0.3811659192825112,
126
+ "grad_norm": 0.5625,
127
+ "learning_rate": 0.00027908463381436484,
128
+ "loss": 0.6601,
129
+ "step": 85
130
+ },
131
+ {
132
+ "epoch": 0.40358744394618834,
133
+ "grad_norm": 0.515625,
134
+ "learning_rate": 0.00027842282268495153,
135
+ "loss": 0.6652,
136
+ "step": 90
137
+ },
138
+ {
139
+ "epoch": 0.4260089686098655,
140
+ "grad_norm": 0.53125,
141
+ "learning_rate": 0.000277698368484725,
142
+ "loss": 0.6648,
143
+ "step": 95
144
+ },
145
+ {
146
+ "epoch": 0.4484304932735426,
147
+ "grad_norm": 0.625,
148
+ "learning_rate": 0.0002769117158961017,
149
+ "loss": 0.668,
150
+ "step": 100
151
+ },
152
+ {
153
+ "epoch": 0.47085201793721976,
154
+ "grad_norm": 0.5234375,
155
+ "learning_rate": 0.000276063347779936,
156
+ "loss": 0.6516,
157
+ "step": 105
158
+ },
159
+ {
160
+ "epoch": 0.49327354260089684,
161
+ "grad_norm": 0.61328125,
162
+ "learning_rate": 0.00027515378487913156,
163
+ "loss": 0.651,
164
+ "step": 110
165
+ },
166
+ {
167
+ "epoch": 0.515695067264574,
168
+ "grad_norm": 0.53515625,
169
+ "learning_rate": 0.00027418358549900095,
170
+ "loss": 0.6457,
171
+ "step": 115
172
+ },
173
+ {
174
+ "epoch": 0.5381165919282511,
175
+ "grad_norm": 0.5390625,
176
+ "learning_rate": 0.0002731533451645679,
177
+ "loss": 0.6383,
178
+ "step": 120
179
+ },
180
+ {
181
+ "epoch": 0.5605381165919282,
182
+ "grad_norm": 0.51953125,
183
+ "learning_rate": 0.0002720636962550239,
184
+ "loss": 0.6304,
185
+ "step": 125
186
+ },
187
+ {
188
+ "epoch": 0.5829596412556054,
189
+ "grad_norm": 0.458984375,
190
+ "learning_rate": 0.000270915307615563,
191
+ "loss": 0.6478,
192
+ "step": 130
193
+ },
194
+ {
195
+ "epoch": 0.6053811659192825,
196
+ "grad_norm": 0.474609375,
197
+ "learning_rate": 0.0002697088841468332,
198
+ "loss": 0.621,
199
+ "step": 135
200
+ },
201
+ {
202
+ "epoch": 0.6278026905829597,
203
+ "grad_norm": 0.5390625,
204
+ "learning_rate": 0.00026844516637225627,
205
+ "loss": 0.644,
206
+ "step": 140
207
+ },
208
+ {
209
+ "epoch": 0.6502242152466368,
210
+ "grad_norm": 0.44140625,
211
+ "learning_rate": 0.0002671249299834821,
212
+ "loss": 0.6311,
213
+ "step": 145
214
+ },
215
+ {
216
+ "epoch": 0.672645739910314,
217
+ "grad_norm": 0.5234375,
218
+ "learning_rate": 0.00026574898536425504,
219
+ "loss": 0.6328,
220
+ "step": 150
221
+ },
222
+ {
223
+ "epoch": 0.695067264573991,
224
+ "grad_norm": 0.49609375,
225
+ "learning_rate": 0.00026431817709298756,
226
+ "loss": 0.607,
227
+ "step": 155
228
+ },
229
+ {
230
+ "epoch": 0.7174887892376681,
231
+ "grad_norm": 0.4375,
232
+ "learning_rate": 0.0002628333834243426,
233
+ "loss": 0.6266,
234
+ "step": 160
235
+ },
236
+ {
237
+ "epoch": 0.7399103139013453,
238
+ "grad_norm": 0.482421875,
239
+ "learning_rate": 0.0002612955157501462,
240
+ "loss": 0.6151,
241
+ "step": 165
242
+ },
243
+ {
244
+ "epoch": 0.7623318385650224,
245
+ "grad_norm": 0.443359375,
246
+ "learning_rate": 0.00025970551803995967,
247
+ "loss": 0.6259,
248
+ "step": 170
249
+ },
250
+ {
251
+ "epoch": 0.7847533632286996,
252
+ "grad_norm": 0.4609375,
253
+ "learning_rate": 0.0002580643662616546,
254
+ "loss": 0.6136,
255
+ "step": 175
256
+ },
257
+ {
258
+ "epoch": 0.8071748878923767,
259
+ "grad_norm": 0.4765625,
260
+ "learning_rate": 0.0002563730677823472,
261
+ "loss": 0.6075,
262
+ "step": 180
263
+ },
264
+ {
265
+ "epoch": 0.8295964125560538,
266
+ "grad_norm": 0.5234375,
267
+ "learning_rate": 0.00025463266075005897,
268
+ "loss": 0.6133,
269
+ "step": 185
270
+ },
271
+ {
272
+ "epoch": 0.852017937219731,
273
+ "grad_norm": 0.47265625,
274
+ "learning_rate": 0.0002528442134564838,
275
+ "loss": 0.597,
276
+ "step": 190
277
+ },
278
+ {
279
+ "epoch": 0.874439461883408,
280
+ "grad_norm": 0.431640625,
281
+ "learning_rate": 0.0002510088236812521,
282
+ "loss": 0.5931,
283
+ "step": 195
284
+ },
285
+ {
286
+ "epoch": 0.8968609865470852,
287
+ "grad_norm": 0.4609375,
288
+ "learning_rate": 0.00024912761801809485,
289
+ "loss": 0.6266,
290
+ "step": 200
291
+ },
292
+ {
293
+ "epoch": 0.9192825112107623,
294
+ "grad_norm": 0.458984375,
295
+ "learning_rate": 0.0002472017511833209,
296
+ "loss": 0.6032,
297
+ "step": 205
298
+ },
299
+ {
300
+ "epoch": 0.9417040358744395,
301
+ "grad_norm": 0.4296875,
302
+ "learning_rate": 0.00024523240530703263,
303
+ "loss": 0.5887,
304
+ "step": 210
305
+ },
306
+ {
307
+ "epoch": 0.9641255605381166,
308
+ "grad_norm": 0.51953125,
309
+ "learning_rate": 0.0002432207892075138,
310
+ "loss": 0.596,
311
+ "step": 215
312
+ },
313
+ {
314
+ "epoch": 0.9865470852017937,
315
+ "grad_norm": 0.443359375,
316
+ "learning_rate": 0.00024116813764923656,
317
+ "loss": 0.6081,
318
+ "step": 220
319
+ },
320
+ {
321
+ "epoch": 0.9955156950672646,
322
+ "eval_loss": 0.5990473628044128,
323
+ "eval_runtime": 3.2112,
324
+ "eval_samples_per_second": 13.079,
325
+ "eval_steps_per_second": 13.079,
326
+ "step": 222
327
+ },
328
+ {
329
+ "epoch": 1.0089686098654709,
330
+ "grad_norm": 0.60546875,
331
+ "learning_rate": 0.00023907571058494136,
332
+ "loss": 0.5292,
333
+ "step": 225
334
+ },
335
+ {
336
+ "epoch": 1.031390134529148,
337
+ "grad_norm": 0.46875,
338
+ "learning_rate": 0.0002369447923822569,
339
+ "loss": 0.4347,
340
+ "step": 230
341
+ },
342
+ {
343
+ "epoch": 1.053811659192825,
344
+ "grad_norm": 0.458984375,
345
+ "learning_rate": 0.00023477669103533273,
346
+ "loss": 0.4224,
347
+ "step": 235
348
+ },
349
+ {
350
+ "epoch": 1.0762331838565022,
351
+ "grad_norm": 0.47265625,
352
+ "learning_rate": 0.0002325727373619704,
353
+ "loss": 0.4291,
354
+ "step": 240
355
+ },
356
+ {
357
+ "epoch": 1.0986547085201794,
358
+ "grad_norm": 0.4609375,
359
+ "learning_rate": 0.0002303342841867443,
360
+ "loss": 0.4202,
361
+ "step": 245
362
+ },
363
+ {
364
+ "epoch": 1.1210762331838564,
365
+ "grad_norm": 0.423828125,
366
+ "learning_rate": 0.0002280627055106151,
367
+ "loss": 0.42,
368
+ "step": 250
369
+ },
370
+ {
371
+ "epoch": 1.1434977578475336,
372
+ "grad_norm": 0.388671875,
373
+ "learning_rate": 0.0002257593956675441,
374
+ "loss": 0.434,
375
+ "step": 255
376
+ },
377
+ {
378
+ "epoch": 1.1659192825112108,
379
+ "grad_norm": 0.4453125,
380
+ "learning_rate": 0.0002234257684686273,
381
+ "loss": 0.4278,
382
+ "step": 260
383
+ },
384
+ {
385
+ "epoch": 1.188340807174888,
386
+ "grad_norm": 0.396484375,
387
+ "learning_rate": 0.00022106325633427373,
388
+ "loss": 0.4261,
389
+ "step": 265
390
+ },
391
+ {
392
+ "epoch": 1.210762331838565,
393
+ "grad_norm": 0.42578125,
394
+ "learning_rate": 0.00021867330941496144,
395
+ "loss": 0.4233,
396
+ "step": 270
397
+ },
398
+ {
399
+ "epoch": 1.2331838565022422,
400
+ "grad_norm": 0.40625,
401
+ "learning_rate": 0.00021625739470111004,
402
+ "loss": 0.4301,
403
+ "step": 275
404
+ },
405
+ {
406
+ "epoch": 1.2556053811659194,
407
+ "grad_norm": 0.384765625,
408
+ "learning_rate": 0.00021381699512261696,
409
+ "loss": 0.4405,
410
+ "step": 280
411
+ },
412
+ {
413
+ "epoch": 1.2780269058295963,
414
+ "grad_norm": 0.421875,
415
+ "learning_rate": 0.00021135360863860965,
416
+ "loss": 0.4323,
417
+ "step": 285
418
+ },
419
+ {
420
+ "epoch": 1.3004484304932735,
421
+ "grad_norm": 0.373046875,
422
+ "learning_rate": 0.00020886874731797242,
423
+ "loss": 0.4345,
424
+ "step": 290
425
+ },
426
+ {
427
+ "epoch": 1.3228699551569507,
428
+ "grad_norm": 0.37890625,
429
+ "learning_rate": 0.00020636393641121277,
430
+ "loss": 0.4321,
431
+ "step": 295
432
+ },
433
+ {
434
+ "epoch": 1.3452914798206277,
435
+ "grad_norm": 0.361328125,
436
+ "learning_rate": 0.0002038407134142364,
437
+ "loss": 0.4273,
438
+ "step": 300
439
+ },
440
+ {
441
+ "epoch": 1.3677130044843049,
442
+ "grad_norm": 0.388671875,
443
+ "learning_rate": 0.0002013006271246058,
444
+ "loss": 0.4319,
445
+ "step": 305
446
+ },
447
+ {
448
+ "epoch": 1.390134529147982,
449
+ "grad_norm": 0.3828125,
450
+ "learning_rate": 0.00019874523669086193,
451
+ "loss": 0.4301,
452
+ "step": 310
453
+ },
454
+ {
455
+ "epoch": 1.4125560538116593,
456
+ "grad_norm": 0.37109375,
457
+ "learning_rate": 0.0001961761106554918,
458
+ "loss": 0.4327,
459
+ "step": 315
460
+ },
461
+ {
462
+ "epoch": 1.4349775784753362,
463
+ "grad_norm": 0.39453125,
464
+ "learning_rate": 0.00019359482599213036,
465
+ "loss": 0.4285,
466
+ "step": 320
467
+ },
468
+ {
469
+ "epoch": 1.4573991031390134,
470
+ "grad_norm": 0.375,
471
+ "learning_rate": 0.0001910029671375871,
472
+ "loss": 0.4392,
473
+ "step": 325
474
+ },
475
+ {
476
+ "epoch": 1.4798206278026906,
477
+ "grad_norm": 0.37890625,
478
+ "learning_rate": 0.00018840212501929134,
479
+ "loss": 0.4245,
480
+ "step": 330
481
+ },
482
+ {
483
+ "epoch": 1.5022421524663678,
484
+ "grad_norm": 0.39453125,
485
+ "learning_rate": 0.00018579389607875394,
486
+ "loss": 0.4231,
487
+ "step": 335
488
+ },
489
+ {
490
+ "epoch": 1.5246636771300448,
491
+ "grad_norm": 0.37109375,
492
+ "learning_rate": 0.0001831798812916439,
493
+ "loss": 0.4239,
494
+ "step": 340
495
+ },
496
+ {
497
+ "epoch": 1.547085201793722,
498
+ "grad_norm": 0.37109375,
499
+ "learning_rate": 0.00018056168518508213,
500
+ "loss": 0.4122,
501
+ "step": 345
502
+ },
503
+ {
504
+ "epoch": 1.5695067264573992,
505
+ "grad_norm": 0.369140625,
506
+ "learning_rate": 0.0001779409148527551,
507
+ "loss": 0.4199,
508
+ "step": 350
509
+ },
510
+ {
511
+ "epoch": 1.5919282511210762,
512
+ "grad_norm": 0.39453125,
513
+ "learning_rate": 0.0001753191789684532,
514
+ "loss": 0.4191,
515
+ "step": 355
516
+ },
517
+ {
518
+ "epoch": 1.6143497757847534,
519
+ "grad_norm": 0.37109375,
520
+ "learning_rate": 0.00017269808679863934,
521
+ "loss": 0.4109,
522
+ "step": 360
523
+ },
524
+ {
525
+ "epoch": 1.6367713004484306,
526
+ "grad_norm": 0.36328125,
527
+ "learning_rate": 0.00017007924721465324,
528
+ "loss": 0.4178,
529
+ "step": 365
530
+ },
531
+ {
532
+ "epoch": 1.6591928251121075,
533
+ "grad_norm": 0.365234375,
534
+ "learning_rate": 0.00016746426770515897,
535
+ "loss": 0.4236,
536
+ "step": 370
537
+ },
538
+ {
539
+ "epoch": 1.6816143497757847,
540
+ "grad_norm": 0.384765625,
541
+ "learning_rate": 0.0001648547533894405,
542
+ "loss": 0.4221,
543
+ "step": 375
544
+ },
545
+ {
546
+ "epoch": 1.704035874439462,
547
+ "grad_norm": 0.357421875,
548
+ "learning_rate": 0.00016225230603215222,
549
+ "loss": 0.4144,
550
+ "step": 380
551
+ },
552
+ {
553
+ "epoch": 1.726457399103139,
554
+ "grad_norm": 0.353515625,
555
+ "learning_rate": 0.0001596585230601281,
556
+ "loss": 0.4171,
557
+ "step": 385
558
+ },
559
+ {
560
+ "epoch": 1.7488789237668163,
561
+ "grad_norm": 0.380859375,
562
+ "learning_rate": 0.00015707499658185395,
563
+ "loss": 0.4144,
564
+ "step": 390
565
+ },
566
+ {
567
+ "epoch": 1.7713004484304933,
568
+ "grad_norm": 0.33984375,
569
+ "learning_rate": 0.0001545033124102035,
570
+ "loss": 0.3981,
571
+ "step": 395
572
+ },
573
+ {
574
+ "epoch": 1.7937219730941703,
575
+ "grad_norm": 0.34765625,
576
+ "learning_rate": 0.00015194504908903986,
577
+ "loss": 0.4076,
578
+ "step": 400
579
+ },
580
+ {
581
+ "epoch": 1.8161434977578477,
582
+ "grad_norm": 0.369140625,
583
+ "learning_rate": 0.0001494017769242775,
584
+ "loss": 0.4093,
585
+ "step": 405
586
+ },
587
+ {
588
+ "epoch": 1.8385650224215246,
589
+ "grad_norm": 0.337890625,
590
+ "learning_rate": 0.00014687505702000225,
591
+ "loss": 0.4092,
592
+ "step": 410
593
+ },
594
+ {
595
+ "epoch": 1.8609865470852018,
596
+ "grad_norm": 0.345703125,
597
+ "learning_rate": 0.00014436644032023824,
598
+ "loss": 0.3973,
599
+ "step": 415
600
+ },
601
+ {
602
+ "epoch": 1.883408071748879,
603
+ "grad_norm": 0.349609375,
604
+ "learning_rate": 0.0001418774666569522,
605
+ "loss": 0.397,
606
+ "step": 420
607
+ },
608
+ {
609
+ "epoch": 1.905829596412556,
610
+ "grad_norm": 0.357421875,
611
+ "learning_rate": 0.00013940966380487815,
612
+ "loss": 0.4015,
613
+ "step": 425
614
+ },
615
+ {
616
+ "epoch": 1.9282511210762332,
617
+ "grad_norm": 0.359375,
618
+ "learning_rate": 0.00013696454654374285,
619
+ "loss": 0.4088,
620
+ "step": 430
621
+ },
622
+ {
623
+ "epoch": 1.9506726457399104,
624
+ "grad_norm": 0.330078125,
625
+ "learning_rate": 0.00013454361572846828,
626
+ "loss": 0.3922,
627
+ "step": 435
628
+ },
629
+ {
630
+ "epoch": 1.9730941704035874,
631
+ "grad_norm": 0.359375,
632
+ "learning_rate": 0.00013214835736792096,
633
+ "loss": 0.3984,
634
+ "step": 440
635
+ },
636
+ {
637
+ "epoch": 1.9820627802690582,
638
+ "eval_loss": 0.5519173741340637,
639
+ "eval_runtime": 3.2083,
640
+ "eval_samples_per_second": 13.091,
641
+ "eval_steps_per_second": 13.091,
642
+ "step": 442
643
+ },
644
+ {
645
+ "epoch": 1.9910313901345291,
646
+ "eval_loss": 0.5516598224639893,
647
+ "eval_runtime": 3.2302,
648
+ "eval_samples_per_second": 13.002,
649
+ "eval_steps_per_second": 13.002,
650
+ "step": 444
651
+ }
652
+ ],
653
+ "logging_steps": 5,
654
+ "max_steps": 669,
655
+ "num_input_tokens_seen": 0,
656
+ "num_train_epochs": 3,
657
+ "save_steps": 500,
658
+ "stateful_callbacks": {
659
+ "TrainerControl": {
660
+ "args": {
661
+ "should_epoch_stop": false,
662
+ "should_evaluate": false,
663
+ "should_log": false,
664
+ "should_save": true,
665
+ "should_training_stop": false
666
+ },
667
+ "attributes": {}
668
+ }
669
+ },
670
+ "total_flos": 7.145669325918044e+17,
671
+ "train_batch_size": 100,
672
+ "trial_name": null,
673
+ "trial_params": null
674
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2003360a4cafa7bd16ec6afc01796d372a7f8d1ce86d025e76d7c5c247f0cc91
3
+ size 5688
vocab.json ADDED
The diff for this file is too large to render. See raw diff