lemonzeng commited on
Commit
dae955a
1 Parent(s): 1d4c408
README.md ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ model-index:
5
+ - name: flashatt1_llama213B_yyj_deruzh.shot3.highcomet_-1.0
6
+ results: []
7
+ ---
8
+
9
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
10
+ should probably proofread and complete it, then remove this comment. -->
11
+
12
+ # flashatt1_llama213B_yyj_deruzh.shot3.highcomet_-1.0
13
+
14
+ This model is a fine-tuned version of [/mnt/nanjing3cephfs/pr-others-prctrans/lemonzeng/search/mGPT/models/llama-2-13b](https://huggingface.co//mnt/nanjing3cephfs/pr-others-prctrans/lemonzeng/search/mGPT/models/llama-2-13b) on the None dataset.
15
+
16
+ ## Model description
17
+
18
+ More information needed
19
+
20
+ ## Intended uses & limitations
21
+
22
+ More information needed
23
+
24
+ ## Training and evaluation data
25
+
26
+ More information needed
27
+
28
+ ## Training procedure
29
+
30
+ ### Training hyperparameters
31
+
32
+ The following hyperparameters were used during training:
33
+ - learning_rate: 2e-05
34
+ - train_batch_size: 4
35
+ - eval_batch_size: 8
36
+ - seed: 42
37
+ - distributed_type: multi-GPU
38
+ - num_devices: 8
39
+ - gradient_accumulation_steps: 4
40
+ - total_train_batch_size: 128
41
+ - total_eval_batch_size: 64
42
+ - optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
43
+ - lr_scheduler_type: linear
44
+ - lr_scheduler_warmup_ratio: 0.03
45
+ - num_epochs: 1.0
46
+
47
+ ### Training results
48
+
49
+
50
+
51
+ ### Framework versions
52
+
53
+ - Transformers 4.28.0
54
+ - Pytorch 1.13.1
55
+ - Datasets 2.14.0
56
+ - Tokenizers 0.13.3
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "steps": 7499,
4
+ "train_loss": 0.5490713825319938,
5
+ "train_runtime": 153878.2498,
6
+ "train_samples": -1,
7
+ "train_samples_per_second": 6.238,
8
+ "train_steps_per_second": 0.049
9
+ }
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/mnt/nanjing3cephfs/pr-others-prctrans/lemonzeng/search/mGPT/models/llama-2-13b",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 5120,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 13824,
12
+ "max_position_embeddings": 2048,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 40,
15
+ "num_hidden_layers": 40,
16
+ "num_key_value_heads": 40,
17
+ "pad_token_id": 0,
18
+ "pretraining_tp": 2,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.28.0",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "temperature": 0.9,
7
+ "top_p": 0.6,
8
+ "transformers_version": "4.28.0"
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18bac1f5fcefe280fd4752ea3fa4a183999c4b4e1caf42c1c2b3565e7ccc5d7a
3
+ size 26031868013
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "</s>",
5
+ "unk_token": "<unk>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "model_max_length": 1000000000000000019884624838656,
22
+ "pad_token": null,
23
+ "sp_model_kwargs": {},
24
+ "tokenizer_class": "LlamaTokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "steps": 7499,
4
+ "train_loss": 0.5490713825319938,
5
+ "train_runtime": 153878.2498,
6
+ "train_samples": -1,
7
+ "train_samples_per_second": 6.238,
8
+ "train_steps_per_second": 0.049
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,618 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.999966663333,
5
+ "global_step": 7499,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.013,
12
+ "learning_rate": 1.7006980333014778e-05,
13
+ "loss": 0.6595,
14
+ "r_loss": 0.0,
15
+ "step": 100,
16
+ "steps": 100
17
+ },
18
+ {
19
+ "epoch": 0.027,
20
+ "learning_rate": 1.9565280790988883e-05,
21
+ "loss": 0.6458,
22
+ "r_loss": 0.0,
23
+ "step": 200,
24
+ "steps": 200
25
+ },
26
+ {
27
+ "epoch": 0.04,
28
+ "learning_rate": 1.9799385482540556e-05,
29
+ "loss": 0.6391,
30
+ "r_loss": 0.0,
31
+ "step": 300,
32
+ "steps": 300
33
+ },
34
+ {
35
+ "epoch": 0.053,
36
+ "learning_rate": 1.9524571075061864e-05,
37
+ "loss": 0.635,
38
+ "r_loss": 0.0,
39
+ "step": 400,
40
+ "steps": 400
41
+ },
42
+ {
43
+ "epoch": 0.067,
44
+ "learning_rate": 1.925250481165796e-05,
45
+ "loss": 0.6268,
46
+ "r_loss": 0.0,
47
+ "step": 500,
48
+ "steps": 500
49
+ },
50
+ {
51
+ "epoch": 0.08,
52
+ "learning_rate": 1.897769040417927e-05,
53
+ "loss": 0.6208,
54
+ "r_loss": 0.0,
55
+ "step": 600,
56
+ "steps": 600
57
+ },
58
+ {
59
+ "epoch": 0.093,
60
+ "learning_rate": 1.8702875996700577e-05,
61
+ "loss": 0.6161,
62
+ "r_loss": 0.0,
63
+ "step": 700,
64
+ "steps": 700
65
+ },
66
+ {
67
+ "epoch": 0.107,
68
+ "learning_rate": 1.842806158922189e-05,
69
+ "loss": 0.6145,
70
+ "r_loss": 0.0,
71
+ "step": 800,
72
+ "steps": 800
73
+ },
74
+ {
75
+ "epoch": 0.12,
76
+ "learning_rate": 1.8153247181743197e-05,
77
+ "loss": 0.6041,
78
+ "r_loss": 0.0,
79
+ "step": 900,
80
+ "steps": 900
81
+ },
82
+ {
83
+ "epoch": 0.133,
84
+ "learning_rate": 1.7878432774264505e-05,
85
+ "loss": 0.6049,
86
+ "r_loss": 0.0,
87
+ "step": 1000,
88
+ "steps": 1000
89
+ },
90
+ {
91
+ "epoch": 0.147,
92
+ "learning_rate": 1.7603618366785813e-05,
93
+ "loss": 0.6019,
94
+ "r_loss": 0.0,
95
+ "step": 1100,
96
+ "steps": 1100
97
+ },
98
+ {
99
+ "epoch": 0.16,
100
+ "learning_rate": 1.732880395930712e-05,
101
+ "loss": 0.5995,
102
+ "r_loss": 0.0,
103
+ "step": 1200,
104
+ "steps": 1200
105
+ },
106
+ {
107
+ "epoch": 0.173,
108
+ "learning_rate": 1.7056737695903218e-05,
109
+ "loss": 0.5949,
110
+ "r_loss": 0.0,
111
+ "step": 1300,
112
+ "steps": 1300
113
+ },
114
+ {
115
+ "epoch": 0.187,
116
+ "learning_rate": 1.6781923288424526e-05,
117
+ "loss": 0.5914,
118
+ "r_loss": 0.0,
119
+ "step": 1400,
120
+ "steps": 1400
121
+ },
122
+ {
123
+ "epoch": 0.2,
124
+ "learning_rate": 1.6507108880945834e-05,
125
+ "loss": 0.5884,
126
+ "r_loss": 0.0,
127
+ "step": 1500,
128
+ "steps": 1500
129
+ },
130
+ {
131
+ "epoch": 0.213,
132
+ "learning_rate": 1.6232294473467146e-05,
133
+ "loss": 0.5839,
134
+ "r_loss": 0.0,
135
+ "step": 1600,
136
+ "steps": 1600
137
+ },
138
+ {
139
+ "epoch": 0.227,
140
+ "learning_rate": 1.5957480065988454e-05,
141
+ "loss": 0.5816,
142
+ "r_loss": 0.0,
143
+ "step": 1700,
144
+ "steps": 1700
145
+ },
146
+ {
147
+ "epoch": 0.24,
148
+ "learning_rate": 1.5682665658509762e-05,
149
+ "loss": 0.5807,
150
+ "r_loss": 0.0,
151
+ "step": 1800,
152
+ "steps": 1800
153
+ },
154
+ {
155
+ "epoch": 0.253,
156
+ "learning_rate": 1.540785125103107e-05,
157
+ "loss": 0.5821,
158
+ "r_loss": 0.0,
159
+ "step": 1900,
160
+ "steps": 1900
161
+ },
162
+ {
163
+ "epoch": 0.267,
164
+ "learning_rate": 1.5133036843552378e-05,
165
+ "loss": 0.5767,
166
+ "r_loss": 0.0,
167
+ "step": 2000,
168
+ "steps": 2000
169
+ },
170
+ {
171
+ "epoch": 0.28,
172
+ "learning_rate": 1.4858222436073688e-05,
173
+ "loss": 0.5704,
174
+ "r_loss": 0.0,
175
+ "step": 2100,
176
+ "steps": 2100
177
+ },
178
+ {
179
+ "epoch": 0.293,
180
+ "learning_rate": 1.4583408028594996e-05,
181
+ "loss": 0.5702,
182
+ "r_loss": 0.0,
183
+ "step": 2200,
184
+ "steps": 2200
185
+ },
186
+ {
187
+ "epoch": 0.307,
188
+ "learning_rate": 1.4308593621116305e-05,
189
+ "loss": 0.573,
190
+ "r_loss": 0.0,
191
+ "step": 2300,
192
+ "steps": 2300
193
+ },
194
+ {
195
+ "epoch": 0.32,
196
+ "learning_rate": 1.4033779213637613e-05,
197
+ "loss": 0.5683,
198
+ "r_loss": 0.0,
199
+ "step": 2400,
200
+ "steps": 2400
201
+ },
202
+ {
203
+ "epoch": 0.333,
204
+ "learning_rate": 1.3758964806158922e-05,
205
+ "loss": 0.5654,
206
+ "r_loss": 0.0,
207
+ "step": 2500,
208
+ "steps": 2500
209
+ },
210
+ {
211
+ "epoch": 0.347,
212
+ "learning_rate": 1.3484150398680231e-05,
213
+ "loss": 0.5613,
214
+ "r_loss": 0.0,
215
+ "step": 2600,
216
+ "steps": 2600
217
+ },
218
+ {
219
+ "epoch": 0.36,
220
+ "learning_rate": 1.320933599120154e-05,
221
+ "loss": 0.5604,
222
+ "r_loss": 0.0,
223
+ "step": 2700,
224
+ "steps": 2700
225
+ },
226
+ {
227
+ "epoch": 0.373,
228
+ "learning_rate": 1.2934521583722849e-05,
229
+ "loss": 0.5551,
230
+ "r_loss": 0.0,
231
+ "step": 2800,
232
+ "steps": 2800
233
+ },
234
+ {
235
+ "epoch": 0.387,
236
+ "learning_rate": 1.2659707176244157e-05,
237
+ "loss": 0.5551,
238
+ "r_loss": 0.0,
239
+ "step": 2900,
240
+ "steps": 2900
241
+ },
242
+ {
243
+ "epoch": 0.4,
244
+ "learning_rate": 1.2384892768765467e-05,
245
+ "loss": 0.5574,
246
+ "r_loss": 0.0,
247
+ "step": 3000,
248
+ "steps": 3000
249
+ },
250
+ {
251
+ "epoch": 0.413,
252
+ "learning_rate": 1.2110078361286775e-05,
253
+ "loss": 0.5539,
254
+ "r_loss": 0.0,
255
+ "step": 3100,
256
+ "steps": 3100
257
+ },
258
+ {
259
+ "epoch": 0.427,
260
+ "learning_rate": 1.1835263953808083e-05,
261
+ "loss": 0.5525,
262
+ "r_loss": 0.0,
263
+ "step": 3200,
264
+ "steps": 3200
265
+ },
266
+ {
267
+ "epoch": 0.44,
268
+ "learning_rate": 1.1560449546329393e-05,
269
+ "loss": 0.5503,
270
+ "r_loss": 0.0,
271
+ "step": 3300,
272
+ "steps": 3300
273
+ },
274
+ {
275
+ "epoch": 0.453,
276
+ "learning_rate": 1.12856351388507e-05,
277
+ "loss": 0.5506,
278
+ "r_loss": 0.0,
279
+ "step": 3400,
280
+ "steps": 3400
281
+ },
282
+ {
283
+ "epoch": 0.467,
284
+ "learning_rate": 1.101082073137201e-05,
285
+ "loss": 0.5422,
286
+ "r_loss": 0.0,
287
+ "step": 3500,
288
+ "steps": 3500
289
+ },
290
+ {
291
+ "epoch": 0.48,
292
+ "learning_rate": 1.0736006323893319e-05,
293
+ "loss": 0.5443,
294
+ "r_loss": 0.0,
295
+ "step": 3600,
296
+ "steps": 3600
297
+ },
298
+ {
299
+ "epoch": 0.493,
300
+ "learning_rate": 1.0461191916414627e-05,
301
+ "loss": 0.5422,
302
+ "r_loss": 0.0,
303
+ "step": 3700,
304
+ "steps": 3700
305
+ },
306
+ {
307
+ "epoch": 0.507,
308
+ "learning_rate": 1.0189125653010724e-05,
309
+ "loss": 0.5378,
310
+ "r_loss": 0.0,
311
+ "step": 3800,
312
+ "steps": 3800
313
+ },
314
+ {
315
+ "epoch": 0.52,
316
+ "learning_rate": 9.914311245532032e-06,
317
+ "loss": 0.5401,
318
+ "r_loss": 0.0,
319
+ "step": 3900,
320
+ "steps": 3900
321
+ },
322
+ {
323
+ "epoch": 0.533,
324
+ "learning_rate": 9.63949683805334e-06,
325
+ "loss": 0.538,
326
+ "r_loss": 0.0,
327
+ "step": 4000,
328
+ "steps": 4000
329
+ },
330
+ {
331
+ "epoch": 0.547,
332
+ "learning_rate": 9.36468243057465e-06,
333
+ "loss": 0.5384,
334
+ "r_loss": 0.0,
335
+ "step": 4100,
336
+ "steps": 4100
337
+ },
338
+ {
339
+ "epoch": 0.56,
340
+ "learning_rate": 9.08986802309596e-06,
341
+ "loss": 0.5306,
342
+ "r_loss": 0.0,
343
+ "step": 4200,
344
+ "steps": 4200
345
+ },
346
+ {
347
+ "epoch": 0.573,
348
+ "learning_rate": 8.815053615617266e-06,
349
+ "loss": 0.5317,
350
+ "r_loss": 0.0,
351
+ "step": 4300,
352
+ "steps": 4300
353
+ },
354
+ {
355
+ "epoch": 0.587,
356
+ "learning_rate": 8.540239208138575e-06,
357
+ "loss": 0.5305,
358
+ "r_loss": 0.0,
359
+ "step": 4400,
360
+ "steps": 4400
361
+ },
362
+ {
363
+ "epoch": 0.6,
364
+ "learning_rate": 8.265424800659885e-06,
365
+ "loss": 0.5313,
366
+ "r_loss": 0.0,
367
+ "step": 4500,
368
+ "steps": 4500
369
+ },
370
+ {
371
+ "epoch": 0.613,
372
+ "learning_rate": 7.990610393181193e-06,
373
+ "loss": 0.531,
374
+ "r_loss": 0.0,
375
+ "step": 4600,
376
+ "steps": 4600
377
+ },
378
+ {
379
+ "epoch": 0.627,
380
+ "learning_rate": 7.715795985702503e-06,
381
+ "loss": 0.5285,
382
+ "r_loss": 0.0,
383
+ "step": 4700,
384
+ "steps": 4700
385
+ },
386
+ {
387
+ "epoch": 0.64,
388
+ "learning_rate": 7.440981578223811e-06,
389
+ "loss": 0.5261,
390
+ "r_loss": 0.0,
391
+ "step": 4800,
392
+ "steps": 4800
393
+ },
394
+ {
395
+ "epoch": 0.653,
396
+ "learning_rate": 7.166167170745119e-06,
397
+ "loss": 0.5178,
398
+ "r_loss": 0.0,
399
+ "step": 4900,
400
+ "steps": 4900
401
+ },
402
+ {
403
+ "epoch": 0.667,
404
+ "learning_rate": 6.891352763266428e-06,
405
+ "loss": 0.5199,
406
+ "r_loss": 0.0,
407
+ "step": 5000,
408
+ "steps": 5000
409
+ },
410
+ {
411
+ "epoch": 0.68,
412
+ "learning_rate": 6.616538355787737e-06,
413
+ "loss": 0.5191,
414
+ "r_loss": 0.0,
415
+ "step": 5100,
416
+ "steps": 5100
417
+ },
418
+ {
419
+ "epoch": 0.693,
420
+ "learning_rate": 6.341723948309046e-06,
421
+ "loss": 0.5197,
422
+ "r_loss": 0.0,
423
+ "step": 5200,
424
+ "steps": 5200
425
+ },
426
+ {
427
+ "epoch": 0.707,
428
+ "learning_rate": 6.066909540830355e-06,
429
+ "loss": 0.5172,
430
+ "r_loss": 0.0,
431
+ "step": 5300,
432
+ "steps": 5300
433
+ },
434
+ {
435
+ "epoch": 0.72,
436
+ "learning_rate": 5.792095133351663e-06,
437
+ "loss": 0.5196,
438
+ "r_loss": 0.0,
439
+ "step": 5400,
440
+ "steps": 5400
441
+ },
442
+ {
443
+ "epoch": 0.733,
444
+ "learning_rate": 5.517280725872972e-06,
445
+ "loss": 0.5113,
446
+ "r_loss": 0.0,
447
+ "step": 5500,
448
+ "steps": 5500
449
+ },
450
+ {
451
+ "epoch": 0.747,
452
+ "learning_rate": 5.245214462469068e-06,
453
+ "loss": 0.5123,
454
+ "r_loss": 0.0,
455
+ "step": 5600,
456
+ "steps": 5600
457
+ },
458
+ {
459
+ "epoch": 0.76,
460
+ "learning_rate": 4.973148199065163e-06,
461
+ "loss": 0.513,
462
+ "r_loss": 0.0,
463
+ "step": 5700,
464
+ "steps": 5700
465
+ },
466
+ {
467
+ "epoch": 0.773,
468
+ "learning_rate": 4.698333791586473e-06,
469
+ "loss": 0.5123,
470
+ "r_loss": 0.0,
471
+ "step": 5800,
472
+ "steps": 5800
473
+ },
474
+ {
475
+ "epoch": 0.787,
476
+ "learning_rate": 4.423519384107781e-06,
477
+ "loss": 0.5103,
478
+ "r_loss": 0.0,
479
+ "step": 5900,
480
+ "steps": 5900
481
+ },
482
+ {
483
+ "epoch": 0.8,
484
+ "learning_rate": 4.14870497662909e-06,
485
+ "loss": 0.5086,
486
+ "r_loss": 0.0,
487
+ "step": 6000,
488
+ "steps": 6000
489
+ },
490
+ {
491
+ "epoch": 0.813,
492
+ "learning_rate": 3.876638713225185e-06,
493
+ "loss": 0.5042,
494
+ "r_loss": 0.0,
495
+ "step": 6100,
496
+ "steps": 6100
497
+ },
498
+ {
499
+ "epoch": 0.827,
500
+ "learning_rate": 3.6018243057464943e-06,
501
+ "loss": 0.5042,
502
+ "r_loss": 0.0,
503
+ "step": 6200,
504
+ "steps": 6200
505
+ },
506
+ {
507
+ "epoch": 0.84,
508
+ "learning_rate": 3.3270098982678032e-06,
509
+ "loss": 0.507,
510
+ "r_loss": 0.0,
511
+ "step": 6300,
512
+ "steps": 6300
513
+ },
514
+ {
515
+ "epoch": 0.853,
516
+ "learning_rate": 3.0521954907891117e-06,
517
+ "loss": 0.5014,
518
+ "r_loss": 0.0,
519
+ "step": 6400,
520
+ "steps": 6400
521
+ },
522
+ {
523
+ "epoch": 0.867,
524
+ "learning_rate": 2.7773810833104206e-06,
525
+ "loss": 0.5033,
526
+ "r_loss": 0.0,
527
+ "step": 6500,
528
+ "steps": 6500
529
+ },
530
+ {
531
+ "epoch": 0.88,
532
+ "learning_rate": 2.5025666758317295e-06,
533
+ "loss": 0.4996,
534
+ "r_loss": 0.0,
535
+ "step": 6600,
536
+ "steps": 6600
537
+ },
538
+ {
539
+ "epoch": 0.893,
540
+ "learning_rate": 2.227752268353038e-06,
541
+ "loss": 0.5003,
542
+ "r_loss": 0.0,
543
+ "step": 6700,
544
+ "steps": 6700
545
+ },
546
+ {
547
+ "epoch": 0.907,
548
+ "learning_rate": 1.952937860874347e-06,
549
+ "loss": 0.5008,
550
+ "r_loss": 0.0,
551
+ "step": 6800,
552
+ "steps": 6800
553
+ },
554
+ {
555
+ "epoch": 0.92,
556
+ "learning_rate": 1.6781234533956558e-06,
557
+ "loss": 0.5023,
558
+ "r_loss": 0.0,
559
+ "step": 6900,
560
+ "steps": 6900
561
+ },
562
+ {
563
+ "epoch": 0.933,
564
+ "learning_rate": 1.4033090459169645e-06,
565
+ "loss": 0.497,
566
+ "r_loss": 0.0,
567
+ "step": 7000,
568
+ "steps": 7000
569
+ },
570
+ {
571
+ "epoch": 0.947,
572
+ "learning_rate": 1.1284946384382732e-06,
573
+ "loss": 0.5002,
574
+ "r_loss": 0.0,
575
+ "step": 7100,
576
+ "steps": 7100
577
+ },
578
+ {
579
+ "epoch": 0.96,
580
+ "learning_rate": 8.536802309595821e-07,
581
+ "loss": 0.4972,
582
+ "r_loss": 0.0,
583
+ "step": 7200,
584
+ "steps": 7200
585
+ },
586
+ {
587
+ "epoch": 0.973,
588
+ "learning_rate": 5.788658234808909e-07,
589
+ "loss": 0.5017,
590
+ "r_loss": 0.0,
591
+ "step": 7300,
592
+ "steps": 7300
593
+ },
594
+ {
595
+ "epoch": 0.987,
596
+ "learning_rate": 3.040514160021996e-07,
597
+ "loss": 0.4991,
598
+ "r_loss": 0.0,
599
+ "step": 7400,
600
+ "steps": 7400
601
+ },
602
+ {
603
+ "epoch": 1.0,
604
+ "step": 7499,
605
+ "steps": 7499,
606
+ "total_flos": 1222855706542080.0,
607
+ "train_loss": 0.5490713825319938,
608
+ "train_runtime": 153878.2498,
609
+ "train_samples_per_second": 6.238,
610
+ "train_steps_per_second": 0.049
611
+ }
612
+ ],
613
+ "max_steps": 7499,
614
+ "num_train_epochs": 1,
615
+ "total_flos": 1222855706542080.0,
616
+ "trial_name": null,
617
+ "trial_params": null
618
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce53b39bbc6b71ed3d17275fbb2e5d02d67cf88833514bae0743957f533ae8fa
3
+ size 5499