bradmin commited on
Commit
fb61ef7
1 Parent(s): 69efe12

Training in progress, step 2000, checkpoint

Browse files
checkpoint-2000/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/polyglot-ko-1.3b",
3
+ "architectures": [
4
+ "GPTNeoXForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": 0.1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout": 0.0,
12
+ "hidden_size": 2048,
13
+ "id2label": {
14
+ "0": "LABEL_0"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 8192,
18
+ "label2id": {
19
+ "LABEL_0": 0
20
+ },
21
+ "layer_norm_eps": 1e-05,
22
+ "max_position_embeddings": 2048,
23
+ "model_type": "gpt_neox",
24
+ "num_attention_heads": 16,
25
+ "num_hidden_layers": 24,
26
+ "pad_token_id": 2,
27
+ "rope_scaling": null,
28
+ "rotary_emb_base": 10000,
29
+ "rotary_pct": 0.5,
30
+ "tie_word_embeddings": false,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.34.1",
33
+ "use_cache": true,
34
+ "use_parallel_residual": true,
35
+ "vocab_size": 30080
36
+ }
checkpoint-2000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e434d6fc19246b128dd1e7178baf716d6fb8585961e6843cbd3918d4c6b95b47
3
+ size 10161845830
checkpoint-2000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a728368b4386ceb14c0b8c93aa425c86b2e58bc4adeb6c5b56519a0f03c00c4
3
+ size 5080945162
checkpoint-2000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f909c445bcaf1e4d1c5603e5765be07e306844aef05dbfcdd44caf594ba8a37
3
+ size 14308
checkpoint-2000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c558b86769650e86271377525642b6221562e0c8ff2daa3e887f8994a64cb164
3
+ size 1064
checkpoint-2000/special_tokens_map.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<|sep|>",
5
+ "<|acc|>",
6
+ "<|tel|>",
7
+ "<|rrn|>"
8
+ ],
9
+ "eos_token": "<|endoftext|>",
10
+ "pad_token": "<|endoftext|>"
11
+ }
checkpoint-2000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2000/tokenizer_config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<|unused0|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<|unused1|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<|endoftext|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<|sep|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "30000": {
36
+ "content": "<|acc|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "30001": {
44
+ "content": "<|tel|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "30002": {
52
+ "content": "<|rrn|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ }
59
+ },
60
+ "additional_special_tokens": [
61
+ "<|endoftext|>",
62
+ "<|sep|>",
63
+ "<|acc|>",
64
+ "<|tel|>",
65
+ "<|rrn|>"
66
+ ],
67
+ "clean_up_tokenization_spaces": true,
68
+ "eos_token": "<|endoftext|>",
69
+ "model_max_length": 1000000000000000019884624838656,
70
+ "pad_token": "<|endoftext|>",
71
+ "tokenizer_class": "PreTrainedTokenizerFast"
72
+ }
checkpoint-2000/trainer_state.json ADDED
@@ -0,0 +1,1255 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.2851602600661572,
5
+ "eval_steps": 500,
6
+ "global_step": 2000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "learning_rate": 8.999954848325688e-06,
14
+ "loss": 0.7277,
15
+ "step": 10
16
+ },
17
+ {
18
+ "epoch": 0.0,
19
+ "learning_rate": 8.999819394208827e-06,
20
+ "loss": 0.6455,
21
+ "step": 20
22
+ },
23
+ {
24
+ "epoch": 0.0,
25
+ "learning_rate": 8.999593640367633e-06,
26
+ "loss": 0.5428,
27
+ "step": 30
28
+ },
29
+ {
30
+ "epoch": 0.01,
31
+ "learning_rate": 8.9992775913324e-06,
32
+ "loss": 0.3486,
33
+ "step": 40
34
+ },
35
+ {
36
+ "epoch": 0.01,
37
+ "learning_rate": 8.998871253445414e-06,
38
+ "loss": 0.3524,
39
+ "step": 50
40
+ },
41
+ {
42
+ "epoch": 0.01,
43
+ "learning_rate": 8.998374634860822e-06,
44
+ "loss": 0.2701,
45
+ "step": 60
46
+ },
47
+ {
48
+ "epoch": 0.01,
49
+ "learning_rate": 8.997787745544478e-06,
50
+ "loss": 0.2106,
51
+ "step": 70
52
+ },
53
+ {
54
+ "epoch": 0.01,
55
+ "learning_rate": 8.997110597273727e-06,
56
+ "loss": 0.2596,
57
+ "step": 80
58
+ },
59
+ {
60
+ "epoch": 0.01,
61
+ "learning_rate": 8.996343203637181e-06,
62
+ "loss": 0.2015,
63
+ "step": 90
64
+ },
65
+ {
66
+ "epoch": 0.01,
67
+ "learning_rate": 8.995485580034448e-06,
68
+ "loss": 0.2462,
69
+ "step": 100
70
+ },
71
+ {
72
+ "epoch": 0.02,
73
+ "learning_rate": 8.99453774367581e-06,
74
+ "loss": 0.2172,
75
+ "step": 110
76
+ },
77
+ {
78
+ "epoch": 0.02,
79
+ "learning_rate": 8.993499713581887e-06,
80
+ "loss": 0.2655,
81
+ "step": 120
82
+ },
83
+ {
84
+ "epoch": 0.02,
85
+ "learning_rate": 8.992371510583257e-06,
86
+ "loss": 0.1823,
87
+ "step": 130
88
+ },
89
+ {
90
+ "epoch": 0.02,
91
+ "learning_rate": 8.991153157320033e-06,
92
+ "loss": 0.227,
93
+ "step": 140
94
+ },
95
+ {
96
+ "epoch": 0.02,
97
+ "learning_rate": 8.989844678241412e-06,
98
+ "loss": 0.2243,
99
+ "step": 150
100
+ },
101
+ {
102
+ "epoch": 0.02,
103
+ "learning_rate": 8.988446099605179e-06,
104
+ "loss": 0.1787,
105
+ "step": 160
106
+ },
107
+ {
108
+ "epoch": 0.02,
109
+ "learning_rate": 8.986957449477188e-06,
110
+ "loss": 0.2211,
111
+ "step": 170
112
+ },
113
+ {
114
+ "epoch": 0.03,
115
+ "learning_rate": 8.98537875773079e-06,
116
+ "loss": 0.1683,
117
+ "step": 180
118
+ },
119
+ {
120
+ "epoch": 0.03,
121
+ "learning_rate": 8.983710056046243e-06,
122
+ "loss": 0.1879,
123
+ "step": 190
124
+ },
125
+ {
126
+ "epoch": 0.03,
127
+ "learning_rate": 8.98195137791007e-06,
128
+ "loss": 0.1809,
129
+ "step": 200
130
+ },
131
+ {
132
+ "epoch": 0.03,
133
+ "learning_rate": 8.980102758614384e-06,
134
+ "loss": 0.2204,
135
+ "step": 210
136
+ },
137
+ {
138
+ "epoch": 0.03,
139
+ "learning_rate": 8.978164235256191e-06,
140
+ "loss": 0.189,
141
+ "step": 220
142
+ },
143
+ {
144
+ "epoch": 0.03,
145
+ "learning_rate": 8.976135846736634e-06,
146
+ "loss": 0.1389,
147
+ "step": 230
148
+ },
149
+ {
150
+ "epoch": 0.03,
151
+ "learning_rate": 8.97401763376022e-06,
152
+ "loss": 0.1231,
153
+ "step": 240
154
+ },
155
+ {
156
+ "epoch": 0.04,
157
+ "learning_rate": 8.971809638833998e-06,
158
+ "loss": 0.2018,
159
+ "step": 250
160
+ },
161
+ {
162
+ "epoch": 0.04,
163
+ "learning_rate": 8.96951190626671e-06,
164
+ "loss": 0.1271,
165
+ "step": 260
166
+ },
167
+ {
168
+ "epoch": 0.04,
169
+ "learning_rate": 8.967124482167896e-06,
170
+ "loss": 0.1364,
171
+ "step": 270
172
+ },
173
+ {
174
+ "epoch": 0.04,
175
+ "learning_rate": 8.964647414446981e-06,
176
+ "loss": 0.1658,
177
+ "step": 280
178
+ },
179
+ {
180
+ "epoch": 0.04,
181
+ "learning_rate": 8.9620807528123e-06,
182
+ "loss": 0.1479,
183
+ "step": 290
184
+ },
185
+ {
186
+ "epoch": 0.04,
187
+ "learning_rate": 8.959424548770104e-06,
188
+ "loss": 0.1353,
189
+ "step": 300
190
+ },
191
+ {
192
+ "epoch": 0.04,
193
+ "learning_rate": 8.95667885562353e-06,
194
+ "loss": 0.1761,
195
+ "step": 310
196
+ },
197
+ {
198
+ "epoch": 0.05,
199
+ "learning_rate": 8.953843728471533e-06,
200
+ "loss": 0.1391,
201
+ "step": 320
202
+ },
203
+ {
204
+ "epoch": 0.05,
205
+ "learning_rate": 8.950919224207774e-06,
206
+ "loss": 0.1776,
207
+ "step": 330
208
+ },
209
+ {
210
+ "epoch": 0.05,
211
+ "learning_rate": 8.94790540151948e-06,
212
+ "loss": 0.2089,
213
+ "step": 340
214
+ },
215
+ {
216
+ "epoch": 0.05,
217
+ "learning_rate": 8.94480232088627e-06,
218
+ "loss": 0.1368,
219
+ "step": 350
220
+ },
221
+ {
222
+ "epoch": 0.05,
223
+ "learning_rate": 8.941610044578937e-06,
224
+ "loss": 0.1501,
225
+ "step": 360
226
+ },
227
+ {
228
+ "epoch": 0.05,
229
+ "learning_rate": 8.938328636658202e-06,
230
+ "loss": 0.1807,
231
+ "step": 370
232
+ },
233
+ {
234
+ "epoch": 0.05,
235
+ "learning_rate": 8.934958162973425e-06,
236
+ "loss": 0.13,
237
+ "step": 380
238
+ },
239
+ {
240
+ "epoch": 0.06,
241
+ "learning_rate": 8.931498691161287e-06,
242
+ "loss": 0.1437,
243
+ "step": 390
244
+ },
245
+ {
246
+ "epoch": 0.06,
247
+ "learning_rate": 8.92795029064443e-06,
248
+ "loss": 0.0828,
249
+ "step": 400
250
+ },
251
+ {
252
+ "epoch": 0.06,
253
+ "learning_rate": 8.924313032630063e-06,
254
+ "loss": 0.1041,
255
+ "step": 410
256
+ },
257
+ {
258
+ "epoch": 0.06,
259
+ "learning_rate": 8.920586990108539e-06,
260
+ "loss": 0.2663,
261
+ "step": 420
262
+ },
263
+ {
264
+ "epoch": 0.06,
265
+ "learning_rate": 8.916772237851882e-06,
266
+ "loss": 0.2055,
267
+ "step": 430
268
+ },
269
+ {
270
+ "epoch": 0.06,
271
+ "learning_rate": 8.912868852412294e-06,
272
+ "loss": 0.151,
273
+ "step": 440
274
+ },
275
+ {
276
+ "epoch": 0.06,
277
+ "learning_rate": 8.908876912120614e-06,
278
+ "loss": 0.1638,
279
+ "step": 450
280
+ },
281
+ {
282
+ "epoch": 0.07,
283
+ "learning_rate": 8.904796497084747e-06,
284
+ "loss": 0.1399,
285
+ "step": 460
286
+ },
287
+ {
288
+ "epoch": 0.07,
289
+ "learning_rate": 8.900627689188059e-06,
290
+ "loss": 0.1615,
291
+ "step": 470
292
+ },
293
+ {
294
+ "epoch": 0.07,
295
+ "learning_rate": 8.89637057208773e-06,
296
+ "loss": 0.1209,
297
+ "step": 480
298
+ },
299
+ {
300
+ "epoch": 0.07,
301
+ "learning_rate": 8.892025231213077e-06,
302
+ "loss": 0.1605,
303
+ "step": 490
304
+ },
305
+ {
306
+ "epoch": 0.07,
307
+ "learning_rate": 8.887591753763842e-06,
308
+ "loss": 0.124,
309
+ "step": 500
310
+ },
311
+ {
312
+ "epoch": 0.07,
313
+ "eval_accuracy": 0.0,
314
+ "eval_loss": 0.13451002538204193,
315
+ "eval_runtime": 446.6893,
316
+ "eval_samples_per_second": 52.338,
317
+ "eval_steps_per_second": 8.724,
318
+ "step": 500
319
+ },
320
+ {
321
+ "epoch": 0.07,
322
+ "learning_rate": 8.883070228708436e-06,
323
+ "loss": 0.1045,
324
+ "step": 510
325
+ },
326
+ {
327
+ "epoch": 0.07,
328
+ "learning_rate": 8.878460746782163e-06,
329
+ "loss": 0.2208,
330
+ "step": 520
331
+ },
332
+ {
333
+ "epoch": 0.08,
334
+ "learning_rate": 8.873763400485387e-06,
335
+ "loss": 0.1483,
336
+ "step": 530
337
+ },
338
+ {
339
+ "epoch": 0.08,
340
+ "learning_rate": 8.868978284081688e-06,
341
+ "loss": 0.1322,
342
+ "step": 540
343
+ },
344
+ {
345
+ "epoch": 0.08,
346
+ "learning_rate": 8.864105493595962e-06,
347
+ "loss": 0.1227,
348
+ "step": 550
349
+ },
350
+ {
351
+ "epoch": 0.08,
352
+ "learning_rate": 8.859145126812497e-06,
353
+ "loss": 0.1371,
354
+ "step": 560
355
+ },
356
+ {
357
+ "epoch": 0.08,
358
+ "learning_rate": 8.854097283273012e-06,
359
+ "loss": 0.1909,
360
+ "step": 570
361
+ },
362
+ {
363
+ "epoch": 0.08,
364
+ "learning_rate": 8.848962064274655e-06,
365
+ "loss": 0.0993,
366
+ "step": 580
367
+ },
368
+ {
369
+ "epoch": 0.08,
370
+ "learning_rate": 8.843739572867977e-06,
371
+ "loss": 0.1053,
372
+ "step": 590
373
+ },
374
+ {
375
+ "epoch": 0.09,
376
+ "learning_rate": 8.838429913854859e-06,
377
+ "loss": 0.1401,
378
+ "step": 600
379
+ },
380
+ {
381
+ "epoch": 0.09,
382
+ "learning_rate": 8.83303319378641e-06,
383
+ "loss": 0.09,
384
+ "step": 610
385
+ },
386
+ {
387
+ "epoch": 0.09,
388
+ "learning_rate": 8.827549520960827e-06,
389
+ "loss": 0.1667,
390
+ "step": 620
391
+ },
392
+ {
393
+ "epoch": 0.09,
394
+ "learning_rate": 8.821979005421223e-06,
395
+ "loss": 0.1069,
396
+ "step": 630
397
+ },
398
+ {
399
+ "epoch": 0.09,
400
+ "learning_rate": 8.816321758953426e-06,
401
+ "loss": 0.1659,
402
+ "step": 640
403
+ },
404
+ {
405
+ "epoch": 0.09,
406
+ "learning_rate": 8.810577895083726e-06,
407
+ "loss": 0.1309,
408
+ "step": 650
409
+ },
410
+ {
411
+ "epoch": 0.09,
412
+ "learning_rate": 8.804747529076592e-06,
413
+ "loss": 0.16,
414
+ "step": 660
415
+ },
416
+ {
417
+ "epoch": 0.1,
418
+ "learning_rate": 8.79883077793238e-06,
419
+ "loss": 0.1041,
420
+ "step": 670
421
+ },
422
+ {
423
+ "epoch": 0.1,
424
+ "learning_rate": 8.792827760384965e-06,
425
+ "loss": 0.1344,
426
+ "step": 680
427
+ },
428
+ {
429
+ "epoch": 0.1,
430
+ "learning_rate": 8.786738596899362e-06,
431
+ "loss": 0.0922,
432
+ "step": 690
433
+ },
434
+ {
435
+ "epoch": 0.1,
436
+ "learning_rate": 8.780563409669322e-06,
437
+ "loss": 0.0813,
438
+ "step": 700
439
+ },
440
+ {
441
+ "epoch": 0.1,
442
+ "learning_rate": 8.774302322614858e-06,
443
+ "loss": 0.1795,
444
+ "step": 710
445
+ },
446
+ {
447
+ "epoch": 0.1,
448
+ "learning_rate": 8.767955461379783e-06,
449
+ "loss": 0.1409,
450
+ "step": 720
451
+ },
452
+ {
453
+ "epoch": 0.1,
454
+ "learning_rate": 8.761522953329163e-06,
455
+ "loss": 0.1362,
456
+ "step": 730
457
+ },
458
+ {
459
+ "epoch": 0.11,
460
+ "learning_rate": 8.75500492754678e-06,
461
+ "loss": 0.1227,
462
+ "step": 740
463
+ },
464
+ {
465
+ "epoch": 0.11,
466
+ "learning_rate": 8.74840151483254e-06,
467
+ "loss": 0.0643,
468
+ "step": 750
469
+ },
470
+ {
471
+ "epoch": 0.11,
472
+ "learning_rate": 8.741712847699832e-06,
473
+ "loss": 0.1895,
474
+ "step": 760
475
+ },
476
+ {
477
+ "epoch": 0.11,
478
+ "learning_rate": 8.734939060372892e-06,
479
+ "loss": 0.0959,
480
+ "step": 770
481
+ },
482
+ {
483
+ "epoch": 0.11,
484
+ "learning_rate": 8.72808028878409e-06,
485
+ "loss": 0.1089,
486
+ "step": 780
487
+ },
488
+ {
489
+ "epoch": 0.11,
490
+ "learning_rate": 8.721136670571216e-06,
491
+ "loss": 0.0959,
492
+ "step": 790
493
+ },
494
+ {
495
+ "epoch": 0.11,
496
+ "learning_rate": 8.714108345074704e-06,
497
+ "loss": 0.1264,
498
+ "step": 800
499
+ },
500
+ {
501
+ "epoch": 0.12,
502
+ "learning_rate": 8.706995453334855e-06,
503
+ "loss": 0.1078,
504
+ "step": 810
505
+ },
506
+ {
507
+ "epoch": 0.12,
508
+ "learning_rate": 8.699798138088988e-06,
509
+ "loss": 0.1278,
510
+ "step": 820
511
+ },
512
+ {
513
+ "epoch": 0.12,
514
+ "learning_rate": 8.692516543768581e-06,
515
+ "loss": 0.1337,
516
+ "step": 830
517
+ },
518
+ {
519
+ "epoch": 0.12,
520
+ "learning_rate": 8.685150816496384e-06,
521
+ "loss": 0.0815,
522
+ "step": 840
523
+ },
524
+ {
525
+ "epoch": 0.12,
526
+ "learning_rate": 8.677701104083467e-06,
527
+ "loss": 0.1033,
528
+ "step": 850
529
+ },
530
+ {
531
+ "epoch": 0.12,
532
+ "learning_rate": 8.670167556026274e-06,
533
+ "loss": 0.1412,
534
+ "step": 860
535
+ },
536
+ {
537
+ "epoch": 0.12,
538
+ "learning_rate": 8.662550323503606e-06,
539
+ "loss": 0.197,
540
+ "step": 870
541
+ },
542
+ {
543
+ "epoch": 0.13,
544
+ "learning_rate": 8.654849559373595e-06,
545
+ "loss": 0.1118,
546
+ "step": 880
547
+ },
548
+ {
549
+ "epoch": 0.13,
550
+ "learning_rate": 8.647065418170644e-06,
551
+ "loss": 0.1132,
552
+ "step": 890
553
+ },
554
+ {
555
+ "epoch": 0.13,
556
+ "learning_rate": 8.639198056102309e-06,
557
+ "loss": 0.0928,
558
+ "step": 900
559
+ },
560
+ {
561
+ "epoch": 0.13,
562
+ "learning_rate": 8.631247631046176e-06,
563
+ "loss": 0.0723,
564
+ "step": 910
565
+ },
566
+ {
567
+ "epoch": 0.13,
568
+ "learning_rate": 8.623214302546691e-06,
569
+ "loss": 0.126,
570
+ "step": 920
571
+ },
572
+ {
573
+ "epoch": 0.13,
574
+ "learning_rate": 8.615098231811958e-06,
575
+ "loss": 0.1363,
576
+ "step": 930
577
+ },
578
+ {
579
+ "epoch": 0.13,
580
+ "learning_rate": 8.606899581710505e-06,
581
+ "loss": 0.1243,
582
+ "step": 940
583
+ },
584
+ {
585
+ "epoch": 0.14,
586
+ "learning_rate": 8.598618516768005e-06,
587
+ "loss": 0.0382,
588
+ "step": 950
589
+ },
590
+ {
591
+ "epoch": 0.14,
592
+ "learning_rate": 8.590255203163995e-06,
593
+ "loss": 0.1295,
594
+ "step": 960
595
+ },
596
+ {
597
+ "epoch": 0.14,
598
+ "learning_rate": 8.581809808728524e-06,
599
+ "loss": 0.1145,
600
+ "step": 970
601
+ },
602
+ {
603
+ "epoch": 0.14,
604
+ "learning_rate": 8.573282502938791e-06,
605
+ "loss": 0.0915,
606
+ "step": 980
607
+ },
608
+ {
609
+ "epoch": 0.14,
610
+ "learning_rate": 8.564673456915746e-06,
611
+ "loss": 0.1918,
612
+ "step": 990
613
+ },
614
+ {
615
+ "epoch": 0.14,
616
+ "learning_rate": 8.55598284342065e-06,
617
+ "loss": 0.1732,
618
+ "step": 1000
619
+ },
620
+ {
621
+ "epoch": 0.14,
622
+ "eval_accuracy": 0.0,
623
+ "eval_loss": 0.12965914607048035,
624
+ "eval_runtime": 448.5256,
625
+ "eval_samples_per_second": 52.124,
626
+ "eval_steps_per_second": 8.688,
627
+ "step": 1000
628
+ },
629
+ {
630
+ "epoch": 0.14,
631
+ "learning_rate": 8.547210836851614e-06,
632
+ "loss": 0.0833,
633
+ "step": 1010
634
+ },
635
+ {
636
+ "epoch": 0.15,
637
+ "learning_rate": 8.538357613240099e-06,
638
+ "loss": 0.1597,
639
+ "step": 1020
640
+ },
641
+ {
642
+ "epoch": 0.15,
643
+ "learning_rate": 8.52942335024738e-06,
644
+ "loss": 0.1041,
645
+ "step": 1030
646
+ },
647
+ {
648
+ "epoch": 0.15,
649
+ "learning_rate": 8.520408227160983e-06,
650
+ "loss": 0.1819,
651
+ "step": 1040
652
+ },
653
+ {
654
+ "epoch": 0.15,
655
+ "learning_rate": 8.511312424891083e-06,
656
+ "loss": 0.1112,
657
+ "step": 1050
658
+ },
659
+ {
660
+ "epoch": 0.15,
661
+ "learning_rate": 8.502136125966886e-06,
662
+ "loss": 0.1372,
663
+ "step": 1060
664
+ },
665
+ {
666
+ "epoch": 0.15,
667
+ "learning_rate": 8.49287951453295e-06,
668
+ "loss": 0.1596,
669
+ "step": 1070
670
+ },
671
+ {
672
+ "epoch": 0.15,
673
+ "learning_rate": 8.483542776345496e-06,
674
+ "loss": 0.1558,
675
+ "step": 1080
676
+ },
677
+ {
678
+ "epoch": 0.16,
679
+ "learning_rate": 8.47412609876869e-06,
680
+ "loss": 0.069,
681
+ "step": 1090
682
+ },
683
+ {
684
+ "epoch": 0.16,
685
+ "learning_rate": 8.464629670770866e-06,
686
+ "loss": 0.1468,
687
+ "step": 1100
688
+ },
689
+ {
690
+ "epoch": 0.16,
691
+ "learning_rate": 8.455053682920747e-06,
692
+ "loss": 0.106,
693
+ "step": 1110
694
+ },
695
+ {
696
+ "epoch": 0.16,
697
+ "learning_rate": 8.445398327383616e-06,
698
+ "loss": 0.1562,
699
+ "step": 1120
700
+ },
701
+ {
702
+ "epoch": 0.16,
703
+ "learning_rate": 8.435663797917459e-06,
704
+ "loss": 0.1404,
705
+ "step": 1130
706
+ },
707
+ {
708
+ "epoch": 0.16,
709
+ "learning_rate": 8.425850289869074e-06,
710
+ "loss": 0.1198,
711
+ "step": 1140
712
+ },
713
+ {
714
+ "epoch": 0.16,
715
+ "learning_rate": 8.415958000170163e-06,
716
+ "loss": 0.107,
717
+ "step": 1150
718
+ },
719
+ {
720
+ "epoch": 0.17,
721
+ "learning_rate": 8.405987127333367e-06,
722
+ "loss": 0.0911,
723
+ "step": 1160
724
+ },
725
+ {
726
+ "epoch": 0.17,
727
+ "learning_rate": 8.395937871448282e-06,
728
+ "loss": 0.066,
729
+ "step": 1170
730
+ },
731
+ {
732
+ "epoch": 0.17,
733
+ "learning_rate": 8.385810434177462e-06,
734
+ "loss": 0.0988,
735
+ "step": 1180
736
+ },
737
+ {
738
+ "epoch": 0.17,
739
+ "learning_rate": 8.375605018752344e-06,
740
+ "loss": 0.1648,
741
+ "step": 1190
742
+ },
743
+ {
744
+ "epoch": 0.17,
745
+ "learning_rate": 8.365321829969196e-06,
746
+ "loss": 0.1124,
747
+ "step": 1200
748
+ },
749
+ {
750
+ "epoch": 0.17,
751
+ "learning_rate": 8.35496107418499e-06,
752
+ "loss": 0.1251,
753
+ "step": 1210
754
+ },
755
+ {
756
+ "epoch": 0.17,
757
+ "learning_rate": 8.34452295931327e-06,
758
+ "loss": 0.1167,
759
+ "step": 1220
760
+ },
761
+ {
762
+ "epoch": 0.18,
763
+ "learning_rate": 8.334007694819972e-06,
764
+ "loss": 0.1238,
765
+ "step": 1230
766
+ },
767
+ {
768
+ "epoch": 0.18,
769
+ "learning_rate": 8.323415491719233e-06,
770
+ "loss": 0.1127,
771
+ "step": 1240
772
+ },
773
+ {
774
+ "epoch": 0.18,
775
+ "learning_rate": 8.312746562569141e-06,
776
+ "loss": 0.0823,
777
+ "step": 1250
778
+ },
779
+ {
780
+ "epoch": 0.18,
781
+ "learning_rate": 8.302001121467481e-06,
782
+ "loss": 0.145,
783
+ "step": 1260
784
+ },
785
+ {
786
+ "epoch": 0.18,
787
+ "learning_rate": 8.291179384047432e-06,
788
+ "loss": 0.1257,
789
+ "step": 1270
790
+ },
791
+ {
792
+ "epoch": 0.18,
793
+ "learning_rate": 8.280281567473247e-06,
794
+ "loss": 0.1014,
795
+ "step": 1280
796
+ },
797
+ {
798
+ "epoch": 0.18,
799
+ "learning_rate": 8.269307890435886e-06,
800
+ "loss": 0.1289,
801
+ "step": 1290
802
+ },
803
+ {
804
+ "epoch": 0.19,
805
+ "learning_rate": 8.258258573148637e-06,
806
+ "loss": 0.104,
807
+ "step": 1300
808
+ },
809
+ {
810
+ "epoch": 0.19,
811
+ "learning_rate": 8.247133837342685e-06,
812
+ "loss": 0.1231,
813
+ "step": 1310
814
+ },
815
+ {
816
+ "epoch": 0.19,
817
+ "learning_rate": 8.235933906262679e-06,
818
+ "loss": 0.1594,
819
+ "step": 1320
820
+ },
821
+ {
822
+ "epoch": 0.19,
823
+ "learning_rate": 8.22465900466223e-06,
824
+ "loss": 0.0999,
825
+ "step": 1330
826
+ },
827
+ {
828
+ "epoch": 0.19,
829
+ "learning_rate": 8.213309358799427e-06,
830
+ "loss": 0.061,
831
+ "step": 1340
832
+ },
833
+ {
834
+ "epoch": 0.19,
835
+ "learning_rate": 8.201885196432273e-06,
836
+ "loss": 0.0618,
837
+ "step": 1350
838
+ },
839
+ {
840
+ "epoch": 0.19,
841
+ "learning_rate": 8.190386746814125e-06,
842
+ "loss": 0.1607,
843
+ "step": 1360
844
+ },
845
+ {
846
+ "epoch": 0.2,
847
+ "learning_rate": 8.1788142406891e-06,
848
+ "loss": 0.0726,
849
+ "step": 1370
850
+ },
851
+ {
852
+ "epoch": 0.2,
853
+ "learning_rate": 8.167167910287428e-06,
854
+ "loss": 0.0594,
855
+ "step": 1380
856
+ },
857
+ {
858
+ "epoch": 0.2,
859
+ "learning_rate": 8.155447989320808e-06,
860
+ "loss": 0.1341,
861
+ "step": 1390
862
+ },
863
+ {
864
+ "epoch": 0.2,
865
+ "learning_rate": 8.14365471297771e-06,
866
+ "loss": 0.1253,
867
+ "step": 1400
868
+ },
869
+ {
870
+ "epoch": 0.2,
871
+ "learning_rate": 8.131788317918651e-06,
872
+ "loss": 0.0865,
873
+ "step": 1410
874
+ },
875
+ {
876
+ "epoch": 0.2,
877
+ "learning_rate": 8.119849042271458e-06,
878
+ "loss": 0.1227,
879
+ "step": 1420
880
+ },
881
+ {
882
+ "epoch": 0.2,
883
+ "learning_rate": 8.10783712562648e-06,
884
+ "loss": 0.1024,
885
+ "step": 1430
886
+ },
887
+ {
888
+ "epoch": 0.21,
889
+ "learning_rate": 8.095752809031783e-06,
890
+ "loss": 0.1495,
891
+ "step": 1440
892
+ },
893
+ {
894
+ "epoch": 0.21,
895
+ "learning_rate": 8.083596334988313e-06,
896
+ "loss": 0.1098,
897
+ "step": 1450
898
+ },
899
+ {
900
+ "epoch": 0.21,
901
+ "learning_rate": 8.071367947445025e-06,
902
+ "loss": 0.1044,
903
+ "step": 1460
904
+ },
905
+ {
906
+ "epoch": 0.21,
907
+ "learning_rate": 8.059067891794002e-06,
908
+ "loss": 0.0757,
909
+ "step": 1470
910
+ },
911
+ {
912
+ "epoch": 0.21,
913
+ "learning_rate": 8.046696414865507e-06,
914
+ "loss": 0.0991,
915
+ "step": 1480
916
+ },
917
+ {
918
+ "epoch": 0.21,
919
+ "learning_rate": 8.034253764923052e-06,
920
+ "loss": 0.141,
921
+ "step": 1490
922
+ },
923
+ {
924
+ "epoch": 0.21,
925
+ "learning_rate": 8.021740191658405e-06,
926
+ "loss": 0.1023,
927
+ "step": 1500
928
+ },
929
+ {
930
+ "epoch": 0.21,
931
+ "eval_accuracy": 0.0,
932
+ "eval_loss": 0.11160164326429367,
933
+ "eval_runtime": 448.3846,
934
+ "eval_samples_per_second": 52.141,
935
+ "eval_steps_per_second": 8.691,
936
+ "step": 1500
937
+ },
938
+ {
939
+ "epoch": 0.22,
940
+ "learning_rate": 8.009155946186583e-06,
941
+ "loss": 0.0782,
942
+ "step": 1510
943
+ },
944
+ {
945
+ "epoch": 0.22,
946
+ "learning_rate": 7.996501281040809e-06,
947
+ "loss": 0.1132,
948
+ "step": 1520
949
+ },
950
+ {
951
+ "epoch": 0.22,
952
+ "learning_rate": 7.983776450167446e-06,
953
+ "loss": 0.042,
954
+ "step": 1530
955
+ },
956
+ {
957
+ "epoch": 0.22,
958
+ "learning_rate": 7.970981708920902e-06,
959
+ "loss": 0.0896,
960
+ "step": 1540
961
+ },
962
+ {
963
+ "epoch": 0.22,
964
+ "learning_rate": 7.958117314058508e-06,
965
+ "loss": 0.1038,
966
+ "step": 1550
967
+ },
968
+ {
969
+ "epoch": 0.22,
970
+ "learning_rate": 7.945183523735359e-06,
971
+ "loss": 0.052,
972
+ "step": 1560
973
+ },
974
+ {
975
+ "epoch": 0.22,
976
+ "learning_rate": 7.932180597499137e-06,
977
+ "loss": 0.1224,
978
+ "step": 1570
979
+ },
980
+ {
981
+ "epoch": 0.23,
982
+ "learning_rate": 7.919108796284908e-06,
983
+ "loss": 0.1473,
984
+ "step": 1580
985
+ },
986
+ {
987
+ "epoch": 0.23,
988
+ "learning_rate": 7.905968382409874e-06,
989
+ "loss": 0.1499,
990
+ "step": 1590
991
+ },
992
+ {
993
+ "epoch": 0.23,
994
+ "learning_rate": 7.89275961956812e-06,
995
+ "loss": 0.0728,
996
+ "step": 1600
997
+ },
998
+ {
999
+ "epoch": 0.23,
1000
+ "learning_rate": 7.879482772825316e-06,
1001
+ "loss": 0.1159,
1002
+ "step": 1610
1003
+ },
1004
+ {
1005
+ "epoch": 0.23,
1006
+ "learning_rate": 7.8661381086134e-06,
1007
+ "loss": 0.1409,
1008
+ "step": 1620
1009
+ },
1010
+ {
1011
+ "epoch": 0.23,
1012
+ "learning_rate": 7.85272589472523e-06,
1013
+ "loss": 0.1065,
1014
+ "step": 1630
1015
+ },
1016
+ {
1017
+ "epoch": 0.23,
1018
+ "learning_rate": 7.839246400309213e-06,
1019
+ "loss": 0.1386,
1020
+ "step": 1640
1021
+ },
1022
+ {
1023
+ "epoch": 0.24,
1024
+ "learning_rate": 7.8256998958639e-06,
1025
+ "loss": 0.0995,
1026
+ "step": 1650
1027
+ },
1028
+ {
1029
+ "epoch": 0.24,
1030
+ "learning_rate": 7.812086653232559e-06,
1031
+ "loss": 0.0947,
1032
+ "step": 1660
1033
+ },
1034
+ {
1035
+ "epoch": 0.24,
1036
+ "learning_rate": 7.798406945597726e-06,
1037
+ "loss": 0.1507,
1038
+ "step": 1670
1039
+ },
1040
+ {
1041
+ "epoch": 0.24,
1042
+ "learning_rate": 7.784661047475712e-06,
1043
+ "loss": 0.0693,
1044
+ "step": 1680
1045
+ },
1046
+ {
1047
+ "epoch": 0.24,
1048
+ "learning_rate": 7.7708492347111e-06,
1049
+ "loss": 0.1194,
1050
+ "step": 1690
1051
+ },
1052
+ {
1053
+ "epoch": 0.24,
1054
+ "learning_rate": 7.756971784471213e-06,
1055
+ "loss": 0.1297,
1056
+ "step": 1700
1057
+ },
1058
+ {
1059
+ "epoch": 0.24,
1060
+ "learning_rate": 7.743028975240545e-06,
1061
+ "loss": 0.0933,
1062
+ "step": 1710
1063
+ },
1064
+ {
1065
+ "epoch": 0.25,
1066
+ "learning_rate": 7.729021086815177e-06,
1067
+ "loss": 0.1029,
1068
+ "step": 1720
1069
+ },
1070
+ {
1071
+ "epoch": 0.25,
1072
+ "learning_rate": 7.71494840029716e-06,
1073
+ "loss": 0.0572,
1074
+ "step": 1730
1075
+ },
1076
+ {
1077
+ "epoch": 0.25,
1078
+ "learning_rate": 7.700811198088876e-06,
1079
+ "loss": 0.0754,
1080
+ "step": 1740
1081
+ },
1082
+ {
1083
+ "epoch": 0.25,
1084
+ "learning_rate": 7.68660976388737e-06,
1085
+ "loss": 0.0957,
1086
+ "step": 1750
1087
+ },
1088
+ {
1089
+ "epoch": 0.25,
1090
+ "learning_rate": 7.672344382678653e-06,
1091
+ "loss": 0.1321,
1092
+ "step": 1760
1093
+ },
1094
+ {
1095
+ "epoch": 0.25,
1096
+ "learning_rate": 7.658015340731994e-06,
1097
+ "loss": 0.0711,
1098
+ "step": 1770
1099
+ },
1100
+ {
1101
+ "epoch": 0.25,
1102
+ "learning_rate": 7.643622925594161e-06,
1103
+ "loss": 0.1211,
1104
+ "step": 1780
1105
+ },
1106
+ {
1107
+ "epoch": 0.26,
1108
+ "learning_rate": 7.629167426083665e-06,
1109
+ "loss": 0.0726,
1110
+ "step": 1790
1111
+ },
1112
+ {
1113
+ "epoch": 0.26,
1114
+ "learning_rate": 7.614649132284948e-06,
1115
+ "loss": 0.0481,
1116
+ "step": 1800
1117
+ },
1118
+ {
1119
+ "epoch": 0.26,
1120
+ "learning_rate": 7.600068335542579e-06,
1121
+ "loss": 0.1569,
1122
+ "step": 1810
1123
+ },
1124
+ {
1125
+ "epoch": 0.26,
1126
+ "learning_rate": 7.585425328455395e-06,
1127
+ "loss": 0.046,
1128
+ "step": 1820
1129
+ },
1130
+ {
1131
+ "epoch": 0.26,
1132
+ "learning_rate": 7.5707204048706365e-06,
1133
+ "loss": 0.0909,
1134
+ "step": 1830
1135
+ },
1136
+ {
1137
+ "epoch": 0.26,
1138
+ "learning_rate": 7.5559538598780434e-06,
1139
+ "loss": 0.1273,
1140
+ "step": 1840
1141
+ },
1142
+ {
1143
+ "epoch": 0.26,
1144
+ "learning_rate": 7.541125989803943e-06,
1145
+ "loss": 0.0636,
1146
+ "step": 1850
1147
+ },
1148
+ {
1149
+ "epoch": 0.27,
1150
+ "learning_rate": 7.526237092205292e-06,
1151
+ "loss": 0.1124,
1152
+ "step": 1860
1153
+ },
1154
+ {
1155
+ "epoch": 0.27,
1156
+ "learning_rate": 7.511287465863719e-06,
1157
+ "loss": 0.1033,
1158
+ "step": 1870
1159
+ },
1160
+ {
1161
+ "epoch": 0.27,
1162
+ "learning_rate": 7.496277410779513e-06,
1163
+ "loss": 0.1055,
1164
+ "step": 1880
1165
+ },
1166
+ {
1167
+ "epoch": 0.27,
1168
+ "learning_rate": 7.481207228165619e-06,
1169
+ "loss": 0.0778,
1170
+ "step": 1890
1171
+ },
1172
+ {
1173
+ "epoch": 0.27,
1174
+ "learning_rate": 7.466077220441581e-06,
1175
+ "loss": 0.0965,
1176
+ "step": 1900
1177
+ },
1178
+ {
1179
+ "epoch": 0.27,
1180
+ "learning_rate": 7.45088769122748e-06,
1181
+ "loss": 0.0561,
1182
+ "step": 1910
1183
+ },
1184
+ {
1185
+ "epoch": 0.27,
1186
+ "learning_rate": 7.435638945337836e-06,
1187
+ "loss": 0.1318,
1188
+ "step": 1920
1189
+ },
1190
+ {
1191
+ "epoch": 0.28,
1192
+ "learning_rate": 7.420331288775502e-06,
1193
+ "loss": 0.0561,
1194
+ "step": 1930
1195
+ },
1196
+ {
1197
+ "epoch": 0.28,
1198
+ "learning_rate": 7.404965028725507e-06,
1199
+ "loss": 0.0997,
1200
+ "step": 1940
1201
+ },
1202
+ {
1203
+ "epoch": 0.28,
1204
+ "learning_rate": 7.3895404735489035e-06,
1205
+ "loss": 0.135,
1206
+ "step": 1950
1207
+ },
1208
+ {
1209
+ "epoch": 0.28,
1210
+ "learning_rate": 7.374057932776579e-06,
1211
+ "loss": 0.0591,
1212
+ "step": 1960
1213
+ },
1214
+ {
1215
+ "epoch": 0.28,
1216
+ "learning_rate": 7.358517717103039e-06,
1217
+ "loss": 0.0574,
1218
+ "step": 1970
1219
+ },
1220
+ {
1221
+ "epoch": 0.28,
1222
+ "learning_rate": 7.342920138380175e-06,
1223
+ "loss": 0.0589,
1224
+ "step": 1980
1225
+ },
1226
+ {
1227
+ "epoch": 0.28,
1228
+ "learning_rate": 7.327265509611007e-06,
1229
+ "loss": 0.0685,
1230
+ "step": 1990
1231
+ },
1232
+ {
1233
+ "epoch": 0.29,
1234
+ "learning_rate": 7.311554144943401e-06,
1235
+ "loss": 0.0386,
1236
+ "step": 2000
1237
+ },
1238
+ {
1239
+ "epoch": 0.29,
1240
+ "eval_accuracy": 0.0,
1241
+ "eval_loss": 0.14258363842964172,
1242
+ "eval_runtime": 447.0432,
1243
+ "eval_samples_per_second": 52.297,
1244
+ "eval_steps_per_second": 8.717,
1245
+ "step": 2000
1246
+ }
1247
+ ],
1248
+ "logging_steps": 10,
1249
+ "max_steps": 7013,
1250
+ "num_train_epochs": 1,
1251
+ "save_steps": 500,
1252
+ "total_flos": 0.0,
1253
+ "trial_name": null,
1254
+ "trial_params": null
1255
+ }
checkpoint-2000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbd473640b089575e3b93f40caac6d96b1006088b463e865229fad92539da1e0
3
+ size 4600