TSebbag commited on
Commit
66903c9
1 Parent(s): 6f5f497

Model files AdinBERT 4 GB

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<unk>NOTUSED": 32005
3
+ }
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/gpfswork/rech/khy/uvb95lb/camembert-base",
3
+ "architectures": [
4
+ "CamembertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 5,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 6,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "camembert",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "output_past": true,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.35.2",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 32005
28
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:375ad07133f66dc770e0d211fc858365bdfcd804c7866cf6e5335f3cd8f638ed
3
+ size 442646188
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:988bc5a00281c6d210a5d34bd143d0363741a432fefe741bf71e61b1869d4314
3
+ size 810912
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s>NOTUSED",
4
+ "</s>NOTUSED",
5
+ "<unk>NOTUSED"
6
+ ],
7
+ "bos_token": "<s>",
8
+ "cls_token": "<s>",
9
+ "eos_token": "</s>",
10
+ "mask_token": {
11
+ "content": "<mask>",
12
+ "lstrip": true,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ "pad_token": "<pad>",
18
+ "sep_token": "</s>",
19
+ "unk_token": "<unk>"
20
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>NOTUSED",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>NOTUSED",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "4": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "5": {
36
+ "content": "<s>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "6": {
44
+ "content": "</s>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "32004": {
52
+ "content": "<mask>",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "32005": {
60
+ "content": "<unk>NOTUSED",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ }
67
+ },
68
+ "additional_special_tokens": [
69
+ "<s>NOTUSED",
70
+ "</s>NOTUSED",
71
+ "<unk>NOTUSED"
72
+ ],
73
+ "bos_token": "<s>",
74
+ "clean_up_tokenization_spaces": true,
75
+ "cls_token": "<s>",
76
+ "eos_token": "</s>",
77
+ "mask_token": "<mask>",
78
+ "model_max_length": 512,
79
+ "pad_token": "<pad>",
80
+ "sep_token": "</s>",
81
+ "tokenizer_class": "CamembertTokenizer",
82
+ "unk_token": "<unk>"
83
+ }
train_results.txt ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ before_init_mem_cpu = 1314717696
2
+ before_init_mem_gpu = 0
3
+ epoch = 6.0
4
+ init_mem_cpu_alloc_delta = 880553984
5
+ init_mem_cpu_peaked_delta = 93917184
6
+ init_mem_gpu_alloc_delta = 443396608
7
+ init_mem_gpu_peaked_delta = 0
8
+ train_loss = 0.8106447110522921
9
+ train_mem_cpu_alloc_delta = 31978672128
10
+ train_mem_cpu_peaked_delta = 500772864
11
+ train_mem_gpu_alloc_delta = 1348273664
12
+ train_mem_gpu_peaked_delta = 64082841600
13
+ train_runtime = 71211.051
14
+ train_samples_per_second = 1017.691
15
+ train_steps_per_second = 1.325
trainer_state.json ADDED
@@ -0,0 +1,1172 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 6.0,
5
+ "eval_steps": 500,
6
+ "global_step": 94368,
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": 0.0,
14
+ "loss": 8.4152,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.03,
19
+ "learning_rate": 4.950000000000001e-06,
20
+ "loss": 3.4041,
21
+ "step": 500
22
+ },
23
+ {
24
+ "epoch": 0.06,
25
+ "learning_rate": 9.950000000000001e-06,
26
+ "loss": 1.6651,
27
+ "step": 1000
28
+ },
29
+ {
30
+ "epoch": 0.1,
31
+ "learning_rate": 1.4950000000000001e-05,
32
+ "loss": 1.5062,
33
+ "step": 1500
34
+ },
35
+ {
36
+ "epoch": 0.13,
37
+ "learning_rate": 1.995e-05,
38
+ "loss": 1.4128,
39
+ "step": 2000
40
+ },
41
+ {
42
+ "epoch": 0.16,
43
+ "learning_rate": 2.495e-05,
44
+ "loss": 1.347,
45
+ "step": 2500
46
+ },
47
+ {
48
+ "epoch": 0.19,
49
+ "learning_rate": 2.995e-05,
50
+ "loss": 1.2902,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 0.22,
55
+ "learning_rate": 3.495e-05,
56
+ "loss": 1.2457,
57
+ "step": 3500
58
+ },
59
+ {
60
+ "epoch": 0.25,
61
+ "learning_rate": 3.995e-05,
62
+ "loss": 1.2037,
63
+ "step": 4000
64
+ },
65
+ {
66
+ "epoch": 0.29,
67
+ "learning_rate": 4.495e-05,
68
+ "loss": 1.1728,
69
+ "step": 4500
70
+ },
71
+ {
72
+ "epoch": 0.32,
73
+ "learning_rate": 4.995e-05,
74
+ "loss": 1.1493,
75
+ "step": 5000
76
+ },
77
+ {
78
+ "epoch": 0.35,
79
+ "learning_rate": 5.495e-05,
80
+ "loss": 1.1211,
81
+ "step": 5500
82
+ },
83
+ {
84
+ "epoch": 0.38,
85
+ "learning_rate": 5.995000000000001e-05,
86
+ "loss": 1.0958,
87
+ "step": 6000
88
+ },
89
+ {
90
+ "epoch": 0.41,
91
+ "learning_rate": 6.494999999999999e-05,
92
+ "loss": 1.0736,
93
+ "step": 6500
94
+ },
95
+ {
96
+ "epoch": 0.45,
97
+ "learning_rate": 6.995e-05,
98
+ "loss": 1.0591,
99
+ "step": 7000
100
+ },
101
+ {
102
+ "epoch": 0.48,
103
+ "learning_rate": 7.494e-05,
104
+ "loss": 1.0399,
105
+ "step": 7500
106
+ },
107
+ {
108
+ "epoch": 0.51,
109
+ "learning_rate": 7.994000000000001e-05,
110
+ "loss": 1.0244,
111
+ "step": 8000
112
+ },
113
+ {
114
+ "epoch": 0.54,
115
+ "learning_rate": 8.494000000000001e-05,
116
+ "loss": 1.0128,
117
+ "step": 8500
118
+ },
119
+ {
120
+ "epoch": 0.57,
121
+ "learning_rate": 8.994e-05,
122
+ "loss": 1.0026,
123
+ "step": 9000
124
+ },
125
+ {
126
+ "epoch": 0.6,
127
+ "learning_rate": 9.494000000000001e-05,
128
+ "loss": 0.9945,
129
+ "step": 9500
130
+ },
131
+ {
132
+ "epoch": 0.64,
133
+ "learning_rate": 9.994e-05,
134
+ "loss": 0.9798,
135
+ "step": 10000
136
+ },
137
+ {
138
+ "epoch": 0.67,
139
+ "learning_rate": 9.941446994120994e-05,
140
+ "loss": 0.9709,
141
+ "step": 10500
142
+ },
143
+ {
144
+ "epoch": 0.7,
145
+ "learning_rate": 9.882182818130097e-05,
146
+ "loss": 0.9623,
147
+ "step": 11000
148
+ },
149
+ {
150
+ "epoch": 0.73,
151
+ "learning_rate": 9.8229186421392e-05,
152
+ "loss": 0.9505,
153
+ "step": 11500
154
+ },
155
+ {
156
+ "epoch": 0.76,
157
+ "learning_rate": 9.763654466148303e-05,
158
+ "loss": 0.9428,
159
+ "step": 12000
160
+ },
161
+ {
162
+ "epoch": 0.79,
163
+ "learning_rate": 9.704390290157406e-05,
164
+ "loss": 0.9323,
165
+ "step": 12500
166
+ },
167
+ {
168
+ "epoch": 0.83,
169
+ "learning_rate": 9.645244642518491e-05,
170
+ "loss": 0.9265,
171
+ "step": 13000
172
+ },
173
+ {
174
+ "epoch": 0.86,
175
+ "learning_rate": 9.585980466527594e-05,
176
+ "loss": 0.9197,
177
+ "step": 13500
178
+ },
179
+ {
180
+ "epoch": 0.89,
181
+ "learning_rate": 9.526716290536697e-05,
182
+ "loss": 0.9122,
183
+ "step": 14000
184
+ },
185
+ {
186
+ "epoch": 0.92,
187
+ "learning_rate": 9.4674521145458e-05,
188
+ "loss": 0.9065,
189
+ "step": 14500
190
+ },
191
+ {
192
+ "epoch": 0.95,
193
+ "learning_rate": 9.408187938554904e-05,
194
+ "loss": 0.9023,
195
+ "step": 15000
196
+ },
197
+ {
198
+ "epoch": 0.99,
199
+ "learning_rate": 9.348923762564006e-05,
200
+ "loss": 0.8965,
201
+ "step": 15500
202
+ },
203
+ {
204
+ "epoch": 1.02,
205
+ "learning_rate": 9.289659586573108e-05,
206
+ "loss": 0.8901,
207
+ "step": 16000
208
+ },
209
+ {
210
+ "epoch": 1.05,
211
+ "learning_rate": 9.230395410582213e-05,
212
+ "loss": 0.8822,
213
+ "step": 16500
214
+ },
215
+ {
216
+ "epoch": 1.08,
217
+ "learning_rate": 9.171131234591315e-05,
218
+ "loss": 0.8767,
219
+ "step": 17000
220
+ },
221
+ {
222
+ "epoch": 1.11,
223
+ "learning_rate": 9.111867058600417e-05,
224
+ "loss": 0.8711,
225
+ "step": 17500
226
+ },
227
+ {
228
+ "epoch": 1.14,
229
+ "learning_rate": 9.052721410961502e-05,
230
+ "loss": 0.8692,
231
+ "step": 18000
232
+ },
233
+ {
234
+ "epoch": 1.18,
235
+ "learning_rate": 8.993457234970606e-05,
236
+ "loss": 0.8655,
237
+ "step": 18500
238
+ },
239
+ {
240
+ "epoch": 1.21,
241
+ "learning_rate": 8.934193058979709e-05,
242
+ "loss": 0.861,
243
+ "step": 19000
244
+ },
245
+ {
246
+ "epoch": 1.24,
247
+ "learning_rate": 8.874928882988811e-05,
248
+ "loss": 0.8566,
249
+ "step": 19500
250
+ },
251
+ {
252
+ "epoch": 1.27,
253
+ "learning_rate": 8.815664706997914e-05,
254
+ "loss": 0.8509,
255
+ "step": 20000
256
+ },
257
+ {
258
+ "epoch": 1.3,
259
+ "learning_rate": 8.756519059359e-05,
260
+ "loss": 0.8492,
261
+ "step": 20500
262
+ },
263
+ {
264
+ "epoch": 1.34,
265
+ "learning_rate": 8.697373411720084e-05,
266
+ "loss": 0.8475,
267
+ "step": 21000
268
+ },
269
+ {
270
+ "epoch": 1.37,
271
+ "learning_rate": 8.638109235729187e-05,
272
+ "loss": 0.8471,
273
+ "step": 21500
274
+ },
275
+ {
276
+ "epoch": 1.4,
277
+ "learning_rate": 8.578845059738289e-05,
278
+ "loss": 0.8393,
279
+ "step": 22000
280
+ },
281
+ {
282
+ "epoch": 1.43,
283
+ "learning_rate": 8.519580883747393e-05,
284
+ "loss": 0.8341,
285
+ "step": 22500
286
+ },
287
+ {
288
+ "epoch": 1.46,
289
+ "learning_rate": 8.460316707756496e-05,
290
+ "loss": 0.8332,
291
+ "step": 23000
292
+ },
293
+ {
294
+ "epoch": 1.49,
295
+ "learning_rate": 8.401052531765598e-05,
296
+ "loss": 0.8295,
297
+ "step": 23500
298
+ },
299
+ {
300
+ "epoch": 1.53,
301
+ "learning_rate": 8.341788355774702e-05,
302
+ "loss": 0.8295,
303
+ "step": 24000
304
+ },
305
+ {
306
+ "epoch": 1.56,
307
+ "learning_rate": 8.282524179783805e-05,
308
+ "loss": 0.8237,
309
+ "step": 24500
310
+ },
311
+ {
312
+ "epoch": 1.59,
313
+ "learning_rate": 8.22337853214489e-05,
314
+ "loss": 0.8213,
315
+ "step": 25000
316
+ },
317
+ {
318
+ "epoch": 1.62,
319
+ "learning_rate": 8.164232884505975e-05,
320
+ "loss": 0.8187,
321
+ "step": 25500
322
+ },
323
+ {
324
+ "epoch": 1.65,
325
+ "learning_rate": 8.104968708515077e-05,
326
+ "loss": 0.8154,
327
+ "step": 26000
328
+ },
329
+ {
330
+ "epoch": 1.68,
331
+ "learning_rate": 8.04570453252418e-05,
332
+ "loss": 0.8133,
333
+ "step": 26500
334
+ },
335
+ {
336
+ "epoch": 1.72,
337
+ "learning_rate": 7.986440356533284e-05,
338
+ "loss": 0.8064,
339
+ "step": 27000
340
+ },
341
+ {
342
+ "epoch": 1.75,
343
+ "learning_rate": 7.927176180542386e-05,
344
+ "loss": 0.8087,
345
+ "step": 27500
346
+ },
347
+ {
348
+ "epoch": 1.78,
349
+ "learning_rate": 7.86803053290347e-05,
350
+ "loss": 0.809,
351
+ "step": 28000
352
+ },
353
+ {
354
+ "epoch": 1.81,
355
+ "learning_rate": 7.808766356912574e-05,
356
+ "loss": 0.8087,
357
+ "step": 28500
358
+ },
359
+ {
360
+ "epoch": 1.84,
361
+ "learning_rate": 7.749502180921678e-05,
362
+ "loss": 0.8018,
363
+ "step": 29000
364
+ },
365
+ {
366
+ "epoch": 1.88,
367
+ "learning_rate": 7.690356533282762e-05,
368
+ "loss": 0.7998,
369
+ "step": 29500
370
+ },
371
+ {
372
+ "epoch": 1.91,
373
+ "learning_rate": 7.631092357291864e-05,
374
+ "loss": 0.7984,
375
+ "step": 30000
376
+ },
377
+ {
378
+ "epoch": 1.94,
379
+ "learning_rate": 7.571828181300968e-05,
380
+ "loss": 0.7941,
381
+ "step": 30500
382
+ },
383
+ {
384
+ "epoch": 1.97,
385
+ "learning_rate": 7.512564005310071e-05,
386
+ "loss": 0.7965,
387
+ "step": 31000
388
+ },
389
+ {
390
+ "epoch": 2.0,
391
+ "learning_rate": 7.453299829319173e-05,
392
+ "loss": 0.7941,
393
+ "step": 31500
394
+ },
395
+ {
396
+ "epoch": 2.03,
397
+ "learning_rate": 7.394035653328276e-05,
398
+ "loss": 0.7901,
399
+ "step": 32000
400
+ },
401
+ {
402
+ "epoch": 2.07,
403
+ "learning_rate": 7.33477147733738e-05,
404
+ "loss": 0.7855,
405
+ "step": 32500
406
+ },
407
+ {
408
+ "epoch": 2.1,
409
+ "learning_rate": 7.275507301346483e-05,
410
+ "loss": 0.7825,
411
+ "step": 33000
412
+ },
413
+ {
414
+ "epoch": 2.13,
415
+ "learning_rate": 7.216243125355585e-05,
416
+ "loss": 0.7848,
417
+ "step": 33500
418
+ },
419
+ {
420
+ "epoch": 2.16,
421
+ "learning_rate": 7.156978949364688e-05,
422
+ "loss": 0.779,
423
+ "step": 34000
424
+ },
425
+ {
426
+ "epoch": 2.19,
427
+ "learning_rate": 7.097714773373792e-05,
428
+ "loss": 0.7778,
429
+ "step": 34500
430
+ },
431
+ {
432
+ "epoch": 2.23,
433
+ "learning_rate": 7.038450597382894e-05,
434
+ "loss": 0.7789,
435
+ "step": 35000
436
+ },
437
+ {
438
+ "epoch": 2.26,
439
+ "learning_rate": 6.979186421391997e-05,
440
+ "loss": 0.7749,
441
+ "step": 35500
442
+ },
443
+ {
444
+ "epoch": 2.29,
445
+ "learning_rate": 6.920040773753082e-05,
446
+ "loss": 0.7719,
447
+ "step": 36000
448
+ },
449
+ {
450
+ "epoch": 2.32,
451
+ "learning_rate": 6.860776597762185e-05,
452
+ "loss": 0.7755,
453
+ "step": 36500
454
+ },
455
+ {
456
+ "epoch": 2.35,
457
+ "learning_rate": 6.801512421771288e-05,
458
+ "loss": 0.7708,
459
+ "step": 37000
460
+ },
461
+ {
462
+ "epoch": 2.38,
463
+ "learning_rate": 6.742248245780391e-05,
464
+ "loss": 0.7677,
465
+ "step": 37500
466
+ },
467
+ {
468
+ "epoch": 2.42,
469
+ "learning_rate": 6.682984069789495e-05,
470
+ "loss": 0.766,
471
+ "step": 38000
472
+ },
473
+ {
474
+ "epoch": 2.45,
475
+ "learning_rate": 6.623719893798597e-05,
476
+ "loss": 0.767,
477
+ "step": 38500
478
+ },
479
+ {
480
+ "epoch": 2.48,
481
+ "learning_rate": 6.5644557178077e-05,
482
+ "loss": 0.7628,
483
+ "step": 39000
484
+ },
485
+ {
486
+ "epoch": 2.51,
487
+ "learning_rate": 6.505191541816802e-05,
488
+ "loss": 0.7638,
489
+ "step": 39500
490
+ },
491
+ {
492
+ "epoch": 2.54,
493
+ "learning_rate": 6.445927365825906e-05,
494
+ "loss": 0.7631,
495
+ "step": 40000
496
+ },
497
+ {
498
+ "epoch": 2.58,
499
+ "learning_rate": 6.38666318983501e-05,
500
+ "loss": 0.7587,
501
+ "step": 40500
502
+ },
503
+ {
504
+ "epoch": 2.61,
505
+ "learning_rate": 6.327636070548075e-05,
506
+ "loss": 0.7595,
507
+ "step": 41000
508
+ },
509
+ {
510
+ "epoch": 2.64,
511
+ "learning_rate": 6.268371894557177e-05,
512
+ "loss": 0.7599,
513
+ "step": 41500
514
+ },
515
+ {
516
+ "epoch": 2.67,
517
+ "learning_rate": 6.209107718566282e-05,
518
+ "loss": 0.7583,
519
+ "step": 42000
520
+ },
521
+ {
522
+ "epoch": 2.7,
523
+ "learning_rate": 6.149843542575384e-05,
524
+ "loss": 0.7534,
525
+ "step": 42500
526
+ },
527
+ {
528
+ "epoch": 2.73,
529
+ "learning_rate": 6.090579366584487e-05,
530
+ "loss": 0.7564,
531
+ "step": 43000
532
+ },
533
+ {
534
+ "epoch": 2.77,
535
+ "learning_rate": 6.0313151905935906e-05,
536
+ "loss": 0.7527,
537
+ "step": 43500
538
+ },
539
+ {
540
+ "epoch": 2.8,
541
+ "learning_rate": 5.9720510146026934e-05,
542
+ "loss": 0.7526,
543
+ "step": 44000
544
+ },
545
+ {
546
+ "epoch": 2.83,
547
+ "learning_rate": 5.9127868386117956e-05,
548
+ "loss": 0.7519,
549
+ "step": 44500
550
+ },
551
+ {
552
+ "epoch": 2.86,
553
+ "learning_rate": 5.85364119097288e-05,
554
+ "loss": 0.749,
555
+ "step": 45000
556
+ },
557
+ {
558
+ "epoch": 2.89,
559
+ "learning_rate": 5.7943770149819844e-05,
560
+ "loss": 0.7492,
561
+ "step": 45500
562
+ },
563
+ {
564
+ "epoch": 2.92,
565
+ "learning_rate": 5.7351128389910865e-05,
566
+ "loss": 0.7468,
567
+ "step": 46000
568
+ },
569
+ {
570
+ "epoch": 2.96,
571
+ "learning_rate": 5.6758486630001894e-05,
572
+ "loss": 0.745,
573
+ "step": 46500
574
+ },
575
+ {
576
+ "epoch": 2.99,
577
+ "learning_rate": 5.616584487009293e-05,
578
+ "loss": 0.7479,
579
+ "step": 47000
580
+ },
581
+ {
582
+ "epoch": 3.02,
583
+ "learning_rate": 5.557320311018396e-05,
584
+ "loss": 0.7431,
585
+ "step": 47500
586
+ },
587
+ {
588
+ "epoch": 3.05,
589
+ "learning_rate": 5.4980561350274985e-05,
590
+ "loss": 0.7406,
591
+ "step": 48000
592
+ },
593
+ {
594
+ "epoch": 3.08,
595
+ "learning_rate": 5.438791959036602e-05,
596
+ "loss": 0.7401,
597
+ "step": 48500
598
+ },
599
+ {
600
+ "epoch": 3.12,
601
+ "learning_rate": 5.379527783045705e-05,
602
+ "loss": 0.7379,
603
+ "step": 49000
604
+ },
605
+ {
606
+ "epoch": 3.15,
607
+ "learning_rate": 5.3203821354067895e-05,
608
+ "loss": 0.7375,
609
+ "step": 49500
610
+ },
611
+ {
612
+ "epoch": 3.18,
613
+ "learning_rate": 5.261117959415892e-05,
614
+ "loss": 0.7339,
615
+ "step": 50000
616
+ },
617
+ {
618
+ "epoch": 3.21,
619
+ "learning_rate": 5.201853783424996e-05,
620
+ "loss": 0.7349,
621
+ "step": 50500
622
+ },
623
+ {
624
+ "epoch": 3.24,
625
+ "learning_rate": 5.1425896074340986e-05,
626
+ "loss": 0.7348,
627
+ "step": 51000
628
+ },
629
+ {
630
+ "epoch": 3.27,
631
+ "learning_rate": 5.083443959795183e-05,
632
+ "loss": 0.7319,
633
+ "step": 51500
634
+ },
635
+ {
636
+ "epoch": 3.31,
637
+ "learning_rate": 5.024179783804286e-05,
638
+ "loss": 0.7271,
639
+ "step": 52000
640
+ },
641
+ {
642
+ "epoch": 3.34,
643
+ "learning_rate": 4.964915607813389e-05,
644
+ "loss": 0.7309,
645
+ "step": 52500
646
+ },
647
+ {
648
+ "epoch": 3.37,
649
+ "learning_rate": 4.905769960174474e-05,
650
+ "loss": 0.733,
651
+ "step": 53000
652
+ },
653
+ {
654
+ "epoch": 3.4,
655
+ "learning_rate": 4.846505784183577e-05,
656
+ "loss": 0.7277,
657
+ "step": 53500
658
+ },
659
+ {
660
+ "epoch": 3.43,
661
+ "learning_rate": 4.7872416081926805e-05,
662
+ "loss": 0.728,
663
+ "step": 54000
664
+ },
665
+ {
666
+ "epoch": 3.47,
667
+ "learning_rate": 4.7279774322017827e-05,
668
+ "loss": 0.7268,
669
+ "step": 54500
670
+ },
671
+ {
672
+ "epoch": 3.5,
673
+ "learning_rate": 4.668713256210886e-05,
674
+ "loss": 0.7261,
675
+ "step": 55000
676
+ },
677
+ {
678
+ "epoch": 3.53,
679
+ "learning_rate": 4.609567608571971e-05,
680
+ "loss": 0.7251,
681
+ "step": 55500
682
+ },
683
+ {
684
+ "epoch": 3.56,
685
+ "learning_rate": 4.5503034325810736e-05,
686
+ "loss": 0.7261,
687
+ "step": 56000
688
+ },
689
+ {
690
+ "epoch": 3.59,
691
+ "learning_rate": 4.4910392565901764e-05,
692
+ "loss": 0.7231,
693
+ "step": 56500
694
+ },
695
+ {
696
+ "epoch": 3.62,
697
+ "learning_rate": 4.43177508059928e-05,
698
+ "loss": 0.7197,
699
+ "step": 57000
700
+ },
701
+ {
702
+ "epoch": 3.66,
703
+ "learning_rate": 4.3726294329603646e-05,
704
+ "loss": 0.7249,
705
+ "step": 57500
706
+ },
707
+ {
708
+ "epoch": 3.69,
709
+ "learning_rate": 4.313483785321449e-05,
710
+ "loss": 0.7204,
711
+ "step": 58000
712
+ },
713
+ {
714
+ "epoch": 3.72,
715
+ "learning_rate": 4.254219609330552e-05,
716
+ "loss": 0.718,
717
+ "step": 58500
718
+ },
719
+ {
720
+ "epoch": 3.75,
721
+ "learning_rate": 4.194955433339655e-05,
722
+ "loss": 0.7205,
723
+ "step": 59000
724
+ },
725
+ {
726
+ "epoch": 3.78,
727
+ "learning_rate": 4.1356912573487584e-05,
728
+ "loss": 0.7164,
729
+ "step": 59500
730
+ },
731
+ {
732
+ "epoch": 3.81,
733
+ "learning_rate": 4.076427081357861e-05,
734
+ "loss": 0.7194,
735
+ "step": 60000
736
+ },
737
+ {
738
+ "epoch": 3.85,
739
+ "learning_rate": 4.017162905366964e-05,
740
+ "loss": 0.7166,
741
+ "step": 60500
742
+ },
743
+ {
744
+ "epoch": 3.88,
745
+ "learning_rate": 3.9578987293760675e-05,
746
+ "loss": 0.7167,
747
+ "step": 61000
748
+ },
749
+ {
750
+ "epoch": 3.91,
751
+ "learning_rate": 3.8986345533851696e-05,
752
+ "loss": 0.7175,
753
+ "step": 61500
754
+ },
755
+ {
756
+ "epoch": 3.94,
757
+ "learning_rate": 3.839370377394273e-05,
758
+ "loss": 0.7104,
759
+ "step": 62000
760
+ },
761
+ {
762
+ "epoch": 3.97,
763
+ "learning_rate": 3.780106201403376e-05,
764
+ "loss": 0.7116,
765
+ "step": 62500
766
+ },
767
+ {
768
+ "epoch": 4.01,
769
+ "learning_rate": 3.720842025412479e-05,
770
+ "loss": 0.7125,
771
+ "step": 63000
772
+ },
773
+ {
774
+ "epoch": 4.04,
775
+ "learning_rate": 3.6615778494215816e-05,
776
+ "loss": 0.7098,
777
+ "step": 63500
778
+ },
779
+ {
780
+ "epoch": 4.07,
781
+ "learning_rate": 3.602432201782667e-05,
782
+ "loss": 0.708,
783
+ "step": 64000
784
+ },
785
+ {
786
+ "epoch": 4.1,
787
+ "learning_rate": 3.543168025791769e-05,
788
+ "loss": 0.7081,
789
+ "step": 64500
790
+ },
791
+ {
792
+ "epoch": 4.13,
793
+ "learning_rate": 3.4839038498008725e-05,
794
+ "loss": 0.7058,
795
+ "step": 65000
796
+ },
797
+ {
798
+ "epoch": 4.16,
799
+ "learning_rate": 3.4246396738099754e-05,
800
+ "loss": 0.7072,
801
+ "step": 65500
802
+ },
803
+ {
804
+ "epoch": 4.2,
805
+ "learning_rate": 3.365375497819078e-05,
806
+ "loss": 0.7068,
807
+ "step": 66000
808
+ },
809
+ {
810
+ "epoch": 4.23,
811
+ "learning_rate": 3.306111321828182e-05,
812
+ "loss": 0.706,
813
+ "step": 66500
814
+ },
815
+ {
816
+ "epoch": 4.26,
817
+ "learning_rate": 3.246965674189266e-05,
818
+ "loss": 0.705,
819
+ "step": 67000
820
+ },
821
+ {
822
+ "epoch": 4.29,
823
+ "learning_rate": 3.187701498198369e-05,
824
+ "loss": 0.7043,
825
+ "step": 67500
826
+ },
827
+ {
828
+ "epoch": 4.32,
829
+ "learning_rate": 3.128437322207472e-05,
830
+ "loss": 0.7025,
831
+ "step": 68000
832
+ },
833
+ {
834
+ "epoch": 4.36,
835
+ "learning_rate": 3.0691731462165755e-05,
836
+ "loss": 0.7019,
837
+ "step": 68500
838
+ },
839
+ {
840
+ "epoch": 4.39,
841
+ "learning_rate": 3.0099089702256783e-05,
842
+ "loss": 0.703,
843
+ "step": 69000
844
+ },
845
+ {
846
+ "epoch": 4.42,
847
+ "learning_rate": 2.9506447942347808e-05,
848
+ "loss": 0.7023,
849
+ "step": 69500
850
+ },
851
+ {
852
+ "epoch": 4.45,
853
+ "learning_rate": 2.891380618243884e-05,
854
+ "loss": 0.7023,
855
+ "step": 70000
856
+ },
857
+ {
858
+ "epoch": 4.48,
859
+ "learning_rate": 2.832234970604969e-05,
860
+ "loss": 0.7,
861
+ "step": 70500
862
+ },
863
+ {
864
+ "epoch": 4.51,
865
+ "learning_rate": 2.772970794614072e-05,
866
+ "loss": 0.6976,
867
+ "step": 71000
868
+ },
869
+ {
870
+ "epoch": 4.55,
871
+ "learning_rate": 2.7137066186231745e-05,
872
+ "loss": 0.7009,
873
+ "step": 71500
874
+ },
875
+ {
876
+ "epoch": 4.58,
877
+ "learning_rate": 2.6544424426322777e-05,
878
+ "loss": 0.6985,
879
+ "step": 72000
880
+ },
881
+ {
882
+ "epoch": 4.61,
883
+ "learning_rate": 2.595178266641381e-05,
884
+ "loss": 0.6976,
885
+ "step": 72500
886
+ },
887
+ {
888
+ "epoch": 4.64,
889
+ "learning_rate": 2.5359140906504837e-05,
890
+ "loss": 0.6988,
891
+ "step": 73000
892
+ },
893
+ {
894
+ "epoch": 4.67,
895
+ "learning_rate": 2.4766499146595868e-05,
896
+ "loss": 0.6988,
897
+ "step": 73500
898
+ },
899
+ {
900
+ "epoch": 4.7,
901
+ "learning_rate": 2.4173857386686896e-05,
902
+ "loss": 0.6964,
903
+ "step": 74000
904
+ },
905
+ {
906
+ "epoch": 4.74,
907
+ "learning_rate": 2.3582400910297743e-05,
908
+ "loss": 0.6972,
909
+ "step": 74500
910
+ },
911
+ {
912
+ "epoch": 4.77,
913
+ "learning_rate": 2.2989759150388775e-05,
914
+ "loss": 0.6948,
915
+ "step": 75000
916
+ },
917
+ {
918
+ "epoch": 4.8,
919
+ "learning_rate": 2.2397117390479806e-05,
920
+ "loss": 0.6946,
921
+ "step": 75500
922
+ },
923
+ {
924
+ "epoch": 4.83,
925
+ "learning_rate": 2.1804475630570834e-05,
926
+ "loss": 0.6927,
927
+ "step": 76000
928
+ },
929
+ {
930
+ "epoch": 4.86,
931
+ "learning_rate": 2.1211833870661862e-05,
932
+ "loss": 0.6909,
933
+ "step": 76500
934
+ },
935
+ {
936
+ "epoch": 4.9,
937
+ "learning_rate": 2.0620377394272712e-05,
938
+ "loss": 0.6906,
939
+ "step": 77000
940
+ },
941
+ {
942
+ "epoch": 4.93,
943
+ "learning_rate": 2.002892091788356e-05,
944
+ "loss": 0.6929,
945
+ "step": 77500
946
+ },
947
+ {
948
+ "epoch": 4.96,
949
+ "learning_rate": 1.9436279157974587e-05,
950
+ "loss": 0.6917,
951
+ "step": 78000
952
+ },
953
+ {
954
+ "epoch": 4.99,
955
+ "learning_rate": 1.884363739806562e-05,
956
+ "loss": 0.6925,
957
+ "step": 78500
958
+ },
959
+ {
960
+ "epoch": 5.02,
961
+ "learning_rate": 1.8250995638156647e-05,
962
+ "loss": 0.6895,
963
+ "step": 79000
964
+ },
965
+ {
966
+ "epoch": 5.05,
967
+ "learning_rate": 1.765835387824768e-05,
968
+ "loss": 0.686,
969
+ "step": 79500
970
+ },
971
+ {
972
+ "epoch": 5.09,
973
+ "learning_rate": 1.706571211833871e-05,
974
+ "loss": 0.6882,
975
+ "step": 80000
976
+ },
977
+ {
978
+ "epoch": 5.12,
979
+ "learning_rate": 1.6473070358429738e-05,
980
+ "loss": 0.6877,
981
+ "step": 80500
982
+ },
983
+ {
984
+ "epoch": 5.15,
985
+ "learning_rate": 1.5880428598520766e-05,
986
+ "loss": 0.688,
987
+ "step": 81000
988
+ },
989
+ {
990
+ "epoch": 5.18,
991
+ "learning_rate": 1.5287786838611798e-05,
992
+ "loss": 0.6863,
993
+ "step": 81500
994
+ },
995
+ {
996
+ "epoch": 5.21,
997
+ "learning_rate": 1.4696330362222643e-05,
998
+ "loss": 0.6882,
999
+ "step": 82000
1000
+ },
1001
+ {
1002
+ "epoch": 5.25,
1003
+ "learning_rate": 1.4104873885833491e-05,
1004
+ "loss": 0.6892,
1005
+ "step": 82500
1006
+ },
1007
+ {
1008
+ "epoch": 5.28,
1009
+ "learning_rate": 1.351223212592452e-05,
1010
+ "loss": 0.6878,
1011
+ "step": 83000
1012
+ },
1013
+ {
1014
+ "epoch": 5.31,
1015
+ "learning_rate": 1.2919590366015552e-05,
1016
+ "loss": 0.6841,
1017
+ "step": 83500
1018
+ },
1019
+ {
1020
+ "epoch": 5.34,
1021
+ "learning_rate": 1.232694860610658e-05,
1022
+ "loss": 0.6841,
1023
+ "step": 84000
1024
+ },
1025
+ {
1026
+ "epoch": 5.37,
1027
+ "learning_rate": 1.173430684619761e-05,
1028
+ "loss": 0.6855,
1029
+ "step": 84500
1030
+ },
1031
+ {
1032
+ "epoch": 5.4,
1033
+ "learning_rate": 1.1141665086288642e-05,
1034
+ "loss": 0.6833,
1035
+ "step": 85000
1036
+ },
1037
+ {
1038
+ "epoch": 5.44,
1039
+ "learning_rate": 1.054902332637967e-05,
1040
+ "loss": 0.683,
1041
+ "step": 85500
1042
+ },
1043
+ {
1044
+ "epoch": 5.47,
1045
+ "learning_rate": 9.9563815664707e-06,
1046
+ "loss": 0.6847,
1047
+ "step": 86000
1048
+ },
1049
+ {
1050
+ "epoch": 5.5,
1051
+ "learning_rate": 9.36373980656173e-06,
1052
+ "loss": 0.6845,
1053
+ "step": 86500
1054
+ },
1055
+ {
1056
+ "epoch": 5.53,
1057
+ "learning_rate": 8.77109804665276e-06,
1058
+ "loss": 0.6795,
1059
+ "step": 87000
1060
+ },
1061
+ {
1062
+ "epoch": 5.56,
1063
+ "learning_rate": 8.17845628674379e-06,
1064
+ "loss": 0.6817,
1065
+ "step": 87500
1066
+ },
1067
+ {
1068
+ "epoch": 5.6,
1069
+ "learning_rate": 7.585814526834819e-06,
1070
+ "loss": 0.6796,
1071
+ "step": 88000
1072
+ },
1073
+ {
1074
+ "epoch": 5.63,
1075
+ "learning_rate": 6.994358050445667e-06,
1076
+ "loss": 0.684,
1077
+ "step": 88500
1078
+ },
1079
+ {
1080
+ "epoch": 5.66,
1081
+ "learning_rate": 6.401716290536697e-06,
1082
+ "loss": 0.6833,
1083
+ "step": 89000
1084
+ },
1085
+ {
1086
+ "epoch": 5.69,
1087
+ "learning_rate": 5.810259814147544e-06,
1088
+ "loss": 0.6805,
1089
+ "step": 89500
1090
+ },
1091
+ {
1092
+ "epoch": 5.72,
1093
+ "learning_rate": 5.217618054238574e-06,
1094
+ "loss": 0.6823,
1095
+ "step": 90000
1096
+ },
1097
+ {
1098
+ "epoch": 5.75,
1099
+ "learning_rate": 4.626161577849421e-06,
1100
+ "loss": 0.6786,
1101
+ "step": 90500
1102
+ },
1103
+ {
1104
+ "epoch": 5.79,
1105
+ "learning_rate": 4.033519817940452e-06,
1106
+ "loss": 0.676,
1107
+ "step": 91000
1108
+ },
1109
+ {
1110
+ "epoch": 5.82,
1111
+ "learning_rate": 3.440878058031481e-06,
1112
+ "loss": 0.6811,
1113
+ "step": 91500
1114
+ },
1115
+ {
1116
+ "epoch": 5.85,
1117
+ "learning_rate": 2.848236298122511e-06,
1118
+ "loss": 0.6805,
1119
+ "step": 92000
1120
+ },
1121
+ {
1122
+ "epoch": 5.88,
1123
+ "learning_rate": 2.2567798217333587e-06,
1124
+ "loss": 0.6805,
1125
+ "step": 92500
1126
+ },
1127
+ {
1128
+ "epoch": 5.91,
1129
+ "learning_rate": 1.6641380618243886e-06,
1130
+ "loss": 0.6783,
1131
+ "step": 93000
1132
+ },
1133
+ {
1134
+ "epoch": 5.94,
1135
+ "learning_rate": 1.0714963019154182e-06,
1136
+ "loss": 0.6806,
1137
+ "step": 93500
1138
+ },
1139
+ {
1140
+ "epoch": 5.98,
1141
+ "learning_rate": 4.78854542006448e-07,
1142
+ "loss": 0.6792,
1143
+ "step": 94000
1144
+ },
1145
+ {
1146
+ "before_init_mem_cpu": 1314717696,
1147
+ "before_init_mem_gpu": 0,
1148
+ "epoch": 6.0,
1149
+ "init_mem_cpu_alloc_delta": 880553984,
1150
+ "init_mem_cpu_peaked_delta": 93917184,
1151
+ "init_mem_gpu_alloc_delta": 443396608,
1152
+ "init_mem_gpu_peaked_delta": 0,
1153
+ "step": 94368,
1154
+ "total_flos": 1.9076000524147884e+19,
1155
+ "train_loss": 0.8106447110522921,
1156
+ "train_mem_cpu_alloc_delta": 31978672128,
1157
+ "train_mem_cpu_peaked_delta": 500772864,
1158
+ "train_mem_gpu_alloc_delta": 1348273664,
1159
+ "train_mem_gpu_peaked_delta": 64082841600,
1160
+ "train_runtime": 71211.051,
1161
+ "train_samples_per_second": 1017.691,
1162
+ "train_steps_per_second": 1.325
1163
+ }
1164
+ ],
1165
+ "logging_steps": 500,
1166
+ "max_steps": 94368,
1167
+ "num_train_epochs": 6,
1168
+ "save_steps": 500,
1169
+ "total_flos": 1.9076000524147884e+19,
1170
+ "trial_name": null,
1171
+ "trial_params": null
1172
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1db7c73e23cd2ded63e824aac9938f7ec857410520f6f92ac807d8b554b9a93e
3
+ size 4664