Hugging Face's logo

shengnan
/
visualize-v0-pre1k-preseed1

Transformers
PyTorch
t5
text-generation-inference
Inference Endpoints
Model card Files Community
shengnan commited on
Commit
ef1bd8e
·
1 Parent(s): acbedba

commit from v-shean

Browse files
Files changed (18) hide show
  1. config.json +59 -0
  2. optimizer.pt +3 -0
  3. pytorch_model.bin +3 -0
  4. rng_state_0.pth +3 -0
  5. rng_state_1.pth +3 -0
  6. rng_state_2.pth +3 -0
  7. rng_state_3.pth +3 -0
  8. rng_state_4.pth +3 -0
  9. rng_state_5.pth +3 -0
  10. rng_state_6.pth +3 -0
  11. rng_state_7.pth +3 -0
  12. scheduler.pt +3 -0
  13. special_tokens_map.json +1 -0
  14. spiece.model +3 -0
  15. tokenizer.json +0 -0
  16. tokenizer_config.json +1 -0
  17. trainer_state.json +624 -0
  18. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "t5-base",
3
+ "architectures": [
4
+ "T5PrefixTuningGeneration"
5
+ ],
6
+ "d_ff": 3072,
7
+ "d_kv": 64,
8
+ "d_model": 768,
9
+ "decoder_start_token_id": 0,
10
+ "dropout_rate": 0.1,
11
+ "early_stopping": true,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "relu",
14
+ "gradient_checkpointing": false,
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "max_length": 1024,
19
+ "model_type": "t5",
20
+ "n_positions": 512,
21
+ "num_decoder_layers": 12,
22
+ "num_heads": 12,
23
+ "num_layers": 12,
24
+ "output_past": true,
25
+ "pad_token_id": 0,
26
+ "relative_attention_num_buckets": 32,
27
+ "task_specific_params": {
28
+ "summarization": {
29
+ "early_stopping": true,
30
+ "length_penalty": 2.0,
31
+ "max_length": 200,
32
+ "min_length": 30,
33
+ "no_repeat_ngram_size": 3,
34
+ "num_beams": 4,
35
+ "prefix": "summarize: "
36
+ },
37
+ "translation_en_to_de": {
38
+ "early_stopping": true,
39
+ "max_length": 300,
40
+ "num_beams": 4,
41
+ "prefix": "translate English to German: "
42
+ },
43
+ "translation_en_to_fr": {
44
+ "early_stopping": true,
45
+ "max_length": 300,
46
+ "num_beams": 4,
47
+ "prefix": "translate English to French: "
48
+ },
49
+ "translation_en_to_ro": {
50
+ "early_stopping": true,
51
+ "max_length": 300,
52
+ "num_beams": 4,
53
+ "prefix": "translate English to Romanian: "
54
+ }
55
+ },
56
+ "transformers_version": "4.6.0",
57
+ "use_cache": true,
58
+ "vocab_size": 32128
59
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:557029adf7c73472b4fdccb04de1181ac7f4befd94b586383cf0e4e8213d6c2b
3
+ size 1783391233
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c247cd68538b8e0ef5144e280138214fb6ac8a2581bfeca08224505566a0fa0e
3
+ size 891737400
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:031633785b1659b4c3ad39f2601502337ebbc83dbca2ffbb5c0a64528db240cb
3
+ size 14657
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca25a233274946f377d5c74f820771f757820fa4e5a207d8894ddb4cfb5242ac
3
+ size 14657
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e0f03808f65d3117d4d58ca978cc5890215dc91538d1a6bc8fdb7d46e0101c5
3
+ size 14657
rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bed8d0919c98c578727e9bb4ef64175f1c8bb4977c839861d2773aa6564d4df9
3
+ size 14657
rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fc6ad0d238a88fba6d93bbcad064bc40760c918a9c9dd176136105ff0aa0728
3
+ size 14657
rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1192e06c24981cbd1ee5e63a54d04a213028151677bcc3e7fce1a487217a32c1
3
+ size 14657
rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54ac72e215940f3549f75edd1a5dadf516e5dfd7c3cbe72a2706f4165c5a2a4e
3
+ size 14657
rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e03eeffd23634eccaa9c65342402ccde0ad7609d330188bacaace5a85859714
3
+ size 14657
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39bb16a10a998b348cbcffde161e721454505d37e5c88d82caf9a40a46e75a65
3
+ size 623
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "t5-base"}
trainer_state.json ADDED
@@ -0,0 +1,624 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.23883448770002388,
5
+ "global_step": 1000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 1e-05,
13
+ "loss": 5.873,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.0,
18
+ "learning_rate": 1e-05,
19
+ "loss": 5.4916,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.01,
24
+ "learning_rate": 1e-05,
25
+ "loss": 4.8477,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.01,
30
+ "learning_rate": 1e-05,
31
+ "loss": 4.5425,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.01,
36
+ "learning_rate": 1e-05,
37
+ "loss": 4.2734,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 0.01,
42
+ "learning_rate": 1e-05,
43
+ "loss": 3.9337,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 0.02,
48
+ "learning_rate": 1e-05,
49
+ "loss": 3.9433,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 0.02,
54
+ "learning_rate": 1e-05,
55
+ "loss": 3.7212,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 0.02,
60
+ "learning_rate": 1e-05,
61
+ "loss": 3.5957,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 0.02,
66
+ "learning_rate": 1e-05,
67
+ "loss": 3.436,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 0.03,
72
+ "learning_rate": 1e-05,
73
+ "loss": 3.387,
74
+ "step": 110
75
+ },
76
+ {
77
+ "epoch": 0.03,
78
+ "learning_rate": 1e-05,
79
+ "loss": 3.4263,
80
+ "step": 120
81
+ },
82
+ {
83
+ "epoch": 0.03,
84
+ "learning_rate": 1e-05,
85
+ "loss": 3.2046,
86
+ "step": 130
87
+ },
88
+ {
89
+ "epoch": 0.03,
90
+ "learning_rate": 1e-05,
91
+ "loss": 3.0605,
92
+ "step": 140
93
+ },
94
+ {
95
+ "epoch": 0.04,
96
+ "learning_rate": 1e-05,
97
+ "loss": 3.1447,
98
+ "step": 150
99
+ },
100
+ {
101
+ "epoch": 0.04,
102
+ "learning_rate": 1e-05,
103
+ "loss": 3.1735,
104
+ "step": 160
105
+ },
106
+ {
107
+ "epoch": 0.04,
108
+ "learning_rate": 1e-05,
109
+ "loss": 2.977,
110
+ "step": 170
111
+ },
112
+ {
113
+ "epoch": 0.04,
114
+ "learning_rate": 1e-05,
115
+ "loss": 3.2005,
116
+ "step": 180
117
+ },
118
+ {
119
+ "epoch": 0.05,
120
+ "learning_rate": 1e-05,
121
+ "loss": 3.0096,
122
+ "step": 190
123
+ },
124
+ {
125
+ "epoch": 0.05,
126
+ "learning_rate": 1e-05,
127
+ "loss": 2.8942,
128
+ "step": 200
129
+ },
130
+ {
131
+ "epoch": 0.05,
132
+ "learning_rate": 1e-05,
133
+ "loss": 2.8821,
134
+ "step": 210
135
+ },
136
+ {
137
+ "epoch": 0.05,
138
+ "learning_rate": 1e-05,
139
+ "loss": 2.8973,
140
+ "step": 220
141
+ },
142
+ {
143
+ "epoch": 0.05,
144
+ "learning_rate": 1e-05,
145
+ "loss": 3.0138,
146
+ "step": 230
147
+ },
148
+ {
149
+ "epoch": 0.06,
150
+ "learning_rate": 1e-05,
151
+ "loss": 2.859,
152
+ "step": 240
153
+ },
154
+ {
155
+ "epoch": 0.06,
156
+ "learning_rate": 1e-05,
157
+ "loss": 2.8366,
158
+ "step": 250
159
+ },
160
+ {
161
+ "epoch": 0.06,
162
+ "learning_rate": 1e-05,
163
+ "loss": 2.7728,
164
+ "step": 260
165
+ },
166
+ {
167
+ "epoch": 0.06,
168
+ "learning_rate": 1e-05,
169
+ "loss": 2.8216,
170
+ "step": 270
171
+ },
172
+ {
173
+ "epoch": 0.07,
174
+ "learning_rate": 1e-05,
175
+ "loss": 3.1418,
176
+ "step": 280
177
+ },
178
+ {
179
+ "epoch": 0.07,
180
+ "learning_rate": 1e-05,
181
+ "loss": 2.7978,
182
+ "step": 290
183
+ },
184
+ {
185
+ "epoch": 0.07,
186
+ "learning_rate": 1e-05,
187
+ "loss": 2.7199,
188
+ "step": 300
189
+ },
190
+ {
191
+ "epoch": 0.07,
192
+ "learning_rate": 1e-05,
193
+ "loss": 2.8219,
194
+ "step": 310
195
+ },
196
+ {
197
+ "epoch": 0.08,
198
+ "learning_rate": 1e-05,
199
+ "loss": 2.5467,
200
+ "step": 320
201
+ },
202
+ {
203
+ "epoch": 0.08,
204
+ "learning_rate": 1e-05,
205
+ "loss": 2.7626,
206
+ "step": 330
207
+ },
208
+ {
209
+ "epoch": 0.08,
210
+ "learning_rate": 1e-05,
211
+ "loss": 2.7639,
212
+ "step": 340
213
+ },
214
+ {
215
+ "epoch": 0.08,
216
+ "learning_rate": 1e-05,
217
+ "loss": 2.6535,
218
+ "step": 350
219
+ },
220
+ {
221
+ "epoch": 0.09,
222
+ "learning_rate": 1e-05,
223
+ "loss": 2.582,
224
+ "step": 360
225
+ },
226
+ {
227
+ "epoch": 0.09,
228
+ "learning_rate": 1e-05,
229
+ "loss": 2.5759,
230
+ "step": 370
231
+ },
232
+ {
233
+ "epoch": 0.09,
234
+ "learning_rate": 1e-05,
235
+ "loss": 2.7389,
236
+ "step": 380
237
+ },
238
+ {
239
+ "epoch": 0.09,
240
+ "learning_rate": 1e-05,
241
+ "loss": 2.5658,
242
+ "step": 390
243
+ },
244
+ {
245
+ "epoch": 0.1,
246
+ "learning_rate": 1e-05,
247
+ "loss": 2.3294,
248
+ "step": 400
249
+ },
250
+ {
251
+ "epoch": 0.1,
252
+ "learning_rate": 1e-05,
253
+ "loss": 2.6136,
254
+ "step": 410
255
+ },
256
+ {
257
+ "epoch": 0.1,
258
+ "learning_rate": 1e-05,
259
+ "loss": 2.5115,
260
+ "step": 420
261
+ },
262
+ {
263
+ "epoch": 0.1,
264
+ "learning_rate": 1e-05,
265
+ "loss": 2.6185,
266
+ "step": 430
267
+ },
268
+ {
269
+ "epoch": 0.11,
270
+ "learning_rate": 1e-05,
271
+ "loss": 2.7034,
272
+ "step": 440
273
+ },
274
+ {
275
+ "epoch": 0.11,
276
+ "learning_rate": 1e-05,
277
+ "loss": 2.542,
278
+ "step": 450
279
+ },
280
+ {
281
+ "epoch": 0.11,
282
+ "learning_rate": 1e-05,
283
+ "loss": 2.4195,
284
+ "step": 460
285
+ },
286
+ {
287
+ "epoch": 0.11,
288
+ "learning_rate": 1e-05,
289
+ "loss": 2.3935,
290
+ "step": 470
291
+ },
292
+ {
293
+ "epoch": 0.11,
294
+ "learning_rate": 1e-05,
295
+ "loss": 2.6524,
296
+ "step": 480
297
+ },
298
+ {
299
+ "epoch": 0.12,
300
+ "learning_rate": 1e-05,
301
+ "loss": 2.5967,
302
+ "step": 490
303
+ },
304
+ {
305
+ "epoch": 0.12,
306
+ "learning_rate": 1e-05,
307
+ "loss": 2.4715,
308
+ "step": 500
309
+ },
310
+ {
311
+ "epoch": 0.12,
312
+ "learning_rate": 1e-05,
313
+ "loss": 2.4646,
314
+ "step": 510
315
+ },
316
+ {
317
+ "epoch": 0.12,
318
+ "learning_rate": 1e-05,
319
+ "loss": 2.51,
320
+ "step": 520
321
+ },
322
+ {
323
+ "epoch": 0.13,
324
+ "learning_rate": 1e-05,
325
+ "loss": 2.4409,
326
+ "step": 530
327
+ },
328
+ {
329
+ "epoch": 0.13,
330
+ "learning_rate": 1e-05,
331
+ "loss": 2.3432,
332
+ "step": 540
333
+ },
334
+ {
335
+ "epoch": 0.13,
336
+ "learning_rate": 1e-05,
337
+ "loss": 2.3886,
338
+ "step": 550
339
+ },
340
+ {
341
+ "epoch": 0.13,
342
+ "learning_rate": 1e-05,
343
+ "loss": 2.49,
344
+ "step": 560
345
+ },
346
+ {
347
+ "epoch": 0.14,
348
+ "learning_rate": 1e-05,
349
+ "loss": 2.3519,
350
+ "step": 570
351
+ },
352
+ {
353
+ "epoch": 0.14,
354
+ "learning_rate": 1e-05,
355
+ "loss": 2.6453,
356
+ "step": 580
357
+ },
358
+ {
359
+ "epoch": 0.14,
360
+ "learning_rate": 1e-05,
361
+ "loss": 2.5263,
362
+ "step": 590
363
+ },
364
+ {
365
+ "epoch": 0.14,
366
+ "learning_rate": 1e-05,
367
+ "loss": 2.4042,
368
+ "step": 600
369
+ },
370
+ {
371
+ "epoch": 0.15,
372
+ "learning_rate": 1e-05,
373
+ "loss": 2.3475,
374
+ "step": 610
375
+ },
376
+ {
377
+ "epoch": 0.15,
378
+ "learning_rate": 1e-05,
379
+ "loss": 2.3979,
380
+ "step": 620
381
+ },
382
+ {
383
+ "epoch": 0.15,
384
+ "learning_rate": 1e-05,
385
+ "loss": 2.2499,
386
+ "step": 630
387
+ },
388
+ {
389
+ "epoch": 0.15,
390
+ "learning_rate": 1e-05,
391
+ "loss": 2.3608,
392
+ "step": 640
393
+ },
394
+ {
395
+ "epoch": 0.16,
396
+ "learning_rate": 1e-05,
397
+ "loss": 2.3991,
398
+ "step": 650
399
+ },
400
+ {
401
+ "epoch": 0.16,
402
+ "learning_rate": 1e-05,
403
+ "loss": 2.2029,
404
+ "step": 660
405
+ },
406
+ {
407
+ "epoch": 0.16,
408
+ "learning_rate": 1e-05,
409
+ "loss": 2.4048,
410
+ "step": 670
411
+ },
412
+ {
413
+ "epoch": 0.16,
414
+ "learning_rate": 1e-05,
415
+ "loss": 2.3327,
416
+ "step": 680
417
+ },
418
+ {
419
+ "epoch": 0.16,
420
+ "learning_rate": 1e-05,
421
+ "loss": 2.3633,
422
+ "step": 690
423
+ },
424
+ {
425
+ "epoch": 0.17,
426
+ "learning_rate": 1e-05,
427
+ "loss": 2.3499,
428
+ "step": 700
429
+ },
430
+ {
431
+ "epoch": 0.17,
432
+ "learning_rate": 1e-05,
433
+ "loss": 2.4361,
434
+ "step": 710
435
+ },
436
+ {
437
+ "epoch": 0.17,
438
+ "learning_rate": 1e-05,
439
+ "loss": 2.1677,
440
+ "step": 720
441
+ },
442
+ {
443
+ "epoch": 0.17,
444
+ "learning_rate": 1e-05,
445
+ "loss": 2.3024,
446
+ "step": 730
447
+ },
448
+ {
449
+ "epoch": 0.18,
450
+ "learning_rate": 1e-05,
451
+ "loss": 2.2208,
452
+ "step": 740
453
+ },
454
+ {
455
+ "epoch": 0.18,
456
+ "learning_rate": 1e-05,
457
+ "loss": 2.1665,
458
+ "step": 750
459
+ },
460
+ {
461
+ "epoch": 0.18,
462
+ "learning_rate": 1e-05,
463
+ "loss": 2.3387,
464
+ "step": 760
465
+ },
466
+ {
467
+ "epoch": 0.18,
468
+ "learning_rate": 1e-05,
469
+ "loss": 2.2972,
470
+ "step": 770
471
+ },
472
+ {
473
+ "epoch": 0.19,
474
+ "learning_rate": 1e-05,
475
+ "loss": 2.2578,
476
+ "step": 780
477
+ },
478
+ {
479
+ "epoch": 0.19,
480
+ "learning_rate": 1e-05,
481
+ "loss": 2.22,
482
+ "step": 790
483
+ },
484
+ {
485
+ "epoch": 0.19,
486
+ "learning_rate": 1e-05,
487
+ "loss": 2.1765,
488
+ "step": 800
489
+ },
490
+ {
491
+ "epoch": 0.19,
492
+ "learning_rate": 1e-05,
493
+ "loss": 2.2855,
494
+ "step": 810
495
+ },
496
+ {
497
+ "epoch": 0.2,
498
+ "learning_rate": 1e-05,
499
+ "loss": 2.3016,
500
+ "step": 820
501
+ },
502
+ {
503
+ "epoch": 0.2,
504
+ "learning_rate": 1e-05,
505
+ "loss": 2.3201,
506
+ "step": 830
507
+ },
508
+ {
509
+ "epoch": 0.2,
510
+ "learning_rate": 1e-05,
511
+ "loss": 2.1431,
512
+ "step": 840
513
+ },
514
+ {
515
+ "epoch": 0.2,
516
+ "learning_rate": 1e-05,
517
+ "loss": 2.2683,
518
+ "step": 850
519
+ },
520
+ {
521
+ "epoch": 0.21,
522
+ "learning_rate": 1e-05,
523
+ "loss": 2.0788,
524
+ "step": 860
525
+ },
526
+ {
527
+ "epoch": 0.21,
528
+ "learning_rate": 1e-05,
529
+ "loss": 2.1208,
530
+ "step": 870
531
+ },
532
+ {
533
+ "epoch": 0.21,
534
+ "learning_rate": 1e-05,
535
+ "loss": 2.3935,
536
+ "step": 880
537
+ },
538
+ {
539
+ "epoch": 0.21,
540
+ "learning_rate": 1e-05,
541
+ "loss": 2.183,
542
+ "step": 890
543
+ },
544
+ {
545
+ "epoch": 0.21,
546
+ "learning_rate": 1e-05,
547
+ "loss": 2.1116,
548
+ "step": 900
549
+ },
550
+ {
551
+ "epoch": 0.22,
552
+ "learning_rate": 1e-05,
553
+ "loss": 2.333,
554
+ "step": 910
555
+ },
556
+ {
557
+ "epoch": 0.22,
558
+ "learning_rate": 1e-05,
559
+ "loss": 2.2625,
560
+ "step": 920
561
+ },
562
+ {
563
+ "epoch": 0.22,
564
+ "learning_rate": 1e-05,
565
+ "loss": 2.1775,
566
+ "step": 930
567
+ },
568
+ {
569
+ "epoch": 0.22,
570
+ "learning_rate": 1e-05,
571
+ "loss": 2.1814,
572
+ "step": 940
573
+ },
574
+ {
575
+ "epoch": 0.23,
576
+ "learning_rate": 1e-05,
577
+ "loss": 2.1495,
578
+ "step": 950
579
+ },
580
+ {
581
+ "epoch": 0.23,
582
+ "learning_rate": 1e-05,
583
+ "loss": 2.1915,
584
+ "step": 960
585
+ },
586
+ {
587
+ "epoch": 0.23,
588
+ "learning_rate": 1e-05,
589
+ "loss": 2.1903,
590
+ "step": 970
591
+ },
592
+ {
593
+ "epoch": 0.23,
594
+ "learning_rate": 1e-05,
595
+ "loss": 2.0176,
596
+ "step": 980
597
+ },
598
+ {
599
+ "epoch": 0.24,
600
+ "learning_rate": 1e-05,
601
+ "loss": 2.1463,
602
+ "step": 990
603
+ },
604
+ {
605
+ "epoch": 0.24,
606
+ "learning_rate": 1e-05,
607
+ "loss": 2.1042,
608
+ "step": 1000
609
+ },
610
+ {
611
+ "epoch": 0.24,
612
+ "eval_accuracy": 0.2134502923976608,
613
+ "eval_loss": 1.9532288312911987,
614
+ "eval_runtime": 169.591,
615
+ "eval_samples_per_second": 4.033,
616
+ "step": 1000
617
+ }
618
+ ],
619
+ "max_steps": 100000,
620
+ "num_train_epochs": 24,
621
+ "total_flos": 1177438977523712.0,
622
+ "trial_name": null,
623
+ "trial_params": null
624
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddbc966e0624ba13f04caa33cf15ea24cedec2a257b7971cb85195db177b7a8c
3
+ size 2543