TahalliAnas commited on
Commit
e2900c2
·
verified ·
1 Parent(s): 323b3c2

first upload from kaggle

Browse files
checkpoint-1080/config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "T5ForConditionalGeneration"
4
+ ],
5
+ "classifier_dropout": 0.0,
6
+ "d_ff": 3072,
7
+ "d_kv": 64,
8
+ "d_model": 768,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "relu",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "relu",
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "is_gated_act": false,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "t5",
19
+ "n_positions": 512,
20
+ "num_decoder_layers": 12,
21
+ "num_heads": 12,
22
+ "num_layers": 12,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
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
+ "torch_dtype": "float32",
57
+ "transformers_version": "4.51.1",
58
+ "use_cache": true,
59
+ "vocab_size": 32128
60
+ }
checkpoint-1080/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.51.1"
7
+ }
checkpoint-1080/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20f592c9301bbfd8856e31fedacce6afa5a2238219cb7a40eb9d13533780098b
3
+ size 891644712
checkpoint-1080/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9e982a9f5c7a20788ca239d726bd5f258be8a55bd5714e42c981834cf5376c7
3
+ size 1783444794
checkpoint-1080/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf635429f74db96ec787efb7984ec03b8b14e1ecad0702acb8e4da9c573f54ef
3
+ size 14244
checkpoint-1080/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:143a5b3812f11a0ce92f4896d57f598a2f196c87d5b52f7101c582a4b86122c2
3
+ size 1064
checkpoint-1080/special_tokens_map.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": {
105
+ "content": "</s>",
106
+ "lstrip": false,
107
+ "normalized": false,
108
+ "rstrip": false,
109
+ "single_word": false
110
+ },
111
+ "pad_token": {
112
+ "content": "<pad>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "unk_token": {
119
+ "content": "<unk>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ }
125
+ }
checkpoint-1080/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
checkpoint-1080/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1080/tokenizer_config.json ADDED
@@ -0,0 +1,943 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": null,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "32000": {
29
+ "content": "<extra_id_99>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "32001": {
37
+ "content": "<extra_id_98>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "32002": {
45
+ "content": "<extra_id_97>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "32003": {
53
+ "content": "<extra_id_96>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "32004": {
61
+ "content": "<extra_id_95>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "32005": {
69
+ "content": "<extra_id_94>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "32006": {
77
+ "content": "<extra_id_93>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "32007": {
85
+ "content": "<extra_id_92>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "32008": {
93
+ "content": "<extra_id_91>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "32009": {
101
+ "content": "<extra_id_90>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "32010": {
109
+ "content": "<extra_id_89>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "32011": {
117
+ "content": "<extra_id_88>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "32012": {
125
+ "content": "<extra_id_87>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "32013": {
133
+ "content": "<extra_id_86>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "32014": {
141
+ "content": "<extra_id_85>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "32015": {
149
+ "content": "<extra_id_84>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "32016": {
157
+ "content": "<extra_id_83>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "32017": {
165
+ "content": "<extra_id_82>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "32018": {
173
+ "content": "<extra_id_81>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "32019": {
181
+ "content": "<extra_id_80>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "32020": {
189
+ "content": "<extra_id_79>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "32021": {
197
+ "content": "<extra_id_78>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "32022": {
205
+ "content": "<extra_id_77>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "32023": {
213
+ "content": "<extra_id_76>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "32024": {
221
+ "content": "<extra_id_75>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "32025": {
229
+ "content": "<extra_id_74>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "32026": {
237
+ "content": "<extra_id_73>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "32027": {
245
+ "content": "<extra_id_72>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "32028": {
253
+ "content": "<extra_id_71>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "32029": {
261
+ "content": "<extra_id_70>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "32030": {
269
+ "content": "<extra_id_69>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "32031": {
277
+ "content": "<extra_id_68>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "32032": {
285
+ "content": "<extra_id_67>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "32033": {
293
+ "content": "<extra_id_66>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "32034": {
301
+ "content": "<extra_id_65>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "32035": {
309
+ "content": "<extra_id_64>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "32036": {
317
+ "content": "<extra_id_63>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "32037": {
325
+ "content": "<extra_id_62>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "32038": {
333
+ "content": "<extra_id_61>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "32039": {
341
+ "content": "<extra_id_60>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "32040": {
349
+ "content": "<extra_id_59>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "32041": {
357
+ "content": "<extra_id_58>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "32042": {
365
+ "content": "<extra_id_57>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "32043": {
373
+ "content": "<extra_id_56>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "32044": {
381
+ "content": "<extra_id_55>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "32045": {
389
+ "content": "<extra_id_54>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "32046": {
397
+ "content": "<extra_id_53>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "32047": {
405
+ "content": "<extra_id_52>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "32048": {
413
+ "content": "<extra_id_51>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "32049": {
421
+ "content": "<extra_id_50>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "32050": {
429
+ "content": "<extra_id_49>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "32051": {
437
+ "content": "<extra_id_48>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "32052": {
445
+ "content": "<extra_id_47>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "32053": {
453
+ "content": "<extra_id_46>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "32054": {
461
+ "content": "<extra_id_45>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "32055": {
469
+ "content": "<extra_id_44>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "32056": {
477
+ "content": "<extra_id_43>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "32057": {
485
+ "content": "<extra_id_42>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "32058": {
493
+ "content": "<extra_id_41>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "32059": {
501
+ "content": "<extra_id_40>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "32060": {
509
+ "content": "<extra_id_39>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "32061": {
517
+ "content": "<extra_id_38>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "32062": {
525
+ "content": "<extra_id_37>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "32063": {
533
+ "content": "<extra_id_36>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "32064": {
541
+ "content": "<extra_id_35>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "32065": {
549
+ "content": "<extra_id_34>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "32066": {
557
+ "content": "<extra_id_33>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "32067": {
565
+ "content": "<extra_id_32>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "32068": {
573
+ "content": "<extra_id_31>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "32069": {
581
+ "content": "<extra_id_30>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "32070": {
589
+ "content": "<extra_id_29>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "32071": {
597
+ "content": "<extra_id_28>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "32072": {
605
+ "content": "<extra_id_27>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "32073": {
613
+ "content": "<extra_id_26>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "32074": {
621
+ "content": "<extra_id_25>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "32075": {
629
+ "content": "<extra_id_24>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "32076": {
637
+ "content": "<extra_id_23>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "32077": {
645
+ "content": "<extra_id_22>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "32078": {
653
+ "content": "<extra_id_21>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "32079": {
661
+ "content": "<extra_id_20>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "32080": {
669
+ "content": "<extra_id_19>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "32081": {
677
+ "content": "<extra_id_18>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "32082": {
685
+ "content": "<extra_id_17>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "32083": {
693
+ "content": "<extra_id_16>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "32084": {
701
+ "content": "<extra_id_15>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "32085": {
709
+ "content": "<extra_id_14>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "32086": {
717
+ "content": "<extra_id_13>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "32087": {
725
+ "content": "<extra_id_12>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "32088": {
733
+ "content": "<extra_id_11>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "32089": {
741
+ "content": "<extra_id_10>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "32090": {
749
+ "content": "<extra_id_9>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "32091": {
757
+ "content": "<extra_id_8>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "32092": {
765
+ "content": "<extra_id_7>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "32093": {
773
+ "content": "<extra_id_6>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "32094": {
781
+ "content": "<extra_id_5>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "32095": {
789
+ "content": "<extra_id_4>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "32096": {
797
+ "content": "<extra_id_3>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "32097": {
805
+ "content": "<extra_id_2>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "32098": {
813
+ "content": "<extra_id_1>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "32099": {
821
+ "content": "<extra_id_0>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ }
828
+ },
829
+ "additional_special_tokens": [
830
+ "<extra_id_0>",
831
+ "<extra_id_1>",
832
+ "<extra_id_2>",
833
+ "<extra_id_3>",
834
+ "<extra_id_4>",
835
+ "<extra_id_5>",
836
+ "<extra_id_6>",
837
+ "<extra_id_7>",
838
+ "<extra_id_8>",
839
+ "<extra_id_9>",
840
+ "<extra_id_10>",
841
+ "<extra_id_11>",
842
+ "<extra_id_12>",
843
+ "<extra_id_13>",
844
+ "<extra_id_14>",
845
+ "<extra_id_15>",
846
+ "<extra_id_16>",
847
+ "<extra_id_17>",
848
+ "<extra_id_18>",
849
+ "<extra_id_19>",
850
+ "<extra_id_20>",
851
+ "<extra_id_21>",
852
+ "<extra_id_22>",
853
+ "<extra_id_23>",
854
+ "<extra_id_24>",
855
+ "<extra_id_25>",
856
+ "<extra_id_26>",
857
+ "<extra_id_27>",
858
+ "<extra_id_28>",
859
+ "<extra_id_29>",
860
+ "<extra_id_30>",
861
+ "<extra_id_31>",
862
+ "<extra_id_32>",
863
+ "<extra_id_33>",
864
+ "<extra_id_34>",
865
+ "<extra_id_35>",
866
+ "<extra_id_36>",
867
+ "<extra_id_37>",
868
+ "<extra_id_38>",
869
+ "<extra_id_39>",
870
+ "<extra_id_40>",
871
+ "<extra_id_41>",
872
+ "<extra_id_42>",
873
+ "<extra_id_43>",
874
+ "<extra_id_44>",
875
+ "<extra_id_45>",
876
+ "<extra_id_46>",
877
+ "<extra_id_47>",
878
+ "<extra_id_48>",
879
+ "<extra_id_49>",
880
+ "<extra_id_50>",
881
+ "<extra_id_51>",
882
+ "<extra_id_52>",
883
+ "<extra_id_53>",
884
+ "<extra_id_54>",
885
+ "<extra_id_55>",
886
+ "<extra_id_56>",
887
+ "<extra_id_57>",
888
+ "<extra_id_58>",
889
+ "<extra_id_59>",
890
+ "<extra_id_60>",
891
+ "<extra_id_61>",
892
+ "<extra_id_62>",
893
+ "<extra_id_63>",
894
+ "<extra_id_64>",
895
+ "<extra_id_65>",
896
+ "<extra_id_66>",
897
+ "<extra_id_67>",
898
+ "<extra_id_68>",
899
+ "<extra_id_69>",
900
+ "<extra_id_70>",
901
+ "<extra_id_71>",
902
+ "<extra_id_72>",
903
+ "<extra_id_73>",
904
+ "<extra_id_74>",
905
+ "<extra_id_75>",
906
+ "<extra_id_76>",
907
+ "<extra_id_77>",
908
+ "<extra_id_78>",
909
+ "<extra_id_79>",
910
+ "<extra_id_80>",
911
+ "<extra_id_81>",
912
+ "<extra_id_82>",
913
+ "<extra_id_83>",
914
+ "<extra_id_84>",
915
+ "<extra_id_85>",
916
+ "<extra_id_86>",
917
+ "<extra_id_87>",
918
+ "<extra_id_88>",
919
+ "<extra_id_89>",
920
+ "<extra_id_90>",
921
+ "<extra_id_91>",
922
+ "<extra_id_92>",
923
+ "<extra_id_93>",
924
+ "<extra_id_94>",
925
+ "<extra_id_95>",
926
+ "<extra_id_96>",
927
+ "<extra_id_97>",
928
+ "<extra_id_98>",
929
+ "<extra_id_99>"
930
+ ],
931
+ "clean_up_tokenization_spaces": false,
932
+ "eos_token": "</s>",
933
+ "extra_ids": 100,
934
+ "extra_special_tokens": {},
935
+ "max_length": 512,
936
+ "model_max_length": 1000000000000000019884624838656,
937
+ "pad_token": "<pad>",
938
+ "stride": 0,
939
+ "tokenizer_class": "T5Tokenizer",
940
+ "truncation_side": "right",
941
+ "truncation_strategy": "longest_first",
942
+ "unk_token": "<unk>"
943
+ }
checkpoint-1080/trainer_state.json ADDED
@@ -0,0 +1,838 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 6.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1080,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.05555555555555555,
14
+ "grad_norm": 0.49686384201049805,
15
+ "learning_rate": 4.958333333333334e-05,
16
+ "loss": 0.0828,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.1111111111111111,
21
+ "grad_norm": 0.5520921945571899,
22
+ "learning_rate": 4.912037037037037e-05,
23
+ "loss": 0.074,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.16666666666666666,
28
+ "grad_norm": 0.3245736062526703,
29
+ "learning_rate": 4.865740740740741e-05,
30
+ "loss": 0.0576,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.2222222222222222,
35
+ "grad_norm": 0.3899650275707245,
36
+ "learning_rate": 4.819444444444445e-05,
37
+ "loss": 0.065,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.2777777777777778,
42
+ "grad_norm": 0.35350099205970764,
43
+ "learning_rate": 4.773148148148148e-05,
44
+ "loss": 0.055,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.3333333333333333,
49
+ "grad_norm": 0.30941131711006165,
50
+ "learning_rate": 4.726851851851852e-05,
51
+ "loss": 0.0558,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.3888888888888889,
56
+ "grad_norm": 0.3238453269004822,
57
+ "learning_rate": 4.6805555555555556e-05,
58
+ "loss": 0.0508,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.4444444444444444,
63
+ "grad_norm": 0.4079723656177521,
64
+ "learning_rate": 4.6342592592592595e-05,
65
+ "loss": 0.0488,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.5,
70
+ "grad_norm": 0.27488774061203003,
71
+ "learning_rate": 4.5879629629629635e-05,
72
+ "loss": 0.051,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.5555555555555556,
77
+ "grad_norm": 0.27709904313087463,
78
+ "learning_rate": 4.541666666666667e-05,
79
+ "loss": 0.046,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.6111111111111112,
84
+ "grad_norm": 0.22847816348075867,
85
+ "learning_rate": 4.49537037037037e-05,
86
+ "loss": 0.0439,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.6666666666666666,
91
+ "grad_norm": 0.23230929672718048,
92
+ "learning_rate": 4.449074074074074e-05,
93
+ "loss": 0.045,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.7222222222222222,
98
+ "grad_norm": 0.19948454201221466,
99
+ "learning_rate": 4.402777777777778e-05,
100
+ "loss": 0.0431,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.7777777777777778,
105
+ "grad_norm": 0.3548349142074585,
106
+ "learning_rate": 4.356481481481482e-05,
107
+ "loss": 0.0442,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.8333333333333334,
112
+ "grad_norm": 0.23642666637897491,
113
+ "learning_rate": 4.3101851851851854e-05,
114
+ "loss": 0.0383,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.8888888888888888,
119
+ "grad_norm": 0.262961208820343,
120
+ "learning_rate": 4.263888888888889e-05,
121
+ "loss": 0.0416,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.9444444444444444,
126
+ "grad_norm": 0.21744681894779205,
127
+ "learning_rate": 4.217592592592593e-05,
128
+ "loss": 0.0427,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 1.0,
133
+ "grad_norm": 0.2349257618188858,
134
+ "learning_rate": 4.171296296296297e-05,
135
+ "loss": 0.0412,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 1.0,
140
+ "eval_loss": 0.029657404869794846,
141
+ "eval_runtime": 6.5879,
142
+ "eval_samples_per_second": 48.574,
143
+ "eval_steps_per_second": 3.036,
144
+ "step": 180
145
+ },
146
+ {
147
+ "epoch": 1.0555555555555556,
148
+ "grad_norm": 0.20215728878974915,
149
+ "learning_rate": 4.125e-05,
150
+ "loss": 0.0384,
151
+ "step": 190
152
+ },
153
+ {
154
+ "epoch": 1.1111111111111112,
155
+ "grad_norm": 0.15817931294441223,
156
+ "learning_rate": 4.078703703703704e-05,
157
+ "loss": 0.0409,
158
+ "step": 200
159
+ },
160
+ {
161
+ "epoch": 1.1666666666666667,
162
+ "grad_norm": 0.1944839209318161,
163
+ "learning_rate": 4.032407407407407e-05,
164
+ "loss": 0.04,
165
+ "step": 210
166
+ },
167
+ {
168
+ "epoch": 1.2222222222222223,
169
+ "grad_norm": 0.40207526087760925,
170
+ "learning_rate": 3.986111111111111e-05,
171
+ "loss": 0.0372,
172
+ "step": 220
173
+ },
174
+ {
175
+ "epoch": 1.2777777777777777,
176
+ "grad_norm": 0.27425676584243774,
177
+ "learning_rate": 3.939814814814815e-05,
178
+ "loss": 0.037,
179
+ "step": 230
180
+ },
181
+ {
182
+ "epoch": 1.3333333333333333,
183
+ "grad_norm": 0.148152157664299,
184
+ "learning_rate": 3.8935185185185185e-05,
185
+ "loss": 0.0366,
186
+ "step": 240
187
+ },
188
+ {
189
+ "epoch": 1.3888888888888888,
190
+ "grad_norm": 0.1749790757894516,
191
+ "learning_rate": 3.8472222222222225e-05,
192
+ "loss": 0.0397,
193
+ "step": 250
194
+ },
195
+ {
196
+ "epoch": 1.4444444444444444,
197
+ "grad_norm": 0.25152885913848877,
198
+ "learning_rate": 3.800925925925926e-05,
199
+ "loss": 0.0384,
200
+ "step": 260
201
+ },
202
+ {
203
+ "epoch": 1.5,
204
+ "grad_norm": 0.15564148128032684,
205
+ "learning_rate": 3.75462962962963e-05,
206
+ "loss": 0.0367,
207
+ "step": 270
208
+ },
209
+ {
210
+ "epoch": 1.5555555555555556,
211
+ "grad_norm": 0.277736634016037,
212
+ "learning_rate": 3.708333333333334e-05,
213
+ "loss": 0.0361,
214
+ "step": 280
215
+ },
216
+ {
217
+ "epoch": 1.6111111111111112,
218
+ "grad_norm": 0.1521805077791214,
219
+ "learning_rate": 3.662037037037037e-05,
220
+ "loss": 0.0358,
221
+ "step": 290
222
+ },
223
+ {
224
+ "epoch": 1.6666666666666665,
225
+ "grad_norm": 0.20427845418453217,
226
+ "learning_rate": 3.6157407407407404e-05,
227
+ "loss": 0.0358,
228
+ "step": 300
229
+ },
230
+ {
231
+ "epoch": 1.7222222222222223,
232
+ "grad_norm": 0.1444249451160431,
233
+ "learning_rate": 3.5694444444444444e-05,
234
+ "loss": 0.036,
235
+ "step": 310
236
+ },
237
+ {
238
+ "epoch": 1.7777777777777777,
239
+ "grad_norm": 0.16637395322322845,
240
+ "learning_rate": 3.5231481481481484e-05,
241
+ "loss": 0.0351,
242
+ "step": 320
243
+ },
244
+ {
245
+ "epoch": 1.8333333333333335,
246
+ "grad_norm": 0.19704970717430115,
247
+ "learning_rate": 3.4768518518518524e-05,
248
+ "loss": 0.0338,
249
+ "step": 330
250
+ },
251
+ {
252
+ "epoch": 1.8888888888888888,
253
+ "grad_norm": 0.18837705254554749,
254
+ "learning_rate": 3.430555555555556e-05,
255
+ "loss": 0.0324,
256
+ "step": 340
257
+ },
258
+ {
259
+ "epoch": 1.9444444444444444,
260
+ "grad_norm": 0.2518753111362457,
261
+ "learning_rate": 3.384259259259259e-05,
262
+ "loss": 0.0379,
263
+ "step": 350
264
+ },
265
+ {
266
+ "epoch": 2.0,
267
+ "grad_norm": 0.2375190258026123,
268
+ "learning_rate": 3.337962962962963e-05,
269
+ "loss": 0.0348,
270
+ "step": 360
271
+ },
272
+ {
273
+ "epoch": 2.0,
274
+ "eval_loss": 0.02760537900030613,
275
+ "eval_runtime": 6.5831,
276
+ "eval_samples_per_second": 48.61,
277
+ "eval_steps_per_second": 3.038,
278
+ "step": 360
279
+ },
280
+ {
281
+ "epoch": 2.0555555555555554,
282
+ "grad_norm": 0.13346998393535614,
283
+ "learning_rate": 3.291666666666667e-05,
284
+ "loss": 0.0365,
285
+ "step": 370
286
+ },
287
+ {
288
+ "epoch": 2.111111111111111,
289
+ "grad_norm": 0.21457839012145996,
290
+ "learning_rate": 3.24537037037037e-05,
291
+ "loss": 0.0336,
292
+ "step": 380
293
+ },
294
+ {
295
+ "epoch": 2.1666666666666665,
296
+ "grad_norm": 0.12173231691122055,
297
+ "learning_rate": 3.199074074074074e-05,
298
+ "loss": 0.0341,
299
+ "step": 390
300
+ },
301
+ {
302
+ "epoch": 2.2222222222222223,
303
+ "grad_norm": 0.15279892086982727,
304
+ "learning_rate": 3.1527777777777775e-05,
305
+ "loss": 0.032,
306
+ "step": 400
307
+ },
308
+ {
309
+ "epoch": 2.2777777777777777,
310
+ "grad_norm": 0.18990376591682434,
311
+ "learning_rate": 3.106481481481482e-05,
312
+ "loss": 0.0349,
313
+ "step": 410
314
+ },
315
+ {
316
+ "epoch": 2.3333333333333335,
317
+ "grad_norm": 0.29108214378356934,
318
+ "learning_rate": 3.0601851851851855e-05,
319
+ "loss": 0.0326,
320
+ "step": 420
321
+ },
322
+ {
323
+ "epoch": 2.388888888888889,
324
+ "grad_norm": 0.14332085847854614,
325
+ "learning_rate": 3.0138888888888888e-05,
326
+ "loss": 0.0328,
327
+ "step": 430
328
+ },
329
+ {
330
+ "epoch": 2.4444444444444446,
331
+ "grad_norm": 0.12165053933858871,
332
+ "learning_rate": 2.9675925925925928e-05,
333
+ "loss": 0.0326,
334
+ "step": 440
335
+ },
336
+ {
337
+ "epoch": 2.5,
338
+ "grad_norm": 0.22552748024463654,
339
+ "learning_rate": 2.9212962962962964e-05,
340
+ "loss": 0.0331,
341
+ "step": 450
342
+ },
343
+ {
344
+ "epoch": 2.5555555555555554,
345
+ "grad_norm": 0.3424241244792938,
346
+ "learning_rate": 2.8749999999999997e-05,
347
+ "loss": 0.0325,
348
+ "step": 460
349
+ },
350
+ {
351
+ "epoch": 2.611111111111111,
352
+ "grad_norm": 0.13250669836997986,
353
+ "learning_rate": 2.828703703703704e-05,
354
+ "loss": 0.0315,
355
+ "step": 470
356
+ },
357
+ {
358
+ "epoch": 2.6666666666666665,
359
+ "grad_norm": 0.15798448026180267,
360
+ "learning_rate": 2.7824074074074074e-05,
361
+ "loss": 0.0315,
362
+ "step": 480
363
+ },
364
+ {
365
+ "epoch": 2.7222222222222223,
366
+ "grad_norm": 0.10952693223953247,
367
+ "learning_rate": 2.7361111111111114e-05,
368
+ "loss": 0.0311,
369
+ "step": 490
370
+ },
371
+ {
372
+ "epoch": 2.7777777777777777,
373
+ "grad_norm": 0.17310163378715515,
374
+ "learning_rate": 2.689814814814815e-05,
375
+ "loss": 0.0326,
376
+ "step": 500
377
+ },
378
+ {
379
+ "epoch": 2.8333333333333335,
380
+ "grad_norm": 0.14377371966838837,
381
+ "learning_rate": 2.6435185185185187e-05,
382
+ "loss": 0.0332,
383
+ "step": 510
384
+ },
385
+ {
386
+ "epoch": 2.888888888888889,
387
+ "grad_norm": 0.10982959717512131,
388
+ "learning_rate": 2.5972222222222226e-05,
389
+ "loss": 0.0331,
390
+ "step": 520
391
+ },
392
+ {
393
+ "epoch": 2.9444444444444446,
394
+ "grad_norm": 0.1141400933265686,
395
+ "learning_rate": 2.550925925925926e-05,
396
+ "loss": 0.033,
397
+ "step": 530
398
+ },
399
+ {
400
+ "epoch": 3.0,
401
+ "grad_norm": 0.0858101025223732,
402
+ "learning_rate": 2.5046296296296296e-05,
403
+ "loss": 0.032,
404
+ "step": 540
405
+ },
406
+ {
407
+ "epoch": 3.0,
408
+ "eval_loss": 0.027356069535017014,
409
+ "eval_runtime": 6.321,
410
+ "eval_samples_per_second": 50.625,
411
+ "eval_steps_per_second": 3.164,
412
+ "step": 540
413
+ },
414
+ {
415
+ "epoch": 3.0555555555555554,
416
+ "grad_norm": 0.159243643283844,
417
+ "learning_rate": 2.4583333333333332e-05,
418
+ "loss": 0.0299,
419
+ "step": 550
420
+ },
421
+ {
422
+ "epoch": 3.111111111111111,
423
+ "grad_norm": 0.08856271952390671,
424
+ "learning_rate": 2.4120370370370372e-05,
425
+ "loss": 0.0317,
426
+ "step": 560
427
+ },
428
+ {
429
+ "epoch": 3.1666666666666665,
430
+ "grad_norm": 0.13010160624980927,
431
+ "learning_rate": 2.365740740740741e-05,
432
+ "loss": 0.0322,
433
+ "step": 570
434
+ },
435
+ {
436
+ "epoch": 3.2222222222222223,
437
+ "grad_norm": 0.10837047547101974,
438
+ "learning_rate": 2.3194444444444445e-05,
439
+ "loss": 0.0325,
440
+ "step": 580
441
+ },
442
+ {
443
+ "epoch": 3.2777777777777777,
444
+ "grad_norm": 0.17628169059753418,
445
+ "learning_rate": 2.273148148148148e-05,
446
+ "loss": 0.0318,
447
+ "step": 590
448
+ },
449
+ {
450
+ "epoch": 3.3333333333333335,
451
+ "grad_norm": 0.1559268981218338,
452
+ "learning_rate": 2.2268518518518518e-05,
453
+ "loss": 0.033,
454
+ "step": 600
455
+ },
456
+ {
457
+ "epoch": 3.388888888888889,
458
+ "grad_norm": 0.15573599934577942,
459
+ "learning_rate": 2.1805555555555558e-05,
460
+ "loss": 0.0314,
461
+ "step": 610
462
+ },
463
+ {
464
+ "epoch": 3.4444444444444446,
465
+ "grad_norm": 0.13026462495326996,
466
+ "learning_rate": 2.1342592592592594e-05,
467
+ "loss": 0.0319,
468
+ "step": 620
469
+ },
470
+ {
471
+ "epoch": 3.5,
472
+ "grad_norm": 0.11255809664726257,
473
+ "learning_rate": 2.087962962962963e-05,
474
+ "loss": 0.0306,
475
+ "step": 630
476
+ },
477
+ {
478
+ "epoch": 3.5555555555555554,
479
+ "grad_norm": 0.15510410070419312,
480
+ "learning_rate": 2.0416666666666667e-05,
481
+ "loss": 0.0538,
482
+ "step": 640
483
+ },
484
+ {
485
+ "epoch": 3.611111111111111,
486
+ "grad_norm": 0.10521262139081955,
487
+ "learning_rate": 1.9953703703703704e-05,
488
+ "loss": 0.03,
489
+ "step": 650
490
+ },
491
+ {
492
+ "epoch": 3.6666666666666665,
493
+ "grad_norm": 0.14359714090824127,
494
+ "learning_rate": 1.9490740740740743e-05,
495
+ "loss": 0.0334,
496
+ "step": 660
497
+ },
498
+ {
499
+ "epoch": 3.7222222222222223,
500
+ "grad_norm": 0.11077132821083069,
501
+ "learning_rate": 1.9027777777777776e-05,
502
+ "loss": 0.0299,
503
+ "step": 670
504
+ },
505
+ {
506
+ "epoch": 3.7777777777777777,
507
+ "grad_norm": 0.1317073106765747,
508
+ "learning_rate": 1.8564814814814816e-05,
509
+ "loss": 0.0327,
510
+ "step": 680
511
+ },
512
+ {
513
+ "epoch": 3.8333333333333335,
514
+ "grad_norm": 0.13942557573318481,
515
+ "learning_rate": 1.8101851851851853e-05,
516
+ "loss": 0.0318,
517
+ "step": 690
518
+ },
519
+ {
520
+ "epoch": 3.888888888888889,
521
+ "grad_norm": 0.10866592079401016,
522
+ "learning_rate": 1.763888888888889e-05,
523
+ "loss": 0.0293,
524
+ "step": 700
525
+ },
526
+ {
527
+ "epoch": 3.9444444444444446,
528
+ "grad_norm": 0.10337399691343307,
529
+ "learning_rate": 1.7175925925925926e-05,
530
+ "loss": 0.0306,
531
+ "step": 710
532
+ },
533
+ {
534
+ "epoch": 4.0,
535
+ "grad_norm": 0.08381380140781403,
536
+ "learning_rate": 1.6712962962962962e-05,
537
+ "loss": 0.0306,
538
+ "step": 720
539
+ },
540
+ {
541
+ "epoch": 4.0,
542
+ "eval_loss": 0.02674299106001854,
543
+ "eval_runtime": 6.3173,
544
+ "eval_samples_per_second": 50.655,
545
+ "eval_steps_per_second": 3.166,
546
+ "step": 720
547
+ },
548
+ {
549
+ "epoch": 4.055555555555555,
550
+ "grad_norm": 0.20555126667022705,
551
+ "learning_rate": 1.6250000000000002e-05,
552
+ "loss": 0.0298,
553
+ "step": 730
554
+ },
555
+ {
556
+ "epoch": 4.111111111111111,
557
+ "grad_norm": 0.11750379204750061,
558
+ "learning_rate": 1.578703703703704e-05,
559
+ "loss": 0.0298,
560
+ "step": 740
561
+ },
562
+ {
563
+ "epoch": 4.166666666666667,
564
+ "grad_norm": 0.11085871607065201,
565
+ "learning_rate": 1.5324074074074075e-05,
566
+ "loss": 0.0305,
567
+ "step": 750
568
+ },
569
+ {
570
+ "epoch": 4.222222222222222,
571
+ "grad_norm": 0.12449198961257935,
572
+ "learning_rate": 1.4861111111111111e-05,
573
+ "loss": 0.03,
574
+ "step": 760
575
+ },
576
+ {
577
+ "epoch": 4.277777777777778,
578
+ "grad_norm": 0.14551545679569244,
579
+ "learning_rate": 1.439814814814815e-05,
580
+ "loss": 0.0308,
581
+ "step": 770
582
+ },
583
+ {
584
+ "epoch": 4.333333333333333,
585
+ "grad_norm": 0.1231958270072937,
586
+ "learning_rate": 1.3935185185185188e-05,
587
+ "loss": 0.0312,
588
+ "step": 780
589
+ },
590
+ {
591
+ "epoch": 4.388888888888889,
592
+ "grad_norm": 0.1063426211476326,
593
+ "learning_rate": 1.3472222222222222e-05,
594
+ "loss": 0.0298,
595
+ "step": 790
596
+ },
597
+ {
598
+ "epoch": 4.444444444444445,
599
+ "grad_norm": 0.12436050921678543,
600
+ "learning_rate": 1.300925925925926e-05,
601
+ "loss": 0.0315,
602
+ "step": 800
603
+ },
604
+ {
605
+ "epoch": 4.5,
606
+ "grad_norm": 0.13953514397144318,
607
+ "learning_rate": 1.2546296296296297e-05,
608
+ "loss": 0.0314,
609
+ "step": 810
610
+ },
611
+ {
612
+ "epoch": 4.555555555555555,
613
+ "grad_norm": 0.0922839418053627,
614
+ "learning_rate": 1.2083333333333333e-05,
615
+ "loss": 0.0308,
616
+ "step": 820
617
+ },
618
+ {
619
+ "epoch": 4.611111111111111,
620
+ "grad_norm": 0.13846085965633392,
621
+ "learning_rate": 1.162037037037037e-05,
622
+ "loss": 0.0297,
623
+ "step": 830
624
+ },
625
+ {
626
+ "epoch": 4.666666666666667,
627
+ "grad_norm": 0.07957114279270172,
628
+ "learning_rate": 1.1157407407407408e-05,
629
+ "loss": 0.0298,
630
+ "step": 840
631
+ },
632
+ {
633
+ "epoch": 4.722222222222222,
634
+ "grad_norm": 0.0851704403758049,
635
+ "learning_rate": 1.0694444444444444e-05,
636
+ "loss": 0.0318,
637
+ "step": 850
638
+ },
639
+ {
640
+ "epoch": 4.777777777777778,
641
+ "grad_norm": 0.11411622166633606,
642
+ "learning_rate": 1.0231481481481483e-05,
643
+ "loss": 0.0295,
644
+ "step": 860
645
+ },
646
+ {
647
+ "epoch": 4.833333333333333,
648
+ "grad_norm": 0.10176681727170944,
649
+ "learning_rate": 9.768518518518519e-06,
650
+ "loss": 0.0316,
651
+ "step": 870
652
+ },
653
+ {
654
+ "epoch": 4.888888888888889,
655
+ "grad_norm": 0.0951576679944992,
656
+ "learning_rate": 9.305555555555555e-06,
657
+ "loss": 0.0308,
658
+ "step": 880
659
+ },
660
+ {
661
+ "epoch": 4.944444444444445,
662
+ "grad_norm": 0.08655095100402832,
663
+ "learning_rate": 8.842592592592592e-06,
664
+ "loss": 0.0294,
665
+ "step": 890
666
+ },
667
+ {
668
+ "epoch": 5.0,
669
+ "grad_norm": 0.1173749566078186,
670
+ "learning_rate": 8.37962962962963e-06,
671
+ "loss": 0.0307,
672
+ "step": 900
673
+ },
674
+ {
675
+ "epoch": 5.0,
676
+ "eval_loss": 0.026756376028060913,
677
+ "eval_runtime": 6.4257,
678
+ "eval_samples_per_second": 49.8,
679
+ "eval_steps_per_second": 3.112,
680
+ "step": 900
681
+ },
682
+ {
683
+ "epoch": 5.055555555555555,
684
+ "grad_norm": 0.10281986743211746,
685
+ "learning_rate": 7.916666666666667e-06,
686
+ "loss": 0.0281,
687
+ "step": 910
688
+ },
689
+ {
690
+ "epoch": 5.111111111111111,
691
+ "grad_norm": 0.10464879125356674,
692
+ "learning_rate": 7.453703703703705e-06,
693
+ "loss": 0.0295,
694
+ "step": 920
695
+ },
696
+ {
697
+ "epoch": 5.166666666666667,
698
+ "grad_norm": 0.14110395312309265,
699
+ "learning_rate": 6.990740740740741e-06,
700
+ "loss": 0.0303,
701
+ "step": 930
702
+ },
703
+ {
704
+ "epoch": 5.222222222222222,
705
+ "grad_norm": 0.08916814625263214,
706
+ "learning_rate": 6.5277777777777784e-06,
707
+ "loss": 0.0303,
708
+ "step": 940
709
+ },
710
+ {
711
+ "epoch": 5.277777777777778,
712
+ "grad_norm": 0.08186755329370499,
713
+ "learning_rate": 6.064814814814815e-06,
714
+ "loss": 0.0305,
715
+ "step": 950
716
+ },
717
+ {
718
+ "epoch": 5.333333333333333,
719
+ "grad_norm": 0.10332108289003372,
720
+ "learning_rate": 5.601851851851852e-06,
721
+ "loss": 0.0303,
722
+ "step": 960
723
+ },
724
+ {
725
+ "epoch": 5.388888888888889,
726
+ "grad_norm": 0.09380320459604263,
727
+ "learning_rate": 5.138888888888889e-06,
728
+ "loss": 0.0281,
729
+ "step": 970
730
+ },
731
+ {
732
+ "epoch": 5.444444444444445,
733
+ "grad_norm": 0.1488436758518219,
734
+ "learning_rate": 4.675925925925926e-06,
735
+ "loss": 0.0308,
736
+ "step": 980
737
+ },
738
+ {
739
+ "epoch": 5.5,
740
+ "grad_norm": 0.11125043779611588,
741
+ "learning_rate": 4.212962962962963e-06,
742
+ "loss": 0.0309,
743
+ "step": 990
744
+ },
745
+ {
746
+ "epoch": 5.555555555555555,
747
+ "grad_norm": 0.08724004775285721,
748
+ "learning_rate": 3.75e-06,
749
+ "loss": 0.0318,
750
+ "step": 1000
751
+ },
752
+ {
753
+ "epoch": 5.611111111111111,
754
+ "grad_norm": 0.12417462468147278,
755
+ "learning_rate": 3.287037037037037e-06,
756
+ "loss": 0.0296,
757
+ "step": 1010
758
+ },
759
+ {
760
+ "epoch": 5.666666666666667,
761
+ "grad_norm": 0.08415894210338593,
762
+ "learning_rate": 2.8240740740740743e-06,
763
+ "loss": 0.0311,
764
+ "step": 1020
765
+ },
766
+ {
767
+ "epoch": 5.722222222222222,
768
+ "grad_norm": 0.09413722902536392,
769
+ "learning_rate": 2.361111111111111e-06,
770
+ "loss": 0.0309,
771
+ "step": 1030
772
+ },
773
+ {
774
+ "epoch": 5.777777777777778,
775
+ "grad_norm": 0.08906271308660507,
776
+ "learning_rate": 1.8981481481481482e-06,
777
+ "loss": 0.0331,
778
+ "step": 1040
779
+ },
780
+ {
781
+ "epoch": 5.833333333333333,
782
+ "grad_norm": 0.2548229992389679,
783
+ "learning_rate": 1.4351851851851853e-06,
784
+ "loss": 0.0325,
785
+ "step": 1050
786
+ },
787
+ {
788
+ "epoch": 5.888888888888889,
789
+ "grad_norm": 0.2592361569404602,
790
+ "learning_rate": 9.722222222222222e-07,
791
+ "loss": 0.0291,
792
+ "step": 1060
793
+ },
794
+ {
795
+ "epoch": 5.944444444444445,
796
+ "grad_norm": 0.13197167217731476,
797
+ "learning_rate": 5.092592592592594e-07,
798
+ "loss": 0.0298,
799
+ "step": 1070
800
+ },
801
+ {
802
+ "epoch": 6.0,
803
+ "grad_norm": 0.0932869166135788,
804
+ "learning_rate": 4.62962962962963e-08,
805
+ "loss": 0.0309,
806
+ "step": 1080
807
+ },
808
+ {
809
+ "epoch": 6.0,
810
+ "eval_loss": 0.026577139273285866,
811
+ "eval_runtime": 6.4249,
812
+ "eval_samples_per_second": 49.806,
813
+ "eval_steps_per_second": 3.113,
814
+ "step": 1080
815
+ }
816
+ ],
817
+ "logging_steps": 10,
818
+ "max_steps": 1080,
819
+ "num_input_tokens_seen": 0,
820
+ "num_train_epochs": 6,
821
+ "save_steps": 500,
822
+ "stateful_callbacks": {
823
+ "TrainerControl": {
824
+ "args": {
825
+ "should_epoch_stop": false,
826
+ "should_evaluate": false,
827
+ "should_log": false,
828
+ "should_save": true,
829
+ "should_training_stop": true
830
+ },
831
+ "attributes": {}
832
+ }
833
+ },
834
+ "total_flos": 2397334005596160.0,
835
+ "train_batch_size": 16,
836
+ "trial_name": null,
837
+ "trial_params": null
838
+ }
checkpoint-1080/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75bef3ad977a2a011647fcdf05ef1333617d0a8cbd7e85fb7c2b6ab8e531adf2
3
+ size 5432
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e80e19e6532baaadc84f26899f4ab298ae62a1bd774601f8d0a59935fd88019c
3
  size 891644712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20f592c9301bbfd8856e31fedacce6afa5a2238219cb7a40eb9d13533780098b
3
  size 891644712
special_tokens_map.json CHANGED
@@ -101,7 +101,25 @@
101
  "<extra_id_98>",
102
  "<extra_id_99>"
103
  ],
104
- "eos_token": "</s>",
105
- "pad_token": "<pad>",
106
- "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
107
  }
 
101
  "<extra_id_98>",
102
  "<extra_id_99>"
103
  ],
104
+ "eos_token": {
105
+ "content": "</s>",
106
+ "lstrip": false,
107
+ "normalized": false,
108
+ "rstrip": false,
109
+ "single_word": false
110
+ },
111
+ "pad_token": {
112
+ "content": "<pad>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "unk_token": {
119
+ "content": "<unk>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ }
125
  }
tokenizer_config.json CHANGED
@@ -932,8 +932,12 @@
932
  "eos_token": "</s>",
933
  "extra_ids": 100,
934
  "extra_special_tokens": {},
 
935
  "model_max_length": 1000000000000000019884624838656,
936
  "pad_token": "<pad>",
 
937
  "tokenizer_class": "T5Tokenizer",
 
 
938
  "unk_token": "<unk>"
939
  }
 
932
  "eos_token": "</s>",
933
  "extra_ids": 100,
934
  "extra_special_tokens": {},
935
+ "max_length": 512,
936
  "model_max_length": 1000000000000000019884624838656,
937
  "pad_token": "<pad>",
938
+ "stride": 0,
939
  "tokenizer_class": "T5Tokenizer",
940
+ "truncation_side": "right",
941
+ "truncation_strategy": "longest_first",
942
  "unk_token": "<unk>"
943
  }