TahalliAnas commited on
Commit
0fa496e
·
verified ·
1 Parent(s): 8e63504

first upload from kaggle

Browse files
checkpoint-3504/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-3504/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-3504/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70879216cd6ea3ceb50cdb0fe9b86860601a7043056bb3911b57091a58c969de
3
+ size 891644712
checkpoint-3504/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2e80b1273df41fe7fc7fdf81ddfb1ce21ee83a01f7ace208d04f1059fb43855
3
+ size 1783444794
checkpoint-3504/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90594e0becf2784c4e045359004be216ceb29fd2e2b0710bac8a1c236380aead
3
+ size 14244
checkpoint-3504/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:004b9277dab993fe0469ef4557b527b9f5efcbbb494b3edc984204d0f772b506
3
+ size 1064
checkpoint-3504/special_tokens_map.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "</s>",
105
+ "pad_token": "<pad>",
106
+ "unk_token": "<unk>"
107
+ }
checkpoint-3504/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
checkpoint-3504/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-3504/tokenizer_config.json ADDED
@@ -0,0 +1,939 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "model_max_length": 1000000000000000019884624838656,
936
+ "pad_token": "<pad>",
937
+ "tokenizer_class": "T5Tokenizer",
938
+ "unk_token": "<unk>"
939
+ }
checkpoint-3504/trainer_state.json ADDED
@@ -0,0 +1,2548 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 8.0,
6
+ "eval_steps": 500,
7
+ "global_step": 3504,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0228310502283105,
14
+ "grad_norm": 2.228510856628418,
15
+ "learning_rate": 4.987157534246575e-05,
16
+ "loss": 6.6129,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.045662100456621,
21
+ "grad_norm": 1.832844614982605,
22
+ "learning_rate": 4.9728881278538815e-05,
23
+ "loss": 3.1197,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.0684931506849315,
28
+ "grad_norm": 1.3700411319732666,
29
+ "learning_rate": 4.958618721461187e-05,
30
+ "loss": 2.1387,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.091324200913242,
35
+ "grad_norm": 1.3453809022903442,
36
+ "learning_rate": 4.9443493150684935e-05,
37
+ "loss": 1.4287,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.1141552511415525,
42
+ "grad_norm": 1.195481777191162,
43
+ "learning_rate": 4.930079908675799e-05,
44
+ "loss": 0.9585,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.136986301369863,
49
+ "grad_norm": 1.0389988422393799,
50
+ "learning_rate": 4.9158105022831055e-05,
51
+ "loss": 0.5942,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.1598173515981735,
56
+ "grad_norm": 0.9327354431152344,
57
+ "learning_rate": 4.901541095890411e-05,
58
+ "loss": 0.4014,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.182648401826484,
63
+ "grad_norm": 0.791429340839386,
64
+ "learning_rate": 4.8872716894977175e-05,
65
+ "loss": 0.2836,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.2054794520547945,
70
+ "grad_norm": 0.7389950156211853,
71
+ "learning_rate": 4.873002283105023e-05,
72
+ "loss": 0.1995,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.228310502283105,
77
+ "grad_norm": 0.6029524207115173,
78
+ "learning_rate": 4.8587328767123295e-05,
79
+ "loss": 0.1431,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.2511415525114155,
84
+ "grad_norm": 0.5200534462928772,
85
+ "learning_rate": 4.844463470319635e-05,
86
+ "loss": 0.1019,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.273972602739726,
91
+ "grad_norm": 0.6404463648796082,
92
+ "learning_rate": 4.830194063926941e-05,
93
+ "loss": 0.0846,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.2968036529680365,
98
+ "grad_norm": 0.4442310631275177,
99
+ "learning_rate": 4.815924657534247e-05,
100
+ "loss": 0.0654,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.319634703196347,
105
+ "grad_norm": 0.4031509757041931,
106
+ "learning_rate": 4.801655251141553e-05,
107
+ "loss": 0.0542,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.3424657534246575,
112
+ "grad_norm": 0.4141863286495209,
113
+ "learning_rate": 4.7873858447488584e-05,
114
+ "loss": 0.0508,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.365296803652968,
119
+ "grad_norm": 0.3440322279930115,
120
+ "learning_rate": 4.773116438356164e-05,
121
+ "loss": 0.0391,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.3881278538812785,
126
+ "grad_norm": 0.6025522947311401,
127
+ "learning_rate": 4.7588470319634704e-05,
128
+ "loss": 0.0381,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.410958904109589,
133
+ "grad_norm": 0.34279781579971313,
134
+ "learning_rate": 4.744577625570776e-05,
135
+ "loss": 0.0339,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.4337899543378995,
140
+ "grad_norm": 0.3098609149456024,
141
+ "learning_rate": 4.7303082191780824e-05,
142
+ "loss": 0.0301,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.45662100456621,
147
+ "grad_norm": 0.29201066493988037,
148
+ "learning_rate": 4.716038812785388e-05,
149
+ "loss": 0.0287,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.4794520547945205,
154
+ "grad_norm": 0.2325911968946457,
155
+ "learning_rate": 4.7017694063926944e-05,
156
+ "loss": 0.0258,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.502283105022831,
161
+ "grad_norm": 0.2296101152896881,
162
+ "learning_rate": 4.6875e-05,
163
+ "loss": 0.0227,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.5251141552511416,
168
+ "grad_norm": 0.24569889903068542,
169
+ "learning_rate": 4.6732305936073064e-05,
170
+ "loss": 0.0232,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.547945205479452,
175
+ "grad_norm": 0.22321540117263794,
176
+ "learning_rate": 4.658961187214612e-05,
177
+ "loss": 0.018,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.5707762557077626,
182
+ "grad_norm": 0.26079800724983215,
183
+ "learning_rate": 4.6446917808219184e-05,
184
+ "loss": 0.0192,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.593607305936073,
189
+ "grad_norm": 0.29277801513671875,
190
+ "learning_rate": 4.630422374429224e-05,
191
+ "loss": 0.02,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.6164383561643836,
196
+ "grad_norm": 0.2620185315608978,
197
+ "learning_rate": 4.61615296803653e-05,
198
+ "loss": 0.0172,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.639269406392694,
203
+ "grad_norm": 0.32734254002571106,
204
+ "learning_rate": 4.601883561643836e-05,
205
+ "loss": 0.0191,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.6621004566210046,
210
+ "grad_norm": 0.34528958797454834,
211
+ "learning_rate": 4.587614155251142e-05,
212
+ "loss": 0.0151,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.684931506849315,
217
+ "grad_norm": 0.16524860262870789,
218
+ "learning_rate": 4.5733447488584474e-05,
219
+ "loss": 0.0154,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.7077625570776256,
224
+ "grad_norm": 0.17619894444942474,
225
+ "learning_rate": 4.559075342465753e-05,
226
+ "loss": 0.0141,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.730593607305936,
231
+ "grad_norm": 0.18591953814029694,
232
+ "learning_rate": 4.5448059360730594e-05,
233
+ "loss": 0.0128,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.7534246575342466,
238
+ "grad_norm": 0.17972640693187714,
239
+ "learning_rate": 4.530536529680365e-05,
240
+ "loss": 0.0119,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.776255707762557,
245
+ "grad_norm": 0.2308385968208313,
246
+ "learning_rate": 4.5162671232876714e-05,
247
+ "loss": 0.0114,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.7990867579908676,
252
+ "grad_norm": 0.13175222277641296,
253
+ "learning_rate": 4.501997716894977e-05,
254
+ "loss": 0.0107,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.821917808219178,
259
+ "grad_norm": 0.1399480700492859,
260
+ "learning_rate": 4.4877283105022834e-05,
261
+ "loss": 0.0097,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.8447488584474886,
266
+ "grad_norm": 0.12605524063110352,
267
+ "learning_rate": 4.473458904109589e-05,
268
+ "loss": 0.0112,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.867579908675799,
273
+ "grad_norm": 0.16242380440235138,
274
+ "learning_rate": 4.4591894977168954e-05,
275
+ "loss": 0.0099,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.8904109589041096,
280
+ "grad_norm": 0.12138999998569489,
281
+ "learning_rate": 4.444920091324201e-05,
282
+ "loss": 0.0089,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.91324200913242,
287
+ "grad_norm": 0.22154438495635986,
288
+ "learning_rate": 4.4306506849315074e-05,
289
+ "loss": 0.009,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.9360730593607306,
294
+ "grad_norm": 0.09284752607345581,
295
+ "learning_rate": 4.416381278538813e-05,
296
+ "loss": 0.0079,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.958904109589041,
301
+ "grad_norm": 0.2589144706726074,
302
+ "learning_rate": 4.4021118721461194e-05,
303
+ "loss": 0.0077,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.9817351598173516,
308
+ "grad_norm": 0.18040631711483002,
309
+ "learning_rate": 4.387842465753425e-05,
310
+ "loss": 0.0073,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 1.0,
315
+ "eval_loss": 0.0013460684567689896,
316
+ "eval_runtime": 71.4572,
317
+ "eval_samples_per_second": 41.983,
318
+ "eval_steps_per_second": 2.631,
319
+ "step": 438
320
+ },
321
+ {
322
+ "epoch": 1.004566210045662,
323
+ "grad_norm": 0.16953226923942566,
324
+ "learning_rate": 4.373573059360731e-05,
325
+ "loss": 0.0071,
326
+ "step": 440
327
+ },
328
+ {
329
+ "epoch": 1.0273972602739727,
330
+ "grad_norm": 0.13055773079395294,
331
+ "learning_rate": 4.359303652968037e-05,
332
+ "loss": 0.0076,
333
+ "step": 450
334
+ },
335
+ {
336
+ "epoch": 1.0502283105022832,
337
+ "grad_norm": 0.11131970584392548,
338
+ "learning_rate": 4.345034246575343e-05,
339
+ "loss": 0.0072,
340
+ "step": 460
341
+ },
342
+ {
343
+ "epoch": 1.0730593607305936,
344
+ "grad_norm": 0.1048307716846466,
345
+ "learning_rate": 4.3307648401826484e-05,
346
+ "loss": 0.0053,
347
+ "step": 470
348
+ },
349
+ {
350
+ "epoch": 1.095890410958904,
351
+ "grad_norm": 0.191425159573555,
352
+ "learning_rate": 4.316495433789954e-05,
353
+ "loss": 0.0061,
354
+ "step": 480
355
+ },
356
+ {
357
+ "epoch": 1.1187214611872145,
358
+ "grad_norm": 0.1289547234773636,
359
+ "learning_rate": 4.3022260273972604e-05,
360
+ "loss": 0.0057,
361
+ "step": 490
362
+ },
363
+ {
364
+ "epoch": 1.1415525114155252,
365
+ "grad_norm": 0.09019248932600021,
366
+ "learning_rate": 4.287956621004566e-05,
367
+ "loss": 0.0049,
368
+ "step": 500
369
+ },
370
+ {
371
+ "epoch": 1.1643835616438356,
372
+ "grad_norm": 0.22927595674991608,
373
+ "learning_rate": 4.2736872146118724e-05,
374
+ "loss": 0.0051,
375
+ "step": 510
376
+ },
377
+ {
378
+ "epoch": 1.187214611872146,
379
+ "grad_norm": 0.1198509931564331,
380
+ "learning_rate": 4.259417808219178e-05,
381
+ "loss": 0.0047,
382
+ "step": 520
383
+ },
384
+ {
385
+ "epoch": 1.2100456621004567,
386
+ "grad_norm": 0.1271675080060959,
387
+ "learning_rate": 4.2451484018264844e-05,
388
+ "loss": 0.0051,
389
+ "step": 530
390
+ },
391
+ {
392
+ "epoch": 1.2328767123287672,
393
+ "grad_norm": 0.13385379314422607,
394
+ "learning_rate": 4.23087899543379e-05,
395
+ "loss": 0.0054,
396
+ "step": 540
397
+ },
398
+ {
399
+ "epoch": 1.2557077625570776,
400
+ "grad_norm": 0.06279306858778,
401
+ "learning_rate": 4.2166095890410964e-05,
402
+ "loss": 0.0046,
403
+ "step": 550
404
+ },
405
+ {
406
+ "epoch": 1.278538812785388,
407
+ "grad_norm": 0.12206210196018219,
408
+ "learning_rate": 4.202340182648402e-05,
409
+ "loss": 0.0046,
410
+ "step": 560
411
+ },
412
+ {
413
+ "epoch": 1.3013698630136985,
414
+ "grad_norm": 0.08528764545917511,
415
+ "learning_rate": 4.1880707762557084e-05,
416
+ "loss": 0.0049,
417
+ "step": 570
418
+ },
419
+ {
420
+ "epoch": 1.3242009132420092,
421
+ "grad_norm": 0.11532297730445862,
422
+ "learning_rate": 4.173801369863014e-05,
423
+ "loss": 0.0044,
424
+ "step": 580
425
+ },
426
+ {
427
+ "epoch": 1.3470319634703196,
428
+ "grad_norm": 0.1577356606721878,
429
+ "learning_rate": 4.1595319634703204e-05,
430
+ "loss": 0.0047,
431
+ "step": 590
432
+ },
433
+ {
434
+ "epoch": 1.36986301369863,
435
+ "grad_norm": 0.0654304102063179,
436
+ "learning_rate": 4.145262557077626e-05,
437
+ "loss": 0.0043,
438
+ "step": 600
439
+ },
440
+ {
441
+ "epoch": 1.3926940639269407,
442
+ "grad_norm": 0.13026106357574463,
443
+ "learning_rate": 4.130993150684932e-05,
444
+ "loss": 0.0046,
445
+ "step": 610
446
+ },
447
+ {
448
+ "epoch": 1.4155251141552512,
449
+ "grad_norm": 0.1981119066476822,
450
+ "learning_rate": 4.1167237442922374e-05,
451
+ "loss": 0.0036,
452
+ "step": 620
453
+ },
454
+ {
455
+ "epoch": 1.4383561643835616,
456
+ "grad_norm": 0.0626244992017746,
457
+ "learning_rate": 4.102454337899544e-05,
458
+ "loss": 0.0029,
459
+ "step": 630
460
+ },
461
+ {
462
+ "epoch": 1.461187214611872,
463
+ "grad_norm": 0.09634381532669067,
464
+ "learning_rate": 4.0881849315068494e-05,
465
+ "loss": 0.0035,
466
+ "step": 640
467
+ },
468
+ {
469
+ "epoch": 1.4840182648401825,
470
+ "grad_norm": 0.10267172008752823,
471
+ "learning_rate": 4.073915525114155e-05,
472
+ "loss": 0.0029,
473
+ "step": 650
474
+ },
475
+ {
476
+ "epoch": 1.5068493150684932,
477
+ "grad_norm": 0.1381852775812149,
478
+ "learning_rate": 4.0596461187214614e-05,
479
+ "loss": 0.0034,
480
+ "step": 660
481
+ },
482
+ {
483
+ "epoch": 1.5296803652968036,
484
+ "grad_norm": 0.05667397379875183,
485
+ "learning_rate": 4.045376712328767e-05,
486
+ "loss": 0.0034,
487
+ "step": 670
488
+ },
489
+ {
490
+ "epoch": 1.5525114155251143,
491
+ "grad_norm": 0.09371186792850494,
492
+ "learning_rate": 4.0311073059360734e-05,
493
+ "loss": 0.0035,
494
+ "step": 680
495
+ },
496
+ {
497
+ "epoch": 1.5753424657534247,
498
+ "grad_norm": 0.09487811475992203,
499
+ "learning_rate": 4.016837899543379e-05,
500
+ "loss": 0.0032,
501
+ "step": 690
502
+ },
503
+ {
504
+ "epoch": 1.5981735159817352,
505
+ "grad_norm": 0.09329680353403091,
506
+ "learning_rate": 4.0025684931506853e-05,
507
+ "loss": 0.0034,
508
+ "step": 700
509
+ },
510
+ {
511
+ "epoch": 1.6210045662100456,
512
+ "grad_norm": 0.10534738004207611,
513
+ "learning_rate": 3.988299086757991e-05,
514
+ "loss": 0.003,
515
+ "step": 710
516
+ },
517
+ {
518
+ "epoch": 1.643835616438356,
519
+ "grad_norm": 0.1082799881696701,
520
+ "learning_rate": 3.9740296803652973e-05,
521
+ "loss": 0.0032,
522
+ "step": 720
523
+ },
524
+ {
525
+ "epoch": 1.6666666666666665,
526
+ "grad_norm": 0.06728220731019974,
527
+ "learning_rate": 3.959760273972603e-05,
528
+ "loss": 0.0031,
529
+ "step": 730
530
+ },
531
+ {
532
+ "epoch": 1.6894977168949772,
533
+ "grad_norm": 0.22814679145812988,
534
+ "learning_rate": 3.9454908675799093e-05,
535
+ "loss": 0.003,
536
+ "step": 740
537
+ },
538
+ {
539
+ "epoch": 1.7123287671232876,
540
+ "grad_norm": 0.10962113738059998,
541
+ "learning_rate": 3.931221461187215e-05,
542
+ "loss": 0.003,
543
+ "step": 750
544
+ },
545
+ {
546
+ "epoch": 1.7351598173515983,
547
+ "grad_norm": 0.054916515946388245,
548
+ "learning_rate": 3.916952054794521e-05,
549
+ "loss": 0.0024,
550
+ "step": 760
551
+ },
552
+ {
553
+ "epoch": 1.7579908675799087,
554
+ "grad_norm": 0.08513092249631882,
555
+ "learning_rate": 3.902682648401826e-05,
556
+ "loss": 0.0027,
557
+ "step": 770
558
+ },
559
+ {
560
+ "epoch": 1.7808219178082192,
561
+ "grad_norm": 0.03006896749138832,
562
+ "learning_rate": 3.888413242009133e-05,
563
+ "loss": 0.0026,
564
+ "step": 780
565
+ },
566
+ {
567
+ "epoch": 1.8036529680365296,
568
+ "grad_norm": 0.0818442776799202,
569
+ "learning_rate": 3.874143835616438e-05,
570
+ "loss": 0.0025,
571
+ "step": 790
572
+ },
573
+ {
574
+ "epoch": 1.82648401826484,
575
+ "grad_norm": 0.06740756332874298,
576
+ "learning_rate": 3.859874429223744e-05,
577
+ "loss": 0.0019,
578
+ "step": 800
579
+ },
580
+ {
581
+ "epoch": 1.8493150684931505,
582
+ "grad_norm": 0.022570671513676643,
583
+ "learning_rate": 3.84560502283105e-05,
584
+ "loss": 0.0026,
585
+ "step": 810
586
+ },
587
+ {
588
+ "epoch": 1.8721461187214612,
589
+ "grad_norm": 0.06723079085350037,
590
+ "learning_rate": 3.831335616438356e-05,
591
+ "loss": 0.0021,
592
+ "step": 820
593
+ },
594
+ {
595
+ "epoch": 1.8949771689497716,
596
+ "grad_norm": 0.12359272688627243,
597
+ "learning_rate": 3.817066210045662e-05,
598
+ "loss": 0.0023,
599
+ "step": 830
600
+ },
601
+ {
602
+ "epoch": 1.9178082191780823,
603
+ "grad_norm": 0.07307197153568268,
604
+ "learning_rate": 3.802796803652968e-05,
605
+ "loss": 0.0024,
606
+ "step": 840
607
+ },
608
+ {
609
+ "epoch": 1.9406392694063928,
610
+ "grad_norm": 0.11846048384904861,
611
+ "learning_rate": 3.788527397260274e-05,
612
+ "loss": 0.0026,
613
+ "step": 850
614
+ },
615
+ {
616
+ "epoch": 1.9634703196347032,
617
+ "grad_norm": 0.043823979794979095,
618
+ "learning_rate": 3.77425799086758e-05,
619
+ "loss": 0.0026,
620
+ "step": 860
621
+ },
622
+ {
623
+ "epoch": 1.9863013698630136,
624
+ "grad_norm": 0.06740803271532059,
625
+ "learning_rate": 3.759988584474886e-05,
626
+ "loss": 0.0026,
627
+ "step": 870
628
+ },
629
+ {
630
+ "epoch": 2.0,
631
+ "eval_loss": 0.0005470711039379239,
632
+ "eval_runtime": 70.9617,
633
+ "eval_samples_per_second": 42.276,
634
+ "eval_steps_per_second": 2.649,
635
+ "step": 876
636
+ },
637
+ {
638
+ "epoch": 2.009132420091324,
639
+ "grad_norm": 0.07825632393360138,
640
+ "learning_rate": 3.745719178082192e-05,
641
+ "loss": 0.0023,
642
+ "step": 880
643
+ },
644
+ {
645
+ "epoch": 2.0319634703196345,
646
+ "grad_norm": 0.07475470006465912,
647
+ "learning_rate": 3.731449771689498e-05,
648
+ "loss": 0.0026,
649
+ "step": 890
650
+ },
651
+ {
652
+ "epoch": 2.0547945205479454,
653
+ "grad_norm": 0.027003251016139984,
654
+ "learning_rate": 3.717180365296804e-05,
655
+ "loss": 0.002,
656
+ "step": 900
657
+ },
658
+ {
659
+ "epoch": 2.077625570776256,
660
+ "grad_norm": 0.02263038419187069,
661
+ "learning_rate": 3.70291095890411e-05,
662
+ "loss": 0.0024,
663
+ "step": 910
664
+ },
665
+ {
666
+ "epoch": 2.1004566210045663,
667
+ "grad_norm": 0.10978245735168457,
668
+ "learning_rate": 3.688641552511416e-05,
669
+ "loss": 0.0016,
670
+ "step": 920
671
+ },
672
+ {
673
+ "epoch": 2.1232876712328768,
674
+ "grad_norm": 0.10029231756925583,
675
+ "learning_rate": 3.6743721461187216e-05,
676
+ "loss": 0.0019,
677
+ "step": 930
678
+ },
679
+ {
680
+ "epoch": 2.146118721461187,
681
+ "grad_norm": 0.13055719435214996,
682
+ "learning_rate": 3.660102739726027e-05,
683
+ "loss": 0.0024,
684
+ "step": 940
685
+ },
686
+ {
687
+ "epoch": 2.1689497716894977,
688
+ "grad_norm": 0.02834697626531124,
689
+ "learning_rate": 3.6458333333333336e-05,
690
+ "loss": 0.0021,
691
+ "step": 950
692
+ },
693
+ {
694
+ "epoch": 2.191780821917808,
695
+ "grad_norm": 0.03155607730150223,
696
+ "learning_rate": 3.631563926940639e-05,
697
+ "loss": 0.0017,
698
+ "step": 960
699
+ },
700
+ {
701
+ "epoch": 2.2146118721461185,
702
+ "grad_norm": 0.012841666117310524,
703
+ "learning_rate": 3.617294520547945e-05,
704
+ "loss": 0.0014,
705
+ "step": 970
706
+ },
707
+ {
708
+ "epoch": 2.237442922374429,
709
+ "grad_norm": 0.06208495423197746,
710
+ "learning_rate": 3.603025114155251e-05,
711
+ "loss": 0.0018,
712
+ "step": 980
713
+ },
714
+ {
715
+ "epoch": 2.26027397260274,
716
+ "grad_norm": 0.03939255326986313,
717
+ "learning_rate": 3.588755707762557e-05,
718
+ "loss": 0.0015,
719
+ "step": 990
720
+ },
721
+ {
722
+ "epoch": 2.2831050228310503,
723
+ "grad_norm": 0.0387921966612339,
724
+ "learning_rate": 3.574486301369863e-05,
725
+ "loss": 0.0016,
726
+ "step": 1000
727
+ },
728
+ {
729
+ "epoch": 2.3059360730593608,
730
+ "grad_norm": 0.037367332726716995,
731
+ "learning_rate": 3.560216894977169e-05,
732
+ "loss": 0.0017,
733
+ "step": 1010
734
+ },
735
+ {
736
+ "epoch": 2.328767123287671,
737
+ "grad_norm": 0.09546244889497757,
738
+ "learning_rate": 3.545947488584475e-05,
739
+ "loss": 0.0016,
740
+ "step": 1020
741
+ },
742
+ {
743
+ "epoch": 2.3515981735159817,
744
+ "grad_norm": 0.05310087651014328,
745
+ "learning_rate": 3.531678082191781e-05,
746
+ "loss": 0.0017,
747
+ "step": 1030
748
+ },
749
+ {
750
+ "epoch": 2.374429223744292,
751
+ "grad_norm": 0.13905133306980133,
752
+ "learning_rate": 3.517408675799087e-05,
753
+ "loss": 0.0016,
754
+ "step": 1040
755
+ },
756
+ {
757
+ "epoch": 2.3972602739726026,
758
+ "grad_norm": 0.13682198524475098,
759
+ "learning_rate": 3.503139269406393e-05,
760
+ "loss": 0.0015,
761
+ "step": 1050
762
+ },
763
+ {
764
+ "epoch": 2.4200913242009134,
765
+ "grad_norm": 0.07560446858406067,
766
+ "learning_rate": 3.488869863013699e-05,
767
+ "loss": 0.0019,
768
+ "step": 1060
769
+ },
770
+ {
771
+ "epoch": 2.442922374429224,
772
+ "grad_norm": 0.024818843230605125,
773
+ "learning_rate": 3.474600456621005e-05,
774
+ "loss": 0.0019,
775
+ "step": 1070
776
+ },
777
+ {
778
+ "epoch": 2.4657534246575343,
779
+ "grad_norm": 0.2794188857078552,
780
+ "learning_rate": 3.4603310502283106e-05,
781
+ "loss": 0.0014,
782
+ "step": 1080
783
+ },
784
+ {
785
+ "epoch": 2.4885844748858448,
786
+ "grad_norm": 0.03945288807153702,
787
+ "learning_rate": 3.446061643835616e-05,
788
+ "loss": 0.0013,
789
+ "step": 1090
790
+ },
791
+ {
792
+ "epoch": 2.5114155251141552,
793
+ "grad_norm": 0.028486991301178932,
794
+ "learning_rate": 3.4317922374429226e-05,
795
+ "loss": 0.0015,
796
+ "step": 1100
797
+ },
798
+ {
799
+ "epoch": 2.5342465753424657,
800
+ "grad_norm": 0.19093026220798492,
801
+ "learning_rate": 3.417522831050228e-05,
802
+ "loss": 0.0016,
803
+ "step": 1110
804
+ },
805
+ {
806
+ "epoch": 2.557077625570776,
807
+ "grad_norm": 0.01798168569803238,
808
+ "learning_rate": 3.4032534246575346e-05,
809
+ "loss": 0.0012,
810
+ "step": 1120
811
+ },
812
+ {
813
+ "epoch": 2.5799086757990866,
814
+ "grad_norm": 0.03545854985713959,
815
+ "learning_rate": 3.38898401826484e-05,
816
+ "loss": 0.0012,
817
+ "step": 1130
818
+ },
819
+ {
820
+ "epoch": 2.602739726027397,
821
+ "grad_norm": 0.0346076525747776,
822
+ "learning_rate": 3.374714611872146e-05,
823
+ "loss": 0.0013,
824
+ "step": 1140
825
+ },
826
+ {
827
+ "epoch": 2.625570776255708,
828
+ "grad_norm": 0.031317390501499176,
829
+ "learning_rate": 3.360445205479452e-05,
830
+ "loss": 0.0011,
831
+ "step": 1150
832
+ },
833
+ {
834
+ "epoch": 2.6484018264840183,
835
+ "grad_norm": 0.018010897561907768,
836
+ "learning_rate": 3.346175799086758e-05,
837
+ "loss": 0.0013,
838
+ "step": 1160
839
+ },
840
+ {
841
+ "epoch": 2.671232876712329,
842
+ "grad_norm": 0.04990324005484581,
843
+ "learning_rate": 3.331906392694064e-05,
844
+ "loss": 0.0017,
845
+ "step": 1170
846
+ },
847
+ {
848
+ "epoch": 2.6940639269406392,
849
+ "grad_norm": 0.10162694752216339,
850
+ "learning_rate": 3.31763698630137e-05,
851
+ "loss": 0.0015,
852
+ "step": 1180
853
+ },
854
+ {
855
+ "epoch": 2.7168949771689497,
856
+ "grad_norm": 0.05713967978954315,
857
+ "learning_rate": 3.303367579908676e-05,
858
+ "loss": 0.0014,
859
+ "step": 1190
860
+ },
861
+ {
862
+ "epoch": 2.73972602739726,
863
+ "grad_norm": 0.12799331545829773,
864
+ "learning_rate": 3.289098173515982e-05,
865
+ "loss": 0.0013,
866
+ "step": 1200
867
+ },
868
+ {
869
+ "epoch": 2.762557077625571,
870
+ "grad_norm": 0.022338515147566795,
871
+ "learning_rate": 3.274828767123288e-05,
872
+ "loss": 0.0013,
873
+ "step": 1210
874
+ },
875
+ {
876
+ "epoch": 2.7853881278538815,
877
+ "grad_norm": 0.01897992566227913,
878
+ "learning_rate": 3.260559360730594e-05,
879
+ "loss": 0.0011,
880
+ "step": 1220
881
+ },
882
+ {
883
+ "epoch": 2.808219178082192,
884
+ "grad_norm": 0.04136025533080101,
885
+ "learning_rate": 3.2462899543379e-05,
886
+ "loss": 0.0017,
887
+ "step": 1230
888
+ },
889
+ {
890
+ "epoch": 2.8310502283105023,
891
+ "grad_norm": 0.09205514937639236,
892
+ "learning_rate": 3.232020547945205e-05,
893
+ "loss": 0.0012,
894
+ "step": 1240
895
+ },
896
+ {
897
+ "epoch": 2.853881278538813,
898
+ "grad_norm": 0.05605219677090645,
899
+ "learning_rate": 3.2177511415525116e-05,
900
+ "loss": 0.0013,
901
+ "step": 1250
902
+ },
903
+ {
904
+ "epoch": 2.8767123287671232,
905
+ "grad_norm": 0.20732928812503815,
906
+ "learning_rate": 3.203481735159817e-05,
907
+ "loss": 0.0016,
908
+ "step": 1260
909
+ },
910
+ {
911
+ "epoch": 2.8995433789954337,
912
+ "grad_norm": 0.01767803728580475,
913
+ "learning_rate": 3.1892123287671236e-05,
914
+ "loss": 0.0011,
915
+ "step": 1270
916
+ },
917
+ {
918
+ "epoch": 2.922374429223744,
919
+ "grad_norm": 0.05888301134109497,
920
+ "learning_rate": 3.174942922374429e-05,
921
+ "loss": 0.0013,
922
+ "step": 1280
923
+ },
924
+ {
925
+ "epoch": 2.9452054794520546,
926
+ "grad_norm": 0.060406286269426346,
927
+ "learning_rate": 3.160673515981735e-05,
928
+ "loss": 0.0012,
929
+ "step": 1290
930
+ },
931
+ {
932
+ "epoch": 2.968036529680365,
933
+ "grad_norm": 0.016563862562179565,
934
+ "learning_rate": 3.146404109589041e-05,
935
+ "loss": 0.0011,
936
+ "step": 1300
937
+ },
938
+ {
939
+ "epoch": 2.990867579908676,
940
+ "grad_norm": 0.032936833798885345,
941
+ "learning_rate": 3.132134703196347e-05,
942
+ "loss": 0.0012,
943
+ "step": 1310
944
+ },
945
+ {
946
+ "epoch": 3.0,
947
+ "eval_loss": 2.3043350665830076e-05,
948
+ "eval_runtime": 71.3592,
949
+ "eval_samples_per_second": 42.041,
950
+ "eval_steps_per_second": 2.635,
951
+ "step": 1314
952
+ },
953
+ {
954
+ "epoch": 3.0136986301369864,
955
+ "grad_norm": 0.043910350650548935,
956
+ "learning_rate": 3.117865296803653e-05,
957
+ "loss": 0.0012,
958
+ "step": 1320
959
+ },
960
+ {
961
+ "epoch": 3.036529680365297,
962
+ "grad_norm": 0.051233988255262375,
963
+ "learning_rate": 3.103595890410959e-05,
964
+ "loss": 0.0012,
965
+ "step": 1330
966
+ },
967
+ {
968
+ "epoch": 3.0593607305936072,
969
+ "grad_norm": 0.0460955835878849,
970
+ "learning_rate": 3.089326484018265e-05,
971
+ "loss": 0.0012,
972
+ "step": 1340
973
+ },
974
+ {
975
+ "epoch": 3.0821917808219177,
976
+ "grad_norm": 0.11139486730098724,
977
+ "learning_rate": 3.075057077625571e-05,
978
+ "loss": 0.0015,
979
+ "step": 1350
980
+ },
981
+ {
982
+ "epoch": 3.105022831050228,
983
+ "grad_norm": 0.020884834229946136,
984
+ "learning_rate": 3.060787671232877e-05,
985
+ "loss": 0.0009,
986
+ "step": 1360
987
+ },
988
+ {
989
+ "epoch": 3.127853881278539,
990
+ "grad_norm": 0.04865699261426926,
991
+ "learning_rate": 3.046518264840183e-05,
992
+ "loss": 0.0009,
993
+ "step": 1370
994
+ },
995
+ {
996
+ "epoch": 3.1506849315068495,
997
+ "grad_norm": 0.04672854766249657,
998
+ "learning_rate": 3.032248858447489e-05,
999
+ "loss": 0.0009,
1000
+ "step": 1380
1001
+ },
1002
+ {
1003
+ "epoch": 3.17351598173516,
1004
+ "grad_norm": 0.04292335361242294,
1005
+ "learning_rate": 3.017979452054795e-05,
1006
+ "loss": 0.0009,
1007
+ "step": 1390
1008
+ },
1009
+ {
1010
+ "epoch": 3.1963470319634704,
1011
+ "grad_norm": 0.06898372620344162,
1012
+ "learning_rate": 3.0037100456621002e-05,
1013
+ "loss": 0.0009,
1014
+ "step": 1400
1015
+ },
1016
+ {
1017
+ "epoch": 3.219178082191781,
1018
+ "grad_norm": 0.08381140232086182,
1019
+ "learning_rate": 2.9894406392694062e-05,
1020
+ "loss": 0.0012,
1021
+ "step": 1410
1022
+ },
1023
+ {
1024
+ "epoch": 3.2420091324200913,
1025
+ "grad_norm": 0.009932724758982658,
1026
+ "learning_rate": 2.9751712328767122e-05,
1027
+ "loss": 0.0009,
1028
+ "step": 1420
1029
+ },
1030
+ {
1031
+ "epoch": 3.2648401826484017,
1032
+ "grad_norm": 0.055948104709386826,
1033
+ "learning_rate": 2.9609018264840182e-05,
1034
+ "loss": 0.0012,
1035
+ "step": 1430
1036
+ },
1037
+ {
1038
+ "epoch": 3.287671232876712,
1039
+ "grad_norm": 0.028575940057635307,
1040
+ "learning_rate": 2.9466324200913242e-05,
1041
+ "loss": 0.0011,
1042
+ "step": 1440
1043
+ },
1044
+ {
1045
+ "epoch": 3.3105022831050226,
1046
+ "grad_norm": 0.023319421336054802,
1047
+ "learning_rate": 2.9323630136986302e-05,
1048
+ "loss": 0.0009,
1049
+ "step": 1450
1050
+ },
1051
+ {
1052
+ "epoch": 3.3333333333333335,
1053
+ "grad_norm": 0.05601884797215462,
1054
+ "learning_rate": 2.9180936073059362e-05,
1055
+ "loss": 0.0009,
1056
+ "step": 1460
1057
+ },
1058
+ {
1059
+ "epoch": 3.356164383561644,
1060
+ "grad_norm": 0.017812812700867653,
1061
+ "learning_rate": 2.9038242009132422e-05,
1062
+ "loss": 0.0008,
1063
+ "step": 1470
1064
+ },
1065
+ {
1066
+ "epoch": 3.3789954337899544,
1067
+ "grad_norm": 0.015839802101254463,
1068
+ "learning_rate": 2.8895547945205482e-05,
1069
+ "loss": 0.0009,
1070
+ "step": 1480
1071
+ },
1072
+ {
1073
+ "epoch": 3.401826484018265,
1074
+ "grad_norm": 0.013905179686844349,
1075
+ "learning_rate": 2.8752853881278542e-05,
1076
+ "loss": 0.0009,
1077
+ "step": 1490
1078
+ },
1079
+ {
1080
+ "epoch": 3.4246575342465753,
1081
+ "grad_norm": 0.034228548407554626,
1082
+ "learning_rate": 2.8610159817351602e-05,
1083
+ "loss": 0.0009,
1084
+ "step": 1500
1085
+ },
1086
+ {
1087
+ "epoch": 3.4474885844748857,
1088
+ "grad_norm": 0.1382512003183365,
1089
+ "learning_rate": 2.846746575342466e-05,
1090
+ "loss": 0.001,
1091
+ "step": 1510
1092
+ },
1093
+ {
1094
+ "epoch": 3.470319634703196,
1095
+ "grad_norm": 0.026061363518238068,
1096
+ "learning_rate": 2.832477168949772e-05,
1097
+ "loss": 0.0007,
1098
+ "step": 1520
1099
+ },
1100
+ {
1101
+ "epoch": 3.493150684931507,
1102
+ "grad_norm": 0.033779580146074295,
1103
+ "learning_rate": 2.818207762557078e-05,
1104
+ "loss": 0.0007,
1105
+ "step": 1530
1106
+ },
1107
+ {
1108
+ "epoch": 3.5159817351598175,
1109
+ "grad_norm": 0.01672547496855259,
1110
+ "learning_rate": 2.803938356164384e-05,
1111
+ "loss": 0.0009,
1112
+ "step": 1540
1113
+ },
1114
+ {
1115
+ "epoch": 3.538812785388128,
1116
+ "grad_norm": 0.03841786831617355,
1117
+ "learning_rate": 2.7896689497716895e-05,
1118
+ "loss": 0.0008,
1119
+ "step": 1550
1120
+ },
1121
+ {
1122
+ "epoch": 3.5616438356164384,
1123
+ "grad_norm": 0.042960572987794876,
1124
+ "learning_rate": 2.7753995433789952e-05,
1125
+ "loss": 0.0008,
1126
+ "step": 1560
1127
+ },
1128
+ {
1129
+ "epoch": 3.584474885844749,
1130
+ "grad_norm": 0.016713028773665428,
1131
+ "learning_rate": 2.7611301369863012e-05,
1132
+ "loss": 0.0007,
1133
+ "step": 1570
1134
+ },
1135
+ {
1136
+ "epoch": 3.6073059360730593,
1137
+ "grad_norm": 0.04062510281801224,
1138
+ "learning_rate": 2.7468607305936072e-05,
1139
+ "loss": 0.0007,
1140
+ "step": 1580
1141
+ },
1142
+ {
1143
+ "epoch": 3.6301369863013697,
1144
+ "grad_norm": 0.013800432905554771,
1145
+ "learning_rate": 2.7325913242009132e-05,
1146
+ "loss": 0.0009,
1147
+ "step": 1590
1148
+ },
1149
+ {
1150
+ "epoch": 3.65296803652968,
1151
+ "grad_norm": 0.03654768317937851,
1152
+ "learning_rate": 2.7183219178082192e-05,
1153
+ "loss": 0.0008,
1154
+ "step": 1600
1155
+ },
1156
+ {
1157
+ "epoch": 3.6757990867579906,
1158
+ "grad_norm": 0.04716182500123978,
1159
+ "learning_rate": 2.7040525114155252e-05,
1160
+ "loss": 0.0007,
1161
+ "step": 1610
1162
+ },
1163
+ {
1164
+ "epoch": 3.6986301369863015,
1165
+ "grad_norm": 0.006938883103430271,
1166
+ "learning_rate": 2.6897831050228312e-05,
1167
+ "loss": 0.0005,
1168
+ "step": 1620
1169
+ },
1170
+ {
1171
+ "epoch": 3.721461187214612,
1172
+ "grad_norm": 0.07364363968372345,
1173
+ "learning_rate": 2.6755136986301372e-05,
1174
+ "loss": 0.0007,
1175
+ "step": 1630
1176
+ },
1177
+ {
1178
+ "epoch": 3.7442922374429224,
1179
+ "grad_norm": 0.028122154995799065,
1180
+ "learning_rate": 2.6612442922374432e-05,
1181
+ "loss": 0.0006,
1182
+ "step": 1640
1183
+ },
1184
+ {
1185
+ "epoch": 3.767123287671233,
1186
+ "grad_norm": 0.008902553468942642,
1187
+ "learning_rate": 2.6469748858447492e-05,
1188
+ "loss": 0.0006,
1189
+ "step": 1650
1190
+ },
1191
+ {
1192
+ "epoch": 3.7899543378995433,
1193
+ "grad_norm": 0.013538227416574955,
1194
+ "learning_rate": 2.6327054794520552e-05,
1195
+ "loss": 0.0007,
1196
+ "step": 1660
1197
+ },
1198
+ {
1199
+ "epoch": 3.8127853881278537,
1200
+ "grad_norm": 0.01429641991853714,
1201
+ "learning_rate": 2.6184360730593612e-05,
1202
+ "loss": 0.0007,
1203
+ "step": 1670
1204
+ },
1205
+ {
1206
+ "epoch": 3.8356164383561646,
1207
+ "grad_norm": 0.03232923895120621,
1208
+ "learning_rate": 2.604166666666667e-05,
1209
+ "loss": 0.0006,
1210
+ "step": 1680
1211
+ },
1212
+ {
1213
+ "epoch": 3.858447488584475,
1214
+ "grad_norm": 0.008046794682741165,
1215
+ "learning_rate": 2.589897260273973e-05,
1216
+ "loss": 0.0008,
1217
+ "step": 1690
1218
+ },
1219
+ {
1220
+ "epoch": 3.8812785388127855,
1221
+ "grad_norm": 0.04098529741168022,
1222
+ "learning_rate": 2.575627853881279e-05,
1223
+ "loss": 0.0006,
1224
+ "step": 1700
1225
+ },
1226
+ {
1227
+ "epoch": 3.904109589041096,
1228
+ "grad_norm": 0.06163308396935463,
1229
+ "learning_rate": 2.5613584474885845e-05,
1230
+ "loss": 0.0007,
1231
+ "step": 1710
1232
+ },
1233
+ {
1234
+ "epoch": 3.9269406392694064,
1235
+ "grad_norm": 0.022219218313694,
1236
+ "learning_rate": 2.54708904109589e-05,
1237
+ "loss": 0.0006,
1238
+ "step": 1720
1239
+ },
1240
+ {
1241
+ "epoch": 3.949771689497717,
1242
+ "grad_norm": 0.09443829208612442,
1243
+ "learning_rate": 2.532819634703196e-05,
1244
+ "loss": 0.0007,
1245
+ "step": 1730
1246
+ },
1247
+ {
1248
+ "epoch": 3.9726027397260273,
1249
+ "grad_norm": 0.03068207949399948,
1250
+ "learning_rate": 2.518550228310502e-05,
1251
+ "loss": 0.0007,
1252
+ "step": 1740
1253
+ },
1254
+ {
1255
+ "epoch": 3.9954337899543377,
1256
+ "grad_norm": 0.09690997749567032,
1257
+ "learning_rate": 2.504280821917808e-05,
1258
+ "loss": 0.0007,
1259
+ "step": 1750
1260
+ },
1261
+ {
1262
+ "epoch": 4.0,
1263
+ "eval_loss": 9.936958122125361e-06,
1264
+ "eval_runtime": 71.0483,
1265
+ "eval_samples_per_second": 42.225,
1266
+ "eval_steps_per_second": 2.646,
1267
+ "step": 1752
1268
+ },
1269
+ {
1270
+ "epoch": 4.018264840182648,
1271
+ "grad_norm": 0.011336731724441051,
1272
+ "learning_rate": 2.490011415525114e-05,
1273
+ "loss": 0.0006,
1274
+ "step": 1760
1275
+ },
1276
+ {
1277
+ "epoch": 4.041095890410959,
1278
+ "grad_norm": 0.015287565998733044,
1279
+ "learning_rate": 2.47574200913242e-05,
1280
+ "loss": 0.0008,
1281
+ "step": 1770
1282
+ },
1283
+ {
1284
+ "epoch": 4.063926940639269,
1285
+ "grad_norm": 0.008016168139874935,
1286
+ "learning_rate": 2.461472602739726e-05,
1287
+ "loss": 0.0007,
1288
+ "step": 1780
1289
+ },
1290
+ {
1291
+ "epoch": 4.0867579908675795,
1292
+ "grad_norm": 0.06609506160020828,
1293
+ "learning_rate": 2.447203196347032e-05,
1294
+ "loss": 0.0006,
1295
+ "step": 1790
1296
+ },
1297
+ {
1298
+ "epoch": 4.109589041095891,
1299
+ "grad_norm": 0.009175929240882397,
1300
+ "learning_rate": 2.432933789954338e-05,
1301
+ "loss": 0.0007,
1302
+ "step": 1800
1303
+ },
1304
+ {
1305
+ "epoch": 4.132420091324201,
1306
+ "grad_norm": 0.0126581359654665,
1307
+ "learning_rate": 2.418664383561644e-05,
1308
+ "loss": 0.0005,
1309
+ "step": 1810
1310
+ },
1311
+ {
1312
+ "epoch": 4.155251141552512,
1313
+ "grad_norm": 0.08836681395769119,
1314
+ "learning_rate": 2.40439497716895e-05,
1315
+ "loss": 0.001,
1316
+ "step": 1820
1317
+ },
1318
+ {
1319
+ "epoch": 4.178082191780822,
1320
+ "grad_norm": 0.025666864588856697,
1321
+ "learning_rate": 2.3901255707762558e-05,
1322
+ "loss": 0.0006,
1323
+ "step": 1830
1324
+ },
1325
+ {
1326
+ "epoch": 4.200913242009133,
1327
+ "grad_norm": 0.03877547010779381,
1328
+ "learning_rate": 2.3758561643835618e-05,
1329
+ "loss": 0.0005,
1330
+ "step": 1840
1331
+ },
1332
+ {
1333
+ "epoch": 4.223744292237443,
1334
+ "grad_norm": 0.016599468886852264,
1335
+ "learning_rate": 2.3615867579908678e-05,
1336
+ "loss": 0.0006,
1337
+ "step": 1850
1338
+ },
1339
+ {
1340
+ "epoch": 4.2465753424657535,
1341
+ "grad_norm": 0.06378292292356491,
1342
+ "learning_rate": 2.3473173515981735e-05,
1343
+ "loss": 0.0012,
1344
+ "step": 1860
1345
+ },
1346
+ {
1347
+ "epoch": 4.269406392694064,
1348
+ "grad_norm": 0.014281521551311016,
1349
+ "learning_rate": 2.3330479452054795e-05,
1350
+ "loss": 0.0008,
1351
+ "step": 1870
1352
+ },
1353
+ {
1354
+ "epoch": 4.292237442922374,
1355
+ "grad_norm": 0.09428286552429199,
1356
+ "learning_rate": 2.3187785388127855e-05,
1357
+ "loss": 0.0009,
1358
+ "step": 1880
1359
+ },
1360
+ {
1361
+ "epoch": 4.315068493150685,
1362
+ "grad_norm": 0.006857575848698616,
1363
+ "learning_rate": 2.3045091324200915e-05,
1364
+ "loss": 0.0006,
1365
+ "step": 1890
1366
+ },
1367
+ {
1368
+ "epoch": 4.337899543378995,
1369
+ "grad_norm": 0.08501231670379639,
1370
+ "learning_rate": 2.2902397260273975e-05,
1371
+ "loss": 0.0006,
1372
+ "step": 1900
1373
+ },
1374
+ {
1375
+ "epoch": 4.360730593607306,
1376
+ "grad_norm": 0.01724555715918541,
1377
+ "learning_rate": 2.275970319634703e-05,
1378
+ "loss": 0.0006,
1379
+ "step": 1910
1380
+ },
1381
+ {
1382
+ "epoch": 4.383561643835616,
1383
+ "grad_norm": 0.008119191974401474,
1384
+ "learning_rate": 2.261700913242009e-05,
1385
+ "loss": 0.0006,
1386
+ "step": 1920
1387
+ },
1388
+ {
1389
+ "epoch": 4.406392694063927,
1390
+ "grad_norm": 0.026137014850974083,
1391
+ "learning_rate": 2.247431506849315e-05,
1392
+ "loss": 0.0005,
1393
+ "step": 1930
1394
+ },
1395
+ {
1396
+ "epoch": 4.429223744292237,
1397
+ "grad_norm": 0.005971621256321669,
1398
+ "learning_rate": 2.233162100456621e-05,
1399
+ "loss": 0.0006,
1400
+ "step": 1940
1401
+ },
1402
+ {
1403
+ "epoch": 4.4520547945205475,
1404
+ "grad_norm": 0.04149805009365082,
1405
+ "learning_rate": 2.218892694063927e-05,
1406
+ "loss": 0.0006,
1407
+ "step": 1950
1408
+ },
1409
+ {
1410
+ "epoch": 4.474885844748858,
1411
+ "grad_norm": 0.00725915003567934,
1412
+ "learning_rate": 2.204623287671233e-05,
1413
+ "loss": 0.0005,
1414
+ "step": 1960
1415
+ },
1416
+ {
1417
+ "epoch": 4.497716894977169,
1418
+ "grad_norm": 0.04520484060049057,
1419
+ "learning_rate": 2.190353881278539e-05,
1420
+ "loss": 0.0006,
1421
+ "step": 1970
1422
+ },
1423
+ {
1424
+ "epoch": 4.52054794520548,
1425
+ "grad_norm": 0.029336770996451378,
1426
+ "learning_rate": 2.1760844748858448e-05,
1427
+ "loss": 0.0005,
1428
+ "step": 1980
1429
+ },
1430
+ {
1431
+ "epoch": 4.54337899543379,
1432
+ "grad_norm": 0.09512148797512054,
1433
+ "learning_rate": 2.1618150684931508e-05,
1434
+ "loss": 0.0008,
1435
+ "step": 1990
1436
+ },
1437
+ {
1438
+ "epoch": 4.566210045662101,
1439
+ "grad_norm": 0.042485009878873825,
1440
+ "learning_rate": 2.1475456621004568e-05,
1441
+ "loss": 0.0005,
1442
+ "step": 2000
1443
+ },
1444
+ {
1445
+ "epoch": 4.589041095890411,
1446
+ "grad_norm": 0.013867770321667194,
1447
+ "learning_rate": 2.1332762557077628e-05,
1448
+ "loss": 0.0006,
1449
+ "step": 2010
1450
+ },
1451
+ {
1452
+ "epoch": 4.6118721461187215,
1453
+ "grad_norm": 0.05775037035346031,
1454
+ "learning_rate": 2.1190068493150684e-05,
1455
+ "loss": 0.0006,
1456
+ "step": 2020
1457
+ },
1458
+ {
1459
+ "epoch": 4.634703196347032,
1460
+ "grad_norm": 0.010395473800599575,
1461
+ "learning_rate": 2.1047374429223744e-05,
1462
+ "loss": 0.0006,
1463
+ "step": 2030
1464
+ },
1465
+ {
1466
+ "epoch": 4.657534246575342,
1467
+ "grad_norm": 0.008579747751355171,
1468
+ "learning_rate": 2.0904680365296804e-05,
1469
+ "loss": 0.0005,
1470
+ "step": 2040
1471
+ },
1472
+ {
1473
+ "epoch": 4.680365296803653,
1474
+ "grad_norm": 0.011320821940898895,
1475
+ "learning_rate": 2.0761986301369864e-05,
1476
+ "loss": 0.0004,
1477
+ "step": 2050
1478
+ },
1479
+ {
1480
+ "epoch": 4.703196347031963,
1481
+ "grad_norm": 0.038680724799633026,
1482
+ "learning_rate": 2.061929223744292e-05,
1483
+ "loss": 0.0005,
1484
+ "step": 2060
1485
+ },
1486
+ {
1487
+ "epoch": 4.726027397260274,
1488
+ "grad_norm": 0.014130471274256706,
1489
+ "learning_rate": 2.047659817351598e-05,
1490
+ "loss": 0.0005,
1491
+ "step": 2070
1492
+ },
1493
+ {
1494
+ "epoch": 4.748858447488584,
1495
+ "grad_norm": 0.01286408118903637,
1496
+ "learning_rate": 2.033390410958904e-05,
1497
+ "loss": 0.0006,
1498
+ "step": 2080
1499
+ },
1500
+ {
1501
+ "epoch": 4.771689497716895,
1502
+ "grad_norm": 0.06255431473255157,
1503
+ "learning_rate": 2.01912100456621e-05,
1504
+ "loss": 0.0006,
1505
+ "step": 2090
1506
+ },
1507
+ {
1508
+ "epoch": 4.794520547945205,
1509
+ "grad_norm": 0.033248186111450195,
1510
+ "learning_rate": 2.004851598173516e-05,
1511
+ "loss": 0.0007,
1512
+ "step": 2100
1513
+ },
1514
+ {
1515
+ "epoch": 4.817351598173516,
1516
+ "grad_norm": 0.008136480115354061,
1517
+ "learning_rate": 1.990582191780822e-05,
1518
+ "loss": 0.0007,
1519
+ "step": 2110
1520
+ },
1521
+ {
1522
+ "epoch": 4.840182648401827,
1523
+ "grad_norm": 0.0758700743317604,
1524
+ "learning_rate": 1.976312785388128e-05,
1525
+ "loss": 0.0006,
1526
+ "step": 2120
1527
+ },
1528
+ {
1529
+ "epoch": 4.863013698630137,
1530
+ "grad_norm": 0.008333769626915455,
1531
+ "learning_rate": 1.962043378995434e-05,
1532
+ "loss": 0.0005,
1533
+ "step": 2130
1534
+ },
1535
+ {
1536
+ "epoch": 4.885844748858448,
1537
+ "grad_norm": 0.010320034809410572,
1538
+ "learning_rate": 1.9477739726027397e-05,
1539
+ "loss": 0.0004,
1540
+ "step": 2140
1541
+ },
1542
+ {
1543
+ "epoch": 4.908675799086758,
1544
+ "grad_norm": 0.00360821932554245,
1545
+ "learning_rate": 1.9335045662100457e-05,
1546
+ "loss": 0.0006,
1547
+ "step": 2150
1548
+ },
1549
+ {
1550
+ "epoch": 4.931506849315069,
1551
+ "grad_norm": 0.02473396062850952,
1552
+ "learning_rate": 1.9192351598173517e-05,
1553
+ "loss": 0.0005,
1554
+ "step": 2160
1555
+ },
1556
+ {
1557
+ "epoch": 4.954337899543379,
1558
+ "grad_norm": 0.022373970597982407,
1559
+ "learning_rate": 1.9049657534246577e-05,
1560
+ "loss": 0.0006,
1561
+ "step": 2170
1562
+ },
1563
+ {
1564
+ "epoch": 4.9771689497716896,
1565
+ "grad_norm": 0.04363209009170532,
1566
+ "learning_rate": 1.8906963470319637e-05,
1567
+ "loss": 0.0005,
1568
+ "step": 2180
1569
+ },
1570
+ {
1571
+ "epoch": 5.0,
1572
+ "grad_norm": 0.0052858320996165276,
1573
+ "learning_rate": 1.8764269406392694e-05,
1574
+ "loss": 0.0005,
1575
+ "step": 2190
1576
+ },
1577
+ {
1578
+ "epoch": 5.0,
1579
+ "eval_loss": 5.627029167953879e-06,
1580
+ "eval_runtime": 71.2259,
1581
+ "eval_samples_per_second": 42.12,
1582
+ "eval_steps_per_second": 2.639,
1583
+ "step": 2190
1584
+ },
1585
+ {
1586
+ "epoch": 5.0228310502283104,
1587
+ "grad_norm": 0.00950402021408081,
1588
+ "learning_rate": 1.8621575342465754e-05,
1589
+ "loss": 0.0005,
1590
+ "step": 2200
1591
+ },
1592
+ {
1593
+ "epoch": 5.045662100456621,
1594
+ "grad_norm": 0.010009740479290485,
1595
+ "learning_rate": 1.8478881278538814e-05,
1596
+ "loss": 0.0005,
1597
+ "step": 2210
1598
+ },
1599
+ {
1600
+ "epoch": 5.068493150684931,
1601
+ "grad_norm": 0.032611336559057236,
1602
+ "learning_rate": 1.833618721461187e-05,
1603
+ "loss": 0.0004,
1604
+ "step": 2220
1605
+ },
1606
+ {
1607
+ "epoch": 5.091324200913242,
1608
+ "grad_norm": 0.00459344731643796,
1609
+ "learning_rate": 1.819349315068493e-05,
1610
+ "loss": 0.0005,
1611
+ "step": 2230
1612
+ },
1613
+ {
1614
+ "epoch": 5.114155251141552,
1615
+ "grad_norm": 0.03434896096587181,
1616
+ "learning_rate": 1.805079908675799e-05,
1617
+ "loss": 0.0008,
1618
+ "step": 2240
1619
+ },
1620
+ {
1621
+ "epoch": 5.136986301369863,
1622
+ "grad_norm": 0.030723148956894875,
1623
+ "learning_rate": 1.790810502283105e-05,
1624
+ "loss": 0.0004,
1625
+ "step": 2250
1626
+ },
1627
+ {
1628
+ "epoch": 5.159817351598173,
1629
+ "grad_norm": 0.0043680015951395035,
1630
+ "learning_rate": 1.776541095890411e-05,
1631
+ "loss": 0.0003,
1632
+ "step": 2260
1633
+ },
1634
+ {
1635
+ "epoch": 5.182648401826484,
1636
+ "grad_norm": 0.011316012591123581,
1637
+ "learning_rate": 1.762271689497717e-05,
1638
+ "loss": 0.0006,
1639
+ "step": 2270
1640
+ },
1641
+ {
1642
+ "epoch": 5.205479452054795,
1643
+ "grad_norm": 0.006297079846262932,
1644
+ "learning_rate": 1.748002283105023e-05,
1645
+ "loss": 0.0005,
1646
+ "step": 2280
1647
+ },
1648
+ {
1649
+ "epoch": 5.228310502283105,
1650
+ "grad_norm": 0.018946554511785507,
1651
+ "learning_rate": 1.733732876712329e-05,
1652
+ "loss": 0.0004,
1653
+ "step": 2290
1654
+ },
1655
+ {
1656
+ "epoch": 5.251141552511416,
1657
+ "grad_norm": 0.017262902110815048,
1658
+ "learning_rate": 1.7194634703196347e-05,
1659
+ "loss": 0.0004,
1660
+ "step": 2300
1661
+ },
1662
+ {
1663
+ "epoch": 5.273972602739726,
1664
+ "grad_norm": 0.010157715529203415,
1665
+ "learning_rate": 1.7051940639269407e-05,
1666
+ "loss": 0.0004,
1667
+ "step": 2310
1668
+ },
1669
+ {
1670
+ "epoch": 5.296803652968037,
1671
+ "grad_norm": 0.012058730237185955,
1672
+ "learning_rate": 1.6909246575342467e-05,
1673
+ "loss": 0.0008,
1674
+ "step": 2320
1675
+ },
1676
+ {
1677
+ "epoch": 5.319634703196347,
1678
+ "grad_norm": 0.006543818395584822,
1679
+ "learning_rate": 1.6766552511415527e-05,
1680
+ "loss": 0.0003,
1681
+ "step": 2330
1682
+ },
1683
+ {
1684
+ "epoch": 5.342465753424658,
1685
+ "grad_norm": 0.010772732086479664,
1686
+ "learning_rate": 1.6623858447488587e-05,
1687
+ "loss": 0.0004,
1688
+ "step": 2340
1689
+ },
1690
+ {
1691
+ "epoch": 5.365296803652968,
1692
+ "grad_norm": 0.0169979240745306,
1693
+ "learning_rate": 1.6481164383561644e-05,
1694
+ "loss": 0.0003,
1695
+ "step": 2350
1696
+ },
1697
+ {
1698
+ "epoch": 5.3881278538812785,
1699
+ "grad_norm": 0.009800782427191734,
1700
+ "learning_rate": 1.6338470319634704e-05,
1701
+ "loss": 0.0003,
1702
+ "step": 2360
1703
+ },
1704
+ {
1705
+ "epoch": 5.410958904109589,
1706
+ "grad_norm": 0.04885419085621834,
1707
+ "learning_rate": 1.6195776255707764e-05,
1708
+ "loss": 0.0004,
1709
+ "step": 2370
1710
+ },
1711
+ {
1712
+ "epoch": 5.433789954337899,
1713
+ "grad_norm": 0.024770863354206085,
1714
+ "learning_rate": 1.605308219178082e-05,
1715
+ "loss": 0.0005,
1716
+ "step": 2380
1717
+ },
1718
+ {
1719
+ "epoch": 5.45662100456621,
1720
+ "grad_norm": 0.0030876509845256805,
1721
+ "learning_rate": 1.591038812785388e-05,
1722
+ "loss": 0.0004,
1723
+ "step": 2390
1724
+ },
1725
+ {
1726
+ "epoch": 5.47945205479452,
1727
+ "grad_norm": 0.018670551478862762,
1728
+ "learning_rate": 1.576769406392694e-05,
1729
+ "loss": 0.0004,
1730
+ "step": 2400
1731
+ },
1732
+ {
1733
+ "epoch": 5.502283105022831,
1734
+ "grad_norm": 0.011356856673955917,
1735
+ "learning_rate": 1.5625e-05,
1736
+ "loss": 0.0006,
1737
+ "step": 2410
1738
+ },
1739
+ {
1740
+ "epoch": 5.525114155251142,
1741
+ "grad_norm": 0.0847870260477066,
1742
+ "learning_rate": 1.548230593607306e-05,
1743
+ "loss": 0.0004,
1744
+ "step": 2420
1745
+ },
1746
+ {
1747
+ "epoch": 5.5479452054794525,
1748
+ "grad_norm": 0.017403950914740562,
1749
+ "learning_rate": 1.533961187214612e-05,
1750
+ "loss": 0.0004,
1751
+ "step": 2430
1752
+ },
1753
+ {
1754
+ "epoch": 5.570776255707763,
1755
+ "grad_norm": 0.17497682571411133,
1756
+ "learning_rate": 1.519691780821918e-05,
1757
+ "loss": 0.0006,
1758
+ "step": 2440
1759
+ },
1760
+ {
1761
+ "epoch": 5.593607305936073,
1762
+ "grad_norm": 0.032679907977581024,
1763
+ "learning_rate": 1.5054223744292237e-05,
1764
+ "loss": 0.0003,
1765
+ "step": 2450
1766
+ },
1767
+ {
1768
+ "epoch": 5.616438356164384,
1769
+ "grad_norm": 0.011194907128810883,
1770
+ "learning_rate": 1.4911529680365297e-05,
1771
+ "loss": 0.0004,
1772
+ "step": 2460
1773
+ },
1774
+ {
1775
+ "epoch": 5.639269406392694,
1776
+ "grad_norm": 0.017079461365938187,
1777
+ "learning_rate": 1.4768835616438357e-05,
1778
+ "loss": 0.0004,
1779
+ "step": 2470
1780
+ },
1781
+ {
1782
+ "epoch": 5.662100456621005,
1783
+ "grad_norm": 0.09856831282377243,
1784
+ "learning_rate": 1.4626141552511415e-05,
1785
+ "loss": 0.0004,
1786
+ "step": 2480
1787
+ },
1788
+ {
1789
+ "epoch": 5.684931506849315,
1790
+ "grad_norm": 0.1313595324754715,
1791
+ "learning_rate": 1.4483447488584475e-05,
1792
+ "loss": 0.0007,
1793
+ "step": 2490
1794
+ },
1795
+ {
1796
+ "epoch": 5.707762557077626,
1797
+ "grad_norm": 0.006652920041233301,
1798
+ "learning_rate": 1.4340753424657535e-05,
1799
+ "loss": 0.0004,
1800
+ "step": 2500
1801
+ },
1802
+ {
1803
+ "epoch": 5.730593607305936,
1804
+ "grad_norm": 0.009232467040419579,
1805
+ "learning_rate": 1.4198059360730595e-05,
1806
+ "loss": 0.0004,
1807
+ "step": 2510
1808
+ },
1809
+ {
1810
+ "epoch": 5.7534246575342465,
1811
+ "grad_norm": 0.013255695812404156,
1812
+ "learning_rate": 1.4055365296803655e-05,
1813
+ "loss": 0.0005,
1814
+ "step": 2520
1815
+ },
1816
+ {
1817
+ "epoch": 5.776255707762557,
1818
+ "grad_norm": 0.017853327095508575,
1819
+ "learning_rate": 1.3912671232876712e-05,
1820
+ "loss": 0.0005,
1821
+ "step": 2530
1822
+ },
1823
+ {
1824
+ "epoch": 5.799086757990867,
1825
+ "grad_norm": 0.011152304708957672,
1826
+ "learning_rate": 1.3769977168949772e-05,
1827
+ "loss": 0.0004,
1828
+ "step": 2540
1829
+ },
1830
+ {
1831
+ "epoch": 5.821917808219178,
1832
+ "grad_norm": 0.00643182685598731,
1833
+ "learning_rate": 1.3627283105022832e-05,
1834
+ "loss": 0.0004,
1835
+ "step": 2550
1836
+ },
1837
+ {
1838
+ "epoch": 5.844748858447488,
1839
+ "grad_norm": 0.016502410173416138,
1840
+ "learning_rate": 1.348458904109589e-05,
1841
+ "loss": 0.0005,
1842
+ "step": 2560
1843
+ },
1844
+ {
1845
+ "epoch": 5.867579908675799,
1846
+ "grad_norm": 0.01771596260368824,
1847
+ "learning_rate": 1.334189497716895e-05,
1848
+ "loss": 0.0005,
1849
+ "step": 2570
1850
+ },
1851
+ {
1852
+ "epoch": 5.890410958904109,
1853
+ "grad_norm": 0.024237055331468582,
1854
+ "learning_rate": 1.319920091324201e-05,
1855
+ "loss": 0.0004,
1856
+ "step": 2580
1857
+ },
1858
+ {
1859
+ "epoch": 5.91324200913242,
1860
+ "grad_norm": 0.03518439084291458,
1861
+ "learning_rate": 1.305650684931507e-05,
1862
+ "loss": 0.0003,
1863
+ "step": 2590
1864
+ },
1865
+ {
1866
+ "epoch": 5.936073059360731,
1867
+ "grad_norm": 0.014818640425801277,
1868
+ "learning_rate": 1.291381278538813e-05,
1869
+ "loss": 0.0004,
1870
+ "step": 2600
1871
+ },
1872
+ {
1873
+ "epoch": 5.958904109589041,
1874
+ "grad_norm": 0.006442646961659193,
1875
+ "learning_rate": 1.2771118721461187e-05,
1876
+ "loss": 0.0005,
1877
+ "step": 2610
1878
+ },
1879
+ {
1880
+ "epoch": 5.981735159817352,
1881
+ "grad_norm": 0.0037180872168391943,
1882
+ "learning_rate": 1.2628424657534247e-05,
1883
+ "loss": 0.0004,
1884
+ "step": 2620
1885
+ },
1886
+ {
1887
+ "epoch": 6.0,
1888
+ "eval_loss": 3.286777655375772e-06,
1889
+ "eval_runtime": 71.001,
1890
+ "eval_samples_per_second": 42.253,
1891
+ "eval_steps_per_second": 2.648,
1892
+ "step": 2628
1893
+ },
1894
+ {
1895
+ "epoch": 6.004566210045662,
1896
+ "grad_norm": 0.00996373500674963,
1897
+ "learning_rate": 1.2485730593607307e-05,
1898
+ "loss": 0.0003,
1899
+ "step": 2630
1900
+ },
1901
+ {
1902
+ "epoch": 6.027397260273973,
1903
+ "grad_norm": 0.0067086792550981045,
1904
+ "learning_rate": 1.2343036529680365e-05,
1905
+ "loss": 0.0005,
1906
+ "step": 2640
1907
+ },
1908
+ {
1909
+ "epoch": 6.050228310502283,
1910
+ "grad_norm": 0.009166865609586239,
1911
+ "learning_rate": 1.2200342465753425e-05,
1912
+ "loss": 0.0005,
1913
+ "step": 2650
1914
+ },
1915
+ {
1916
+ "epoch": 6.073059360730594,
1917
+ "grad_norm": 0.005400144029408693,
1918
+ "learning_rate": 1.2057648401826485e-05,
1919
+ "loss": 0.0003,
1920
+ "step": 2660
1921
+ },
1922
+ {
1923
+ "epoch": 6.095890410958904,
1924
+ "grad_norm": 0.0033110773656517267,
1925
+ "learning_rate": 1.1914954337899543e-05,
1926
+ "loss": 0.0003,
1927
+ "step": 2670
1928
+ },
1929
+ {
1930
+ "epoch": 6.1187214611872145,
1931
+ "grad_norm": 0.017671756446361542,
1932
+ "learning_rate": 1.1772260273972603e-05,
1933
+ "loss": 0.0003,
1934
+ "step": 2680
1935
+ },
1936
+ {
1937
+ "epoch": 6.141552511415525,
1938
+ "grad_norm": 0.016568470746278763,
1939
+ "learning_rate": 1.1629566210045663e-05,
1940
+ "loss": 0.0005,
1941
+ "step": 2690
1942
+ },
1943
+ {
1944
+ "epoch": 6.164383561643835,
1945
+ "grad_norm": 0.11980602890253067,
1946
+ "learning_rate": 1.1486872146118723e-05,
1947
+ "loss": 0.0004,
1948
+ "step": 2700
1949
+ },
1950
+ {
1951
+ "epoch": 6.187214611872146,
1952
+ "grad_norm": 0.03170336037874222,
1953
+ "learning_rate": 1.1344178082191781e-05,
1954
+ "loss": 0.0004,
1955
+ "step": 2710
1956
+ },
1957
+ {
1958
+ "epoch": 6.210045662100456,
1959
+ "grad_norm": 0.01595723256468773,
1960
+ "learning_rate": 1.1201484018264841e-05,
1961
+ "loss": 0.0006,
1962
+ "step": 2720
1963
+ },
1964
+ {
1965
+ "epoch": 6.232876712328767,
1966
+ "grad_norm": 0.05525317043066025,
1967
+ "learning_rate": 1.10587899543379e-05,
1968
+ "loss": 0.0004,
1969
+ "step": 2730
1970
+ },
1971
+ {
1972
+ "epoch": 6.255707762557078,
1973
+ "grad_norm": 0.00609338004142046,
1974
+ "learning_rate": 1.091609589041096e-05,
1975
+ "loss": 0.0004,
1976
+ "step": 2740
1977
+ },
1978
+ {
1979
+ "epoch": 6.2785388127853885,
1980
+ "grad_norm": 0.061812903732061386,
1981
+ "learning_rate": 1.0773401826484018e-05,
1982
+ "loss": 0.0004,
1983
+ "step": 2750
1984
+ },
1985
+ {
1986
+ "epoch": 6.301369863013699,
1987
+ "grad_norm": 0.004055253695696592,
1988
+ "learning_rate": 1.0630707762557078e-05,
1989
+ "loss": 0.0003,
1990
+ "step": 2760
1991
+ },
1992
+ {
1993
+ "epoch": 6.324200913242009,
1994
+ "grad_norm": 0.010857106186449528,
1995
+ "learning_rate": 1.0488013698630138e-05,
1996
+ "loss": 0.0004,
1997
+ "step": 2770
1998
+ },
1999
+ {
2000
+ "epoch": 6.34703196347032,
2001
+ "grad_norm": 0.008729905821383,
2002
+ "learning_rate": 1.0345319634703198e-05,
2003
+ "loss": 0.0003,
2004
+ "step": 2780
2005
+ },
2006
+ {
2007
+ "epoch": 6.36986301369863,
2008
+ "grad_norm": 0.003697366453707218,
2009
+ "learning_rate": 1.0202625570776256e-05,
2010
+ "loss": 0.0003,
2011
+ "step": 2790
2012
+ },
2013
+ {
2014
+ "epoch": 6.392694063926941,
2015
+ "grad_norm": 0.0052353376522660255,
2016
+ "learning_rate": 1.0059931506849316e-05,
2017
+ "loss": 0.0003,
2018
+ "step": 2800
2019
+ },
2020
+ {
2021
+ "epoch": 6.415525114155251,
2022
+ "grad_norm": 0.06486661732196808,
2023
+ "learning_rate": 9.917237442922375e-06,
2024
+ "loss": 0.0003,
2025
+ "step": 2810
2026
+ },
2027
+ {
2028
+ "epoch": 6.438356164383562,
2029
+ "grad_norm": 0.036493659019470215,
2030
+ "learning_rate": 9.774543378995435e-06,
2031
+ "loss": 0.0004,
2032
+ "step": 2820
2033
+ },
2034
+ {
2035
+ "epoch": 6.461187214611872,
2036
+ "grad_norm": 0.010287893004715443,
2037
+ "learning_rate": 9.631849315068493e-06,
2038
+ "loss": 0.0005,
2039
+ "step": 2830
2040
+ },
2041
+ {
2042
+ "epoch": 6.4840182648401825,
2043
+ "grad_norm": 0.04603143036365509,
2044
+ "learning_rate": 9.489155251141553e-06,
2045
+ "loss": 0.0005,
2046
+ "step": 2840
2047
+ },
2048
+ {
2049
+ "epoch": 6.506849315068493,
2050
+ "grad_norm": 0.016138222068548203,
2051
+ "learning_rate": 9.346461187214613e-06,
2052
+ "loss": 0.0004,
2053
+ "step": 2850
2054
+ },
2055
+ {
2056
+ "epoch": 6.529680365296803,
2057
+ "grad_norm": 0.018696075305342674,
2058
+ "learning_rate": 9.203767123287671e-06,
2059
+ "loss": 0.0003,
2060
+ "step": 2860
2061
+ },
2062
+ {
2063
+ "epoch": 6.552511415525114,
2064
+ "grad_norm": 0.009262233041226864,
2065
+ "learning_rate": 9.061073059360731e-06,
2066
+ "loss": 0.0003,
2067
+ "step": 2870
2068
+ },
2069
+ {
2070
+ "epoch": 6.575342465753424,
2071
+ "grad_norm": 0.005299023352563381,
2072
+ "learning_rate": 8.918378995433791e-06,
2073
+ "loss": 0.0003,
2074
+ "step": 2880
2075
+ },
2076
+ {
2077
+ "epoch": 6.598173515981735,
2078
+ "grad_norm": 0.00924585945904255,
2079
+ "learning_rate": 8.77568493150685e-06,
2080
+ "loss": 0.0005,
2081
+ "step": 2890
2082
+ },
2083
+ {
2084
+ "epoch": 6.621004566210045,
2085
+ "grad_norm": 0.023650696501135826,
2086
+ "learning_rate": 8.632990867579908e-06,
2087
+ "loss": 0.0003,
2088
+ "step": 2900
2089
+ },
2090
+ {
2091
+ "epoch": 6.6438356164383565,
2092
+ "grad_norm": 0.005081293638795614,
2093
+ "learning_rate": 8.490296803652968e-06,
2094
+ "loss": 0.0003,
2095
+ "step": 2910
2096
+ },
2097
+ {
2098
+ "epoch": 6.666666666666667,
2099
+ "grad_norm": 0.012082752771675587,
2100
+ "learning_rate": 8.347602739726028e-06,
2101
+ "loss": 0.0003,
2102
+ "step": 2920
2103
+ },
2104
+ {
2105
+ "epoch": 6.689497716894977,
2106
+ "grad_norm": 0.004923298954963684,
2107
+ "learning_rate": 8.204908675799088e-06,
2108
+ "loss": 0.0004,
2109
+ "step": 2930
2110
+ },
2111
+ {
2112
+ "epoch": 6.712328767123288,
2113
+ "grad_norm": 0.012247243896126747,
2114
+ "learning_rate": 8.062214611872146e-06,
2115
+ "loss": 0.0003,
2116
+ "step": 2940
2117
+ },
2118
+ {
2119
+ "epoch": 6.735159817351598,
2120
+ "grad_norm": 0.003992004320025444,
2121
+ "learning_rate": 7.919520547945206e-06,
2122
+ "loss": 0.0004,
2123
+ "step": 2950
2124
+ },
2125
+ {
2126
+ "epoch": 6.757990867579909,
2127
+ "grad_norm": 0.11996075510978699,
2128
+ "learning_rate": 7.776826484018266e-06,
2129
+ "loss": 0.0004,
2130
+ "step": 2960
2131
+ },
2132
+ {
2133
+ "epoch": 6.780821917808219,
2134
+ "grad_norm": 0.005172852426767349,
2135
+ "learning_rate": 7.634132420091324e-06,
2136
+ "loss": 0.0003,
2137
+ "step": 2970
2138
+ },
2139
+ {
2140
+ "epoch": 6.80365296803653,
2141
+ "grad_norm": 0.006295430473983288,
2142
+ "learning_rate": 7.4914383561643835e-06,
2143
+ "loss": 0.0004,
2144
+ "step": 2980
2145
+ },
2146
+ {
2147
+ "epoch": 6.82648401826484,
2148
+ "grad_norm": 0.004225455224514008,
2149
+ "learning_rate": 7.3487442922374434e-06,
2150
+ "loss": 0.0003,
2151
+ "step": 2990
2152
+ },
2153
+ {
2154
+ "epoch": 6.8493150684931505,
2155
+ "grad_norm": 0.0032389916013926268,
2156
+ "learning_rate": 7.206050228310503e-06,
2157
+ "loss": 0.0003,
2158
+ "step": 3000
2159
+ },
2160
+ {
2161
+ "epoch": 6.872146118721461,
2162
+ "grad_norm": 0.038855355232954025,
2163
+ "learning_rate": 7.063356164383563e-06,
2164
+ "loss": 0.0003,
2165
+ "step": 3010
2166
+ },
2167
+ {
2168
+ "epoch": 6.894977168949771,
2169
+ "grad_norm": 0.003689020639285445,
2170
+ "learning_rate": 6.920662100456621e-06,
2171
+ "loss": 0.0004,
2172
+ "step": 3020
2173
+ },
2174
+ {
2175
+ "epoch": 6.917808219178082,
2176
+ "grad_norm": 0.01840381883084774,
2177
+ "learning_rate": 6.777968036529681e-06,
2178
+ "loss": 0.0003,
2179
+ "step": 3030
2180
+ },
2181
+ {
2182
+ "epoch": 6.940639269406392,
2183
+ "grad_norm": 0.00360796507447958,
2184
+ "learning_rate": 6.63527397260274e-06,
2185
+ "loss": 0.0003,
2186
+ "step": 3040
2187
+ },
2188
+ {
2189
+ "epoch": 6.963470319634704,
2190
+ "grad_norm": 0.01734967716038227,
2191
+ "learning_rate": 6.4925799086758e-06,
2192
+ "loss": 0.0003,
2193
+ "step": 3050
2194
+ },
2195
+ {
2196
+ "epoch": 6.986301369863014,
2197
+ "grad_norm": 0.03626614063978195,
2198
+ "learning_rate": 6.349885844748858e-06,
2199
+ "loss": 0.0003,
2200
+ "step": 3060
2201
+ },
2202
+ {
2203
+ "epoch": 7.0,
2204
+ "eval_loss": 2.8402284897310892e-06,
2205
+ "eval_runtime": 70.9798,
2206
+ "eval_samples_per_second": 42.266,
2207
+ "eval_steps_per_second": 2.649,
2208
+ "step": 3066
2209
+ },
2210
+ {
2211
+ "epoch": 7.0091324200913245,
2212
+ "grad_norm": 0.029538586735725403,
2213
+ "learning_rate": 6.207191780821918e-06,
2214
+ "loss": 0.0003,
2215
+ "step": 3070
2216
+ },
2217
+ {
2218
+ "epoch": 7.031963470319635,
2219
+ "grad_norm": 0.011442271992564201,
2220
+ "learning_rate": 6.0644977168949774e-06,
2221
+ "loss": 0.0003,
2222
+ "step": 3080
2223
+ },
2224
+ {
2225
+ "epoch": 7.054794520547945,
2226
+ "grad_norm": 0.009785550646483898,
2227
+ "learning_rate": 5.921803652968037e-06,
2228
+ "loss": 0.0003,
2229
+ "step": 3090
2230
+ },
2231
+ {
2232
+ "epoch": 7.077625570776256,
2233
+ "grad_norm": 0.048744283616542816,
2234
+ "learning_rate": 5.779109589041097e-06,
2235
+ "loss": 0.0006,
2236
+ "step": 3100
2237
+ },
2238
+ {
2239
+ "epoch": 7.100456621004566,
2240
+ "grad_norm": 0.007315410766750574,
2241
+ "learning_rate": 5.636415525114156e-06,
2242
+ "loss": 0.0002,
2243
+ "step": 3110
2244
+ },
2245
+ {
2246
+ "epoch": 7.123287671232877,
2247
+ "grad_norm": 0.007827061228454113,
2248
+ "learning_rate": 5.493721461187215e-06,
2249
+ "loss": 0.0004,
2250
+ "step": 3120
2251
+ },
2252
+ {
2253
+ "epoch": 7.146118721461187,
2254
+ "grad_norm": 0.0036791411694139242,
2255
+ "learning_rate": 5.351027397260274e-06,
2256
+ "loss": 0.0003,
2257
+ "step": 3130
2258
+ },
2259
+ {
2260
+ "epoch": 7.168949771689498,
2261
+ "grad_norm": 0.010082785040140152,
2262
+ "learning_rate": 5.208333333333334e-06,
2263
+ "loss": 0.0003,
2264
+ "step": 3140
2265
+ },
2266
+ {
2267
+ "epoch": 7.191780821917808,
2268
+ "grad_norm": 0.008839433081448078,
2269
+ "learning_rate": 5.065639269406393e-06,
2270
+ "loss": 0.0003,
2271
+ "step": 3150
2272
+ },
2273
+ {
2274
+ "epoch": 7.2146118721461185,
2275
+ "grad_norm": 0.009164104238152504,
2276
+ "learning_rate": 4.922945205479452e-06,
2277
+ "loss": 0.0003,
2278
+ "step": 3160
2279
+ },
2280
+ {
2281
+ "epoch": 7.237442922374429,
2282
+ "grad_norm": 0.06758883595466614,
2283
+ "learning_rate": 4.7802511415525114e-06,
2284
+ "loss": 0.0003,
2285
+ "step": 3170
2286
+ },
2287
+ {
2288
+ "epoch": 7.260273972602739,
2289
+ "grad_norm": 0.0034141126088798046,
2290
+ "learning_rate": 4.6375570776255714e-06,
2291
+ "loss": 0.0004,
2292
+ "step": 3180
2293
+ },
2294
+ {
2295
+ "epoch": 7.28310502283105,
2296
+ "grad_norm": 0.009116005152463913,
2297
+ "learning_rate": 4.494863013698631e-06,
2298
+ "loss": 0.0003,
2299
+ "step": 3190
2300
+ },
2301
+ {
2302
+ "epoch": 7.30593607305936,
2303
+ "grad_norm": 0.014750838279724121,
2304
+ "learning_rate": 4.35216894977169e-06,
2305
+ "loss": 0.0003,
2306
+ "step": 3200
2307
+ },
2308
+ {
2309
+ "epoch": 7.328767123287671,
2310
+ "grad_norm": 0.013239488005638123,
2311
+ "learning_rate": 4.209474885844749e-06,
2312
+ "loss": 0.0003,
2313
+ "step": 3210
2314
+ },
2315
+ {
2316
+ "epoch": 7.351598173515982,
2317
+ "grad_norm": 0.009504084475338459,
2318
+ "learning_rate": 4.066780821917809e-06,
2319
+ "loss": 0.0004,
2320
+ "step": 3220
2321
+ },
2322
+ {
2323
+ "epoch": 7.3744292237442925,
2324
+ "grad_norm": 0.018879897892475128,
2325
+ "learning_rate": 3.924086757990868e-06,
2326
+ "loss": 0.0004,
2327
+ "step": 3230
2328
+ },
2329
+ {
2330
+ "epoch": 7.397260273972603,
2331
+ "grad_norm": 0.01805570162832737,
2332
+ "learning_rate": 3.7813926940639276e-06,
2333
+ "loss": 0.0003,
2334
+ "step": 3240
2335
+ },
2336
+ {
2337
+ "epoch": 7.420091324200913,
2338
+ "grad_norm": 0.08645830303430557,
2339
+ "learning_rate": 3.6386986301369863e-06,
2340
+ "loss": 0.0005,
2341
+ "step": 3250
2342
+ },
2343
+ {
2344
+ "epoch": 7.442922374429224,
2345
+ "grad_norm": 0.01047169417142868,
2346
+ "learning_rate": 3.4960045662100463e-06,
2347
+ "loss": 0.0003,
2348
+ "step": 3260
2349
+ },
2350
+ {
2351
+ "epoch": 7.465753424657534,
2352
+ "grad_norm": 0.00378281413577497,
2353
+ "learning_rate": 3.353310502283105e-06,
2354
+ "loss": 0.0003,
2355
+ "step": 3270
2356
+ },
2357
+ {
2358
+ "epoch": 7.488584474885845,
2359
+ "grad_norm": 0.008809005841612816,
2360
+ "learning_rate": 3.210616438356165e-06,
2361
+ "loss": 0.0003,
2362
+ "step": 3280
2363
+ },
2364
+ {
2365
+ "epoch": 7.511415525114155,
2366
+ "grad_norm": 0.006725851446390152,
2367
+ "learning_rate": 3.0679223744292237e-06,
2368
+ "loss": 0.0003,
2369
+ "step": 3290
2370
+ },
2371
+ {
2372
+ "epoch": 7.534246575342466,
2373
+ "grad_norm": 0.011108343489468098,
2374
+ "learning_rate": 2.9252283105022833e-06,
2375
+ "loss": 0.0003,
2376
+ "step": 3300
2377
+ },
2378
+ {
2379
+ "epoch": 7.557077625570776,
2380
+ "grad_norm": 0.006323591805994511,
2381
+ "learning_rate": 2.7825342465753424e-06,
2382
+ "loss": 0.0003,
2383
+ "step": 3310
2384
+ },
2385
+ {
2386
+ "epoch": 7.579908675799087,
2387
+ "grad_norm": 0.01762283407151699,
2388
+ "learning_rate": 2.639840182648402e-06,
2389
+ "loss": 0.0003,
2390
+ "step": 3320
2391
+ },
2392
+ {
2393
+ "epoch": 7.602739726027397,
2394
+ "grad_norm": 0.003676204476505518,
2395
+ "learning_rate": 2.497146118721461e-06,
2396
+ "loss": 0.0002,
2397
+ "step": 3330
2398
+ },
2399
+ {
2400
+ "epoch": 7.6255707762557075,
2401
+ "grad_norm": 0.04348291829228401,
2402
+ "learning_rate": 2.3544520547945207e-06,
2403
+ "loss": 0.0003,
2404
+ "step": 3340
2405
+ },
2406
+ {
2407
+ "epoch": 7.648401826484018,
2408
+ "grad_norm": 0.01973540708422661,
2409
+ "learning_rate": 2.21175799086758e-06,
2410
+ "loss": 0.0004,
2411
+ "step": 3350
2412
+ },
2413
+ {
2414
+ "epoch": 7.671232876712329,
2415
+ "grad_norm": 0.0020602825097739697,
2416
+ "learning_rate": 2.0690639269406394e-06,
2417
+ "loss": 0.0003,
2418
+ "step": 3360
2419
+ },
2420
+ {
2421
+ "epoch": 7.69406392694064,
2422
+ "grad_norm": 0.031328316777944565,
2423
+ "learning_rate": 1.9263698630136986e-06,
2424
+ "loss": 0.0003,
2425
+ "step": 3370
2426
+ },
2427
+ {
2428
+ "epoch": 7.71689497716895,
2429
+ "grad_norm": 0.004346560686826706,
2430
+ "learning_rate": 1.7836757990867581e-06,
2431
+ "loss": 0.0003,
2432
+ "step": 3380
2433
+ },
2434
+ {
2435
+ "epoch": 7.739726027397261,
2436
+ "grad_norm": 0.020926913246512413,
2437
+ "learning_rate": 1.6409817351598175e-06,
2438
+ "loss": 0.0003,
2439
+ "step": 3390
2440
+ },
2441
+ {
2442
+ "epoch": 7.762557077625571,
2443
+ "grad_norm": 0.012918849475681782,
2444
+ "learning_rate": 1.4982876712328766e-06,
2445
+ "loss": 0.0005,
2446
+ "step": 3400
2447
+ },
2448
+ {
2449
+ "epoch": 7.7853881278538815,
2450
+ "grad_norm": 0.03088468685746193,
2451
+ "learning_rate": 1.355593607305936e-06,
2452
+ "loss": 0.0004,
2453
+ "step": 3410
2454
+ },
2455
+ {
2456
+ "epoch": 7.808219178082192,
2457
+ "grad_norm": 0.02280372381210327,
2458
+ "learning_rate": 1.2128995433789954e-06,
2459
+ "loss": 0.0006,
2460
+ "step": 3420
2461
+ },
2462
+ {
2463
+ "epoch": 7.831050228310502,
2464
+ "grad_norm": 0.0038483564276248217,
2465
+ "learning_rate": 1.0702054794520547e-06,
2466
+ "loss": 0.0003,
2467
+ "step": 3430
2468
+ },
2469
+ {
2470
+ "epoch": 7.853881278538813,
2471
+ "grad_norm": 0.026072148233652115,
2472
+ "learning_rate": 9.275114155251142e-07,
2473
+ "loss": 0.0004,
2474
+ "step": 3440
2475
+ },
2476
+ {
2477
+ "epoch": 7.876712328767123,
2478
+ "grad_norm": 0.05634905397891998,
2479
+ "learning_rate": 7.848173515981735e-07,
2480
+ "loss": 0.0003,
2481
+ "step": 3450
2482
+ },
2483
+ {
2484
+ "epoch": 7.899543378995434,
2485
+ "grad_norm": 0.003738977015018463,
2486
+ "learning_rate": 6.421232876712329e-07,
2487
+ "loss": 0.0003,
2488
+ "step": 3460
2489
+ },
2490
+ {
2491
+ "epoch": 7.922374429223744,
2492
+ "grad_norm": 0.00907827913761139,
2493
+ "learning_rate": 4.994292237442923e-07,
2494
+ "loss": 0.0003,
2495
+ "step": 3470
2496
+ },
2497
+ {
2498
+ "epoch": 7.945205479452055,
2499
+ "grad_norm": 0.02188229374587536,
2500
+ "learning_rate": 3.567351598173516e-07,
2501
+ "loss": 0.0003,
2502
+ "step": 3480
2503
+ },
2504
+ {
2505
+ "epoch": 7.968036529680365,
2506
+ "grad_norm": 0.020626889541745186,
2507
+ "learning_rate": 2.1404109589041096e-07,
2508
+ "loss": 0.0003,
2509
+ "step": 3490
2510
+ },
2511
+ {
2512
+ "epoch": 7.9908675799086755,
2513
+ "grad_norm": 0.010182246565818787,
2514
+ "learning_rate": 7.134703196347032e-08,
2515
+ "loss": 0.0004,
2516
+ "step": 3500
2517
+ },
2518
+ {
2519
+ "epoch": 8.0,
2520
+ "eval_loss": 2.446558710289537e-06,
2521
+ "eval_runtime": 70.9518,
2522
+ "eval_samples_per_second": 42.282,
2523
+ "eval_steps_per_second": 2.65,
2524
+ "step": 3504
2525
+ }
2526
+ ],
2527
+ "logging_steps": 10,
2528
+ "max_steps": 3504,
2529
+ "num_input_tokens_seen": 0,
2530
+ "num_train_epochs": 8,
2531
+ "save_steps": 500,
2532
+ "stateful_callbacks": {
2533
+ "TrainerControl": {
2534
+ "args": {
2535
+ "should_epoch_stop": false,
2536
+ "should_evaluate": false,
2537
+ "should_log": false,
2538
+ "should_save": true,
2539
+ "should_training_stop": true
2540
+ },
2541
+ "attributes": {}
2542
+ }
2543
+ },
2544
+ "total_flos": 8742142387077120.0,
2545
+ "train_batch_size": 16,
2546
+ "trial_name": null,
2547
+ "trial_params": null
2548
+ }
checkpoint-3504/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:536a15733a09a147c1cc9faed7a9ba8819a6e01002dd2ab5aedf45c4f5cfa948
3
+ size 5432
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b46cdbe0a335237fdde02d571f771dcac636ebebaa3a391ab42d74df56cf72e4
3
  size 891644712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70879216cd6ea3ceb50cdb0fe9b86860601a7043056bb3911b57091a58c969de
3
  size 891644712
special_tokens_map.json CHANGED
@@ -101,25 +101,7 @@
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
  }
 
101
  "<extra_id_98>",
102
  "<extra_id_99>"
103
  ],
104
+ "eos_token": "</s>",
105
+ "pad_token": "<pad>",
106
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
107
  }
tokenizer_config.json CHANGED
@@ -932,12 +932,8 @@
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
  }
 
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
  }