Dohahemdann commited on
Commit
81be9ae
·
verified ·
1 Parent(s): 2a5b2c5

Upload checkpoint-1000 from fine-tuning

Browse files
checkpoints/checkpoint-1000/config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "T5ForConditionalGeneration"
4
+ ],
5
+ "classifier_dropout": 0.0,
6
+ "d_ff": 2048,
7
+ "d_kv": 64,
8
+ "d_model": 768,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "gated-gelu",
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "is_gated_act": true,
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
+ "tie_word_embeddings": false,
57
+ "torch_dtype": "float32",
58
+ "transformers_version": "4.51.1",
59
+ "use_cache": true,
60
+ "vocab_size": 32128
61
+ }
checkpoints/checkpoint-1000/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
+ }
checkpoints/checkpoint-1000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dce41ae40f23cbebbb2ee5e85a1e03344eeaf0a979f38cfa802aa59bacf2b94
3
+ size 990345064
checkpoints/checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecbdea171f9cd7871e34c1447144e427cca177b2595cd6d2c1b73478359b7cc7
3
+ size 1980860410
checkpoints/checkpoint-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b085027095bb525d7b7c3a061ba17bf3bc69e7e0c0ea123bcb606140a9db1c4
3
+ size 14244
checkpoints/checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:777449c878f11dc9312c83f02330bc18b2f03969f84fbda805772c4519d61049
3
+ size 1064
checkpoints/checkpoint-1000/special_tokens_map.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": {
105
+ "content": "</s>",
106
+ "lstrip": false,
107
+ "normalized": false,
108
+ "rstrip": false,
109
+ "single_word": false
110
+ },
111
+ "pad_token": {
112
+ "content": "<pad>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "unk_token": {
119
+ "content": "<unk>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ }
125
+ }
checkpoints/checkpoint-1000/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
checkpoints/checkpoint-1000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/checkpoint-1000/tokenizer_config.json ADDED
@@ -0,0 +1,940 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 512,
936
+ "pad_token": "<pad>",
937
+ "sp_model_kwargs": {},
938
+ "tokenizer_class": "T5Tokenizer",
939
+ "unk_token": "<unk>"
940
+ }
checkpoints/checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,734 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.5510204081632653,
6
+ "eval_steps": 500,
7
+ "global_step": 1000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.025510204081632654,
14
+ "grad_norm": 2.016150951385498,
15
+ "learning_rate": 0.00029770408163265304,
16
+ "loss": 1.9547,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.05102040816326531,
21
+ "grad_norm": 2.4335200786590576,
22
+ "learning_rate": 0.00029515306122448976,
23
+ "loss": 1.5455,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.07653061224489796,
28
+ "grad_norm": 2.820722818374634,
29
+ "learning_rate": 0.0002926020408163265,
30
+ "loss": 1.558,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.10204081632653061,
35
+ "grad_norm": 1.7485514879226685,
36
+ "learning_rate": 0.0002900510204081632,
37
+ "loss": 1.4405,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.12755102040816327,
42
+ "grad_norm": 1.4179495573043823,
43
+ "learning_rate": 0.0002875,
44
+ "loss": 1.451,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.15306122448979592,
49
+ "grad_norm": 1.792877197265625,
50
+ "learning_rate": 0.0002849489795918367,
51
+ "loss": 1.4533,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.17857142857142858,
56
+ "grad_norm": 1.5444788932800293,
57
+ "learning_rate": 0.00028239795918367345,
58
+ "loss": 1.4007,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.20408163265306123,
63
+ "grad_norm": 1.8548578023910522,
64
+ "learning_rate": 0.00027984693877551017,
65
+ "loss": 1.4197,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.22959183673469388,
70
+ "grad_norm": 1.4318586587905884,
71
+ "learning_rate": 0.0002772959183673469,
72
+ "loss": 1.3465,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.25510204081632654,
77
+ "grad_norm": 1.6237703561782837,
78
+ "learning_rate": 0.0002747448979591837,
79
+ "loss": 1.4478,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.28061224489795916,
84
+ "grad_norm": 1.2553024291992188,
85
+ "learning_rate": 0.0002721938775510204,
86
+ "loss": 1.4103,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.30612244897959184,
91
+ "grad_norm": 1.4535470008850098,
92
+ "learning_rate": 0.00026964285714285713,
93
+ "loss": 1.4637,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.33163265306122447,
98
+ "grad_norm": 1.362635612487793,
99
+ "learning_rate": 0.00026709183673469386,
100
+ "loss": 1.4474,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.35714285714285715,
105
+ "grad_norm": 1.2966548204421997,
106
+ "learning_rate": 0.0002645408163265306,
107
+ "loss": 1.3955,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.3826530612244898,
112
+ "grad_norm": 1.3156458139419556,
113
+ "learning_rate": 0.00026198979591836736,
114
+ "loss": 1.429,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.40816326530612246,
119
+ "grad_norm": 1.230600357055664,
120
+ "learning_rate": 0.00025943877551020403,
121
+ "loss": 1.4009,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.4336734693877551,
126
+ "grad_norm": 1.4969375133514404,
127
+ "learning_rate": 0.0002568877551020408,
128
+ "loss": 1.3173,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.45918367346938777,
133
+ "grad_norm": 1.3649333715438843,
134
+ "learning_rate": 0.00025433673469387754,
135
+ "loss": 1.3243,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.4846938775510204,
140
+ "grad_norm": 1.449601650238037,
141
+ "learning_rate": 0.00025178571428571426,
142
+ "loss": 1.3303,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.5102040816326531,
147
+ "grad_norm": 2.1325271129608154,
148
+ "learning_rate": 0.000249234693877551,
149
+ "loss": 1.4918,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.5357142857142857,
154
+ "grad_norm": 1.608302354812622,
155
+ "learning_rate": 0.0002466836734693877,
156
+ "loss": 1.3717,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.5612244897959183,
161
+ "grad_norm": 1.438018798828125,
162
+ "learning_rate": 0.00024413265306122447,
163
+ "loss": 1.3609,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.5867346938775511,
168
+ "grad_norm": 1.2611685991287231,
169
+ "learning_rate": 0.0002415816326530612,
170
+ "loss": 1.4213,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.6122448979591837,
175
+ "grad_norm": 1.3596704006195068,
176
+ "learning_rate": 0.00023903061224489795,
177
+ "loss": 1.4048,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.6377551020408163,
182
+ "grad_norm": 1.2733218669891357,
183
+ "learning_rate": 0.00023647959183673467,
184
+ "loss": 1.471,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.6632653061224489,
189
+ "grad_norm": 1.4014158248901367,
190
+ "learning_rate": 0.0002339285714285714,
191
+ "loss": 1.4012,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.6887755102040817,
196
+ "grad_norm": 1.276021122932434,
197
+ "learning_rate": 0.00023137755102040815,
198
+ "loss": 1.4331,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.7142857142857143,
203
+ "grad_norm": 1.207608699798584,
204
+ "learning_rate": 0.00022882653061224488,
205
+ "loss": 1.319,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.7397959183673469,
210
+ "grad_norm": 1.1684128046035767,
211
+ "learning_rate": 0.00022627551020408163,
212
+ "loss": 1.3643,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.7653061224489796,
217
+ "grad_norm": 1.370298981666565,
218
+ "learning_rate": 0.00022372448979591833,
219
+ "loss": 1.3675,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.7908163265306123,
224
+ "grad_norm": 1.1974862813949585,
225
+ "learning_rate": 0.00022117346938775508,
226
+ "loss": 1.3311,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.8163265306122449,
231
+ "grad_norm": 1.1502070426940918,
232
+ "learning_rate": 0.0002186224489795918,
233
+ "loss": 1.4007,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.8418367346938775,
238
+ "grad_norm": 1.3686124086380005,
239
+ "learning_rate": 0.00021607142857142856,
240
+ "loss": 1.3495,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.8673469387755102,
245
+ "grad_norm": 1.5245591402053833,
246
+ "learning_rate": 0.0002135204081632653,
247
+ "loss": 1.4297,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.8928571428571429,
252
+ "grad_norm": 1.3602415323257446,
253
+ "learning_rate": 0.000210969387755102,
254
+ "loss": 1.4253,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.9183673469387755,
259
+ "grad_norm": 1.4920992851257324,
260
+ "learning_rate": 0.00020841836734693877,
261
+ "loss": 1.4094,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.9438775510204082,
266
+ "grad_norm": 1.1482244729995728,
267
+ "learning_rate": 0.0002058673469387755,
268
+ "loss": 1.3904,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.9693877551020408,
273
+ "grad_norm": 1.1585501432418823,
274
+ "learning_rate": 0.00020331632653061222,
275
+ "loss": 1.3538,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.9948979591836735,
280
+ "grad_norm": 1.4000365734100342,
281
+ "learning_rate": 0.00020076530612244897,
282
+ "loss": 1.3892,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 1.0204081632653061,
287
+ "grad_norm": 1.0782071352005005,
288
+ "learning_rate": 0.0001982142857142857,
289
+ "loss": 1.1418,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 1.0459183673469388,
294
+ "grad_norm": 1.6901600360870361,
295
+ "learning_rate": 0.00019566326530612245,
296
+ "loss": 1.1591,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 1.0714285714285714,
301
+ "grad_norm": 1.435246229171753,
302
+ "learning_rate": 0.00019311224489795915,
303
+ "loss": 1.1675,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 1.096938775510204,
308
+ "grad_norm": 1.122884750366211,
309
+ "learning_rate": 0.0001905612244897959,
310
+ "loss": 1.1153,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 1.1224489795918366,
315
+ "grad_norm": 1.6136234998703003,
316
+ "learning_rate": 0.00018801020408163263,
317
+ "loss": 1.1185,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 1.1479591836734695,
322
+ "grad_norm": 1.2358646392822266,
323
+ "learning_rate": 0.00018545918367346938,
324
+ "loss": 1.1855,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 1.1734693877551021,
329
+ "grad_norm": 1.2392523288726807,
330
+ "learning_rate": 0.0001829081632653061,
331
+ "loss": 1.1508,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 1.1989795918367347,
336
+ "grad_norm": 1.416016936302185,
337
+ "learning_rate": 0.00018035714285714283,
338
+ "loss": 1.1844,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 1.2244897959183674,
343
+ "grad_norm": 1.1348795890808105,
344
+ "learning_rate": 0.00017780612244897958,
345
+ "loss": 1.105,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 1.25,
350
+ "grad_norm": 1.2848577499389648,
351
+ "learning_rate": 0.0001752551020408163,
352
+ "loss": 1.1786,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 1.2755102040816326,
357
+ "grad_norm": 1.2211813926696777,
358
+ "learning_rate": 0.00017270408163265304,
359
+ "loss": 1.1044,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 1.3010204081632653,
364
+ "grad_norm": 1.3097877502441406,
365
+ "learning_rate": 0.0001701530612244898,
366
+ "loss": 1.1237,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 1.3265306122448979,
371
+ "grad_norm": 1.1218714714050293,
372
+ "learning_rate": 0.00016760204081632651,
373
+ "loss": 1.1362,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 1.3520408163265305,
378
+ "grad_norm": 1.4992038011550903,
379
+ "learning_rate": 0.00016505102040816327,
380
+ "loss": 1.1386,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 1.3775510204081631,
385
+ "grad_norm": 1.4027036428451538,
386
+ "learning_rate": 0.00016249999999999997,
387
+ "loss": 1.2063,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 1.403061224489796,
392
+ "grad_norm": 1.2812182903289795,
393
+ "learning_rate": 0.00015994897959183672,
394
+ "loss": 1.1816,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 1.4285714285714286,
399
+ "grad_norm": 1.2382524013519287,
400
+ "learning_rate": 0.00015739795918367347,
401
+ "loss": 1.2008,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 1.4540816326530612,
406
+ "grad_norm": 1.4030746221542358,
407
+ "learning_rate": 0.0001548469387755102,
408
+ "loss": 1.1321,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 1.4795918367346939,
413
+ "grad_norm": 1.0693562030792236,
414
+ "learning_rate": 0.00015229591836734692,
415
+ "loss": 1.1405,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 1.5051020408163265,
420
+ "grad_norm": 1.3409092426300049,
421
+ "learning_rate": 0.00014974489795918368,
422
+ "loss": 1.1788,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 1.5306122448979593,
427
+ "grad_norm": 1.269675612449646,
428
+ "learning_rate": 0.0001471938775510204,
429
+ "loss": 1.1553,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 1.556122448979592,
434
+ "grad_norm": 1.210330843925476,
435
+ "learning_rate": 0.00014464285714285713,
436
+ "loss": 1.2281,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 1.5816326530612246,
441
+ "grad_norm": 1.1834529638290405,
442
+ "learning_rate": 0.00014209183673469385,
443
+ "loss": 1.1667,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 1.6071428571428572,
448
+ "grad_norm": 1.3494176864624023,
449
+ "learning_rate": 0.0001395408163265306,
450
+ "loss": 1.1599,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 1.6326530612244898,
455
+ "grad_norm": 1.3258039951324463,
456
+ "learning_rate": 0.00013698979591836733,
457
+ "loss": 1.1009,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 1.6581632653061225,
462
+ "grad_norm": 1.1357011795043945,
463
+ "learning_rate": 0.00013443877551020408,
464
+ "loss": 1.1258,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 1.683673469387755,
469
+ "grad_norm": 1.292371392250061,
470
+ "learning_rate": 0.0001318877551020408,
471
+ "loss": 1.1593,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 1.7091836734693877,
476
+ "grad_norm": 1.0983706712722778,
477
+ "learning_rate": 0.00012933673469387754,
478
+ "loss": 1.1902,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 1.7346938775510203,
483
+ "grad_norm": 1.2399263381958008,
484
+ "learning_rate": 0.00012678571428571426,
485
+ "loss": 1.146,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 1.760204081632653,
490
+ "grad_norm": 1.248655915260315,
491
+ "learning_rate": 0.00012423469387755101,
492
+ "loss": 1.1565,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 1.7857142857142856,
497
+ "grad_norm": 1.5907831192016602,
498
+ "learning_rate": 0.00012168367346938774,
499
+ "loss": 1.2047,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 1.8112244897959182,
504
+ "grad_norm": 1.0962166786193848,
505
+ "learning_rate": 0.00011913265306122448,
506
+ "loss": 1.1444,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 1.836734693877551,
511
+ "grad_norm": 1.3463186025619507,
512
+ "learning_rate": 0.00011658163265306122,
513
+ "loss": 1.2113,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 1.8622448979591837,
518
+ "grad_norm": 1.2715240716934204,
519
+ "learning_rate": 0.00011403061224489795,
520
+ "loss": 1.1477,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 1.8877551020408163,
525
+ "grad_norm": 1.52438485622406,
526
+ "learning_rate": 0.00011147959183673468,
527
+ "loss": 1.1421,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 1.913265306122449,
532
+ "grad_norm": 1.2634963989257812,
533
+ "learning_rate": 0.00010892857142857141,
534
+ "loss": 1.1075,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 1.9387755102040818,
539
+ "grad_norm": 1.599583387374878,
540
+ "learning_rate": 0.00010637755102040815,
541
+ "loss": 1.1303,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 1.9642857142857144,
546
+ "grad_norm": 1.16295325756073,
547
+ "learning_rate": 0.0001038265306122449,
548
+ "loss": 1.1476,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 1.989795918367347,
553
+ "grad_norm": 1.2175824642181396,
554
+ "learning_rate": 0.00010127551020408163,
555
+ "loss": 1.0897,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 2.0153061224489797,
560
+ "grad_norm": 1.2181735038757324,
561
+ "learning_rate": 9.872448979591835e-05,
562
+ "loss": 1.104,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 2.0408163265306123,
567
+ "grad_norm": 1.384055733680725,
568
+ "learning_rate": 9.61734693877551e-05,
569
+ "loss": 1.0201,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 2.066326530612245,
574
+ "grad_norm": 1.5154542922973633,
575
+ "learning_rate": 9.362244897959182e-05,
576
+ "loss": 1.0368,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 2.0918367346938775,
581
+ "grad_norm": 1.238797903060913,
582
+ "learning_rate": 9.107142857142856e-05,
583
+ "loss": 0.9879,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 2.11734693877551,
588
+ "grad_norm": 1.595146894454956,
589
+ "learning_rate": 8.852040816326531e-05,
590
+ "loss": 1.0086,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 2.142857142857143,
595
+ "grad_norm": 1.3335082530975342,
596
+ "learning_rate": 8.596938775510204e-05,
597
+ "loss": 1.0318,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 2.1683673469387754,
602
+ "grad_norm": 1.291253924369812,
603
+ "learning_rate": 8.341836734693876e-05,
604
+ "loss": 1.0189,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 2.193877551020408,
609
+ "grad_norm": 1.2663589715957642,
610
+ "learning_rate": 8.08673469387755e-05,
611
+ "loss": 1.018,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 2.2193877551020407,
616
+ "grad_norm": 1.0520204305648804,
617
+ "learning_rate": 7.831632653061223e-05,
618
+ "loss": 1.0115,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 2.2448979591836733,
623
+ "grad_norm": 1.2855923175811768,
624
+ "learning_rate": 7.576530612244897e-05,
625
+ "loss": 1.0153,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 2.270408163265306,
630
+ "grad_norm": 1.1759591102600098,
631
+ "learning_rate": 7.321428571428571e-05,
632
+ "loss": 1.0412,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 2.295918367346939,
637
+ "grad_norm": 1.2009315490722656,
638
+ "learning_rate": 7.066326530612245e-05,
639
+ "loss": 1.0501,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 2.3214285714285716,
644
+ "grad_norm": 1.2560603618621826,
645
+ "learning_rate": 6.811224489795917e-05,
646
+ "loss": 0.9785,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 2.3469387755102042,
651
+ "grad_norm": 1.2625336647033691,
652
+ "learning_rate": 6.556122448979591e-05,
653
+ "loss": 1.0727,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 2.372448979591837,
658
+ "grad_norm": 1.2614808082580566,
659
+ "learning_rate": 6.301020408163265e-05,
660
+ "loss": 1.0349,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 2.3979591836734695,
665
+ "grad_norm": 1.1793627738952637,
666
+ "learning_rate": 6.045918367346938e-05,
667
+ "loss": 1.045,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 2.423469387755102,
672
+ "grad_norm": 1.4077281951904297,
673
+ "learning_rate": 5.7908163265306116e-05,
674
+ "loss": 1.0496,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 2.4489795918367347,
679
+ "grad_norm": 1.2881996631622314,
680
+ "learning_rate": 5.5357142857142855e-05,
681
+ "loss": 1.0157,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 2.4744897959183674,
686
+ "grad_norm": 1.5866761207580566,
687
+ "learning_rate": 5.280612244897959e-05,
688
+ "loss": 1.0002,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 2.5,
693
+ "grad_norm": 1.34805166721344,
694
+ "learning_rate": 5.025510204081632e-05,
695
+ "loss": 1.0039,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 2.5255102040816326,
700
+ "grad_norm": 1.1400980949401855,
701
+ "learning_rate": 4.770408163265306e-05,
702
+ "loss": 1.0247,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 2.5510204081632653,
707
+ "grad_norm": 1.1816837787628174,
708
+ "learning_rate": 4.515306122448979e-05,
709
+ "loss": 0.9672,
710
+ "step": 1000
711
+ }
712
+ ],
713
+ "logging_steps": 10,
714
+ "max_steps": 1176,
715
+ "num_input_tokens_seen": 0,
716
+ "num_train_epochs": 3,
717
+ "save_steps": 500,
718
+ "stateful_callbacks": {
719
+ "TrainerControl": {
720
+ "args": {
721
+ "should_epoch_stop": false,
722
+ "should_evaluate": false,
723
+ "should_log": false,
724
+ "should_save": true,
725
+ "should_training_stop": false
726
+ },
727
+ "attributes": {}
728
+ }
729
+ },
730
+ "total_flos": 1.0926170204332032e+16,
731
+ "train_batch_size": 16,
732
+ "trial_name": null,
733
+ "trial_params": null
734
+ }
checkpoints/checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3473ca5eef48df07544c65e2e264fa4c3624db42ed8a29c4d32828443469c32
3
+ size 5240