felerminoali commited on
Commit
15acd94
·
verified ·
1 Parent(s): e22aba6

Training in progress, step 15000

Browse files
all_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 3.0,
3
- "total_flos": 3.152977773933363e+16,
4
- "train_loss": 3.293868990633756,
5
- "train_runtime": 5199.8209,
6
  "train_samples": 65573,
7
- "train_samples_per_second": 37.832,
8
- "train_steps_per_second": 3.784
9
  }
 
1
  {
2
  "epoch": 3.0,
3
+ "total_flos": 4.51806634222551e+16,
4
+ "train_loss": 2.926649949844495,
5
+ "train_runtime": 7468.4511,
6
  "train_samples": 65573,
7
+ "train_samples_per_second": 26.34,
8
+ "train_steps_per_second": 3.293
9
  }
config.json CHANGED
@@ -1,32 +1,33 @@
1
  {
2
  "architectures": [
3
- "MT5ForConditionalGeneration"
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": "mt5",
19
- "num_decoder_layers": 12,
20
  "num_heads": 12,
21
- "num_layers": 12,
22
  "output_past": true,
23
  "pad_token_id": 0,
24
  "relative_attention_max_distance": 128,
25
  "relative_attention_num_buckets": 32,
26
  "tie_word_embeddings": false,
27
- "tokenizer_class": "T5Tokenizer",
28
  "torch_dtype": "float32",
29
  "transformers_version": "4.53.0.dev0",
30
  "use_cache": true,
31
- "vocab_size": 250100
32
  }
 
1
  {
2
  "architectures": [
3
+ "T5ForConditionalGeneration"
4
  ],
5
  "classifier_dropout": 0.0,
6
+ "d_ff": 3968,
7
  "d_kv": 64,
8
+ "d_model": 1536,
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
+ "gradient_checkpointing": false,
15
  "initializer_factor": 1.0,
16
  "is_encoder_decoder": true,
17
  "is_gated_act": true,
18
  "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "num_decoder_layers": 6,
21
  "num_heads": 12,
22
+ "num_layers": 18,
23
  "output_past": true,
24
  "pad_token_id": 0,
25
  "relative_attention_max_distance": 128,
26
  "relative_attention_num_buckets": 32,
27
  "tie_word_embeddings": false,
28
+ "tokenizer_class": "ByT5Tokenizer",
29
  "torch_dtype": "float32",
30
  "transformers_version": "4.53.0.dev0",
31
  "use_cache": true,
32
+ "vocab_size": 384
33
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5732d5336f4683f368e90fc68efc09ba26fc675825f19d447eb93ec99a36b38e
3
- size 2329565040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24043151dc356b158255d9b936eee73e2f489d046853f653aced1f9e25420ae2
3
+ size 2326643632
runs/Jun08_20-02-00_serv-9213/events.out.tfevents.1749405760.serv-9213.3242817.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9484f82caaa56414784206e5e5682f445152ee84f41ca0d6dc8be5eb3fda4a42
3
- size 11086
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c7568bbeb9ae9e4eb6bc4fdd8682bba47d055ee3577e4ad4ce2636b81d22f9b
3
+ size 11508
special_tokens_map.json CHANGED
@@ -1,22 +1,149 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "eos_token": {
3
  "content": "</s>",
4
  "lstrip": false,
5
- "normalized": false,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "pad_token": {
10
  "content": "<pad>",
11
  "lstrip": false,
12
- "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
  "unk_token": {
17
  "content": "<unk>",
18
  "lstrip": false,
19
- "normalized": false,
20
  "rstrip": false,
21
  "single_word": false
22
  }
 
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
+ "<extra_id_100>",
104
+ "<extra_id_101>",
105
+ "<extra_id_102>",
106
+ "<extra_id_103>",
107
+ "<extra_id_104>",
108
+ "<extra_id_105>",
109
+ "<extra_id_106>",
110
+ "<extra_id_107>",
111
+ "<extra_id_108>",
112
+ "<extra_id_109>",
113
+ "<extra_id_110>",
114
+ "<extra_id_111>",
115
+ "<extra_id_112>",
116
+ "<extra_id_113>",
117
+ "<extra_id_114>",
118
+ "<extra_id_115>",
119
+ "<extra_id_116>",
120
+ "<extra_id_117>",
121
+ "<extra_id_118>",
122
+ "<extra_id_119>",
123
+ "<extra_id_120>",
124
+ "<extra_id_121>",
125
+ "<extra_id_122>",
126
+ "<extra_id_123>",
127
+ "<extra_id_124>"
128
+ ],
129
  "eos_token": {
130
  "content": "</s>",
131
  "lstrip": false,
132
+ "normalized": true,
133
  "rstrip": false,
134
  "single_word": false
135
  },
136
  "pad_token": {
137
  "content": "<pad>",
138
  "lstrip": false,
139
+ "normalized": true,
140
  "rstrip": false,
141
  "single_word": false
142
  },
143
  "unk_token": {
144
  "content": "<unk>",
145
  "lstrip": false,
146
+ "normalized": true,
147
  "rstrip": false,
148
  "single_word": false
149
  }
tokenizer_config.json CHANGED
@@ -1,10 +1,9 @@
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
@@ -12,7 +11,7 @@
12
  "1": {
13
  "content": "</s>",
14
  "lstrip": false,
15
- "normalized": false,
16
  "rstrip": false,
17
  "single_word": false,
18
  "special": true
@@ -20,20 +19,1145 @@
20
  "2": {
21
  "content": "<unk>",
22
  "lstrip": false,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
23
  "normalized": false,
24
  "rstrip": false,
25
  "single_word": false,
26
  "special": true
27
  }
28
  },
29
- "additional_special_tokens": [],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
30
  "clean_up_tokenization_spaces": false,
31
  "eos_token": "</s>",
32
  "extra_ids": 0,
33
  "extra_special_tokens": {},
34
  "model_max_length": 1000000000000000019884624838656,
35
  "pad_token": "<pad>",
36
- "sp_model_kwargs": {},
37
- "tokenizer_class": "T5Tokenizer",
38
  "unk_token": "<unk>"
39
  }
 
1
  {
 
2
  "added_tokens_decoder": {
3
  "0": {
4
  "content": "<pad>",
5
  "lstrip": false,
6
+ "normalized": true,
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
 
11
  "1": {
12
  "content": "</s>",
13
  "lstrip": false,
14
+ "normalized": true,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
 
19
  "2": {
20
  "content": "<unk>",
21
  "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "259": {
28
+ "content": "<extra_id_0>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "260": {
36
+ "content": "<extra_id_1>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "261": {
44
+ "content": "<extra_id_2>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "262": {
52
+ "content": "<extra_id_3>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "263": {
60
+ "content": "<extra_id_4>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "264": {
68
+ "content": "<extra_id_5>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "265": {
76
+ "content": "<extra_id_6>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "266": {
84
+ "content": "<extra_id_7>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "267": {
92
+ "content": "<extra_id_8>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "268": {
100
+ "content": "<extra_id_9>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "269": {
108
+ "content": "<extra_id_10>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "270": {
116
+ "content": "<extra_id_11>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "271": {
124
+ "content": "<extra_id_12>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "272": {
132
+ "content": "<extra_id_13>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "273": {
140
+ "content": "<extra_id_14>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "274": {
148
+ "content": "<extra_id_15>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "275": {
156
+ "content": "<extra_id_16>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "276": {
164
+ "content": "<extra_id_17>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "277": {
172
+ "content": "<extra_id_18>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "278": {
180
+ "content": "<extra_id_19>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "279": {
188
+ "content": "<extra_id_20>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "280": {
196
+ "content": "<extra_id_21>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "281": {
204
+ "content": "<extra_id_22>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "282": {
212
+ "content": "<extra_id_23>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "283": {
220
+ "content": "<extra_id_24>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "284": {
228
+ "content": "<extra_id_25>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "285": {
236
+ "content": "<extra_id_26>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "286": {
244
+ "content": "<extra_id_27>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "287": {
252
+ "content": "<extra_id_28>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "288": {
260
+ "content": "<extra_id_29>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "289": {
268
+ "content": "<extra_id_30>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "290": {
276
+ "content": "<extra_id_31>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "291": {
284
+ "content": "<extra_id_32>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "292": {
292
+ "content": "<extra_id_33>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "293": {
300
+ "content": "<extra_id_34>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "294": {
308
+ "content": "<extra_id_35>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "295": {
316
+ "content": "<extra_id_36>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "296": {
324
+ "content": "<extra_id_37>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "297": {
332
+ "content": "<extra_id_38>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "298": {
340
+ "content": "<extra_id_39>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "299": {
348
+ "content": "<extra_id_40>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "300": {
356
+ "content": "<extra_id_41>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "301": {
364
+ "content": "<extra_id_42>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "302": {
372
+ "content": "<extra_id_43>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "303": {
380
+ "content": "<extra_id_44>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "304": {
388
+ "content": "<extra_id_45>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "305": {
396
+ "content": "<extra_id_46>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "306": {
404
+ "content": "<extra_id_47>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "307": {
412
+ "content": "<extra_id_48>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "308": {
420
+ "content": "<extra_id_49>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "309": {
428
+ "content": "<extra_id_50>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "310": {
436
+ "content": "<extra_id_51>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "311": {
444
+ "content": "<extra_id_52>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "312": {
452
+ "content": "<extra_id_53>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "313": {
460
+ "content": "<extra_id_54>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "314": {
468
+ "content": "<extra_id_55>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "315": {
476
+ "content": "<extra_id_56>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "316": {
484
+ "content": "<extra_id_57>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "317": {
492
+ "content": "<extra_id_58>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "318": {
500
+ "content": "<extra_id_59>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "319": {
508
+ "content": "<extra_id_60>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "320": {
516
+ "content": "<extra_id_61>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "321": {
524
+ "content": "<extra_id_62>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "322": {
532
+ "content": "<extra_id_63>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "323": {
540
+ "content": "<extra_id_64>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "324": {
548
+ "content": "<extra_id_65>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "325": {
556
+ "content": "<extra_id_66>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "326": {
564
+ "content": "<extra_id_67>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "327": {
572
+ "content": "<extra_id_68>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "328": {
580
+ "content": "<extra_id_69>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "329": {
588
+ "content": "<extra_id_70>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "330": {
596
+ "content": "<extra_id_71>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "331": {
604
+ "content": "<extra_id_72>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "332": {
612
+ "content": "<extra_id_73>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "333": {
620
+ "content": "<extra_id_74>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "334": {
628
+ "content": "<extra_id_75>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "335": {
636
+ "content": "<extra_id_76>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "336": {
644
+ "content": "<extra_id_77>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "337": {
652
+ "content": "<extra_id_78>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "338": {
660
+ "content": "<extra_id_79>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "339": {
668
+ "content": "<extra_id_80>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "340": {
676
+ "content": "<extra_id_81>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "341": {
684
+ "content": "<extra_id_82>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "342": {
692
+ "content": "<extra_id_83>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "343": {
700
+ "content": "<extra_id_84>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "344": {
708
+ "content": "<extra_id_85>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "345": {
716
+ "content": "<extra_id_86>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "346": {
724
+ "content": "<extra_id_87>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "347": {
732
+ "content": "<extra_id_88>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "348": {
740
+ "content": "<extra_id_89>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "349": {
748
+ "content": "<extra_id_90>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "350": {
756
+ "content": "<extra_id_91>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "351": {
764
+ "content": "<extra_id_92>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "352": {
772
+ "content": "<extra_id_93>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "353": {
780
+ "content": "<extra_id_94>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "354": {
788
+ "content": "<extra_id_95>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "355": {
796
+ "content": "<extra_id_96>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "356": {
804
+ "content": "<extra_id_97>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "357": {
812
+ "content": "<extra_id_98>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "358": {
820
+ "content": "<extra_id_99>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "359": {
828
+ "content": "<extra_id_100>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "360": {
836
+ "content": "<extra_id_101>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "361": {
844
+ "content": "<extra_id_102>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "362": {
852
+ "content": "<extra_id_103>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "363": {
860
+ "content": "<extra_id_104>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "364": {
868
+ "content": "<extra_id_105>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "365": {
876
+ "content": "<extra_id_106>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "366": {
884
+ "content": "<extra_id_107>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "367": {
892
+ "content": "<extra_id_108>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "368": {
900
+ "content": "<extra_id_109>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "369": {
908
+ "content": "<extra_id_110>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "370": {
916
+ "content": "<extra_id_111>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "371": {
924
+ "content": "<extra_id_112>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "372": {
932
+ "content": "<extra_id_113>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "373": {
940
+ "content": "<extra_id_114>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "374": {
948
+ "content": "<extra_id_115>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "375": {
956
+ "content": "<extra_id_116>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "376": {
964
+ "content": "<extra_id_117>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "377": {
972
+ "content": "<extra_id_118>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "378": {
980
+ "content": "<extra_id_119>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "379": {
988
+ "content": "<extra_id_120>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "380": {
996
+ "content": "<extra_id_121>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "381": {
1004
+ "content": "<extra_id_122>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "382": {
1012
+ "content": "<extra_id_123>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "383": {
1020
+ "content": "<extra_id_124>",
1021
+ "lstrip": false,
1022
  "normalized": false,
1023
  "rstrip": false,
1024
  "single_word": false,
1025
  "special": true
1026
  }
1027
  },
1028
+ "additional_special_tokens": [
1029
+ "<extra_id_0>",
1030
+ "<extra_id_1>",
1031
+ "<extra_id_2>",
1032
+ "<extra_id_3>",
1033
+ "<extra_id_4>",
1034
+ "<extra_id_5>",
1035
+ "<extra_id_6>",
1036
+ "<extra_id_7>",
1037
+ "<extra_id_8>",
1038
+ "<extra_id_9>",
1039
+ "<extra_id_10>",
1040
+ "<extra_id_11>",
1041
+ "<extra_id_12>",
1042
+ "<extra_id_13>",
1043
+ "<extra_id_14>",
1044
+ "<extra_id_15>",
1045
+ "<extra_id_16>",
1046
+ "<extra_id_17>",
1047
+ "<extra_id_18>",
1048
+ "<extra_id_19>",
1049
+ "<extra_id_20>",
1050
+ "<extra_id_21>",
1051
+ "<extra_id_22>",
1052
+ "<extra_id_23>",
1053
+ "<extra_id_24>",
1054
+ "<extra_id_25>",
1055
+ "<extra_id_26>",
1056
+ "<extra_id_27>",
1057
+ "<extra_id_28>",
1058
+ "<extra_id_29>",
1059
+ "<extra_id_30>",
1060
+ "<extra_id_31>",
1061
+ "<extra_id_32>",
1062
+ "<extra_id_33>",
1063
+ "<extra_id_34>",
1064
+ "<extra_id_35>",
1065
+ "<extra_id_36>",
1066
+ "<extra_id_37>",
1067
+ "<extra_id_38>",
1068
+ "<extra_id_39>",
1069
+ "<extra_id_40>",
1070
+ "<extra_id_41>",
1071
+ "<extra_id_42>",
1072
+ "<extra_id_43>",
1073
+ "<extra_id_44>",
1074
+ "<extra_id_45>",
1075
+ "<extra_id_46>",
1076
+ "<extra_id_47>",
1077
+ "<extra_id_48>",
1078
+ "<extra_id_49>",
1079
+ "<extra_id_50>",
1080
+ "<extra_id_51>",
1081
+ "<extra_id_52>",
1082
+ "<extra_id_53>",
1083
+ "<extra_id_54>",
1084
+ "<extra_id_55>",
1085
+ "<extra_id_56>",
1086
+ "<extra_id_57>",
1087
+ "<extra_id_58>",
1088
+ "<extra_id_59>",
1089
+ "<extra_id_60>",
1090
+ "<extra_id_61>",
1091
+ "<extra_id_62>",
1092
+ "<extra_id_63>",
1093
+ "<extra_id_64>",
1094
+ "<extra_id_65>",
1095
+ "<extra_id_66>",
1096
+ "<extra_id_67>",
1097
+ "<extra_id_68>",
1098
+ "<extra_id_69>",
1099
+ "<extra_id_70>",
1100
+ "<extra_id_71>",
1101
+ "<extra_id_72>",
1102
+ "<extra_id_73>",
1103
+ "<extra_id_74>",
1104
+ "<extra_id_75>",
1105
+ "<extra_id_76>",
1106
+ "<extra_id_77>",
1107
+ "<extra_id_78>",
1108
+ "<extra_id_79>",
1109
+ "<extra_id_80>",
1110
+ "<extra_id_81>",
1111
+ "<extra_id_82>",
1112
+ "<extra_id_83>",
1113
+ "<extra_id_84>",
1114
+ "<extra_id_85>",
1115
+ "<extra_id_86>",
1116
+ "<extra_id_87>",
1117
+ "<extra_id_88>",
1118
+ "<extra_id_89>",
1119
+ "<extra_id_90>",
1120
+ "<extra_id_91>",
1121
+ "<extra_id_92>",
1122
+ "<extra_id_93>",
1123
+ "<extra_id_94>",
1124
+ "<extra_id_95>",
1125
+ "<extra_id_96>",
1126
+ "<extra_id_97>",
1127
+ "<extra_id_98>",
1128
+ "<extra_id_99>",
1129
+ "<extra_id_100>",
1130
+ "<extra_id_101>",
1131
+ "<extra_id_102>",
1132
+ "<extra_id_103>",
1133
+ "<extra_id_104>",
1134
+ "<extra_id_105>",
1135
+ "<extra_id_106>",
1136
+ "<extra_id_107>",
1137
+ "<extra_id_108>",
1138
+ "<extra_id_109>",
1139
+ "<extra_id_110>",
1140
+ "<extra_id_111>",
1141
+ "<extra_id_112>",
1142
+ "<extra_id_113>",
1143
+ "<extra_id_114>",
1144
+ "<extra_id_115>",
1145
+ "<extra_id_116>",
1146
+ "<extra_id_117>",
1147
+ "<extra_id_118>",
1148
+ "<extra_id_119>",
1149
+ "<extra_id_120>",
1150
+ "<extra_id_121>",
1151
+ "<extra_id_122>",
1152
+ "<extra_id_123>",
1153
+ "<extra_id_124>"
1154
+ ],
1155
  "clean_up_tokenization_spaces": false,
1156
  "eos_token": "</s>",
1157
  "extra_ids": 0,
1158
  "extra_special_tokens": {},
1159
  "model_max_length": 1000000000000000019884624838656,
1160
  "pad_token": "<pad>",
1161
+ "tokenizer_class": "ByT5Tokenizer",
 
1162
  "unk_token": "<unk>"
1163
  }
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 3.0,
3
- "total_flos": 3.152977773933363e+16,
4
- "train_loss": 3.293868990633756,
5
- "train_runtime": 5199.8209,
6
  "train_samples": 65573,
7
- "train_samples_per_second": 37.832,
8
- "train_steps_per_second": 3.784
9
  }
 
1
  {
2
  "epoch": 3.0,
3
+ "total_flos": 4.51806634222551e+16,
4
+ "train_loss": 2.926649949844495,
5
+ "train_runtime": 7468.4511,
6
  "train_samples": 65573,
7
+ "train_samples_per_second": 26.34,
8
+ "train_steps_per_second": 3.293
9
  }
trainer_state.json CHANGED
@@ -4,296 +4,366 @@
4
  "best_model_checkpoint": null,
5
  "epoch": 3.0,
6
  "eval_steps": 500,
7
- "global_step": 19674,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
11
  "log_history": [
12
  {
13
- "epoch": 0.07624275693809088,
14
- "grad_norm": 1.6701425313949585,
15
- "learning_rate": 4.8731828809596425e-05,
16
- "loss": 6.0178,
17
  "step": 500
18
  },
19
  {
20
- "epoch": 0.15248551387618176,
21
- "grad_norm": 2.0213375091552734,
22
- "learning_rate": 4.7461116193961576e-05,
23
- "loss": 4.7129,
24
  "step": 1000
25
  },
26
  {
27
- "epoch": 0.22872827081427263,
28
- "grad_norm": 1.732784628868103,
29
- "learning_rate": 4.619040357832673e-05,
30
- "loss": 4.3454,
31
  "step": 1500
32
  },
33
  {
34
- "epoch": 0.3049710277523635,
35
- "grad_norm": 2.5012331008911133,
36
- "learning_rate": 4.4919690962691876e-05,
37
- "loss": 4.1171,
38
  "step": 2000
39
  },
40
  {
41
- "epoch": 0.3812137846904544,
42
- "grad_norm": 1.6402555704116821,
43
- "learning_rate": 4.364897834705703e-05,
44
- "loss": 3.9315,
45
  "step": 2500
46
  },
47
  {
48
- "epoch": 0.45745654162854527,
49
- "grad_norm": 1.7107372283935547,
50
- "learning_rate": 4.2378265731422184e-05,
51
- "loss": 3.7945,
52
  "step": 3000
53
  },
54
  {
55
- "epoch": 0.5336992985666361,
56
- "grad_norm": 1.807631254196167,
57
- "learning_rate": 4.1107553115787334e-05,
58
- "loss": 3.7192,
59
  "step": 3500
60
  },
61
  {
62
- "epoch": 0.609942055504727,
63
- "grad_norm": 1.6103076934814453,
64
- "learning_rate": 3.983684050015249e-05,
65
- "loss": 3.6197,
66
  "step": 4000
67
  },
68
  {
69
- "epoch": 0.6861848124428179,
70
- "grad_norm": 1.4974479675292969,
71
- "learning_rate": 3.856612788451764e-05,
72
- "loss": 3.5347,
73
  "step": 4500
74
  },
75
  {
76
- "epoch": 0.7624275693809088,
77
- "grad_norm": 3.2841522693634033,
78
- "learning_rate": 3.729541526888279e-05,
79
- "loss": 3.4796,
80
  "step": 5000
81
  },
82
  {
83
- "epoch": 0.8386703263189997,
84
- "grad_norm": 2.2029266357421875,
85
- "learning_rate": 3.602470265324794e-05,
86
- "loss": 3.4246,
87
  "step": 5500
88
  },
89
  {
90
- "epoch": 0.9149130832570905,
91
- "grad_norm": 1.9195083379745483,
92
- "learning_rate": 3.475399003761309e-05,
93
- "loss": 3.3296,
94
  "step": 6000
95
  },
96
  {
97
- "epoch": 0.9911558401951814,
98
- "grad_norm": 1.755679726600647,
99
- "learning_rate": 3.348327742197825e-05,
100
- "loss": 3.3107,
101
  "step": 6500
102
  },
103
  {
104
- "epoch": 1.0673985971332725,
105
- "grad_norm": 1.8641302585601807,
106
- "learning_rate": 3.22125648063434e-05,
107
- "loss": 3.2435,
108
  "step": 7000
109
  },
110
  {
111
- "epoch": 1.1436413540713632,
112
- "grad_norm": 7.194948673248291,
113
- "learning_rate": 3.094185219070855e-05,
114
- "loss": 3.2139,
115
  "step": 7500
116
  },
117
  {
118
- "epoch": 1.219884111009454,
119
- "grad_norm": 1.8638546466827393,
120
- "learning_rate": 2.96711395750737e-05,
121
- "loss": 3.1774,
122
  "step": 8000
123
  },
124
  {
125
- "epoch": 1.296126867947545,
126
- "grad_norm": 2.06630802154541,
127
- "learning_rate": 2.8400426959438852e-05,
128
- "loss": 3.1274,
129
  "step": 8500
130
  },
131
  {
132
- "epoch": 1.3723696248856359,
133
- "grad_norm": 2.8304669857025146,
134
- "learning_rate": 2.712971434380401e-05,
135
- "loss": 3.1018,
136
  "step": 9000
137
  },
138
  {
139
- "epoch": 1.4486123818237266,
140
- "grad_norm": 1.7093334197998047,
141
- "learning_rate": 2.5859001728169156e-05,
142
- "loss": 3.0839,
143
  "step": 9500
144
  },
145
  {
146
- "epoch": 1.5248551387618177,
147
- "grad_norm": 1.8173112869262695,
148
- "learning_rate": 2.458828911253431e-05,
149
- "loss": 3.0706,
150
  "step": 10000
151
  },
152
  {
153
- "epoch": 1.6010978956999085,
154
- "grad_norm": 1.8194465637207031,
155
- "learning_rate": 2.3317576496899464e-05,
156
- "loss": 3.0355,
157
  "step": 10500
158
  },
159
  {
160
- "epoch": 1.6773406526379993,
161
- "grad_norm": 1.7631820440292358,
162
- "learning_rate": 2.2046863881264614e-05,
163
- "loss": 3.0401,
164
  "step": 11000
165
  },
166
  {
167
- "epoch": 1.7535834095760903,
168
- "grad_norm": 1.5933923721313477,
169
- "learning_rate": 2.0776151265629768e-05,
170
- "loss": 2.9889,
171
  "step": 11500
172
  },
173
  {
174
- "epoch": 1.8298261665141813,
175
- "grad_norm": 1.50958251953125,
176
- "learning_rate": 1.950543864999492e-05,
177
- "loss": 3.0041,
178
  "step": 12000
179
  },
180
  {
181
- "epoch": 1.906068923452272,
182
- "grad_norm": 1.6473861932754517,
183
- "learning_rate": 1.823472603436007e-05,
184
- "loss": 2.9745,
185
  "step": 12500
186
  },
187
  {
188
- "epoch": 1.9823116803903629,
189
- "grad_norm": 1.6490463018417358,
190
- "learning_rate": 1.6964013418725223e-05,
191
- "loss": 2.956,
192
  "step": 13000
193
  },
194
  {
195
- "epoch": 2.058554437328454,
196
- "grad_norm": 1.997188687324524,
197
- "learning_rate": 1.5693300803090373e-05,
198
- "loss": 2.9205,
199
  "step": 13500
200
  },
201
  {
202
- "epoch": 2.134797194266545,
203
- "grad_norm": 2.4612667560577393,
204
- "learning_rate": 1.4422588187455527e-05,
205
- "loss": 2.9218,
206
  "step": 14000
207
  },
208
  {
209
- "epoch": 2.2110399512046355,
210
- "grad_norm": 1.5982125997543335,
211
- "learning_rate": 1.3151875571820677e-05,
212
- "loss": 2.9016,
213
  "step": 14500
214
  },
215
  {
216
- "epoch": 2.2872827081427265,
217
- "grad_norm": 1.731216549873352,
218
- "learning_rate": 1.188116295618583e-05,
219
- "loss": 2.8894,
220
  "step": 15000
221
  },
222
  {
223
- "epoch": 2.3635254650808175,
224
- "grad_norm": 2.2783565521240234,
225
- "learning_rate": 1.0610450340550982e-05,
226
- "loss": 2.8617,
227
  "step": 15500
228
  },
229
  {
230
- "epoch": 2.439768222018908,
231
- "grad_norm": 2.1560938358306885,
232
- "learning_rate": 9.339737724916134e-06,
233
- "loss": 2.8748,
234
  "step": 16000
235
  },
236
  {
237
- "epoch": 2.516010978956999,
238
- "grad_norm": 1.7220749855041504,
239
- "learning_rate": 8.069025109281286e-06,
240
- "loss": 2.8617,
241
  "step": 16500
242
  },
243
  {
244
- "epoch": 2.59225373589509,
245
- "grad_norm": 1.6343811750411987,
246
- "learning_rate": 6.798312493646437e-06,
247
- "loss": 2.836,
248
  "step": 17000
249
  },
250
  {
251
- "epoch": 2.6684964928331807,
252
- "grad_norm": 2.060800552368164,
253
- "learning_rate": 5.527599878011589e-06,
254
- "loss": 2.8513,
255
  "step": 17500
256
  },
257
  {
258
- "epoch": 2.7447392497712717,
259
- "grad_norm": 1.5987133979797363,
260
- "learning_rate": 4.256887262376741e-06,
261
- "loss": 2.8465,
262
  "step": 18000
263
  },
264
  {
265
- "epoch": 2.8209820067093627,
266
- "grad_norm": 1.5240155458450317,
267
- "learning_rate": 2.986174646741893e-06,
268
- "loss": 2.8378,
269
  "step": 18500
270
  },
271
  {
272
- "epoch": 2.8972247636474533,
273
- "grad_norm": 1.5195047855377197,
274
- "learning_rate": 1.715462031107045e-06,
275
- "loss": 2.8309,
276
  "step": 19000
277
  },
278
  {
279
- "epoch": 2.9734675205855443,
280
- "grad_norm": 2.4305648803710938,
281
- "learning_rate": 4.447494154721969e-07,
282
- "loss": 2.824,
283
  "step": 19500
284
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
285
  {
286
  "epoch": 3.0,
287
- "step": 19674,
288
- "total_flos": 3.152977773933363e+16,
289
- "train_loss": 3.293868990633756,
290
- "train_runtime": 5199.8209,
291
- "train_samples_per_second": 37.832,
292
- "train_steps_per_second": 3.784
293
  }
294
  ],
295
  "logging_steps": 500,
296
- "max_steps": 19674,
297
  "num_input_tokens_seen": 0,
298
  "num_train_epochs": 3,
299
  "save_steps": 1000,
@@ -309,8 +379,8 @@
309
  "attributes": {}
310
  }
311
  },
312
- "total_flos": 3.152977773933363e+16,
313
- "train_batch_size": 10,
314
  "trial_name": null,
315
  "trial_params": null
316
  }
 
4
  "best_model_checkpoint": null,
5
  "epoch": 3.0,
6
  "eval_steps": 500,
7
+ "global_step": 24591,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
11
  "log_history": [
12
  {
13
+ "epoch": 0.0609979260705136,
14
+ "grad_norm": 2.1482937335968018,
15
+ "learning_rate": 4.8985401163027127e-05,
16
+ "loss": 5.1096,
17
  "step": 500
18
  },
19
  {
20
+ "epoch": 0.1219958521410272,
21
+ "grad_norm": 1.8602643013000488,
22
+ "learning_rate": 4.79687690618519e-05,
23
+ "loss": 4.2904,
24
  "step": 1000
25
  },
26
  {
27
+ "epoch": 0.1829937782115408,
28
+ "grad_norm": 2.2239928245544434,
29
+ "learning_rate": 4.6952136960676673e-05,
30
+ "loss": 3.9507,
31
  "step": 1500
32
  },
33
  {
34
+ "epoch": 0.2439917042820544,
35
+ "grad_norm": 1.9908227920532227,
36
+ "learning_rate": 4.593550485950145e-05,
37
+ "loss": 3.7767,
38
  "step": 2000
39
  },
40
  {
41
+ "epoch": 0.304989630352568,
42
+ "grad_norm": 2.2968549728393555,
43
+ "learning_rate": 4.491887275832622e-05,
44
+ "loss": 3.6462,
45
  "step": 2500
46
  },
47
  {
48
+ "epoch": 0.3659875564230816,
49
+ "grad_norm": 1.7772067785263062,
50
+ "learning_rate": 4.3902240657150994e-05,
51
+ "loss": 3.5216,
52
  "step": 3000
53
  },
54
  {
55
+ "epoch": 0.4269854824935952,
56
+ "grad_norm": 1.9565205574035645,
57
+ "learning_rate": 4.288560855597577e-05,
58
+ "loss": 3.4266,
59
  "step": 3500
60
  },
61
  {
62
+ "epoch": 0.4879834085641088,
63
+ "grad_norm": 2.3488683700561523,
64
+ "learning_rate": 4.186897645480054e-05,
65
+ "loss": 3.348,
66
  "step": 4000
67
  },
68
  {
69
+ "epoch": 0.5489813346346224,
70
+ "grad_norm": 2.3590667247772217,
71
+ "learning_rate": 4.085234435362531e-05,
72
+ "loss": 3.2803,
73
  "step": 4500
74
  },
75
  {
76
+ "epoch": 0.609979260705136,
77
+ "grad_norm": 1.8940634727478027,
78
+ "learning_rate": 3.983571225245009e-05,
79
+ "loss": 3.2199,
80
  "step": 5000
81
  },
82
  {
83
+ "epoch": 0.6709771867756497,
84
+ "grad_norm": 2.2232987880706787,
85
+ "learning_rate": 3.8819080151274854e-05,
86
+ "loss": 3.1632,
87
  "step": 5500
88
  },
89
  {
90
+ "epoch": 0.7319751128461632,
91
+ "grad_norm": 1.9332739114761353,
92
+ "learning_rate": 3.7802448050099634e-05,
93
+ "loss": 3.1074,
94
  "step": 6000
95
  },
96
  {
97
+ "epoch": 0.7929730389166768,
98
+ "grad_norm": 1.869598150253296,
99
+ "learning_rate": 3.678581594892441e-05,
100
+ "loss": 3.0732,
101
  "step": 6500
102
  },
103
  {
104
+ "epoch": 0.8539709649871904,
105
+ "grad_norm": 1.6995704174041748,
106
+ "learning_rate": 3.5769183847749174e-05,
107
+ "loss": 3.0224,
108
  "step": 7000
109
  },
110
  {
111
+ "epoch": 0.9149688910577041,
112
+ "grad_norm": 2.039504051208496,
113
+ "learning_rate": 3.4752551746573955e-05,
114
+ "loss": 2.9645,
115
  "step": 7500
116
  },
117
  {
118
+ "epoch": 0.9759668171282176,
119
+ "grad_norm": 1.8474594354629517,
120
+ "learning_rate": 3.373591964539872e-05,
121
+ "loss": 2.9575,
122
  "step": 8000
123
  },
124
  {
125
+ "epoch": 1.0369647431987312,
126
+ "grad_norm": 1.9620344638824463,
127
+ "learning_rate": 3.2719287544223495e-05,
128
+ "loss": 2.8944,
129
  "step": 8500
130
  },
131
  {
132
+ "epoch": 1.0979626692692448,
133
+ "grad_norm": 1.8038884401321411,
134
+ "learning_rate": 3.1702655443048275e-05,
135
+ "loss": 2.877,
136
  "step": 9000
137
  },
138
  {
139
+ "epoch": 1.1589605953397584,
140
+ "grad_norm": 1.9445528984069824,
141
+ "learning_rate": 3.068602334187304e-05,
142
+ "loss": 2.8539,
143
  "step": 9500
144
  },
145
  {
146
+ "epoch": 1.219958521410272,
147
+ "grad_norm": 1.7721298933029175,
148
+ "learning_rate": 2.966939124069782e-05,
149
+ "loss": 2.8176,
150
  "step": 10000
151
  },
152
  {
153
+ "epoch": 1.2809564474807855,
154
+ "grad_norm": 2.3092963695526123,
155
+ "learning_rate": 2.865275913952259e-05,
156
+ "loss": 2.7872,
157
  "step": 10500
158
  },
159
  {
160
+ "epoch": 1.3419543735512993,
161
+ "grad_norm": 2.0396852493286133,
162
+ "learning_rate": 2.7636127038347365e-05,
163
+ "loss": 2.7764,
164
  "step": 11000
165
  },
166
  {
167
+ "epoch": 1.402952299621813,
168
+ "grad_norm": 1.755911946296692,
169
+ "learning_rate": 2.6619494937172135e-05,
170
+ "loss": 2.7607,
171
  "step": 11500
172
  },
173
  {
174
+ "epoch": 1.4639502256923265,
175
+ "grad_norm": 2.1026928424835205,
176
+ "learning_rate": 2.560286283599691e-05,
177
+ "loss": 2.7469,
178
  "step": 12000
179
  },
180
  {
181
+ "epoch": 1.52494815176284,
182
+ "grad_norm": 1.655788540840149,
183
+ "learning_rate": 2.4586230734821682e-05,
184
+ "loss": 2.7264,
185
  "step": 12500
186
  },
187
  {
188
+ "epoch": 1.5859460778333536,
189
+ "grad_norm": 2.534583568572998,
190
+ "learning_rate": 2.3569598633646456e-05,
191
+ "loss": 2.7102,
192
  "step": 13000
193
  },
194
  {
195
+ "epoch": 1.6469440039038674,
196
+ "grad_norm": 1.9951140880584717,
197
+ "learning_rate": 2.2552966532471232e-05,
198
+ "loss": 2.7136,
199
  "step": 13500
200
  },
201
  {
202
+ "epoch": 1.707941929974381,
203
+ "grad_norm": 2.0365281105041504,
204
+ "learning_rate": 2.1536334431296002e-05,
205
+ "loss": 2.6968,
206
  "step": 14000
207
  },
208
  {
209
+ "epoch": 1.7689398560448946,
210
+ "grad_norm": 1.7324215173721313,
211
+ "learning_rate": 2.0519702330120776e-05,
212
+ "loss": 2.6767,
213
  "step": 14500
214
  },
215
  {
216
+ "epoch": 1.8299377821154081,
217
+ "grad_norm": 1.9328315258026123,
218
+ "learning_rate": 1.950307022894555e-05,
219
+ "loss": 2.6868,
220
  "step": 15000
221
  },
222
  {
223
+ "epoch": 1.8909357081859217,
224
+ "grad_norm": 1.9608515501022339,
225
+ "learning_rate": 1.8486438127770323e-05,
226
+ "loss": 2.6585,
227
  "step": 15500
228
  },
229
  {
230
+ "epoch": 1.9519336342564353,
231
+ "grad_norm": 2.448692560195923,
232
+ "learning_rate": 1.7469806026595096e-05,
233
+ "loss": 2.6456,
234
  "step": 16000
235
  },
236
  {
237
+ "epoch": 2.012931560326949,
238
+ "grad_norm": 2.166044235229492,
239
+ "learning_rate": 1.645317392541987e-05,
240
+ "loss": 2.6379,
241
  "step": 16500
242
  },
243
  {
244
+ "epoch": 2.0739294863974624,
245
+ "grad_norm": 2.6067957878112793,
246
+ "learning_rate": 1.5436541824244643e-05,
247
+ "loss": 2.6017,
248
  "step": 17000
249
  },
250
  {
251
+ "epoch": 2.134927412467976,
252
+ "grad_norm": 2.173795700073242,
253
+ "learning_rate": 1.4419909723069416e-05,
254
+ "loss": 2.6037,
255
  "step": 17500
256
  },
257
  {
258
+ "epoch": 2.1959253385384896,
259
+ "grad_norm": 2.3912558555603027,
260
+ "learning_rate": 1.340327762189419e-05,
261
+ "loss": 2.5863,
262
  "step": 18000
263
  },
264
  {
265
+ "epoch": 2.256923264609003,
266
+ "grad_norm": 2.6069979667663574,
267
+ "learning_rate": 1.2386645520718963e-05,
268
+ "loss": 2.5806,
269
  "step": 18500
270
  },
271
  {
272
+ "epoch": 2.3179211906795167,
273
+ "grad_norm": 2.0667498111724854,
274
+ "learning_rate": 1.1370013419543737e-05,
275
+ "loss": 2.5738,
276
  "step": 19000
277
  },
278
  {
279
+ "epoch": 2.3789191167500303,
280
+ "grad_norm": 2.186269760131836,
281
+ "learning_rate": 1.0353381318368509e-05,
282
+ "loss": 2.5831,
283
  "step": 19500
284
  },
285
+ {
286
+ "epoch": 2.439917042820544,
287
+ "grad_norm": 1.7841541767120361,
288
+ "learning_rate": 9.336749217193284e-06,
289
+ "loss": 2.561,
290
+ "step": 20000
291
+ },
292
+ {
293
+ "epoch": 2.500914968891058,
294
+ "grad_norm": 2.1247878074645996,
295
+ "learning_rate": 8.320117116018055e-06,
296
+ "loss": 2.5534,
297
+ "step": 20500
298
+ },
299
+ {
300
+ "epoch": 2.561912894961571,
301
+ "grad_norm": 1.7261439561843872,
302
+ "learning_rate": 7.303485014842829e-06,
303
+ "loss": 2.5288,
304
+ "step": 21000
305
+ },
306
+ {
307
+ "epoch": 2.622910821032085,
308
+ "grad_norm": 1.6930060386657715,
309
+ "learning_rate": 6.286852913667603e-06,
310
+ "loss": 2.5449,
311
+ "step": 21500
312
+ },
313
+ {
314
+ "epoch": 2.6839087471025986,
315
+ "grad_norm": 1.9172097444534302,
316
+ "learning_rate": 5.270220812492376e-06,
317
+ "loss": 2.5482,
318
+ "step": 22000
319
+ },
320
+ {
321
+ "epoch": 2.744906673173112,
322
+ "grad_norm": 1.56685209274292,
323
+ "learning_rate": 4.253588711317149e-06,
324
+ "loss": 2.5493,
325
+ "step": 22500
326
+ },
327
+ {
328
+ "epoch": 2.805904599243626,
329
+ "grad_norm": 2.165651321411133,
330
+ "learning_rate": 3.2369566101419217e-06,
331
+ "loss": 2.5481,
332
+ "step": 23000
333
+ },
334
+ {
335
+ "epoch": 2.8669025253141394,
336
+ "grad_norm": 2.2414863109588623,
337
+ "learning_rate": 2.220324508966695e-06,
338
+ "loss": 2.5216,
339
+ "step": 23500
340
+ },
341
+ {
342
+ "epoch": 2.927900451384653,
343
+ "grad_norm": 2.2040302753448486,
344
+ "learning_rate": 1.2036924077914685e-06,
345
+ "loss": 2.5239,
346
+ "step": 24000
347
+ },
348
+ {
349
+ "epoch": 2.9888983774551665,
350
+ "grad_norm": 2.3587329387664795,
351
+ "learning_rate": 1.8706030661624173e-07,
352
+ "loss": 2.5358,
353
+ "step": 24500
354
+ },
355
  {
356
  "epoch": 3.0,
357
+ "step": 24591,
358
+ "total_flos": 4.51806634222551e+16,
359
+ "train_loss": 2.926649949844495,
360
+ "train_runtime": 7468.4511,
361
+ "train_samples_per_second": 26.34,
362
+ "train_steps_per_second": 3.293
363
  }
364
  ],
365
  "logging_steps": 500,
366
+ "max_steps": 24591,
367
  "num_input_tokens_seen": 0,
368
  "num_train_epochs": 3,
369
  "save_steps": 1000,
 
379
  "attributes": {}
380
  }
381
  },
382
+ "total_flos": 4.51806634222551e+16,
383
+ "train_batch_size": 8,
384
  "trial_name": null,
385
  "trial_params": null
386
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7441f3322f86b65770a610bb76f0b310b4d9974737785dccffd87491ea07c8f7
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:583c085002f3b09350ff1d2f4be0ea59ee41e34677f0d4d11068ef36b0692867
3
  size 5496