Hugging Face's logo

hgroener
/
bygpt5_poetry_medium_de_unc

Fill-Mask
Transformers
PyTorch
bygpt5
Inference Endpoints
Model card Files Community
hgroener commited on
Commit
8878e39
·
verified ·
1 Parent(s): 965c4c6

Upload folder using huggingface_hub

Browse files
Files changed (10) hide show
  1. added_tokens.json +5 -0
  2. config.json +34 -0
  3. optimizer.pt +3 -0
  4. pytorch_model.bin +3 -0
  5. rng_state.pth +3 -0
  6. scheduler.pt +3 -0
  7. special_tokens_map.json +139 -0
  8. tokenizer_config.json +160 -0
  9. trainer_state.json +128 -0
  10. training_args.bin +3 -0
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "</quatrain>": 386,
3
+ "<quatrain>": 385,
4
+ "[PAD]": 384
5
+ }
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nllg/bygpt5-medium-de",
3
+ "architectures": [
4
+ "ByGPT5LMHeadModel"
5
+ ],
6
+ "d_ff": 3840,
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_decoder": true,
17
+ "is_encoder_decoder": false,
18
+ "is_gated_act": true,
19
+ "layer_norm_epsilon": 1e-06,
20
+ "model_type": "bygpt5",
21
+ "num_decoder_layers": 12,
22
+ "num_heads": 16,
23
+ "num_layers": 12,
24
+ "output_past": true,
25
+ "pad_token_id": 0,
26
+ "relative_attention_max_distance": 128,
27
+ "relative_attention_num_buckets": 32,
28
+ "tie_word_embeddings": false,
29
+ "tokenizer_class": "ByT5Tokenizer",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.20.0",
32
+ "use_cache": true,
33
+ "vocab_size": 387
34
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8542aca253b9885a76d489f5b1cab4954711c2d2fbb78a92ef6bb784c381b9da
3
+ size 2312562170
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be041f632be8a61ce11cb1de0b85d8b1b33c0e80f05dd02f9e59061a3b2d863d
3
+ size 1156286410
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c3a7c618d54a8cc2bfd1abed1b0ca28fe3ed1d2f1b3a7e3c84e5c167ef923c2
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66089859c774a7f6f2e34554544bff1d9b3fc25e9a4f6dd72fe24e4a84bdc8b4
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "bos_token": "<quatrain>",
130
+ "eos_token": "</quatrain>",
131
+ "pad_token": "[PAD]",
132
+ "unk_token": {
133
+ "content": "<unk>",
134
+ "lstrip": false,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false
138
+ }
139
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,160 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "additional_special_tokens": [
6
+ "<extra_id_0>",
7
+ "<extra_id_1>",
8
+ "<extra_id_2>",
9
+ "<extra_id_3>",
10
+ "<extra_id_4>",
11
+ "<extra_id_5>",
12
+ "<extra_id_6>",
13
+ "<extra_id_7>",
14
+ "<extra_id_8>",
15
+ "<extra_id_9>",
16
+ "<extra_id_10>",
17
+ "<extra_id_11>",
18
+ "<extra_id_12>",
19
+ "<extra_id_13>",
20
+ "<extra_id_14>",
21
+ "<extra_id_15>",
22
+ "<extra_id_16>",
23
+ "<extra_id_17>",
24
+ "<extra_id_18>",
25
+ "<extra_id_19>",
26
+ "<extra_id_20>",
27
+ "<extra_id_21>",
28
+ "<extra_id_22>",
29
+ "<extra_id_23>",
30
+ "<extra_id_24>",
31
+ "<extra_id_25>",
32
+ "<extra_id_26>",
33
+ "<extra_id_27>",
34
+ "<extra_id_28>",
35
+ "<extra_id_29>",
36
+ "<extra_id_30>",
37
+ "<extra_id_31>",
38
+ "<extra_id_32>",
39
+ "<extra_id_33>",
40
+ "<extra_id_34>",
41
+ "<extra_id_35>",
42
+ "<extra_id_36>",
43
+ "<extra_id_37>",
44
+ "<extra_id_38>",
45
+ "<extra_id_39>",
46
+ "<extra_id_40>",
47
+ "<extra_id_41>",
48
+ "<extra_id_42>",
49
+ "<extra_id_43>",
50
+ "<extra_id_44>",
51
+ "<extra_id_45>",
52
+ "<extra_id_46>",
53
+ "<extra_id_47>",
54
+ "<extra_id_48>",
55
+ "<extra_id_49>",
56
+ "<extra_id_50>",
57
+ "<extra_id_51>",
58
+ "<extra_id_52>",
59
+ "<extra_id_53>",
60
+ "<extra_id_54>",
61
+ "<extra_id_55>",
62
+ "<extra_id_56>",
63
+ "<extra_id_57>",
64
+ "<extra_id_58>",
65
+ "<extra_id_59>",
66
+ "<extra_id_60>",
67
+ "<extra_id_61>",
68
+ "<extra_id_62>",
69
+ "<extra_id_63>",
70
+ "<extra_id_64>",
71
+ "<extra_id_65>",
72
+ "<extra_id_66>",
73
+ "<extra_id_67>",
74
+ "<extra_id_68>",
75
+ "<extra_id_69>",
76
+ "<extra_id_70>",
77
+ "<extra_id_71>",
78
+ "<extra_id_72>",
79
+ "<extra_id_73>",
80
+ "<extra_id_74>",
81
+ "<extra_id_75>",
82
+ "<extra_id_76>",
83
+ "<extra_id_77>",
84
+ "<extra_id_78>",
85
+ "<extra_id_79>",
86
+ "<extra_id_80>",
87
+ "<extra_id_81>",
88
+ "<extra_id_82>",
89
+ "<extra_id_83>",
90
+ "<extra_id_84>",
91
+ "<extra_id_85>",
92
+ "<extra_id_86>",
93
+ "<extra_id_87>",
94
+ "<extra_id_88>",
95
+ "<extra_id_89>",
96
+ "<extra_id_90>",
97
+ "<extra_id_91>",
98
+ "<extra_id_92>",
99
+ "<extra_id_93>",
100
+ "<extra_id_94>",
101
+ "<extra_id_95>",
102
+ "<extra_id_96>",
103
+ "<extra_id_97>",
104
+ "<extra_id_98>",
105
+ "<extra_id_99>",
106
+ "<extra_id_100>",
107
+ "<extra_id_101>",
108
+ "<extra_id_102>",
109
+ "<extra_id_103>",
110
+ "<extra_id_104>",
111
+ "<extra_id_105>",
112
+ "<extra_id_106>",
113
+ "<extra_id_107>",
114
+ "<extra_id_108>",
115
+ "<extra_id_109>",
116
+ "<extra_id_110>",
117
+ "<extra_id_111>",
118
+ "<extra_id_112>",
119
+ "<extra_id_113>",
120
+ "<extra_id_114>",
121
+ "<extra_id_115>",
122
+ "<extra_id_116>",
123
+ "<extra_id_117>",
124
+ "<extra_id_118>",
125
+ "<extra_id_119>",
126
+ "<extra_id_120>",
127
+ "<extra_id_121>",
128
+ "<extra_id_122>",
129
+ "<extra_id_123>",
130
+ "<extra_id_124>"
131
+ ],
132
+ "eos_token": {
133
+ "__type": "AddedToken",
134
+ "content": "</s>",
135
+ "lstrip": false,
136
+ "normalized": true,
137
+ "rstrip": false,
138
+ "single_word": false
139
+ },
140
+ "extra_ids": 125,
141
+ "name_or_path": "nllg/bygpt5-medium-de",
142
+ "pad_token": {
143
+ "__type": "AddedToken",
144
+ "content": "<pad>",
145
+ "lstrip": false,
146
+ "normalized": true,
147
+ "rstrip": false,
148
+ "single_word": false
149
+ },
150
+ "special_tokens_map_file": "/storage/ukp/work/jbelouadi/.cache/huggingface/transformers/1d7794e7e6dcb9aff7f1b0f72b85d665041ce4cfc7c59cf78a0e83302f9ab8e3.063895353d5ef9e19a25220cb616c43abc5e84a2f11b1ffb71c29e097572a109",
151
+ "tokenizer_class": "ByGPT5Tokenizer",
152
+ "unk_token": {
153
+ "__type": "AddedToken",
154
+ "content": "<unk>",
155
+ "lstrip": false,
156
+ "normalized": true,
157
+ "rstrip": false,
158
+ "single_word": false
159
+ }
160
+ }
trainer_state.json ADDED
@@ -0,0 +1,128 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9924605488777161,
3
+ "best_model_checkpoint": "bygpt5_quatags/medium/de/checkpoint-126920",
4
+ "epoch": 7.999984242290541,
5
+ "global_step": 126920,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 3.948825306755581e-05,
13
+ "loss": 1.1845,
14
+ "step": 15865
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_loss": 1.065978765487671,
19
+ "eval_runtime": 768.0142,
20
+ "eval_samples_per_second": 36.725,
21
+ "eval_steps_per_second": 4.591,
22
+ "step": 15865
23
+ },
24
+ {
25
+ "epoch": 2.0,
26
+ "learning_rate": 3.7044424560391055e-05,
27
+ "loss": 1.0667,
28
+ "step": 31730
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "eval_loss": 1.032117247581482,
33
+ "eval_runtime": 767.5288,
34
+ "eval_samples_per_second": 36.748,
35
+ "eval_steps_per_second": 4.594,
36
+ "step": 31730
37
+ },
38
+ {
39
+ "epoch": 3.0,
40
+ "learning_rate": 3.2828277417204576e-05,
41
+ "loss": 1.0313,
42
+ "step": 47595
43
+ },
44
+ {
45
+ "epoch": 3.0,
46
+ "eval_loss": 1.0152138471603394,
47
+ "eval_runtime": 766.8529,
48
+ "eval_samples_per_second": 36.78,
49
+ "eval_steps_per_second": 4.598,
50
+ "step": 47595
51
+ },
52
+ {
53
+ "epoch": 4.0,
54
+ "learning_rate": 2.7278216356653993e-05,
55
+ "loss": 1.0059,
56
+ "step": 63460
57
+ },
58
+ {
59
+ "epoch": 4.0,
60
+ "eval_loss": 1.0045779943466187,
61
+ "eval_runtime": 766.1088,
62
+ "eval_samples_per_second": 36.816,
63
+ "eval_steps_per_second": 4.602,
64
+ "step": 63460
65
+ },
66
+ {
67
+ "epoch": 5.0,
68
+ "learning_rate": 2.0971349547678654e-05,
69
+ "loss": 0.9863,
70
+ "step": 79325
71
+ },
72
+ {
73
+ "epoch": 5.0,
74
+ "eval_loss": 0.9978464841842651,
75
+ "eval_runtime": 768.9099,
76
+ "eval_samples_per_second": 36.682,
77
+ "eval_steps_per_second": 4.586,
78
+ "step": 79325
79
+ },
80
+ {
81
+ "epoch": 6.0,
82
+ "learning_rate": 1.4563479569054354e-05,
83
+ "loss": 0.9709,
84
+ "step": 95190
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "eval_loss": 0.9945968389511108,
89
+ "eval_runtime": 767.824,
90
+ "eval_samples_per_second": 36.734,
91
+ "eval_steps_per_second": 4.592,
92
+ "step": 95190
93
+ },
94
+ {
95
+ "epoch": 7.0,
96
+ "learning_rate": 8.720911542440145e-06,
97
+ "loss": 0.9593,
98
+ "step": 111055
99
+ },
100
+ {
101
+ "epoch": 7.0,
102
+ "eval_loss": 0.993177056312561,
103
+ "eval_runtime": 767.6275,
104
+ "eval_samples_per_second": 36.743,
105
+ "eval_steps_per_second": 4.593,
106
+ "step": 111055
107
+ },
108
+ {
109
+ "epoch": 8.0,
110
+ "learning_rate": 4.051169186756774e-06,
111
+ "loss": 0.9513,
112
+ "step": 126920
113
+ },
114
+ {
115
+ "epoch": 8.0,
116
+ "eval_loss": 0.9924605488777161,
117
+ "eval_runtime": 766.8127,
118
+ "eval_samples_per_second": 36.782,
119
+ "eval_steps_per_second": 4.598,
120
+ "step": 126920
121
+ }
122
+ ],
123
+ "max_steps": 158650,
124
+ "num_train_epochs": 10,
125
+ "total_flos": 7.396317829251072e+17,
126
+ "trial_name": null,
127
+ "trial_params": null
128
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dd6a7259206a09e60be85767c1e03a68818aeeb7ed9b0704bc0d56bf48bd157
3
+ size 3768