Katpeeler commited on
Commit
ea6caeb
1 Parent(s): 97f87cf

Training in progress, step 100

Browse files
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": null,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": null,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 512,
16
+ "n_head": 8,
17
+ "n_inner": null,
18
+ "n_layer": 6,
19
+ "n_positions": 512,
20
+ "pad_token_id": 3,
21
+ "reorder_and_upcast_attn": false,
22
+ "resid_pdrop": 0.1,
23
+ "scale_attn_by_inverse_layer_idx": false,
24
+ "scale_attn_weights": true,
25
+ "summary_activation": null,
26
+ "summary_first_dropout": 0.1,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "task_specific_params": {
31
+ "text-generation": {
32
+ "do_sample": true,
33
+ "max_length": 50
34
+ }
35
+ },
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.35.2",
38
+ "use_cache": true,
39
+ "vocab_size": 119
40
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:204fba854d5c46182f3bdbf89248d269a856523ae246c3eac222dc8f4f6d6494
3
+ size 76961160
special_tokens_map.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "pad_token": "[PAD]"
3
+ }
tokenizer.json ADDED
@@ -0,0 +1,183 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "[UNK]",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "[CLS]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "[SEP]",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "[PAD]",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 4,
44
+ "content": "[MASK]",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ }
51
+ ],
52
+ "normalizer": null,
53
+ "pre_tokenizer": {
54
+ "type": "WhitespaceSplit"
55
+ },
56
+ "post_processor": null,
57
+ "decoder": null,
58
+ "model": {
59
+ "type": "WordLevel",
60
+ "vocab": {
61
+ "[UNK]": 0,
62
+ "[CLS]": 1,
63
+ "[SEP]": 2,
64
+ "[PAD]": 3,
65
+ "[MASK]": 4,
66
+ "TIME_DELTA=4": 5,
67
+ "TIME_DELTA=2": 6,
68
+ "BAR_END": 7,
69
+ "BAR_START": 8,
70
+ "TRACK_START": 9,
71
+ "TRACK_END": 10,
72
+ "NOTE_OFF=67": 11,
73
+ "NOTE_ON=67": 12,
74
+ "NOTE_ON=65": 13,
75
+ "NOTE_OFF=65": 14,
76
+ "NOTE_ON=62": 15,
77
+ "NOTE_OFF=62": 16,
78
+ "NOTE_ON=60": 17,
79
+ "NOTE_OFF=60": 18,
80
+ "TIME_DELTA=8": 19,
81
+ "NOTE_OFF=64": 20,
82
+ "NOTE_ON=64": 21,
83
+ "NOTE_ON=63": 22,
84
+ "NOTE_OFF=63": 23,
85
+ "NOTE_OFF=66": 24,
86
+ "NOTE_ON=66": 25,
87
+ "NOTE_OFF=69": 26,
88
+ "NOTE_ON=69": 27,
89
+ "NOTE_OFF=68": 28,
90
+ "NOTE_ON=68": 29,
91
+ "NOTE_ON=61": 30,
92
+ "NOTE_OFF=61": 31,
93
+ "NOTE_OFF=58": 32,
94
+ "NOTE_ON=58": 33,
95
+ "NOTE_ON=55": 34,
96
+ "NOTE_OFF=55": 35,
97
+ "NOTE_OFF=70": 36,
98
+ "NOTE_ON=70": 37,
99
+ "NOTE_OFF=59": 38,
100
+ "NOTE_ON=59": 39,
101
+ "NOTE_OFF=57": 40,
102
+ "NOTE_ON=57": 41,
103
+ "NOTE_ON=56": 42,
104
+ "NOTE_OFF=56": 43,
105
+ "NOTE_OFF=53": 44,
106
+ "NOTE_ON=53": 45,
107
+ "NOTE_OFF=71": 46,
108
+ "NOTE_ON=71": 47,
109
+ "NOTE_ON=72": 48,
110
+ "NOTE_OFF=72": 49,
111
+ "NOTE_ON=54": 50,
112
+ "NOTE_OFF=54": 51,
113
+ "NOTE_ON=52": 52,
114
+ "NOTE_OFF=52": 53,
115
+ "NOTE_OFF=50": 54,
116
+ "NOTE_ON=50": 55,
117
+ "NOTE_ON=51": 56,
118
+ "NOTE_OFF=51": 57,
119
+ "NOTE_ON=48": 58,
120
+ "NOTE_OFF=48": 59,
121
+ "NOTE_OFF=73": 60,
122
+ "NOTE_ON=73": 61,
123
+ "NOTE_OFF=74": 62,
124
+ "NOTE_ON=74": 63,
125
+ "NOTE_OFF=49": 64,
126
+ "NOTE_ON=49": 65,
127
+ "NOTE_ON=47": 66,
128
+ "NOTE_OFF=47": 67,
129
+ "NOTE_ON=75": 68,
130
+ "NOTE_OFF=75": 69,
131
+ "NOTE_OFF=46": 70,
132
+ "NOTE_ON=46": 71,
133
+ "INST=24": 72,
134
+ "PIECE_END": 73,
135
+ "INST=48": 74,
136
+ "GENRE=JSFAKES": 75,
137
+ "INST=0": 76,
138
+ "PIECE_START": 77,
139
+ "STYLE=JSFAKES": 78,
140
+ "INST=32": 79,
141
+ "TIME_DELTA=1": 80,
142
+ "NOTE_OFF=45": 81,
143
+ "NOTE_ON=45": 82,
144
+ "NOTE_ON=76": 83,
145
+ "NOTE_OFF=76": 84,
146
+ "TIME_DELTA=6": 85,
147
+ "NOTE_OFF=44": 86,
148
+ "NOTE_ON=44": 87,
149
+ "TIME_DELTA=12": 88,
150
+ "NOTE_ON=43": 89,
151
+ "NOTE_OFF=43": 90,
152
+ "NOTE_OFF=77": 91,
153
+ "NOTE_ON=77": 92,
154
+ "NOTE_OFF=78": 93,
155
+ "NOTE_ON=78": 94,
156
+ "NOTE_OFF=41": 95,
157
+ "NOTE_ON=41": 96,
158
+ "NOTE_ON=42": 97,
159
+ "NOTE_OFF=42": 98,
160
+ "NOTE_ON=79": 99,
161
+ "NOTE_OFF=79": 100,
162
+ "NOTE_OFF=40": 101,
163
+ "NOTE_ON=40": 102,
164
+ "TIME_DELTA=16": 103,
165
+ "NOTE_ON=39": 104,
166
+ "NOTE_OFF=39": 105,
167
+ "NOTE_OFF=80": 106,
168
+ "NOTE_ON=80": 107,
169
+ "TIME_DELTA=3": 108,
170
+ "NOTE_OFF=38": 109,
171
+ "NOTE_ON=38": 110,
172
+ "NOTE_OFF=37": 111,
173
+ "NOTE_ON=37": 112,
174
+ "NOTE_ON=36": 113,
175
+ "NOTE_OFF=36": 114,
176
+ "NOTE_OFF=81": 115,
177
+ "NOTE_ON=81": 116,
178
+ "TIME_DELTA=7": 117,
179
+ "TIME_DELTA=10": 118
180
+ },
181
+ "unk_token": "[UNK]"
182
+ }
183
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[UNK]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[PAD]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "max_length": 512,
46
+ "model_max_length": 1000000000000000019884624838656,
47
+ "pad_token": "[PAD]",
48
+ "stride": 0,
49
+ "tokenizer_class": "PreTrainedTokenizerFast",
50
+ "truncation_side": "right",
51
+ "truncation_strategy": "longest_first"
52
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f826119a9c2933798270bc11da26570e22af77134444b388f22700971145da9
3
+ size 4536