Hugging Face's logo

Progz
/
MIDICausalFinetuning2

Text Generation
Transformers
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
Progz commited on
Commit
18d452b
•
1 Parent(s): 37b7349

MIDICausalFinetuning2

Browse files
Files changed (5) hide show
  1. README.md +102 -102
  2. config.json +5 -6
  3. generation_config.json +2 -2
  4. model.safetensors +2 -2
  5. training_args.bin +1 -1
README.md CHANGED
@@ -11,9 +11,9 @@ should probably proofread and complete it, then remove this comment. -->
11
 
12
  # MIDICausalFinetuning2
13
 
14
- This model was trained from scratch on the None dataset.
15
  It achieves the following results on the evaluation set:
16
- - Loss: 0.0792
17
 
18
  ## Model description
19
 
@@ -44,106 +44,106 @@ The following hyperparameters were used during training:
44
 
45
  | Training Loss | Epoch | Step | Validation Loss |
46
  |:-------------:|:-----:|:----:|:---------------:|
47
- | No log | 1.0 | 1 | 0.2220 |
48
- | No log | 2.0 | 2 | 0.3231 |
49
- | No log | 3.0 | 3 | 0.1594 |
50
- | No log | 4.0 | 4 | 0.2779 |
51
- | No log | 5.0 | 5 | 0.5279 |
52
- | No log | 6.0 | 6 | 0.5107 |
53
- | No log | 7.0 | 7 | 0.3730 |
54
- | No log | 8.0 | 8 | 0.1183 |
55
- | No log | 9.0 | 9 | 0.2105 |
56
- | No log | 10.0 | 10 | 0.3465 |
57
- | No log | 11.0 | 11 | 0.3662 |
58
- | No log | 12.0 | 12 | 0.3249 |
59
- | No log | 13.0 | 13 | 0.2316 |
60
- | No log | 14.0 | 14 | 0.1033 |
61
- | No log | 15.0 | 15 | 0.1101 |
62
- | No log | 16.0 | 16 | 0.1897 |
63
- | No log | 17.0 | 17 | 0.2074 |
64
- | No log | 18.0 | 18 | 0.1727 |
65
- | No log | 19.0 | 19 | 0.1067 |
66
- | No log | 20.0 | 20 | 0.0694 |
67
- | No log | 21.0 | 21 | 0.1424 |
68
- | No log | 22.0 | 22 | 0.2002 |
69
- | No log | 23.0 | 23 | 0.2203 |
70
- | No log | 24.0 | 24 | 0.2071 |
71
- | No log | 25.0 | 25 | 0.1653 |
72
- | No log | 26.0 | 26 | 0.1028 |
73
- | No log | 27.0 | 27 | 0.0684 |
74
- | No log | 28.0 | 28 | 0.1184 |
75
- | No log | 29.0 | 29 | 0.1826 |
76
- | No log | 30.0 | 30 | 0.2139 |
77
- | No log | 31.0 | 31 | 0.2120 |
78
- | No log | 32.0 | 32 | 0.1774 |
79
- | No log | 33.0 | 33 | 0.1160 |
80
- | No log | 34.0 | 34 | 0.0666 |
81
- | No log | 35.0 | 35 | 0.1077 |
82
- | No log | 36.0 | 36 | 0.1752 |
83
- | No log | 37.0 | 37 | 0.2090 |
84
- | No log | 38.0 | 38 | 0.2131 |
85
- | No log | 39.0 | 39 | 0.1884 |
86
- | No log | 40.0 | 40 | 0.1337 |
87
- | No log | 41.0 | 41 | 0.0706 |
88
- | No log | 42.0 | 42 | 0.1016 |
89
- | No log | 43.0 | 43 | 0.1948 |
90
- | No log | 44.0 | 44 | 0.2694 |
91
- | No log | 45.0 | 45 | 0.3035 |
92
- | No log | 46.0 | 46 | 0.2986 |
93
- | No log | 47.0 | 47 | 0.2562 |
94
- | No log | 48.0 | 48 | 0.1692 |
95
- | No log | 49.0 | 49 | 0.0745 |
96
- | No log | 50.0 | 50 | 0.1205 |
97
- | No log | 51.0 | 51 | 0.1986 |
98
- | No log | 52.0 | 52 | 0.2338 |
99
- | No log | 53.0 | 53 | 0.2541 |
100
- | No log | 54.0 | 54 | 0.2320 |
101
- | No log | 55.0 | 55 | 0.1643 |
102
- | No log | 56.0 | 56 | 0.0704 |
103
- | No log | 57.0 | 57 | 0.0978 |
104
- | No log | 58.0 | 58 | 0.1339 |
105
- | No log | 59.0 | 59 | 0.1193 |
106
- | No log | 60.0 | 60 | 0.0714 |
107
- | No log | 61.0 | 61 | 0.0755 |
108
- | No log | 62.0 | 62 | 0.1143 |
109
- | No log | 63.0 | 63 | 0.1206 |
110
- | No log | 64.0 | 64 | 0.0819 |
111
- | No log | 65.0 | 65 | 0.0846 |
112
- | No log | 66.0 | 66 | 0.2298 |
113
- | No log | 67.0 | 67 | 0.3107 |
114
- | No log | 68.0 | 68 | 0.4166 |
115
- | No log | 69.0 | 69 | 0.4878 |
116
- | No log | 70.0 | 70 | 0.5105 |
117
- | No log | 71.0 | 71 | 0.5005 |
118
- | No log | 72.0 | 72 | 0.4607 |
119
- | No log | 73.0 | 73 | 0.3838 |
120
- | No log | 74.0 | 74 | 0.2592 |
121
- | No log | 75.0 | 75 | 0.0993 |
122
- | No log | 76.0 | 76 | 0.1212 |
123
- | No log | 77.0 | 77 | 0.2278 |
124
- | No log | 78.0 | 78 | 0.2807 |
125
- | No log | 79.0 | 79 | 0.2971 |
126
- | No log | 80.0 | 80 | 0.2864 |
127
- | No log | 81.0 | 81 | 0.2735 |
128
- | No log | 82.0 | 82 | 0.2480 |
129
- | No log | 83.0 | 83 | 0.2467 |
130
- | No log | 84.0 | 84 | 0.2657 |
131
- | No log | 85.0 | 85 | 0.2947 |
132
- | No log | 86.0 | 86 | 0.3001 |
133
- | No log | 87.0 | 87 | 0.2881 |
134
- | No log | 88.0 | 88 | 0.2645 |
135
- | No log | 89.0 | 89 | 0.2312 |
136
- | No log | 90.0 | 90 | 0.1919 |
137
- | No log | 91.0 | 91 | 0.1683 |
138
- | No log | 92.0 | 92 | 0.1534 |
139
- | No log | 93.0 | 93 | 0.1325 |
140
- | No log | 94.0 | 94 | 0.1247 |
141
- | No log | 95.0 | 95 | 0.1123 |
142
- | No log | 96.0 | 96 | 0.1052 |
143
- | No log | 97.0 | 97 | 0.0964 |
144
- | No log | 98.0 | 98 | 0.0883 |
145
- | No log | 99.0 | 99 | 0.0824 |
146
- | No log | 100.0 | 100 | 0.0792 |
147
 
148
 
149
  ### Framework versions
 
11
 
12
  # MIDICausalFinetuning2
13
 
14
+ This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
15
  It achieves the following results on the evaluation set:
16
+ - Loss: 0.1068
17
 
18
  ## Model description
19
 
 
44
 
45
  | Training Loss | Epoch | Step | Validation Loss |
46
  |:-------------:|:-----:|:----:|:---------------:|
47
+ | No log | 1.0 | 1 | 3.6134 |
48
+ | No log | 2.0 | 2 | 3.0302 |
49
+ | No log | 3.0 | 3 | 2.6249 |
50
+ | No log | 4.0 | 4 | 2.2908 |
51
+ | No log | 5.0 | 5 | 1.9804 |
52
+ | No log | 6.0 | 6 | 1.6890 |
53
+ | No log | 7.0 | 7 | 1.4256 |
54
+ | No log | 8.0 | 8 | 1.1977 |
55
+ | No log | 9.0 | 9 | 1.0097 |
56
+ | No log | 10.0 | 10 | 0.8565 |
57
+ | No log | 11.0 | 11 | 0.7343 |
58
+ | No log | 12.0 | 12 | 0.6354 |
59
+ | No log | 13.0 | 13 | 0.5562 |
60
+ | No log | 14.0 | 14 | 0.4943 |
61
+ | No log | 15.0 | 15 | 0.4439 |
62
+ | No log | 16.0 | 16 | 0.4030 |
63
+ | No log | 17.0 | 17 | 0.3669 |
64
+ | No log | 18.0 | 18 | 0.3356 |
65
+ | No log | 19.0 | 19 | 0.3081 |
66
+ | No log | 20.0 | 20 | 0.2850 |
67
+ | No log | 21.0 | 21 | 0.2650 |
68
+ | No log | 22.0 | 22 | 0.2477 |
69
+ | No log | 23.0 | 23 | 0.2327 |
70
+ | No log | 24.0 | 24 | 0.2189 |
71
+ | No log | 25.0 | 25 | 0.2075 |
72
+ | No log | 26.0 | 26 | 0.1977 |
73
+ | No log | 27.0 | 27 | 0.1889 |
74
+ | No log | 28.0 | 28 | 0.1809 |
75
+ | No log | 29.0 | 29 | 0.1740 |
76
+ | No log | 30.0 | 30 | 0.1678 |
77
+ | No log | 31.0 | 31 | 0.1622 |
78
+ | No log | 32.0 | 32 | 0.1575 |
79
+ | No log | 33.0 | 33 | 0.1534 |
80
+ | No log | 34.0 | 34 | 0.1499 |
81
+ | No log | 35.0 | 35 | 0.1466 |
82
+ | No log | 36.0 | 36 | 0.1435 |
83
+ | No log | 37.0 | 37 | 0.1408 |
84
+ | No log | 38.0 | 38 | 0.1385 |
85
+ | No log | 39.0 | 39 | 0.1362 |
86
+ | No log | 40.0 | 40 | 0.1342 |
87
+ | No log | 41.0 | 41 | 0.1320 |
88
+ | No log | 42.0 | 42 | 0.1300 |
89
+ | No log | 43.0 | 43 | 0.1283 |
90
+ | No log | 44.0 | 44 | 0.1271 |
91
+ | No log | 45.0 | 45 | 0.1258 |
92
+ | No log | 46.0 | 46 | 0.1244 |
93
+ | No log | 47.0 | 47 | 0.1231 |
94
+ | No log | 48.0 | 48 | 0.1223 |
95
+ | No log | 49.0 | 49 | 0.1216 |
96
+ | No log | 50.0 | 50 | 0.1213 |
97
+ | No log | 51.0 | 51 | 0.1209 |
98
+ | No log | 52.0 | 52 | 0.1201 |
99
+ | No log | 53.0 | 53 | 0.1190 |
100
+ | No log | 54.0 | 54 | 0.1178 |
101
+ | No log | 55.0 | 55 | 0.1169 |
102
+ | No log | 56.0 | 56 | 0.1164 |
103
+ | No log | 57.0 | 57 | 0.1161 |
104
+ | No log | 58.0 | 58 | 0.1160 |
105
+ | No log | 59.0 | 59 | 0.1160 |
106
+ | No log | 60.0 | 60 | 0.1161 |
107
+ | No log | 61.0 | 61 | 0.1158 |
108
+ | No log | 62.0 | 62 | 0.1155 |
109
+ | No log | 63.0 | 63 | 0.1146 |
110
+ | No log | 64.0 | 64 | 0.1135 |
111
+ | No log | 65.0 | 65 | 0.1125 |
112
+ | No log | 66.0 | 66 | 0.1120 |
113
+ | No log | 67.0 | 67 | 0.1121 |
114
+ | No log | 68.0 | 68 | 0.1124 |
115
+ | No log | 69.0 | 69 | 0.1126 |
116
+ | No log | 70.0 | 70 | 0.1131 |
117
+ | No log | 71.0 | 71 | 0.1133 |
118
+ | No log | 72.0 | 72 | 0.1128 |
119
+ | No log | 73.0 | 73 | 0.1119 |
120
+ | No log | 74.0 | 74 | 0.1113 |
121
+ | No log | 75.0 | 75 | 0.1107 |
122
+ | No log | 76.0 | 76 | 0.1101 |
123
+ | No log | 77.0 | 77 | 0.1096 |
124
+ | No log | 78.0 | 78 | 0.1092 |
125
+ | No log | 79.0 | 79 | 0.1090 |
126
+ | No log | 80.0 | 80 | 0.1088 |
127
+ | No log | 81.0 | 81 | 0.1089 |
128
+ | No log | 82.0 | 82 | 0.1089 |
129
+ | No log | 83.0 | 83 | 0.1090 |
130
+ | No log | 84.0 | 84 | 0.1090 |
131
+ | No log | 85.0 | 85 | 0.1089 |
132
+ | No log | 86.0 | 86 | 0.1088 |
133
+ | No log | 87.0 | 87 | 0.1087 |
134
+ | No log | 88.0 | 88 | 0.1086 |
135
+ | No log | 89.0 | 89 | 0.1083 |
136
+ | No log | 90.0 | 90 | 0.1080 |
137
+ | No log | 91.0 | 91 | 0.1077 |
138
+ | No log | 92.0 | 92 | 0.1074 |
139
+ | No log | 93.0 | 93 | 0.1072 |
140
+ | No log | 94.0 | 94 | 0.1071 |
141
+ | No log | 95.0 | 95 | 0.1070 |
142
+ | No log | 96.0 | 96 | 0.1069 |
143
+ | No log | 97.0 | 97 | 0.1069 |
144
+ | No log | 98.0 | 98 | 0.1069 |
145
+ | No log | 99.0 | 99 | 0.1068 |
146
+ | No log | 100.0 | 100 | 0.1068 |
147
 
148
 
149
  ### Framework versions
config.json CHANGED
@@ -1,19 +1,18 @@
1
  {
2
- "_name_or_path": "MIDICausalFinetuning2/",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPT2LMHeadModel"
6
  ],
7
  "attn_pdrop": 0.1,
8
- "bos_token_id": 50256,
9
  "embd_pdrop": 0.1,
10
- "eos_token_id": 50256,
11
  "initializer_range": 0.02,
12
  "layer_norm_epsilon": 1e-05,
13
  "model_type": "gpt2",
14
  "n_ctx": 1024,
15
- "n_embd": 768,
16
- "n_head": 12,
17
  "n_inner": null,
18
  "n_layer": 6,
19
  "n_positions": 1024,
@@ -29,5 +28,5 @@
29
  "torch_dtype": "float32",
30
  "transformers_version": "4.41.2",
31
  "use_cache": true,
32
- "vocab_size": 50257
33
  }
 
1
  {
 
2
  "activation_function": "gelu_new",
3
  "architectures": [
4
  "GPT2LMHeadModel"
5
  ],
6
  "attn_pdrop": 0.1,
7
+ "bos_token_id": 90,
8
  "embd_pdrop": 0.1,
9
+ "eos_token_id": 90,
10
  "initializer_range": 0.02,
11
  "layer_norm_epsilon": 1e-05,
12
  "model_type": "gpt2",
13
  "n_ctx": 1024,
14
+ "n_embd": 400,
15
+ "n_head": 10,
16
  "n_inner": null,
17
  "n_layer": 6,
18
  "n_positions": 1024,
 
28
  "torch_dtype": "float32",
29
  "transformers_version": "4.41.2",
30
  "use_cache": true,
31
+ "vocab_size": 100
32
  }
generation_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_from_model_config": true,
3
- "bos_token_id": 50256,
4
- "eos_token_id": 50256,
5
  "transformers_version": "4.41.2"
6
  }
 
1
  {
2
  "_from_model_config": true,
3
+ "bos_token_id": 90,
4
+ "eos_token_id": 90,
5
  "transformers_version": "4.41.2"
6
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d99dd8f3ae89df1fee45d66ea9e4472bb111bfa7d44033b766e7c4c55c74fec8
3
- size 327657928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c9b6a967d656ad309fb693a28be59ff806604d805703ebb5df05fbaa6ceea20
3
+ size 48013952
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e95b4d1a6e6c93de9adcd2d769355b50ecfa64e4bd8d786b89f85fbee004d17
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c91f04cbadf50a1c039de513d4899e6716902460142bd69d8bd5b1745cd13909
3
  size 5112