Hugging Face's logo

sunsetsobserver
/
MIDI_Transformer_Mistral_10k-vocab_100k-steps

Text Generation
Transformers
Safetensors
mistral
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
sunsetsobserver commited on
Commit
54340e4
•
1 Parent(s): 56d97b0

Upload 9 files

Browse files
Files changed (9) hide show
  1. README.md +161 -0
  2. all_results.json +7 -0
  3. config.json +26 -0
  4. generation_config.json +7 -0
  5. model.safetensors +3 -0
  6. tokenizer.json +0 -0
  7. train_results.json +7 -0
  8. trainer_state.json +0 -0
  9. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,161 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ metrics:
5
+ - accuracy
6
+ model-index:
7
+ - name: runs
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # runs
15
+
16
+ This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 24.0950
19
+ - Accuracy: 0.0013
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 0.0001
39
+ - train_batch_size: 16
40
+ - eval_batch_size: 48
41
+ - seed: 444
42
+ - gradient_accumulation_steps: 3
43
+ - total_train_batch_size: 48
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: cosine_with_restarts
46
+ - lr_scheduler_warmup_ratio: 0.3
47
+ - training_steps: 100000
48
+ - mixed_precision_training: Native AMP
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
+ |:-------------:|:------:|:------:|:---------------:|:--------:|
54
+ | 8.2359 | 6.04 | 1000 | 8.2170 | 0.0070 |
55
+ | 7.7137 | 12.07 | 2000 | 7.7007 | 0.0064 |
56
+ | 6.5277 | 18.11 | 3000 | 6.5254 | 0.0000 |
57
+ | 6.0375 | 24.14 | 4000 | 6.0532 | 0.0000 |
58
+ | 5.6908 | 30.18 | 5000 | 5.7100 | 0.0001 |
59
+ | 5.4294 | 36.22 | 6000 | 5.4758 | 0.0002 |
60
+ | 5.2161 | 42.25 | 7000 | 5.2891 | 0.0006 |
61
+ | 5.0151 | 48.29 | 8000 | 5.1152 | 0.0021 |
62
+ | 4.8349 | 54.33 | 9000 | 4.9847 | 0.0020 |
63
+ | 4.6358 | 60.36 | 10000 | 4.8754 | 0.0022 |
64
+ | 4.4326 | 66.4 | 11000 | 4.7809 | 0.0021 |
65
+ | 4.2632 | 72.43 | 12000 | 4.7416 | 0.0017 |
66
+ | 4.0415 | 78.47 | 13000 | 4.7503 | 0.0016 |
67
+ | 3.8196 | 84.51 | 14000 | 4.8472 | 0.0014 |
68
+ | 3.6207 | 90.54 | 15000 | 5.0215 | 0.0014 |
69
+ | 3.3163 | 96.58 | 16000 | 5.2939 | 0.0014 |
70
+ | 3.0377 | 102.62 | 17000 | 5.6685 | 0.0014 |
71
+ | 2.7272 | 108.65 | 18000 | 6.1649 | 0.0013 |
72
+ | 2.4319 | 114.69 | 19000 | 6.7556 | 0.0013 |
73
+ | 2.1647 | 120.72 | 20000 | 7.3951 | 0.0013 |
74
+ | 1.9001 | 126.76 | 21000 | 8.0823 | 0.0013 |
75
+ | 1.6708 | 132.8 | 22000 | 8.8230 | 0.0013 |
76
+ | 1.4762 | 138.83 | 23000 | 9.5335 | 0.0013 |
77
+ | 1.2833 | 144.87 | 24000 | 10.1973 | 0.0013 |
78
+ | 1.1451 | 150.91 | 25000 | 10.8213 | 0.0013 |
79
+ | 1.0251 | 156.94 | 26000 | 11.4402 | 0.0013 |
80
+ | 0.9164 | 162.98 | 27000 | 11.9995 | 0.0013 |
81
+ | 0.8174 | 169.01 | 28000 | 12.5680 | 0.0013 |
82
+ | 0.6862 | 175.05 | 29000 | 13.0050 | 0.0013 |
83
+ | 0.5738 | 181.09 | 30000 | 13.4692 | 0.0013 |
84
+ | 0.4524 | 187.12 | 31000 | 13.9220 | 0.0013 |
85
+ | 0.4252 | 193.16 | 32000 | 14.3340 | 0.0013 |
86
+ | 0.3952 | 199.2 | 33000 | 14.7961 | 0.0013 |
87
+ | 0.3684 | 205.23 | 34000 | 15.2421 | 0.0013 |
88
+ | 0.3338 | 211.27 | 35000 | 15.6433 | 0.0013 |
89
+ | 0.307 | 217.3 | 36000 | 16.0182 | 0.0013 |
90
+ | 0.2951 | 223.34 | 37000 | 16.3087 | 0.0013 |
91
+ | 0.28 | 229.38 | 38000 | 16.6556 | 0.0013 |
92
+ | 0.2688 | 235.41 | 39000 | 16.9303 | 0.0013 |
93
+ | 0.2582 | 241.45 | 40000 | 17.2209 | 0.0013 |
94
+ | 0.238 | 247.48 | 41000 | 17.5311 | 0.0013 |
95
+ | 0.2261 | 253.52 | 42000 | 17.7731 | 0.0013 |
96
+ | 0.21 | 259.56 | 43000 | 18.0205 | 0.0013 |
97
+ | 0.2073 | 265.59 | 44000 | 18.2693 | 0.0013 |
98
+ | 0.1976 | 271.63 | 45000 | 18.4634 | 0.0013 |
99
+ | 0.1865 | 277.67 | 46000 | 18.7215 | 0.0012 |
100
+ | 0.1769 | 283.7 | 47000 | 18.9467 | 0.0013 |
101
+ | 0.1649 | 289.74 | 48000 | 19.1423 | 0.0013 |
102
+ | 0.1517 | 295.77 | 49000 | 19.3638 | 0.0013 |
103
+ | 0.1491 | 301.81 | 50000 | 19.5879 | 0.0013 |
104
+ | 0.1387 | 307.85 | 51000 | 19.7823 | 0.0013 |
105
+ | 0.1332 | 313.88 | 52000 | 19.9663 | 0.0013 |
106
+ | 0.1256 | 319.92 | 53000 | 20.1907 | 0.0013 |
107
+ | 0.1154 | 325.96 | 54000 | 20.3939 | 0.0013 |
108
+ | 0.1091 | 331.99 | 55000 | 20.5926 | 0.0013 |
109
+ | 0.0928 | 338.03 | 56000 | 20.8044 | 0.0013 |
110
+ | 0.0812 | 344.06 | 57000 | 20.9873 | 0.0013 |
111
+ | 0.0677 | 350.1 | 58000 | 21.1931 | 0.0013 |
112
+ | 0.0609 | 356.14 | 59000 | 21.3650 | 0.0013 |
113
+ | 0.058 | 362.17 | 60000 | 21.5868 | 0.0013 |
114
+ | 0.0532 | 368.21 | 61000 | 21.7740 | 0.0013 |
115
+ | 0.0481 | 374.25 | 62000 | 21.9339 | 0.0013 |
116
+ | 0.0358 | 380.28 | 63000 | 22.1660 | 0.0012 |
117
+ | 0.0117 | 386.32 | 64000 | 22.4226 | 0.0013 |
118
+ | 0.0768 | 392.35 | 65000 | 22.2193 | 0.0013 |
119
+ | 0.0339 | 398.39 | 66000 | 22.3833 | 0.0013 |
120
+ | 0.0191 | 404.43 | 67000 | 22.5927 | 0.0013 |
121
+ | 0.0493 | 410.46 | 68000 | 22.6069 | 0.0013 |
122
+ | 0.0115 | 416.5 | 69000 | 22.8652 | 0.0012 |
123
+ | 0.0111 | 422.54 | 70000 | 22.9982 | 0.0012 |
124
+ | 0.1182 | 428.57 | 71000 | 22.6628 | 0.0013 |
125
+ | 0.0118 | 434.61 | 72000 | 22.9036 | 0.0013 |
126
+ | 0.0111 | 440.64 | 73000 | 23.0692 | 0.0013 |
127
+ | 0.011 | 446.68 | 74000 | 23.1857 | 0.0013 |
128
+ | 0.0386 | 452.72 | 75000 | 22.9263 | 0.0013 |
129
+ | 0.0109 | 458.75 | 76000 | 23.1548 | 0.0013 |
130
+ | 0.0109 | 464.79 | 77000 | 23.2761 | 0.0012 |
131
+ | 0.0108 | 470.82 | 78000 | 23.3763 | 0.0013 |
132
+ | 0.0131 | 476.86 | 79000 | 23.2048 | 0.0013 |
133
+ | 0.0108 | 482.9 | 80000 | 23.3772 | 0.0013 |
134
+ | 0.0106 | 488.93 | 81000 | 23.4733 | 0.0013 |
135
+ | 0.0106 | 494.97 | 82000 | 23.5654 | 0.0013 |
136
+ | 0.0242 | 501.01 | 83000 | 23.5459 | 0.0013 |
137
+ | 0.0104 | 507.04 | 84000 | 23.5695 | 0.0013 |
138
+ | 0.01 | 513.08 | 85000 | 23.6659 | 0.0013 |
139
+ | 0.0098 | 519.11 | 86000 | 23.7337 | 0.0013 |
140
+ | 0.0097 | 525.15 | 87000 | 23.7961 | 0.0013 |
141
+ | 0.0097 | 531.19 | 88000 | 23.8573 | 0.0013 |
142
+ | 0.0097 | 537.22 | 89000 | 23.9052 | 0.0013 |
143
+ | 0.0097 | 543.26 | 90000 | 23.9524 | 0.0013 |
144
+ | 0.0096 | 549.3 | 91000 | 23.9823 | 0.0013 |
145
+ | 0.0096 | 555.33 | 92000 | 24.0084 | 0.0013 |
146
+ | 0.0095 | 561.37 | 93000 | 24.0364 | 0.0013 |
147
+ | 0.0095 | 567.4 | 94000 | 24.0545 | 0.0013 |
148
+ | 0.0094 | 573.44 | 95000 | 24.0701 | 0.0013 |
149
+ | 0.0094 | 579.48 | 96000 | 24.0826 | 0.0013 |
150
+ | 0.0093 | 585.51 | 97000 | 24.0898 | 0.0013 |
151
+ | 0.0093 | 591.55 | 98000 | 24.0935 | 0.0013 |
152
+ | 0.0093 | 597.59 | 99000 | 24.0944 | 0.0013 |
153
+ | 0.0092 | 603.62 | 100000 | 24.0950 | 0.0013 |
154
+
155
+
156
+ ### Framework versions
157
+
158
+ - Transformers 4.37.2
159
+ - Pytorch 2.2.0+cu121
160
+ - Datasets 2.17.0
161
+ - Tokenizers 0.15.1
all_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 603.62,
3
+ "train_loss": 1.1590602387964726,
4
+ "train_runtime": 91564.1404,
5
+ "train_samples_per_second": 52.422,
6
+ "train_steps_per_second": 1.092
7
+ }
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MistralForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 2,
7
+ "eos_token_id": 3,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 512,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 2048,
12
+ "max_position_embeddings": 8192,
13
+ "model_type": "mistral",
14
+ "num_attention_heads": 8,
15
+ "num_hidden_layers": 8,
16
+ "num_key_value_heads": 4,
17
+ "pad_token_id": 0,
18
+ "rms_norm_eps": 1e-06,
19
+ "rope_theta": 10000.0,
20
+ "sliding_window": 256,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.37.2",
24
+ "use_cache": true,
25
+ "vocab_size": 10000
26
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 3,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.37.2"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c1247e57feefd0721e9dc8cef693affcfbc1e2146251ce42407dbcd57b597e1
3
+ size 166832176
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 603.62,
3
+ "train_loss": 1.1590602387964726,
4
+ "train_runtime": 91564.1404,
5
+ "train_samples_per_second": 52.422,
6
+ "train_steps_per_second": 1.092
7
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66c4d5509c43eef8667a3ddeca37d26f95e56853bbe64a5e1fe0c02098435fbe
3
+ size 4664