jane102350 commited on
Commit
ba69eaf
1 Parent(s): 893fbd2

End of training

Browse files
Files changed (2) hide show
  1. README.md +3 -1
  2. trainer_state.json +47 -75
README.md CHANGED
@@ -2,6 +2,8 @@
2
  license: cc-by-nc-4.0
3
  library_name: peft
4
  tags:
 
 
5
  - generated_from_trainer
6
  base_model: facebook/musicgen-melody
7
  model-index:
@@ -14,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  # musicgen-melody-lora-kk-colab
16
 
17
- This model is a fine-tuned version of [facebook/musicgen-melody](https://huggingface.co/facebook/musicgen-melody) on an unknown dataset.
18
 
19
  ## Model description
20
 
 
2
  license: cc-by-nc-4.0
3
  library_name: peft
4
  tags:
5
+ - text-to-audio
6
+ - tiny-kazakh-dombra
7
  - generated_from_trainer
8
  base_model: facebook/musicgen-melody
9
  model-index:
 
16
 
17
  # musicgen-melody-lora-kk-colab
18
 
19
+ This model is a fine-tuned version of [facebook/musicgen-melody](https://huggingface.co/facebook/musicgen-melody) on the kk-lib-dataset dataset.
20
 
21
  ## Model description
22
 
trainer_state.json CHANGED
@@ -1,139 +1,111 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 6.564102564102564,
5
  "eval_steps": 500,
6
- "global_step": 32,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 0.41025641025641024,
13
- "grad_norm": 1.4377572536468506,
14
- "learning_rate": 0.0001875,
15
- "loss": 9.492,
16
  "step": 2
17
  },
18
  {
19
  "epoch": 0.8205128205128205,
20
- "grad_norm": 2.2069075107574463,
21
- "learning_rate": 0.000175,
22
- "loss": 8.8969,
23
  "step": 4
24
  },
25
  {
26
  "epoch": 1.2307692307692308,
27
- "grad_norm": 2.2332770824432373,
28
- "learning_rate": 0.00016250000000000002,
29
- "loss": 8.1134,
30
  "step": 6
31
  },
32
  {
33
  "epoch": 1.641025641025641,
34
- "grad_norm": 2.1227211952209473,
35
- "learning_rate": 0.00015000000000000001,
36
- "loss": 7.5957,
37
  "step": 8
38
  },
39
  {
40
  "epoch": 2.051282051282051,
41
- "grad_norm": 1.8074111938476562,
42
- "learning_rate": 0.0001375,
43
- "loss": 6.9518,
44
  "step": 10
45
  },
46
  {
47
  "epoch": 2.4615384615384617,
48
- "grad_norm": 1.6330405473709106,
49
- "learning_rate": 0.000125,
50
- "loss": 6.7793,
51
  "step": 12
52
  },
53
  {
54
  "epoch": 2.871794871794872,
55
- "grad_norm": 1.6258740425109863,
56
- "learning_rate": 0.00011250000000000001,
57
- "loss": 6.6454,
58
  "step": 14
59
  },
60
  {
61
  "epoch": 3.282051282051282,
62
- "grad_norm": 1.0058015584945679,
63
- "learning_rate": 0.0001,
64
- "loss": 6.6708,
65
  "step": 16
66
  },
67
  {
68
  "epoch": 3.6923076923076925,
69
- "grad_norm": 1.2760761976242065,
70
- "learning_rate": 8.75e-05,
71
- "loss": 6.4539,
72
  "step": 18
73
  },
74
  {
75
  "epoch": 4.102564102564102,
76
- "grad_norm": 1.0890202522277832,
77
- "learning_rate": 7.500000000000001e-05,
78
- "loss": 6.56,
79
  "step": 20
80
  },
81
  {
82
  "epoch": 4.512820512820513,
83
- "grad_norm": 0.9972789287567139,
84
- "learning_rate": 6.25e-05,
85
- "loss": 6.4305,
86
  "step": 22
87
  },
88
  {
89
  "epoch": 4.923076923076923,
90
- "grad_norm": 0.7041062712669373,
91
- "learning_rate": 5e-05,
92
- "loss": 6.4812,
93
- "step": 24
94
- },
95
- {
96
- "epoch": 5.333333333333333,
97
- "grad_norm": 0.6713021397590637,
98
- "learning_rate": 3.7500000000000003e-05,
99
- "loss": 6.2827,
100
- "step": 26
101
- },
102
- {
103
- "epoch": 5.743589743589744,
104
- "grad_norm": 0.7198984026908875,
105
- "learning_rate": 2.5e-05,
106
- "loss": 6.3623,
107
- "step": 28
108
- },
109
- {
110
- "epoch": 6.153846153846154,
111
- "grad_norm": 0.8625803589820862,
112
- "learning_rate": 1.25e-05,
113
- "loss": 6.3825,
114
- "step": 30
115
- },
116
- {
117
- "epoch": 6.564102564102564,
118
- "grad_norm": 0.4870496690273285,
119
  "learning_rate": 0.0,
120
- "loss": 6.4128,
121
- "step": 32
122
  },
123
  {
124
- "epoch": 6.564102564102564,
125
- "step": 32,
126
- "total_flos": 177335876845380.0,
127
- "train_loss": 7.031960189342499,
128
- "train_runtime": 130.3681,
129
- "train_samples_per_second": 4.725,
130
  "train_steps_per_second": 0.245
131
  }
132
  ],
133
  "logging_steps": 2,
134
- "max_steps": 32,
135
  "num_input_tokens_seen": 0,
136
- "num_train_epochs": 8,
137
  "save_steps": 500,
138
  "stateful_callbacks": {
139
  "TrainerControl": {
@@ -147,7 +119,7 @@
147
  "attributes": {}
148
  }
149
  },
150
- "total_flos": 177335876845380.0,
151
  "train_batch_size": 2,
152
  "trial_name": null,
153
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 4.923076923076923,
5
  "eval_steps": 500,
6
+ "global_step": 24,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 0.41025641025641024,
13
+ "grad_norm": 1.4702763557434082,
14
+ "learning_rate": 0.00018333333333333334,
15
+ "loss": 9.483,
16
  "step": 2
17
  },
18
  {
19
  "epoch": 0.8205128205128205,
20
+ "grad_norm": 2.237931966781616,
21
+ "learning_rate": 0.0001666666666666667,
22
+ "loss": 8.8833,
23
  "step": 4
24
  },
25
  {
26
  "epoch": 1.2307692307692308,
27
+ "grad_norm": 2.2123219966888428,
28
+ "learning_rate": 0.00015000000000000001,
29
+ "loss": 8.119,
30
  "step": 6
31
  },
32
  {
33
  "epoch": 1.641025641025641,
34
+ "grad_norm": 2.0387604236602783,
35
+ "learning_rate": 0.00013333333333333334,
36
+ "loss": 7.6202,
37
  "step": 8
38
  },
39
  {
40
  "epoch": 2.051282051282051,
41
+ "grad_norm": 1.8973811864852905,
42
+ "learning_rate": 0.00011666666666666668,
43
+ "loss": 6.9965,
44
  "step": 10
45
  },
46
  {
47
  "epoch": 2.4615384615384617,
48
+ "grad_norm": 1.8106874227523804,
49
+ "learning_rate": 0.0001,
50
+ "loss": 6.8357,
51
  "step": 12
52
  },
53
  {
54
  "epoch": 2.871794871794872,
55
+ "grad_norm": 1.7481627464294434,
56
+ "learning_rate": 8.333333333333334e-05,
57
+ "loss": 6.7018,
58
  "step": 14
59
  },
60
  {
61
  "epoch": 3.282051282051282,
62
+ "grad_norm": 0.9489405155181885,
63
+ "learning_rate": 6.666666666666667e-05,
64
+ "loss": 6.7105,
65
  "step": 16
66
  },
67
  {
68
  "epoch": 3.6923076923076925,
69
+ "grad_norm": 1.1118030548095703,
70
+ "learning_rate": 5e-05,
71
+ "loss": 6.4967,
72
  "step": 18
73
  },
74
  {
75
  "epoch": 4.102564102564102,
76
+ "grad_norm": 1.162569522857666,
77
+ "learning_rate": 3.3333333333333335e-05,
78
+ "loss": 6.6138,
79
  "step": 20
80
  },
81
  {
82
  "epoch": 4.512820512820513,
83
+ "grad_norm": 1.045633316040039,
84
+ "learning_rate": 1.6666666666666667e-05,
85
+ "loss": 6.4841,
86
  "step": 22
87
  },
88
  {
89
  "epoch": 4.923076923076923,
90
+ "grad_norm": 0.8710927367210388,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
91
  "learning_rate": 0.0,
92
+ "loss": 6.5578,
93
+ "step": 24
94
  },
95
  {
96
+ "epoch": 4.923076923076923,
97
+ "step": 24,
98
+ "total_flos": 147993926084196.0,
99
+ "train_loss": 7.291865587234497,
100
+ "train_runtime": 97.928,
101
+ "train_samples_per_second": 4.718,
102
  "train_steps_per_second": 0.245
103
  }
104
  ],
105
  "logging_steps": 2,
106
+ "max_steps": 24,
107
  "num_input_tokens_seen": 0,
108
+ "num_train_epochs": 6,
109
  "save_steps": 500,
110
  "stateful_callbacks": {
111
  "TrainerControl": {
 
119
  "attributes": {}
120
  }
121
  },
122
+ "total_flos": 147993926084196.0,
123
  "train_batch_size": 2,
124
  "trial_name": null,
125
  "trial_params": null