istvanj commited on
Commit
2891ab5
·
verified ·
1 Parent(s): 0ee8711

End of training

Browse files
Files changed (2) hide show
  1. README.md +3 -1
  2. trainer_state.json +89 -40
README.md CHANGED
@@ -3,6 +3,8 @@ library_name: peft
3
  license: cc-by-nc-4.0
4
  base_model: facebook/musicgen-melody
5
  tags:
 
 
6
  - generated_from_trainer
7
  model-index:
8
  - name: musicgen-melody-lora-dnb-colab-gs-5-lr-2e-05
@@ -14,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  # musicgen-melody-lora-dnb-colab-gs-5-lr-2e-05
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
 
 
3
  license: cc-by-nc-4.0
4
  base_model: facebook/musicgen-melody
5
  tags:
6
+ - text-to-audio
7
+ - dnb
8
  - generated_from_trainer
9
  model-index:
10
  - name: musicgen-melody-lora-dnb-colab-gs-5-lr-2e-05
 
16
 
17
  # musicgen-melody-lora-dnb-colab-gs-5-lr-2e-05
18
 
19
+ This model is a fine-tuned version of [facebook/musicgen-melody](https://huggingface.co/facebook/musicgen-melody) on the istvanj/ncs-dnb dataset.
20
 
21
  ## Model description
22
 
trainer_state.json CHANGED
@@ -1,97 +1,146 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 2.6666666666666665,
5
  "eval_steps": 500,
6
- "global_step": 21,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 0.26666666666666666,
13
- "grad_norm": 8.306109428405762,
14
- "learning_rate": 1.8095238095238097e-05,
15
- "loss": 9.6984,
16
  "step": 2
17
  },
18
  {
19
  "epoch": 0.5333333333333333,
20
- "grad_norm": 8.965208053588867,
21
- "learning_rate": 1.6190476190476193e-05,
22
- "loss": 9.666,
23
  "step": 4
24
  },
25
  {
26
  "epoch": 0.8,
27
- "grad_norm": 9.015539169311523,
28
- "learning_rate": 1.4285714285714287e-05,
29
- "loss": 9.6517,
30
  "step": 6
31
  },
32
  {
33
  "epoch": 1.0,
34
  "grad_norm": NaN,
35
- "learning_rate": 1.3333333333333333e-05,
36
- "loss": 7.1945,
37
  "step": 8
38
  },
39
  {
40
  "epoch": 1.2666666666666666,
41
- "grad_norm": 9.043198585510254,
42
- "learning_rate": 1.1428571428571429e-05,
43
- "loss": 9.6038,
44
  "step": 10
45
  },
46
  {
47
  "epoch": 1.5333333333333332,
48
- "grad_norm": 9.583108901977539,
49
- "learning_rate": 9.523809523809525e-06,
50
- "loss": 9.5671,
51
  "step": 12
52
  },
53
  {
54
  "epoch": 1.8,
55
- "grad_norm": 10.154290199279785,
56
- "learning_rate": 7.61904761904762e-06,
57
- "loss": 9.5022,
58
  "step": 14
59
  },
60
  {
61
  "epoch": 2.0,
62
- "grad_norm": 5.452324867248535,
63
- "learning_rate": 5.7142857142857145e-06,
64
- "loss": 7.1576,
65
  "step": 16
66
  },
67
  {
68
  "epoch": 2.2666666666666666,
69
- "grad_norm": 9.685518264770508,
70
- "learning_rate": 3.80952380952381e-06,
71
- "loss": 9.5174,
72
  "step": 18
73
  },
74
  {
75
  "epoch": 2.533333333333333,
76
- "grad_norm": 10.151938438415527,
77
- "learning_rate": 1.904761904761905e-06,
78
- "loss": 9.4679,
79
  "step": 20
80
  },
81
  {
82
- "epoch": 2.6666666666666665,
83
- "step": 21,
84
- "total_flos": 82187025809664.0,
85
- "train_loss": 9.120764187404088,
86
- "train_runtime": 574.346,
87
- "train_samples_per_second": 0.627,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
88
  "train_steps_per_second": 0.037
89
  }
90
  ],
91
  "logging_steps": 2,
92
- "max_steps": 21,
93
  "num_input_tokens_seen": 0,
94
- "num_train_epochs": 3,
95
  "save_steps": 500,
96
  "stateful_callbacks": {
97
  "TrainerControl": {
@@ -105,7 +154,7 @@
105
  "attributes": {}
106
  }
107
  },
108
- "total_flos": 82187025809664.0,
109
  "train_batch_size": 2,
110
  "trial_name": null,
111
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 4.4,
5
  "eval_steps": 500,
6
+ "global_step": 35,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 0.26666666666666666,
13
+ "grad_norm": 7.714407444000244,
14
+ "learning_rate": 1.885714285714286e-05,
15
+ "loss": 9.6987,
16
  "step": 2
17
  },
18
  {
19
  "epoch": 0.5333333333333333,
20
+ "grad_norm": 8.402449607849121,
21
+ "learning_rate": 1.7714285714285717e-05,
22
+ "loss": 9.6675,
23
  "step": 4
24
  },
25
  {
26
  "epoch": 0.8,
27
+ "grad_norm": 8.54103946685791,
28
+ "learning_rate": 1.6571428571428574e-05,
29
+ "loss": 9.6521,
30
  "step": 6
31
  },
32
  {
33
  "epoch": 1.0,
34
  "grad_norm": NaN,
35
+ "learning_rate": 1.6000000000000003e-05,
36
+ "loss": 7.1927,
37
  "step": 8
38
  },
39
  {
40
  "epoch": 1.2666666666666666,
41
+ "grad_norm": 8.744111061096191,
42
+ "learning_rate": 1.4857142857142858e-05,
43
+ "loss": 9.599,
44
  "step": 10
45
  },
46
  {
47
  "epoch": 1.5333333333333332,
48
+ "grad_norm": 9.355561256408691,
49
+ "learning_rate": 1.3714285714285716e-05,
50
+ "loss": 9.5552,
51
  "step": 12
52
  },
53
  {
54
  "epoch": 1.8,
55
+ "grad_norm": 10.12316608428955,
56
+ "learning_rate": 1.2571428571428572e-05,
57
+ "loss": 9.4807,
58
  "step": 14
59
  },
60
  {
61
  "epoch": 2.0,
62
+ "grad_norm": 5.6569437980651855,
63
+ "learning_rate": 1.1428571428571429e-05,
64
+ "loss": 7.134,
65
  "step": 16
66
  },
67
  {
68
  "epoch": 2.2666666666666666,
69
+ "grad_norm": 10.050814628601074,
70
+ "learning_rate": 1.0285714285714285e-05,
71
+ "loss": 9.4691,
72
  "step": 18
73
  },
74
  {
75
  "epoch": 2.533333333333333,
76
+ "grad_norm": 10.766989707946777,
77
+ "learning_rate": 9.142857142857144e-06,
78
+ "loss": 9.4027,
79
  "step": 20
80
  },
81
  {
82
+ "epoch": 2.8,
83
+ "grad_norm": 11.306514739990234,
84
+ "learning_rate": 8.000000000000001e-06,
85
+ "loss": 9.4043,
86
+ "step": 22
87
+ },
88
+ {
89
+ "epoch": 3.0,
90
+ "grad_norm": 6.406909942626953,
91
+ "learning_rate": 6.857142857142858e-06,
92
+ "loss": 6.9995,
93
+ "step": 24
94
+ },
95
+ {
96
+ "epoch": 3.2666666666666666,
97
+ "grad_norm": 12.331953048706055,
98
+ "learning_rate": 5.7142857142857145e-06,
99
+ "loss": 9.3525,
100
+ "step": 26
101
+ },
102
+ {
103
+ "epoch": 3.533333333333333,
104
+ "grad_norm": 11.795371055603027,
105
+ "learning_rate": 4.571428571428572e-06,
106
+ "loss": 9.3326,
107
+ "step": 28
108
+ },
109
+ {
110
+ "epoch": 3.8,
111
+ "grad_norm": 12.696221351623535,
112
+ "learning_rate": 3.428571428571429e-06,
113
+ "loss": 9.3262,
114
+ "step": 30
115
+ },
116
+ {
117
+ "epoch": 4.0,
118
+ "grad_norm": 6.24462890625,
119
+ "learning_rate": 2.285714285714286e-06,
120
+ "loss": 6.9159,
121
+ "step": 32
122
+ },
123
+ {
124
+ "epoch": 4.266666666666667,
125
+ "grad_norm": 12.694133758544922,
126
+ "learning_rate": 1.142857142857143e-06,
127
+ "loss": 9.286,
128
+ "step": 34
129
+ },
130
+ {
131
+ "epoch": 4.4,
132
+ "step": 35,
133
+ "total_flos": 135900533909640.0,
134
+ "train_loss": 8.918893187386649,
135
+ "train_runtime": 949.0763,
136
+ "train_samples_per_second": 0.632,
137
  "train_steps_per_second": 0.037
138
  }
139
  ],
140
  "logging_steps": 2,
141
+ "max_steps": 35,
142
  "num_input_tokens_seen": 0,
143
+ "num_train_epochs": 5,
144
  "save_steps": 500,
145
  "stateful_callbacks": {
146
  "TrainerControl": {
 
154
  "attributes": {}
155
  }
156
  },
157
+ "total_flos": 135900533909640.0,
158
  "train_batch_size": 2,
159
  "trial_name": null,
160
  "trial_params": null