DevPanda004 commited on
Commit
281622b
·
verified ·
1 Parent(s): a48201f

End of training

Browse files
Files changed (2) hide show
  1. README.md +3 -1
  2. trainer_state.json +49 -28
README.md CHANGED
@@ -3,6 +3,8 @@ library_name: peft
3
  license: cc-by-nc-4.0
4
  base_model: facebook/musicgen-small
5
  tags:
 
 
6
  - generated_from_trainer
7
  model-index:
8
  - name: musicgen-small-ft1
@@ -14,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  # musicgen-small-ft1
16
 
17
- This model is a fine-tuned version of [facebook/musicgen-small](https://huggingface.co/facebook/musicgen-small) on an unknown dataset.
18
 
19
  ## Model description
20
 
 
3
  license: cc-by-nc-4.0
4
  base_model: facebook/musicgen-small
5
  tags:
6
+ - text-to-audio
7
+ - indian
8
  - generated_from_trainer
9
  model-index:
10
  - name: musicgen-small-ft1
 
16
 
17
  # musicgen-small-ft1
18
 
19
+ This model is a fine-tuned version of [facebook/musicgen-small](https://huggingface.co/facebook/musicgen-small) on the DevPanda004/indian-music-and-metadata-3 dataset.
20
 
21
  ## Model description
22
 
trainer_state.json CHANGED
@@ -1,55 +1,76 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 2.32,
5
  "eval_steps": 500,
6
- "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.64,
13
- "grad_norm": 19.88896369934082,
14
- "learning_rate": 0.00015555555555555556,
15
- "loss": 9.6148,
16
  "step": 2
17
  },
18
  {
19
- "epoch": 1.0,
20
- "grad_norm": 3.0083649158477783,
21
- "learning_rate": 0.00011111111111111112,
22
- "loss": 5.1146,
23
  "step": 4
24
  },
25
  {
26
- "epoch": 1.6400000000000001,
27
- "grad_norm": 17.57530975341797,
28
- "learning_rate": 6.666666666666667e-05,
29
- "loss": 8.3805,
30
  "step": 6
31
  },
32
  {
33
- "epoch": 2.0,
34
- "grad_norm": 3.7451229095458984,
35
- "learning_rate": 2.2222222222222223e-05,
36
- "loss": 4.5262,
37
  "step": 8
38
  },
39
  {
40
- "epoch": 2.32,
41
- "step": 9,
42
- "total_flos": 87485929268832.0,
43
- "train_loss": 7.02129332224528,
44
- "train_runtime": 224.2171,
45
- "train_samples_per_second": 2.676,
46
- "train_steps_per_second": 0.04
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 2,
50
- "max_steps": 9,
51
  "num_input_tokens_seen": 0,
52
- "num_train_epochs": 3,
53
  "save_steps": 500,
54
  "stateful_callbacks": {
55
  "TrainerControl": {
@@ -63,7 +84,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 87485929268832.0,
67
  "train_batch_size": 8,
68
  "trial_name": null,
69
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.8888888888888888,
5
  "eval_steps": 500,
6
+ "global_step": 14,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 0.25396825396825395,
13
+ "grad_norm": 19.76939582824707,
14
+ "learning_rate": 0.00017142857142857143,
15
+ "loss": 9.5977,
16
  "step": 2
17
  },
18
  {
19
+ "epoch": 0.5079365079365079,
20
+ "grad_norm": 23.03803062438965,
21
+ "learning_rate": 0.00014285714285714287,
22
+ "loss": 8.8963,
23
  "step": 4
24
  },
25
  {
26
+ "epoch": 0.7619047619047619,
27
+ "grad_norm": 19.974302291870117,
28
+ "learning_rate": 0.00011428571428571428,
29
+ "loss": 8.297,
30
  "step": 6
31
  },
32
  {
33
+ "epoch": 1.126984126984127,
34
+ "grad_norm": 51.25042724609375,
35
+ "learning_rate": 8.571428571428571e-05,
36
+ "loss": 9.9734,
37
  "step": 8
38
  },
39
  {
40
+ "epoch": 1.380952380952381,
41
+ "grad_norm": 21.681840896606445,
42
+ "learning_rate": 5.714285714285714e-05,
43
+ "loss": 7.6149,
44
+ "step": 10
45
+ },
46
+ {
47
+ "epoch": 1.6349206349206349,
48
+ "grad_norm": 17.052457809448242,
49
+ "learning_rate": 2.857142857142857e-05,
50
+ "loss": 7.5471,
51
+ "step": 12
52
+ },
53
+ {
54
+ "epoch": 1.8888888888888888,
55
+ "grad_norm": 11.491819381713867,
56
+ "learning_rate": 0.0,
57
+ "loss": 7.4192,
58
+ "step": 14
59
+ },
60
+ {
61
+ "epoch": 1.8888888888888888,
62
+ "step": 14,
63
+ "total_flos": 180166080636000.0,
64
+ "train_loss": 8.477952480316162,
65
+ "train_runtime": 453.3902,
66
+ "train_samples_per_second": 2.206,
67
+ "train_steps_per_second": 0.031
68
  }
69
  ],
70
  "logging_steps": 2,
71
+ "max_steps": 14,
72
  "num_input_tokens_seen": 0,
73
+ "num_train_epochs": 2,
74
  "save_steps": 500,
75
  "stateful_callbacks": {
76
  "TrainerControl": {
 
84
  "attributes": {}
85
  }
86
  },
87
+ "total_flos": 180166080636000.0,
88
  "train_batch_size": 8,
89
  "trial_name": null,
90
  "trial_params": null