jazzson commited on
Commit
ec24a82
1 Parent(s): 47dcc2e

End of training

Browse files
Files changed (2) hide show
  1. README.md +3 -1
  2. trainer_state.json +66 -24
README.md CHANGED
@@ -3,6 +3,8 @@ base_model: facebook/musicgen-melody
3
  library_name: peft
4
  license: cc-by-nc-4.0
5
  tags:
 
 
6
  - generated_from_trainer
7
  model-index:
8
  - name: musicgen-melody-lora-jay-test3-colab
@@ -14,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  # musicgen-melody-lora-jay-test3-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
 
 
3
  library_name: peft
4
  license: cc-by-nc-4.0
5
  tags:
6
+ - text-to-audio
7
+ - jaychou
8
  - generated_from_trainer
9
  model-index:
10
  - name: musicgen-melody-lora-jay-test3-colab
 
16
 
17
  # musicgen-melody-lora-jay-test3-colab
18
 
19
+ This model is a fine-tuned version of [facebook/musicgen-melody](https://huggingface.co/facebook/musicgen-melody) on the jazzson/datasetJayChou dataset.
20
 
21
  ## Model description
22
 
trainer_state.json CHANGED
@@ -1,55 +1,97 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 5.333333333333333,
5
  "eval_steps": 500,
6
- "global_step": 8,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 1.3333333333333333,
13
- "grad_norm": 1.9667768478393555,
14
- "learning_rate": 0.00015000000000000001,
15
- "loss": 9.3086,
16
  "step": 2
17
  },
18
  {
19
  "epoch": 2.6666666666666665,
20
- "grad_norm": 1.3830890655517578,
21
- "learning_rate": 0.0001,
22
- "loss": 7.9088,
23
  "step": 4
24
  },
25
  {
26
  "epoch": 4.0,
27
- "grad_norm": 1.0656214952468872,
28
- "learning_rate": 5e-05,
29
- "loss": 7.4385,
30
  "step": 6
31
  },
32
  {
33
  "epoch": 5.333333333333333,
34
- "grad_norm": 0.9365198016166687,
35
- "learning_rate": 0.0,
36
- "loss": 7.2958,
37
  "step": 8
38
  },
39
  {
40
- "epoch": 5.333333333333333,
41
- "step": 8,
42
- "total_flos": 36142266989280.0,
43
- "train_loss": 7.987936019897461,
44
- "train_runtime": 213.0103,
45
- "train_samples_per_second": 0.901,
46
- "train_steps_per_second": 0.038
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 2,
50
- "max_steps": 8,
51
  "num_input_tokens_seen": 0,
52
- "num_train_epochs": 8,
53
  "save_steps": 500,
54
  "stateful_callbacks": {
55
  "TrainerControl": {
@@ -63,7 +105,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 36142266989280.0,
67
  "train_batch_size": 2,
68
  "trial_name": null,
69
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 13.333333333333334,
5
  "eval_steps": 500,
6
+ "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 1.3333333333333333,
13
+ "grad_norm": 1.1772643327713013,
14
+ "learning_rate": 0.00018,
15
+ "loss": 7.2879,
16
  "step": 2
17
  },
18
  {
19
  "epoch": 2.6666666666666665,
20
+ "grad_norm": 1.1918418407440186,
21
+ "learning_rate": 0.00016,
22
+ "loss": 7.2794,
23
  "step": 4
24
  },
25
  {
26
  "epoch": 4.0,
27
+ "grad_norm": 0.3022441864013672,
28
+ "learning_rate": 0.00014,
29
+ "loss": 7.1624,
30
  "step": 6
31
  },
32
  {
33
  "epoch": 5.333333333333333,
34
+ "grad_norm": 0.3200594186782837,
35
+ "learning_rate": 0.00012,
36
+ "loss": 7.0943,
37
  "step": 8
38
  },
39
  {
40
+ "epoch": 6.666666666666667,
41
+ "grad_norm": 0.40559494495391846,
42
+ "learning_rate": 0.0001,
43
+ "loss": 7.0771,
44
+ "step": 10
45
+ },
46
+ {
47
+ "epoch": 8.0,
48
+ "grad_norm": 0.3001839816570282,
49
+ "learning_rate": 8e-05,
50
+ "loss": 7.0229,
51
+ "step": 12
52
+ },
53
+ {
54
+ "epoch": 9.333333333333334,
55
+ "grad_norm": 0.290673166513443,
56
+ "learning_rate": 6e-05,
57
+ "loss": 7.0285,
58
+ "step": 14
59
+ },
60
+ {
61
+ "epoch": 10.666666666666666,
62
+ "grad_norm": 0.25998666882514954,
63
+ "learning_rate": 4e-05,
64
+ "loss": 7.014,
65
+ "step": 16
66
+ },
67
+ {
68
+ "epoch": 12.0,
69
+ "grad_norm": 0.2689404785633087,
70
+ "learning_rate": 2e-05,
71
+ "loss": 6.9955,
72
+ "step": 18
73
+ },
74
+ {
75
+ "epoch": 13.333333333333334,
76
+ "grad_norm": 0.4722444713115692,
77
+ "learning_rate": 0.0,
78
+ "loss": 6.9773,
79
+ "step": 20
80
+ },
81
+ {
82
+ "epoch": 13.333333333333334,
83
+ "step": 20,
84
+ "total_flos": 90355667473200.0,
85
+ "train_loss": 7.093942546844483,
86
+ "train_runtime": 549.5985,
87
+ "train_samples_per_second": 0.873,
88
+ "train_steps_per_second": 0.036
89
  }
90
  ],
91
  "logging_steps": 2,
92
+ "max_steps": 20,
93
  "num_input_tokens_seen": 0,
94
+ "num_train_epochs": 20,
95
  "save_steps": 500,
96
  "stateful_callbacks": {
97
  "TrainerControl": {
 
105
  "attributes": {}
106
  }
107
  },
108
+ "total_flos": 90355667473200.0,
109
  "train_batch_size": 2,
110
  "trial_name": null,
111
  "trial_params": null