Hugging Face's logo

talargv
/
musicgen-punk-sanity

Text-to-Audio
Transformers
Safetensors
musicgen
Generated from Trainer
Inference Endpoints
Model card Files Community
talargv commited on
Commit
98b40d0
·
verified ·
1 Parent(s): 2d30d3b

End of training

Browse files
Files changed (1) hide show
  1. trainer_state.json +18 -18
trainer_state.json CHANGED
@@ -10,54 +10,54 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.5925925925925926,
13
- "grad_norm": 15.139309883117676,
14
  "learning_rate": 8.333333333333334e-05,
15
- "loss": 8.8267,
16
  "step": 2
17
  },
18
  {
19
  "epoch": 1.0,
20
- "grad_norm": 1.202364444732666,
21
  "learning_rate": 6.666666666666667e-05,
22
- "loss": 5.6996,
23
  "step": 4
24
  },
25
  {
26
  "epoch": 1.5925925925925926,
27
- "grad_norm": 1.9876203536987305,
28
  "learning_rate": 5e-05,
29
- "loss": 7.493,
30
  "step": 6
31
  },
32
  {
33
  "epoch": 2.0,
34
- "grad_norm": 0.3745439350605011,
35
  "learning_rate": 3.3333333333333335e-05,
36
- "loss": 4.9872,
37
  "step": 8
38
  },
39
  {
40
  "epoch": 2.5925925925925926,
41
- "grad_norm": 0.7483978271484375,
42
  "learning_rate": 1.6666666666666667e-05,
43
- "loss": 7.2222,
44
  "step": 10
45
  },
46
  {
47
  "epoch": 3.0,
48
- "grad_norm": 0.4470316469669342,
49
  "learning_rate": 0.0,
50
- "loss": 4.9442,
51
  "step": 12
52
  },
53
  {
54
  "epoch": 3.0,
55
  "step": 12,
56
- "total_flos": 15029702637624.0,
57
- "train_loss": 6.5288089116414385,
58
- "train_runtime": 46.6637,
59
- "train_samples_per_second": 4.629,
60
- "train_steps_per_second": 0.257
61
  }
62
  ],
63
  "logging_steps": 2,
@@ -77,7 +77,7 @@
77
  "attributes": {}
78
  }
79
  },
80
- "total_flos": 15029702637624.0,
81
  "train_batch_size": 2,
82
  "trial_name": null,
83
  "trial_params": null
 
10
  "log_history": [
11
  {
12
  "epoch": 0.5925925925925926,
13
+ "grad_norm": 16.085969924926758,
14
  "learning_rate": 8.333333333333334e-05,
15
+ "loss": 8.8634,
16
  "step": 2
17
  },
18
  {
19
  "epoch": 1.0,
20
+ "grad_norm": 1.1762865781784058,
21
  "learning_rate": 6.666666666666667e-05,
22
+ "loss": 5.6966,
23
  "step": 4
24
  },
25
  {
26
  "epoch": 1.5925925925925926,
27
+ "grad_norm": 2.515094518661499,
28
  "learning_rate": 5e-05,
29
+ "loss": 7.5589,
30
  "step": 6
31
  },
32
  {
33
  "epoch": 2.0,
34
+ "grad_norm": 0.3776528835296631,
35
  "learning_rate": 3.3333333333333335e-05,
36
+ "loss": 4.9983,
37
  "step": 8
38
  },
39
  {
40
  "epoch": 2.5925925925925926,
41
+ "grad_norm": 0.8414855599403381,
42
  "learning_rate": 1.6666666666666667e-05,
43
+ "loss": 7.2323,
44
  "step": 10
45
  },
46
  {
47
  "epoch": 3.0,
48
+ "grad_norm": 0.46793699264526367,
49
  "learning_rate": 0.0,
50
+ "loss": 4.9528,
51
  "step": 12
52
  },
53
  {
54
  "epoch": 3.0,
55
  "step": 12,
56
+ "total_flos": 16597381341504.0,
57
+ "train_loss": 6.5503848393758135,
58
+ "train_runtime": 47.4701,
59
+ "train_samples_per_second": 4.55,
60
+ "train_steps_per_second": 0.253
61
  }
62
  ],
63
  "logging_steps": 2,
 
77
  "attributes": {}
78
  }
79
  },
80
+ "total_flos": 16597381341504.0,
81
  "train_batch_size": 2,
82
  "trial_name": null,
83
  "trial_params": null