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
ef3602d
·
verified ·
1 Parent(s): ee9aca0

End of training

Browse files
Files changed (1) hide show
  1. trainer_state.json +34 -76
trainer_state.json CHANGED
@@ -1,109 +1,67 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 3.48,
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": 0.32,
13
- "grad_norm": 20.783666610717773,
14
- "learning_rate": 9.166666666666667e-05,
15
- "loss": 9.056,
16
- "step": 2
17
- },
18
- {
19
- "epoch": 0.64,
20
- "grad_norm": 8.394305229187012,
21
  "learning_rate": 8.333333333333334e-05,
22
- "loss": 7.8186,
23
- "step": 4
24
- },
25
- {
26
- "epoch": 0.96,
27
- "grad_norm": 118.83284759521484,
28
- "learning_rate": 7.500000000000001e-05,
29
- "loss": 7.813,
30
- "step": 6
31
  },
32
  {
33
- "epoch": 1.16,
34
- "grad_norm": 2.4560327529907227,
35
  "learning_rate": 6.666666666666667e-05,
36
- "loss": 4.6111,
37
- "step": 8
38
- },
39
- {
40
- "epoch": 1.48,
41
- "grad_norm": 1.5673390626907349,
42
- "learning_rate": 5.833333333333334e-05,
43
- "loss": 7.3,
44
- "step": 10
45
  },
46
  {
47
- "epoch": 1.8,
48
- "grad_norm": 0.7503612637519836,
49
  "learning_rate": 5e-05,
50
- "loss": 7.2109,
51
- "step": 12
52
  },
53
  {
54
  "epoch": 2.0,
55
- "grad_norm": 0.3985859155654907,
56
- "learning_rate": 4.166666666666667e-05,
57
- "loss": 4.4783,
58
- "step": 14
59
- },
60
- {
61
- "epoch": 2.32,
62
- "grad_norm": 0.75257807970047,
63
  "learning_rate": 3.3333333333333335e-05,
64
- "loss": 7.1595,
65
- "step": 16
66
- },
67
- {
68
- "epoch": 2.64,
69
- "grad_norm": 0.9470282793045044,
70
- "learning_rate": 2.5e-05,
71
- "loss": 7.0686,
72
- "step": 18
73
  },
74
  {
75
- "epoch": 2.96,
76
- "grad_norm": 0.8260803818702698,
77
  "learning_rate": 1.6666666666666667e-05,
78
- "loss": 7.1408,
79
- "step": 20
80
- },
81
- {
82
- "epoch": 3.16,
83
- "grad_norm": 0.8250037431716919,
84
- "learning_rate": 8.333333333333334e-06,
85
- "loss": 4.3964,
86
- "step": 22
87
  },
88
  {
89
- "epoch": 3.48,
90
- "grad_norm": 0.704397976398468,
91
  "learning_rate": 0.0,
92
- "loss": 7.0209,
93
- "step": 24
94
  },
95
  {
96
- "epoch": 3.48,
97
- "step": 24,
98
- "total_flos": 8125245367344.0,
99
- "train_loss": 6.756168842315674,
100
- "train_runtime": 57.8175,
101
- "train_samples_per_second": 6.918,
102
- "train_steps_per_second": 0.415
103
  }
104
  ],
105
  "logging_steps": 2,
106
- "max_steps": 24,
107
  "num_input_tokens_seen": 0,
108
  "num_train_epochs": 4,
109
  "save_steps": 500,
@@ -119,7 +77,7 @@
119
  "attributes": {}
120
  }
121
  },
122
- "total_flos": 8125245367344.0,
123
  "train_batch_size": 2,
124
  "trial_name": null,
125
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
  "eval_steps": 500,
6
+ "global_step": 12,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 0.5925925925925926,
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,
64
+ "max_steps": 12,
65
  "num_input_tokens_seen": 0,
66
  "num_train_epochs": 4,
67
  "save_steps": 500,
 
77
  "attributes": {}
78
  }
79
  },
80
+ "total_flos": 15029702637624.0,
81
  "train_batch_size": 2,
82
  "trial_name": null,
83
  "trial_params": null