Hugging Face's logo

talargv
/
musicgen-finetune-aav

PEFT
Safetensors
musicgen
Generated from Trainer
Model card Files Community
talargv commited on
Commit
40354a5
•
1 Parent(s): 97d1d08

End of training

Browse files
Files changed (1) hide show
  1. trainer_state.json +167 -27
trainer_state.json CHANGED
@@ -1,53 +1,193 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 4.0,
5
  "eval_steps": 500,
6
- "global_step": 4,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 1.0,
13
- "grad_norm": Infinity,
14
- "learning_rate": 0.0001,
15
- "loss": 3.4942,
16
  "step": 1
17
  },
18
  {
19
- "epoch": 2.0,
20
- "grad_norm": 90.76869201660156,
21
- "learning_rate": 7.500000000000001e-05,
22
- "loss": 3.5171,
23
  "step": 2
24
  },
25
  {
26
- "epoch": 3.0,
27
- "grad_norm": 52.46024703979492,
28
- "learning_rate": 5e-05,
29
- "loss": 3.0473,
30
  "step": 3
31
  },
32
  {
33
- "epoch": 4.0,
34
- "grad_norm": 12.389888763427734,
35
- "learning_rate": 2.5e-05,
36
- "loss": 2.8469,
37
  "step": 4
38
  },
39
  {
40
- "epoch": 4.0,
41
- "step": 4,
42
- "total_flos": 333548660400.0,
43
- "train_loss": 3.2263943552970886,
44
- "train_runtime": 27.0103,
45
- "train_samples_per_second": 0.74,
46
- "train_steps_per_second": 0.148
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
50
- "max_steps": 4,
51
  "num_input_tokens_seen": 0,
52
  "num_train_epochs": 4,
53
  "save_steps": 500,
@@ -63,7 +203,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 333548660400.0,
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": 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": 0.16,
13
+ "grad_norm": 1.5084160566329956,
14
+ "learning_rate": 9.583333333333334e-05,
15
+ "loss": 8.8645,
16
  "step": 1
17
  },
18
  {
19
+ "epoch": 0.32,
20
+ "grad_norm": 2.5204503536224365,
21
+ "learning_rate": 9.166666666666667e-05,
22
+ "loss": 8.8921,
23
  "step": 2
24
  },
25
  {
26
+ "epoch": 0.48,
27
+ "grad_norm": 3.3422935009002686,
28
+ "learning_rate": 8.75e-05,
29
+ "loss": 8.7772,
30
  "step": 3
31
  },
32
  {
33
+ "epoch": 0.64,
34
+ "grad_norm": 2.7903430461883545,
35
+ "learning_rate": 8.333333333333334e-05,
36
+ "loss": 8.8086,
37
  "step": 4
38
  },
39
  {
40
+ "epoch": 0.8,
41
+ "grad_norm": 3.484639883041382,
42
+ "learning_rate": 7.916666666666666e-05,
43
+ "loss": 8.7218,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.96,
48
+ "grad_norm": 3.7417964935302734,
49
+ "learning_rate": 7.500000000000001e-05,
50
+ "loss": 8.6749,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 1.0,
55
+ "grad_norm": 1.1924405097961426,
56
+ "learning_rate": 7.083333333333334e-05,
57
+ "loss": 2.1487,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 1.16,
62
+ "grad_norm": 4.196799278259277,
63
+ "learning_rate": 6.666666666666667e-05,
64
+ "loss": 8.5763,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 1.32,
69
+ "grad_norm": 4.983647346496582,
70
+ "learning_rate": 6.25e-05,
71
+ "loss": 8.5008,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 1.48,
76
+ "grad_norm": 5.189249515533447,
77
+ "learning_rate": 5.833333333333334e-05,
78
+ "loss": 8.563,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 1.6400000000000001,
83
+ "grad_norm": 5.226248741149902,
84
+ "learning_rate": 5.4166666666666664e-05,
85
+ "loss": 8.4476,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 1.8,
90
+ "grad_norm": 6.8095383644104,
91
+ "learning_rate": 5e-05,
92
+ "loss": 8.5864,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 1.96,
97
+ "grad_norm": 5.697165012359619,
98
+ "learning_rate": 4.5833333333333334e-05,
99
+ "loss": 8.4354,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 2.0,
104
+ "grad_norm": 2.0124471187591553,
105
+ "learning_rate": 4.166666666666667e-05,
106
+ "loss": 2.0576,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 2.16,
111
+ "grad_norm": 6.587825298309326,
112
+ "learning_rate": 3.7500000000000003e-05,
113
+ "loss": 8.5304,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 2.32,
118
+ "grad_norm": 7.581618309020996,
119
+ "learning_rate": 3.3333333333333335e-05,
120
+ "loss": 8.4023,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 2.48,
125
+ "grad_norm": 5.851335525512695,
126
+ "learning_rate": 2.916666666666667e-05,
127
+ "loss": 8.331,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 2.64,
132
+ "grad_norm": 5.349519729614258,
133
+ "learning_rate": 2.5e-05,
134
+ "loss": 8.2898,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 2.8,
139
+ "grad_norm": 5.025180339813232,
140
+ "learning_rate": 2.0833333333333336e-05,
141
+ "loss": 8.2701,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 2.96,
146
+ "grad_norm": 6.174531936645508,
147
+ "learning_rate": 1.6666666666666667e-05,
148
+ "loss": 8.3265,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 3.0,
153
+ "grad_norm": 1.5616778135299683,
154
+ "learning_rate": 1.25e-05,
155
+ "loss": 2.0624,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 3.16,
160
+ "grad_norm": 5.868183612823486,
161
+ "learning_rate": 8.333333333333334e-06,
162
+ "loss": 8.3152,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 3.32,
167
+ "grad_norm": 6.4429545402526855,
168
+ "learning_rate": 4.166666666666667e-06,
169
+ "loss": 8.3426,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 3.48,
174
+ "grad_norm": 5.181556224822998,
175
+ "learning_rate": 0.0,
176
+ "loss": 8.2739,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 3.48,
181
+ "step": 24,
182
+ "total_flos": 57308909613696.0,
183
+ "train_loss": 7.716630697250366,
184
+ "train_runtime": 171.0458,
185
+ "train_samples_per_second": 2.339,
186
+ "train_steps_per_second": 0.14
187
  }
188
  ],
189
  "logging_steps": 1,
190
+ "max_steps": 24,
191
  "num_input_tokens_seen": 0,
192
  "num_train_epochs": 4,
193
  "save_steps": 500,
 
203
  "attributes": {}
204
  }
205
  },
206
+ "total_flos": 57308909613696.0,
207
  "train_batch_size": 2,
208
  "trial_name": null,
209
  "trial_params": null