Hugging Face's logo

jihong008
/
musicgen-melody-lora-punk-colab

PEFT
Safetensors
Generated from Trainer
Model card Files Community
jihong008 commited on
Commit
4af0069
·
verified ·
1 Parent(s): e586fe9

Training in progress, step 28

Browse files
Files changed (6) hide show
  1. adapter_config.json +11 -11
  2. adapter_model.safetensors +1 -1
  3. all_results.json +6 -6
  4. train_results.json +6 -6
  5. trainer_state.json +97 -27
  6. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -23,22 +23,22 @@
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
- "embed_tokens.2",
27
- "v_proj",
28
  "fc2",
29
- "audio_enc_to_dec_proj",
30
- "embed_tokens.0",
31
- "embed_tokens.1",
32
- "q_proj",
33
- "enc_to_dec_proj",
34
- "embed_tokens.3",
35
  "lm_heads.3",
36
- "lm_heads.1",
37
- "out_proj",
38
  "lm_heads.2",
 
 
39
  "lm_heads.0",
 
 
 
 
40
  "k_proj",
41
- "fc1"
 
 
 
 
42
  ],
43
  "task_type": null,
44
  "use_dora": false,
 
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
 
 
26
  "fc2",
 
 
 
 
 
 
27
  "lm_heads.3",
 
 
28
  "lm_heads.2",
29
+ "q_proj",
30
+ "embed_tokens.3",
31
  "lm_heads.0",
32
+ "audio_enc_to_dec_proj",
33
+ "fc1",
34
+ "enc_to_dec_proj",
35
+ "embed_tokens.2",
36
  "k_proj",
37
+ "embed_tokens.0",
38
+ "out_proj",
39
+ "lm_heads.1",
40
+ "embed_tokens.1",
41
+ "v_proj"
42
  ],
43
  "task_type": null,
44
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1fbc9a7cc45bc2049c0744d1dcb44a4e7fc11b71163218cca0038a5ccf48394b
3
  size 43594480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9d3d4aeaad756a5f6fe85132368a98a076d7c00abd1c5b2211ccc997f6aa91d
3
  size 43594480
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 3.764705882352941,
3
- "train_loss": 9.197454690933228,
4
- "train_runtime": 36.5767,
5
- "train_samples": 33,
6
- "train_samples_per_second": 3.609,
7
- "train_steps_per_second": 0.219
8
  }
 
1
  {
2
+ "epoch": 3.6721311475409837,
3
+ "train_loss": 7.743570498057774,
4
+ "train_runtime": 121.4704,
5
+ "train_samples": 122,
6
+ "train_samples_per_second": 4.017,
7
+ "train_steps_per_second": 0.231
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 3.764705882352941,
3
- "train_loss": 9.197454690933228,
4
- "train_runtime": 36.5767,
5
- "train_samples": 33,
6
- "train_samples_per_second": 3.609,
7
- "train_steps_per_second": 0.219
8
  }
 
1
  {
2
+ "epoch": 3.6721311475409837,
3
+ "train_loss": 7.743570498057774,
4
+ "train_runtime": 121.4704,
5
+ "train_samples": 122,
6
+ "train_samples_per_second": 4.017,
7
+ "train_steps_per_second": 0.231
8
  }
trainer_state.json CHANGED
@@ -1,53 +1,123 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 3.764705882352941,
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": 0.9411764705882353,
13
- "grad_norm": 0.858464241027832,
14
- "learning_rate": 0.00015000000000000001,
15
- "loss": 9.5253,
16
  "step": 2
17
  },
18
  {
19
- "epoch": 1.8823529411764706,
20
- "grad_norm": 1.1875278949737549,
21
- "learning_rate": 0.0001,
22
- "loss": 9.2917,
23
  "step": 4
24
  },
25
  {
26
- "epoch": 2.8235294117647056,
27
- "grad_norm": 1.371861219406128,
28
- "learning_rate": 5e-05,
29
- "loss": 9.0606,
30
  "step": 6
31
  },
32
  {
33
- "epoch": 3.764705882352941,
34
- "grad_norm": 1.4962043762207031,
35
- "learning_rate": 0.0,
36
- "loss": 8.9123,
37
  "step": 8
38
  },
39
  {
40
- "epoch": 3.764705882352941,
41
- "step": 8,
42
- "total_flos": 36858669560664.0,
43
- "train_loss": 9.197454690933228,
44
- "train_runtime": 36.5767,
45
- "train_samples_per_second": 3.609,
46
- "train_steps_per_second": 0.219
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 2,
50
- "max_steps": 8,
51
  "num_input_tokens_seen": 0,
52
  "num_train_epochs": 4,
53
  "save_steps": 500,
@@ -63,7 +133,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 36858669560664.0,
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": 3.6721311475409837,
5
  "eval_steps": 500,
6
+ "global_step": 28,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 0.26229508196721313,
13
+ "grad_norm": 1.0287491083145142,
14
+ "learning_rate": 0.00018571428571428572,
15
+ "loss": 9.4306,
16
  "step": 2
17
  },
18
  {
19
+ "epoch": 0.5245901639344263,
20
+ "grad_norm": 1.8649983406066895,
21
+ "learning_rate": 0.00017142857142857143,
22
+ "loss": 9.1591,
23
  "step": 4
24
  },
25
  {
26
+ "epoch": 0.7868852459016393,
27
+ "grad_norm": 1.8567523956298828,
28
+ "learning_rate": 0.00015714285714285716,
29
+ "loss": 8.7072,
30
  "step": 6
31
  },
32
  {
33
+ "epoch": 1.0491803278688525,
34
+ "grad_norm": 2.180053234100342,
35
+ "learning_rate": 0.00014285714285714287,
36
+ "loss": 8.2864,
37
  "step": 8
38
  },
39
  {
40
+ "epoch": 1.3114754098360657,
41
+ "grad_norm": 2.318220853805542,
42
+ "learning_rate": 0.00012857142857142858,
43
+ "loss": 7.8084,
44
+ "step": 10
45
+ },
46
+ {
47
+ "epoch": 1.5737704918032787,
48
+ "grad_norm": 2.61151385307312,
49
+ "learning_rate": 0.00011428571428571428,
50
+ "loss": 7.8655,
51
+ "step": 12
52
+ },
53
+ {
54
+ "epoch": 1.8360655737704918,
55
+ "grad_norm": 2.6175003051757812,
56
+ "learning_rate": 0.0001,
57
+ "loss": 7.6385,
58
+ "step": 14
59
+ },
60
+ {
61
+ "epoch": 2.098360655737705,
62
+ "grad_norm": 1.4860339164733887,
63
+ "learning_rate": 8.571428571428571e-05,
64
+ "loss": 7.0809,
65
+ "step": 16
66
+ },
67
+ {
68
+ "epoch": 2.360655737704918,
69
+ "grad_norm": 1.5985082387924194,
70
+ "learning_rate": 7.142857142857143e-05,
71
+ "loss": 7.2482,
72
+ "step": 18
73
+ },
74
+ {
75
+ "epoch": 2.6229508196721314,
76
+ "grad_norm": 1.956580638885498,
77
+ "learning_rate": 5.714285714285714e-05,
78
+ "loss": 7.0691,
79
+ "step": 20
80
+ },
81
+ {
82
+ "epoch": 2.8852459016393444,
83
+ "grad_norm": 1.449498176574707,
84
+ "learning_rate": 4.2857142857142856e-05,
85
+ "loss": 7.0927,
86
+ "step": 22
87
+ },
88
+ {
89
+ "epoch": 3.1475409836065573,
90
+ "grad_norm": 1.9451191425323486,
91
+ "learning_rate": 2.857142857142857e-05,
92
+ "loss": 6.8079,
93
+ "step": 24
94
+ },
95
+ {
96
+ "epoch": 3.4098360655737707,
97
+ "grad_norm": 1.4124294519424438,
98
+ "learning_rate": 1.4285714285714285e-05,
99
+ "loss": 7.0556,
100
+ "step": 26
101
+ },
102
+ {
103
+ "epoch": 3.6721311475409837,
104
+ "grad_norm": 1.6439225673675537,
105
+ "learning_rate": 0.0,
106
+ "loss": 7.1598,
107
+ "step": 28
108
+ },
109
+ {
110
+ "epoch": 3.6721311475409837,
111
+ "step": 28,
112
+ "total_flos": 131289516862176.0,
113
+ "train_loss": 7.743570498057774,
114
+ "train_runtime": 121.4704,
115
+ "train_samples_per_second": 4.017,
116
+ "train_steps_per_second": 0.231
117
  }
118
  ],
119
  "logging_steps": 2,
120
+ "max_steps": 28,
121
  "num_input_tokens_seen": 0,
122
  "num_train_epochs": 4,
123
  "save_steps": 500,
 
133
  "attributes": {}
134
  }
135
  },
136
+ "total_flos": 131289516862176.0,
137
  "train_batch_size": 2,
138
  "trial_name": null,
139
  "trial_params": null
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dda95e344fbc5fafe01ef7ae8bb96b4c7f86267c4bb377a7ff668174d581b215
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1637a4130ec7c578e47549d30e4fc16da4b978ca4e0d66b5de6e12e322f6ff7
3
  size 5304