Hugging Face's logo

jihong008
/
musicgen-melody-lora-punk-colab

PEFT
Safetensors
Generated from Trainer
Model card Files Community
jihong008 commited on
Commit
a81da48
·
verified ·
1 Parent(s): d29a8b8

Training in progress, step 28

Browse files
Files changed (6) hide show
  1. adapter_config.json +10 -10
  2. adapter_model.safetensors +1 -1
  3. all_results.json +4 -4
  4. train_results.json +4 -4
  5. trainer_state.json +12 -12
  6. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -23,21 +23,21 @@
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
- "lm_heads.2",
27
- "lm_heads.3",
28
  "v_proj",
29
- "embed_tokens.3",
 
 
30
  "embed_tokens.1",
31
- "lm_heads.1",
32
- "lm_heads.0",
33
- "out_proj",
34
  "q_proj",
35
- "fc2",
36
  "enc_to_dec_proj",
 
 
 
 
 
 
37
  "k_proj",
38
- "embed_tokens.0",
39
- "embed_tokens.2",
40
- "audio_enc_to_dec_proj",
41
  "fc1"
42
  ],
43
  "task_type": null,
 
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,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d3ee6f0a532947f286fd10028d7b5ed05cf7581dfdda47040cf5d3989f8da173
3
  size 43594480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fbc9a7cc45bc2049c0744d1dcb44a4e7fc11b71163218cca0038a5ccf48394b
3
  size 43594480
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 3.764705882352941,
3
- "train_loss": 9.197729110717773,
4
- "train_runtime": 36.8812,
5
  "train_samples": 33,
6
- "train_samples_per_second": 3.579,
7
- "train_steps_per_second": 0.217
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
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 3.764705882352941,
3
- "train_loss": 9.197729110717773,
4
- "train_runtime": 36.8812,
5
  "train_samples": 33,
6
- "train_samples_per_second": 3.579,
7
- "train_steps_per_second": 0.217
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
  }
trainer_state.json CHANGED
@@ -10,40 +10,40 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.9411764705882353,
13
- "grad_norm": 0.8986203670501709,
14
  "learning_rate": 0.00015000000000000001,
15
- "loss": 9.5251,
16
  "step": 2
17
  },
18
  {
19
  "epoch": 1.8823529411764706,
20
- "grad_norm": 1.1994189023971558,
21
  "learning_rate": 0.0001,
22
- "loss": 9.292,
23
  "step": 4
24
  },
25
  {
26
  "epoch": 2.8235294117647056,
27
- "grad_norm": 1.3807952404022217,
28
  "learning_rate": 5e-05,
29
- "loss": 9.0613,
30
  "step": 6
31
  },
32
  {
33
  "epoch": 3.764705882352941,
34
- "grad_norm": 1.505556583404541,
35
  "learning_rate": 0.0,
36
- "loss": 8.9125,
37
  "step": 8
38
  },
39
  {
40
  "epoch": 3.764705882352941,
41
  "step": 8,
42
  "total_flos": 36858669560664.0,
43
- "train_loss": 9.197729110717773,
44
- "train_runtime": 36.8812,
45
- "train_samples_per_second": 3.579,
46
- "train_steps_per_second": 0.217
47
  }
48
  ],
49
  "logging_steps": 2,
 
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,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3345c3f211bd0d480043830ef6fda7b32c9e127c3cb703d215ec2ad31ebb6527
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dda95e344fbc5fafe01ef7ae8bb96b4c7f86267c4bb377a7ff668174d581b215
3
  size 5304