sanchit-gandhi HF staff commited on
Commit
f6df1e6
1 Parent(s): 8b04577

End of training

Browse files
Files changed (5) hide show
  1. README.md +7 -1
  2. all_results.json +16 -0
  3. eval_results.json +10 -0
  4. train_results.json +9 -0
  5. trainer_state.json +189 -0
README.md CHANGED
@@ -2,6 +2,8 @@
2
  license: cc-by-nc-4.0
3
  library_name: peft
4
  tags:
 
 
5
  - generated_from_trainer
6
  base_model: facebook/musicgen-melody-large
7
  model-index:
@@ -16,7 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
16
  [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/sanchit-gandhi/black-eyed-peas/runs/lad7ytx9)
17
  # black-eyed-peas-v1-crafted-prompt-3-epochs-text-only-piano-prompts
18
 
19
- This model is a fine-tuned version of [facebook/musicgen-melody-large](https://huggingface.co/facebook/musicgen-melody-large) on an unknown dataset.
 
 
 
 
20
 
21
  ## Model description
22
 
 
2
  license: cc-by-nc-4.0
3
  library_name: peft
4
  tags:
5
+ - text-to-audio
6
+ - sweet-dreambooths/black-eyed-peas-v1-piano-prompts
7
  - generated_from_trainer
8
  base_model: facebook/musicgen-melody-large
9
  model-index:
 
18
  [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/sanchit-gandhi/black-eyed-peas/runs/lad7ytx9)
19
  # black-eyed-peas-v1-crafted-prompt-3-epochs-text-only-piano-prompts
20
 
21
+ This model is a fine-tuned version of [facebook/musicgen-melody-large](https://huggingface.co/facebook/musicgen-melody-large) on the SWEET-DREAMBOOTHS/BLACK-EYED-PEAS-V1-PIANO-PROMPTS - DEFAULT dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 3.0926
24
+ - Text Cosine Sim: 0.4584
25
+ - Audio Cosine Sim: 0.5483
26
 
27
  ## Model description
28
 
all_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.6879999999999997,
3
+ "eval_audio_cosine_sim": 0.5482687950134277,
4
+ "eval_loss": 3.092636823654175,
5
+ "eval_runtime": 967.8097,
6
+ "eval_samples": 12,
7
+ "eval_samples_per_second": 0.012,
8
+ "eval_steps_per_second": 0.012,
9
+ "eval_text_cosine_sim": 0.4583999812602997,
10
+ "total_flos": 247581948423984.0,
11
+ "train_loss": 9.755998475211006,
12
+ "train_runtime": 4065.4818,
13
+ "train_samples": 125,
14
+ "train_samples_per_second": 0.092,
15
+ "train_steps_per_second": 0.005
16
+ }
eval_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.6879999999999997,
3
+ "eval_audio_cosine_sim": 0.5482687950134277,
4
+ "eval_loss": 3.092636823654175,
5
+ "eval_runtime": 967.8097,
6
+ "eval_samples": 12,
7
+ "eval_samples_per_second": 0.012,
8
+ "eval_steps_per_second": 0.012,
9
+ "eval_text_cosine_sim": 0.4583999812602997
10
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.6879999999999997,
3
+ "total_flos": 247581948423984.0,
4
+ "train_loss": 9.755998475211006,
5
+ "train_runtime": 4065.4818,
6
+ "train_samples": 125,
7
+ "train_samples_per_second": 0.092,
8
+ "train_steps_per_second": 0.005
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,189 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.6879999999999997,
5
+ "eval_steps": 30,
6
+ "global_step": 21,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.128,
13
+ "grad_norm": 1.7691179513931274,
14
+ "learning_rate": 2.857142857142857e-05,
15
+ "loss": 10.1767,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.256,
20
+ "grad_norm": 1.533618450164795,
21
+ "learning_rate": 2.7142857142857144e-05,
22
+ "loss": 10.1053,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.384,
27
+ "grad_norm": 1.8578174114227295,
28
+ "learning_rate": 2.5714285714285714e-05,
29
+ "loss": 10.1344,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.512,
34
+ "grad_norm": 1.893380880355835,
35
+ "learning_rate": 2.4285714285714288e-05,
36
+ "loss": 10.0509,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.64,
41
+ "grad_norm": 1.9985988140106201,
42
+ "learning_rate": 2.2857142857142858e-05,
43
+ "loss": 9.9777,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.768,
48
+ "grad_norm": 2.318725109100342,
49
+ "learning_rate": 2.1428571428571428e-05,
50
+ "loss": 10.0346,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.896,
55
+ "grad_norm": 2.3330538272857666,
56
+ "learning_rate": 1.9999999999999998e-05,
57
+ "loss": 10.0432,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 1.024,
62
+ "grad_norm": 2.386380672454834,
63
+ "learning_rate": 1.8571428571428572e-05,
64
+ "loss": 9.9037,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 1.152,
69
+ "grad_norm": 2.525782346725464,
70
+ "learning_rate": 1.7142857142857142e-05,
71
+ "loss": 9.8192,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 1.28,
76
+ "grad_norm": 2.6987812519073486,
77
+ "learning_rate": 1.5714285714285715e-05,
78
+ "loss": 9.7915,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 1.408,
83
+ "grad_norm": 2.681642532348633,
84
+ "learning_rate": 1.4285714285714285e-05,
85
+ "loss": 9.6911,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 1.536,
90
+ "grad_norm": 2.9579291343688965,
91
+ "learning_rate": 1.2857142857142857e-05,
92
+ "loss": 9.6579,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 1.6640000000000001,
97
+ "grad_norm": 3.073641300201416,
98
+ "learning_rate": 1.1428571428571429e-05,
99
+ "loss": 9.6782,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 1.792,
104
+ "grad_norm": 3.179450035095215,
105
+ "learning_rate": 9.999999999999999e-06,
106
+ "loss": 9.5699,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 1.92,
111
+ "grad_norm": 3.1641924381256104,
112
+ "learning_rate": 8.571428571428571e-06,
113
+ "loss": 9.5342,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 2.048,
118
+ "grad_norm": 3.2276086807250977,
119
+ "learning_rate": 7.142857142857143e-06,
120
+ "loss": 9.5571,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 2.176,
125
+ "grad_norm": 3.0624403953552246,
126
+ "learning_rate": 5.7142857142857145e-06,
127
+ "loss": 9.4244,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 2.304,
132
+ "grad_norm": 3.3281595706939697,
133
+ "learning_rate": 4.2857142857142855e-06,
134
+ "loss": 9.4145,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 2.432,
139
+ "grad_norm": 3.577859878540039,
140
+ "learning_rate": 2.8571428571428573e-06,
141
+ "loss": 9.499,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 2.56,
146
+ "grad_norm": 3.7756576538085938,
147
+ "learning_rate": 1.4285714285714286e-06,
148
+ "loss": 9.4644,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 2.6879999999999997,
153
+ "grad_norm": 3.3084795475006104,
154
+ "learning_rate": 0.0,
155
+ "loss": 9.348,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 2.6879999999999997,
160
+ "step": 21,
161
+ "total_flos": 247581948423984.0,
162
+ "train_loss": 9.755998475211006,
163
+ "train_runtime": 4065.4818,
164
+ "train_samples_per_second": 0.092,
165
+ "train_steps_per_second": 0.005
166
+ }
167
+ ],
168
+ "logging_steps": 1.0,
169
+ "max_steps": 21,
170
+ "num_input_tokens_seen": 0,
171
+ "num_train_epochs": 3,
172
+ "save_steps": 500,
173
+ "stateful_callbacks": {
174
+ "TrainerControl": {
175
+ "args": {
176
+ "should_epoch_stop": false,
177
+ "should_evaluate": false,
178
+ "should_log": false,
179
+ "should_save": false,
180
+ "should_training_stop": false
181
+ },
182
+ "attributes": {}
183
+ }
184
+ },
185
+ "total_flos": 247581948423984.0,
186
+ "train_batch_size": 1,
187
+ "trial_name": null,
188
+ "trial_params": null
189
+ }