End of training
Browse files- README.md +3 -1
- trainer_state.json +140 -0
README.md
CHANGED
@@ -3,6 +3,8 @@ library_name: peft
|
|
3 |
license: cc-by-nc-4.0
|
4 |
base_model: facebook/musicgen-melody
|
5 |
tags:
|
|
|
|
|
6 |
- generated_from_trainer
|
7 |
model-index:
|
8 |
- name: musicgen-melody-lora-dnb-colab-gs-4-lr-0.0001
|
@@ -14,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
# musicgen-melody-lora-dnb-colab-gs-4-lr-0.0001
|
16 |
|
17 |
-
This model is a fine-tuned version of [facebook/musicgen-melody](https://huggingface.co/facebook/musicgen-melody) on
|
18 |
|
19 |
## Model description
|
20 |
|
|
|
3 |
license: cc-by-nc-4.0
|
4 |
base_model: facebook/musicgen-melody
|
5 |
tags:
|
6 |
+
- text-to-audio
|
7 |
+
- dnb
|
8 |
- generated_from_trainer
|
9 |
model-index:
|
10 |
- name: musicgen-melody-lora-dnb-colab-gs-4-lr-0.0001
|
|
|
16 |
|
17 |
# musicgen-melody-lora-dnb-colab-gs-4-lr-0.0001
|
18 |
|
19 |
+
This model is a fine-tuned version of [facebook/musicgen-melody](https://huggingface.co/facebook/musicgen-melody) on the istvanj/ncs-dnb dataset.
|
20 |
|
21 |
## Model description
|
22 |
|
trainer_state.json
ADDED
@@ -0,0 +1,140 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.533333333333333,
|
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": 0.26666666666666666,
|
13 |
+
"grad_norm": 7.743002891540527,
|
14 |
+
"learning_rate": 9.285714285714286e-05,
|
15 |
+
"loss": 9.6715,
|
16 |
+
"step": 2
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.5333333333333333,
|
20 |
+
"grad_norm": 10.184503555297852,
|
21 |
+
"learning_rate": 8.571428571428571e-05,
|
22 |
+
"loss": 9.4915,
|
23 |
+
"step": 4
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.8,
|
27 |
+
"grad_norm": 11.913558006286621,
|
28 |
+
"learning_rate": 7.857142857142858e-05,
|
29 |
+
"loss": 9.2876,
|
30 |
+
"step": 6
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 1.0,
|
34 |
+
"grad_norm": 8.506986618041992,
|
35 |
+
"learning_rate": 7.142857142857143e-05,
|
36 |
+
"loss": 6.794,
|
37 |
+
"step": 8
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 1.2666666666666666,
|
41 |
+
"grad_norm": 16.136363983154297,
|
42 |
+
"learning_rate": 6.428571428571429e-05,
|
43 |
+
"loss": 8.7684,
|
44 |
+
"step": 10
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.5333333333333332,
|
48 |
+
"grad_norm": 17.197826385498047,
|
49 |
+
"learning_rate": 5.714285714285714e-05,
|
50 |
+
"loss": 8.4057,
|
51 |
+
"step": 12
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 1.8,
|
55 |
+
"grad_norm": 17.818504333496094,
|
56 |
+
"learning_rate": 5e-05,
|
57 |
+
"loss": 8.0786,
|
58 |
+
"step": 14
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 2.0,
|
62 |
+
"grad_norm": 7.011114120483398,
|
63 |
+
"learning_rate": 4.2857142857142856e-05,
|
64 |
+
"loss": 5.9957,
|
65 |
+
"step": 16
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 2.2666666666666666,
|
69 |
+
"grad_norm": 15.747384071350098,
|
70 |
+
"learning_rate": 3.571428571428572e-05,
|
71 |
+
"loss": 7.8072,
|
72 |
+
"step": 18
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 2.533333333333333,
|
76 |
+
"grad_norm": 10.231032371520996,
|
77 |
+
"learning_rate": 2.857142857142857e-05,
|
78 |
+
"loss": 7.7025,
|
79 |
+
"step": 20
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 2.8,
|
83 |
+
"grad_norm": 14.580495834350586,
|
84 |
+
"learning_rate": 2.1428571428571428e-05,
|
85 |
+
"loss": 7.6752,
|
86 |
+
"step": 22
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 3.0,
|
90 |
+
"grad_norm": 4.722076416015625,
|
91 |
+
"learning_rate": 1.4285714285714285e-05,
|
92 |
+
"loss": 5.6959,
|
93 |
+
"step": 24
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 3.2666666666666666,
|
97 |
+
"grad_norm": 8.84581470489502,
|
98 |
+
"learning_rate": 7.142857142857143e-06,
|
99 |
+
"loss": 7.5967,
|
100 |
+
"step": 26
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 3.533333333333333,
|
104 |
+
"grad_norm": 8.689848899841309,
|
105 |
+
"learning_rate": 0.0,
|
106 |
+
"loss": 7.5943,
|
107 |
+
"step": 28
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 3.533333333333333,
|
111 |
+
"step": 28,
|
112 |
+
"total_flos": 108812813622552.0,
|
113 |
+
"train_loss": 7.897485290254865,
|
114 |
+
"train_runtime": 759.4252,
|
115 |
+
"train_samples_per_second": 0.632,
|
116 |
+
"train_steps_per_second": 0.037
|
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,
|
124 |
+
"stateful_callbacks": {
|
125 |
+
"TrainerControl": {
|
126 |
+
"args": {
|
127 |
+
"should_epoch_stop": false,
|
128 |
+
"should_evaluate": false,
|
129 |
+
"should_log": false,
|
130 |
+
"should_save": true,
|
131 |
+
"should_training_stop": true
|
132 |
+
},
|
133 |
+
"attributes": {}
|
134 |
+
}
|
135 |
+
},
|
136 |
+
"total_flos": 108812813622552.0,
|
137 |
+
"train_batch_size": 2,
|
138 |
+
"trial_name": null,
|
139 |
+
"trial_params": null
|
140 |
+
}
|