memepottaboah
commited on
End of training
Browse files- README.md +3 -1
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +168 -0
README.md
CHANGED
@@ -3,6 +3,8 @@ library_name: peft
|
|
3 |
license: cc-by-nc-4.0
|
4 |
base_model: facebook/musicgen-small
|
5 |
tags:
|
|
|
|
|
6 |
- generated_from_trainer
|
7 |
model-index:
|
8 |
- name: musicgen-80snewwave-tiny
|
@@ -14,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
# musicgen-80snewwave-tiny
|
16 |
|
17 |
-
This model is a fine-tuned version of [facebook/musicgen-small](https://huggingface.co/facebook/musicgen-small) on
|
18 |
|
19 |
## Model description
|
20 |
|
|
|
3 |
license: cc-by-nc-4.0
|
4 |
base_model: facebook/musicgen-small
|
5 |
tags:
|
6 |
+
- text-to-audio
|
7 |
+
- memepottaboah/80snewwave
|
8 |
- generated_from_trainer
|
9 |
model-index:
|
10 |
- name: musicgen-80snewwave-tiny
|
|
|
16 |
|
17 |
# musicgen-80snewwave-tiny
|
18 |
|
19 |
+
This model is a fine-tuned version of [facebook/musicgen-small](https://huggingface.co/facebook/musicgen-small) on the MEMEPOTTABOAH/80SNEWWAVE - DEFAULT dataset.
|
20 |
|
21 |
## Model description
|
22 |
|
all_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"total_flos": 3916062733824.0,
|
4 |
+
"train_loss": 7.966650274064806,
|
5 |
+
"train_runtime": 225.7222,
|
6 |
+
"train_samples": 96,
|
7 |
+
"train_samples_per_second": 1.276,
|
8 |
+
"train_steps_per_second": 0.08
|
9 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"total_flos": 3916062733824.0,
|
4 |
+
"train_loss": 7.966650274064806,
|
5 |
+
"train_runtime": 225.7222,
|
6 |
+
"train_samples": 96,
|
7 |
+
"train_samples_per_second": 1.276,
|
8 |
+
"train_steps_per_second": 0.08
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,168 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 18,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.16666666666666666,
|
13 |
+
"grad_norm": 9.99618148803711,
|
14 |
+
"learning_rate": 0.00018888888888888888,
|
15 |
+
"loss": 9.3055,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.3333333333333333,
|
20 |
+
"grad_norm": NaN,
|
21 |
+
"learning_rate": 0.00018888888888888888,
|
22 |
+
"loss": 9.113,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.5,
|
27 |
+
"grad_norm": 11.599903106689453,
|
28 |
+
"learning_rate": 0.00017777777777777779,
|
29 |
+
"loss": 9.0899,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.6666666666666666,
|
34 |
+
"grad_norm": 19.80902099609375,
|
35 |
+
"learning_rate": 0.0001666666666666667,
|
36 |
+
"loss": 8.8174,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.8333333333333334,
|
41 |
+
"grad_norm": 25.931373596191406,
|
42 |
+
"learning_rate": 0.00015555555555555556,
|
43 |
+
"loss": 8.4004,
|
44 |
+
"step": 5
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.0,
|
48 |
+
"grad_norm": 16.526399612426758,
|
49 |
+
"learning_rate": 0.00014444444444444444,
|
50 |
+
"loss": 8.0775,
|
51 |
+
"step": 6
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 1.1666666666666667,
|
55 |
+
"grad_norm": 9.473867416381836,
|
56 |
+
"learning_rate": 0.00013333333333333334,
|
57 |
+
"loss": 7.8921,
|
58 |
+
"step": 7
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 1.3333333333333333,
|
62 |
+
"grad_norm": 7.662047863006592,
|
63 |
+
"learning_rate": 0.00012222222222222224,
|
64 |
+
"loss": 7.7038,
|
65 |
+
"step": 8
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 1.5,
|
69 |
+
"grad_norm": 7.1017746925354,
|
70 |
+
"learning_rate": 0.00011111111111111112,
|
71 |
+
"loss": 7.6557,
|
72 |
+
"step": 9
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 1.6666666666666665,
|
76 |
+
"grad_norm": 6.771383285522461,
|
77 |
+
"learning_rate": 0.0001,
|
78 |
+
"loss": 7.6096,
|
79 |
+
"step": 10
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 1.8333333333333335,
|
83 |
+
"grad_norm": 6.0268144607543945,
|
84 |
+
"learning_rate": 8.888888888888889e-05,
|
85 |
+
"loss": 7.5339,
|
86 |
+
"step": 11
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 2.0,
|
90 |
+
"grad_norm": 5.064662456512451,
|
91 |
+
"learning_rate": 7.777777777777778e-05,
|
92 |
+
"loss": 7.5378,
|
93 |
+
"step": 12
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 2.1666666666666665,
|
97 |
+
"grad_norm": 4.9883012771606445,
|
98 |
+
"learning_rate": 6.666666666666667e-05,
|
99 |
+
"loss": 7.4656,
|
100 |
+
"step": 13
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 2.3333333333333335,
|
104 |
+
"grad_norm": 4.80706787109375,
|
105 |
+
"learning_rate": 5.555555555555556e-05,
|
106 |
+
"loss": 7.4576,
|
107 |
+
"step": 14
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 2.5,
|
111 |
+
"grad_norm": 5.370234489440918,
|
112 |
+
"learning_rate": 4.4444444444444447e-05,
|
113 |
+
"loss": 7.4857,
|
114 |
+
"step": 15
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 2.6666666666666665,
|
118 |
+
"grad_norm": 4.275276184082031,
|
119 |
+
"learning_rate": 3.3333333333333335e-05,
|
120 |
+
"loss": 7.4279,
|
121 |
+
"step": 16
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 2.8333333333333335,
|
125 |
+
"grad_norm": 3.863494396209717,
|
126 |
+
"learning_rate": 2.2222222222222223e-05,
|
127 |
+
"loss": 7.45,
|
128 |
+
"step": 17
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 3.0,
|
132 |
+
"grad_norm": 4.486358165740967,
|
133 |
+
"learning_rate": 1.1111111111111112e-05,
|
134 |
+
"loss": 7.3764,
|
135 |
+
"step": 18
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 3.0,
|
139 |
+
"step": 18,
|
140 |
+
"total_flos": 3916062733824.0,
|
141 |
+
"train_loss": 7.966650274064806,
|
142 |
+
"train_runtime": 225.7222,
|
143 |
+
"train_samples_per_second": 1.276,
|
144 |
+
"train_steps_per_second": 0.08
|
145 |
+
}
|
146 |
+
],
|
147 |
+
"logging_steps": 1.0,
|
148 |
+
"max_steps": 18,
|
149 |
+
"num_input_tokens_seen": 0,
|
150 |
+
"num_train_epochs": 3,
|
151 |
+
"save_steps": 500,
|
152 |
+
"stateful_callbacks": {
|
153 |
+
"TrainerControl": {
|
154 |
+
"args": {
|
155 |
+
"should_epoch_stop": false,
|
156 |
+
"should_evaluate": false,
|
157 |
+
"should_log": false,
|
158 |
+
"should_save": true,
|
159 |
+
"should_training_stop": true
|
160 |
+
},
|
161 |
+
"attributes": {}
|
162 |
+
}
|
163 |
+
},
|
164 |
+
"total_flos": 3916062733824.0,
|
165 |
+
"train_batch_size": 2,
|
166 |
+
"trial_name": null,
|
167 |
+
"trial_params": null
|
168 |
+
}
|