foureyednymph
commited on
Commit
•
644cce9
1
Parent(s):
918773a
End of training
Browse files- README.md +3 -1
- trainer_state.json +33 -40
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
|
7 |
model-index:
|
@@ -14,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
# musicgen-melody-lora-pop-colab-epoch10
|
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 |
|
|
|
2 |
license: cc-by-nc-4.0
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
+
- text-to-audio
|
6 |
+
- afterschool-large
|
7 |
- generated_from_trainer
|
8 |
base_model: facebook/musicgen-melody
|
9 |
model-index:
|
|
|
16 |
|
17 |
# musicgen-melody-lora-pop-colab-epoch10
|
18 |
|
19 |
+
This model is a fine-tuned version of [facebook/musicgen-melody](https://huggingface.co/facebook/musicgen-melody) on the foureyednymph/afterschool-large dataset.
|
20 |
|
21 |
## Model description
|
22 |
|
trainer_state.json
CHANGED
@@ -1,69 +1,62 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
-
"epoch":
|
13 |
-
"grad_norm": 1.
|
14 |
-
"learning_rate": 0.
|
15 |
-
"loss": 9.
|
16 |
"step": 2
|
17 |
},
|
18 |
{
|
19 |
-
"epoch":
|
20 |
-
"grad_norm": 1.
|
21 |
-
"learning_rate": 0.
|
22 |
-
"loss": 9.
|
23 |
"step": 4
|
24 |
},
|
25 |
{
|
26 |
-
"epoch":
|
27 |
-
"grad_norm": 1.
|
28 |
-
"learning_rate":
|
29 |
-
"loss": 8.
|
30 |
"step": 6
|
31 |
},
|
32 |
{
|
33 |
-
"epoch":
|
34 |
-
"grad_norm": 1.
|
35 |
-
"learning_rate":
|
36 |
-
"loss": 8.
|
37 |
"step": 8
|
38 |
},
|
39 |
{
|
40 |
-
"epoch":
|
41 |
-
"grad_norm": 2.
|
42 |
-
"learning_rate": 3.3333333333333335e-05,
|
43 |
-
"loss": 8.1063,
|
44 |
-
"step": 10
|
45 |
-
},
|
46 |
-
{
|
47 |
-
"epoch": 3.84,
|
48 |
-
"grad_norm": 1.7291364669799805,
|
49 |
"learning_rate": 0.0,
|
50 |
-
"loss":
|
51 |
-
"step":
|
52 |
},
|
53 |
{
|
54 |
-
"epoch":
|
55 |
-
"step":
|
56 |
-
"total_flos":
|
57 |
-
"train_loss": 8.
|
58 |
-
"train_runtime":
|
59 |
-
"train_samples_per_second":
|
60 |
-
"train_steps_per_second": 0.
|
61 |
}
|
62 |
],
|
63 |
"logging_steps": 2,
|
64 |
-
"max_steps":
|
65 |
"num_input_tokens_seen": 0,
|
66 |
-
"num_train_epochs":
|
67 |
"save_steps": 500,
|
68 |
"stateful_callbacks": {
|
69 |
"TrainerControl": {
|
@@ -77,8 +70,8 @@
|
|
77 |
"attributes": {}
|
78 |
}
|
79 |
},
|
80 |
-
"total_flos":
|
81 |
-
"train_batch_size":
|
82 |
"trial_name": null,
|
83 |
"trial_params": null
|
84 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 6.153846153846154,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 10,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 1.2307692307692308,
|
13 |
+
"grad_norm": 1.047078013420105,
|
14 |
+
"learning_rate": 0.00016,
|
15 |
+
"loss": 9.5015,
|
16 |
"step": 2
|
17 |
},
|
18 |
{
|
19 |
+
"epoch": 2.4615384615384617,
|
20 |
+
"grad_norm": 1.4213268756866455,
|
21 |
+
"learning_rate": 0.00012,
|
22 |
+
"loss": 9.1618,
|
23 |
"step": 4
|
24 |
},
|
25 |
{
|
26 |
+
"epoch": 3.6923076923076925,
|
27 |
+
"grad_norm": 1.623157024383545,
|
28 |
+
"learning_rate": 8e-05,
|
29 |
+
"loss": 8.7262,
|
30 |
"step": 6
|
31 |
},
|
32 |
{
|
33 |
+
"epoch": 4.923076923076923,
|
34 |
+
"grad_norm": 1.7331207990646362,
|
35 |
+
"learning_rate": 4e-05,
|
36 |
+
"loss": 8.3712,
|
37 |
"step": 8
|
38 |
},
|
39 |
{
|
40 |
+
"epoch": 6.153846153846154,
|
41 |
+
"grad_norm": 2.034743547439575,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
42 |
"learning_rate": 0.0,
|
43 |
+
"loss": 8.0607,
|
44 |
+
"step": 10
|
45 |
},
|
46 |
{
|
47 |
+
"epoch": 6.153846153846154,
|
48 |
+
"step": 10,
|
49 |
+
"total_flos": 86603100263016.0,
|
50 |
+
"train_loss": 8.76425724029541,
|
51 |
+
"train_runtime": 482.9591,
|
52 |
+
"train_samples_per_second": 1.015,
|
53 |
+
"train_steps_per_second": 0.021
|
54 |
}
|
55 |
],
|
56 |
"logging_steps": 2,
|
57 |
+
"max_steps": 10,
|
58 |
"num_input_tokens_seen": 0,
|
59 |
+
"num_train_epochs": 10,
|
60 |
"save_steps": 500,
|
61 |
"stateful_callbacks": {
|
62 |
"TrainerControl": {
|
|
|
70 |
"attributes": {}
|
71 |
}
|
72 |
},
|
73 |
+
"total_flos": 86603100263016.0,
|
74 |
+
"train_batch_size": 4,
|
75 |
"trial_name": null,
|
76 |
"trial_params": null
|
77 |
}
|