DevPanda004
commited on
End of training
Browse files- README.md +3 -1
- trainer_state.json +21 -56
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-small-ft1
|
@@ -14,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
# musicgen-small-ft1
|
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 |
+
- indian
|
8 |
- generated_from_trainer
|
9 |
model-index:
|
10 |
- name: musicgen-small-ft1
|
|
|
16 |
|
17 |
# musicgen-small-ft1
|
18 |
|
19 |
+
This model is a fine-tuned version of [facebook/musicgen-small](https://huggingface.co/facebook/musicgen-small) on the DevPanda004/indian-music-and-metadata-3 dataset.
|
20 |
|
21 |
## Model description
|
22 |
|
trainer_state.json
CHANGED
@@ -1,76 +1,41 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 1.
|
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": 0.
|
13 |
-
"grad_norm":
|
14 |
-
"learning_rate": 0.
|
15 |
-
"loss": 9.
|
16 |
"step": 2
|
17 |
},
|
18 |
{
|
19 |
-
"epoch": 0
|
20 |
-
"grad_norm": 23.
|
21 |
-
"learning_rate": 0.00014285714285714287,
|
22 |
-
"loss": 8.8963,
|
23 |
-
"step": 4
|
24 |
-
},
|
25 |
-
{
|
26 |
-
"epoch": 0.7619047619047619,
|
27 |
-
"grad_norm": 19.974302291870117,
|
28 |
-
"learning_rate": 0.00011428571428571428,
|
29 |
-
"loss": 8.297,
|
30 |
-
"step": 6
|
31 |
-
},
|
32 |
-
{
|
33 |
-
"epoch": 1.126984126984127,
|
34 |
-
"grad_norm": 51.25042724609375,
|
35 |
-
"learning_rate": 8.571428571428571e-05,
|
36 |
-
"loss": 9.9734,
|
37 |
-
"step": 8
|
38 |
-
},
|
39 |
-
{
|
40 |
-
"epoch": 1.380952380952381,
|
41 |
-
"grad_norm": 21.681840896606445,
|
42 |
-
"learning_rate": 5.714285714285714e-05,
|
43 |
-
"loss": 7.6149,
|
44 |
-
"step": 10
|
45 |
-
},
|
46 |
-
{
|
47 |
-
"epoch": 1.6349206349206349,
|
48 |
-
"grad_norm": 17.052457809448242,
|
49 |
-
"learning_rate": 2.857142857142857e-05,
|
50 |
-
"loss": 7.5471,
|
51 |
-
"step": 12
|
52 |
-
},
|
53 |
-
{
|
54 |
-
"epoch": 1.8888888888888888,
|
55 |
-
"grad_norm": 11.491819381713867,
|
56 |
"learning_rate": 0.0,
|
57 |
-
"loss":
|
58 |
-
"step":
|
59 |
},
|
60 |
{
|
61 |
-
"epoch": 1.
|
62 |
-
"step":
|
63 |
-
"total_flos":
|
64 |
-
"train_loss":
|
65 |
-
"train_runtime":
|
66 |
-
"train_samples_per_second": 2.
|
67 |
-
"train_steps_per_second": 0.
|
68 |
}
|
69 |
],
|
70 |
"logging_steps": 2,
|
71 |
-
"max_steps":
|
72 |
"num_input_tokens_seen": 0,
|
73 |
-
"num_train_epochs":
|
74 |
"save_steps": 500,
|
75 |
"stateful_callbacks": {
|
76 |
"TrainerControl": {
|
@@ -84,8 +49,8 @@
|
|
84 |
"attributes": {}
|
85 |
}
|
86 |
},
|
87 |
-
"total_flos":
|
88 |
-
"train_batch_size":
|
89 |
"trial_name": null,
|
90 |
"trial_params": null
|
91 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 4,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.5,
|
13 |
+
"grad_norm": 21.075090408325195,
|
14 |
+
"learning_rate": 0.0001,
|
15 |
+
"loss": 9.6178,
|
16 |
"step": 2
|
17 |
},
|
18 |
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"grad_norm": 23.55191421508789,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
21 |
"learning_rate": 0.0,
|
22 |
+
"loss": 9.0839,
|
23 |
+
"step": 4
|
24 |
},
|
25 |
{
|
26 |
+
"epoch": 1.0,
|
27 |
+
"step": 4,
|
28 |
+
"total_flos": 102769451882784.0,
|
29 |
+
"train_loss": 9.350837230682373,
|
30 |
+
"train_runtime": 237.6937,
|
31 |
+
"train_samples_per_second": 2.104,
|
32 |
+
"train_steps_per_second": 0.017
|
33 |
}
|
34 |
],
|
35 |
"logging_steps": 2,
|
36 |
+
"max_steps": 4,
|
37 |
"num_input_tokens_seen": 0,
|
38 |
+
"num_train_epochs": 1,
|
39 |
"save_steps": 500,
|
40 |
"stateful_callbacks": {
|
41 |
"TrainerControl": {
|
|
|
49 |
"attributes": {}
|
50 |
}
|
51 |
},
|
52 |
+
"total_flos": 102769451882784.0,
|
53 |
+
"train_batch_size": 16,
|
54 |
"trial_name": null,
|
55 |
"trial_params": null
|
56 |
}
|