End of training
Browse files- README.md +3 -1
- trainer_state.json +53 -32
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-baishidaoren-epoch3
|
@@ -14,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
# musicgen-melody-lora-baishidaoren-epoch3
|
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 |
+
- baoshidaoren_music_snippets
|
8 |
- generated_from_trainer
|
9 |
model-index:
|
10 |
- name: musicgen-melody-lora-baishidaoren-epoch3
|
|
|
16 |
|
17 |
# musicgen-melody-lora-baishidaoren-epoch3
|
18 |
|
19 |
+
This model is a fine-tuned version of [facebook/musicgen-melody](https://huggingface.co/facebook/musicgen-melody) on the zuona/baoshidaoren_music_snippets dataset.
|
20 |
|
21 |
## Model description
|
22 |
|
trainer_state.json
CHANGED
@@ -1,76 +1,97 @@
|
|
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": 0.25396825396825395,
|
13 |
-
"grad_norm":
|
14 |
-
"learning_rate": 0.
|
15 |
-
"loss": 71.
|
16 |
"step": 2
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.5079365079365079,
|
20 |
-
"grad_norm":
|
21 |
-
"learning_rate": 0.
|
22 |
-
"loss":
|
23 |
"step": 4
|
24 |
},
|
25 |
{
|
26 |
"epoch": 0.7619047619047619,
|
27 |
-
"grad_norm":
|
28 |
-
"learning_rate": 0.
|
29 |
-
"loss":
|
30 |
"step": 6
|
31 |
},
|
32 |
{
|
33 |
"epoch": 1.126984126984127,
|
34 |
-
"grad_norm":
|
35 |
-
"learning_rate": 0.
|
36 |
-
"loss":
|
37 |
"step": 8
|
38 |
},
|
39 |
{
|
40 |
"epoch": 1.380952380952381,
|
41 |
-
"grad_norm":
|
42 |
-
"learning_rate":
|
43 |
-
"loss":
|
44 |
"step": 10
|
45 |
},
|
46 |
{
|
47 |
"epoch": 1.6349206349206349,
|
48 |
-
"grad_norm":
|
49 |
-
"learning_rate":
|
50 |
-
"loss":
|
51 |
"step": 12
|
52 |
},
|
53 |
{
|
54 |
"epoch": 1.8888888888888888,
|
55 |
-
"grad_norm": 21.
|
56 |
-
"learning_rate":
|
57 |
-
"loss":
|
58 |
"step": 14
|
59 |
},
|
60 |
{
|
61 |
-
"epoch":
|
62 |
-
"
|
63 |
-
"
|
64 |
-
"
|
65 |
-
"
|
66 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
67 |
"train_steps_per_second": 0.027
|
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": {
|
@@ -84,7 +105,7 @@
|
|
84 |
"attributes": {}
|
85 |
}
|
86 |
},
|
87 |
-
"total_flos":
|
88 |
"train_batch_size": 2,
|
89 |
"trial_name": null,
|
90 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.888888888888889,
|
5 |
"eval_steps": 500,
|
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": 0.25396825396825395,
|
13 |
+
"grad_norm": 22.455032348632812,
|
14 |
+
"learning_rate": 0.00018095238095238095,
|
15 |
+
"loss": 71.5526,
|
16 |
"step": 2
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.5079365079365079,
|
20 |
+
"grad_norm": NaN,
|
21 |
+
"learning_rate": 0.00018095238095238095,
|
22 |
+
"loss": 68.4573,
|
23 |
"step": 4
|
24 |
},
|
25 |
{
|
26 |
"epoch": 0.7619047619047619,
|
27 |
+
"grad_norm": 27.567764282226562,
|
28 |
+
"learning_rate": 0.00016190476190476192,
|
29 |
+
"loss": 66.9582,
|
30 |
"step": 6
|
31 |
},
|
32 |
{
|
33 |
"epoch": 1.126984126984127,
|
34 |
+
"grad_norm": 61.912845611572266,
|
35 |
+
"learning_rate": 0.00014285714285714287,
|
36 |
+
"loss": 78.8634,
|
37 |
"step": 8
|
38 |
},
|
39 |
{
|
40 |
"epoch": 1.380952380952381,
|
41 |
+
"grad_norm": 38.26054000854492,
|
42 |
+
"learning_rate": 0.0001238095238095238,
|
43 |
+
"loss": 53.5637,
|
44 |
"step": 10
|
45 |
},
|
46 |
{
|
47 |
"epoch": 1.6349206349206349,
|
48 |
+
"grad_norm": 19.41400146484375,
|
49 |
+
"learning_rate": 0.00010476190476190477,
|
50 |
+
"loss": 47.919,
|
51 |
"step": 12
|
52 |
},
|
53 |
{
|
54 |
"epoch": 1.8888888888888888,
|
55 |
+
"grad_norm": 21.822195053100586,
|
56 |
+
"learning_rate": 8.571428571428571e-05,
|
57 |
+
"loss": 47.9407,
|
58 |
"step": 14
|
59 |
},
|
60 |
{
|
61 |
+
"epoch": 2.253968253968254,
|
62 |
+
"grad_norm": 18.68866729736328,
|
63 |
+
"learning_rate": 6.666666666666667e-05,
|
64 |
+
"loss": 63.3071,
|
65 |
+
"step": 16
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 2.507936507936508,
|
69 |
+
"grad_norm": 28.52600860595703,
|
70 |
+
"learning_rate": 4.761904761904762e-05,
|
71 |
+
"loss": 43.1297,
|
72 |
+
"step": 18
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 2.761904761904762,
|
76 |
+
"grad_norm": 12.20601749420166,
|
77 |
+
"learning_rate": 2.857142857142857e-05,
|
78 |
+
"loss": 43.0936,
|
79 |
+
"step": 20
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 2.888888888888889,
|
83 |
+
"step": 21,
|
84 |
+
"total_flos": 331427311589016.0,
|
85 |
+
"train_loss": 57.708736782982236,
|
86 |
+
"train_runtime": 785.4183,
|
87 |
+
"train_samples_per_second": 0.481,
|
88 |
"train_steps_per_second": 0.027
|
89 |
}
|
90 |
],
|
91 |
"logging_steps": 2,
|
92 |
+
"max_steps": 21,
|
93 |
"num_input_tokens_seen": 0,
|
94 |
+
"num_train_epochs": 3,
|
95 |
"save_steps": 500,
|
96 |
"stateful_callbacks": {
|
97 |
"TrainerControl": {
|
|
|
105 |
"attributes": {}
|
106 |
}
|
107 |
},
|
108 |
+
"total_flos": 331427311589016.0,
|
109 |
"train_batch_size": 2,
|
110 |
"trial_name": null,
|
111 |
"trial_params": null
|