End of training
Browse files- README.md +6 -1
- all_results.json +15 -0
- eval_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +70 -0
README.md
CHANGED
@@ -3,6 +3,8 @@ base_model: facebook/musicgen-small
|
|
3 |
library_name: peft
|
4 |
license: cc-by-nc-4.0
|
5 |
tags:
|
|
|
|
|
6 |
- generated_from_trainer
|
7 |
model-index:
|
8 |
- name: musicgen-small-lora-afrobeats
|
@@ -15,7 +17,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](None)
|
16 |
# musicgen-small-lora-afrobeats
|
17 |
|
18 |
-
This model is a fine-tuned version of [facebook/musicgen-small](https://huggingface.co/facebook/musicgen-small) on
|
|
|
|
|
|
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
3 |
library_name: peft
|
4 |
license: cc-by-nc-4.0
|
5 |
tags:
|
6 |
+
- text-to-audio
|
7 |
+
- ogbanugot/musicgen
|
8 |
- generated_from_trainer
|
9 |
model-index:
|
10 |
- name: musicgen-small-lora-afrobeats
|
|
|
17 |
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](None)
|
18 |
# musicgen-small-lora-afrobeats
|
19 |
|
20 |
+
This model is a fine-tuned version of [facebook/musicgen-small](https://huggingface.co/facebook/musicgen-small) on the OGBANUGOT/MUSICGEN - DEFAULT dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 2.6942
|
23 |
+
- Clap: 0.1203
|
24 |
|
25 |
## Model description
|
26 |
|
all_results.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"eval_clap": 0.12032415717840195,
|
4 |
+
"eval_loss": 2.694244861602783,
|
5 |
+
"eval_runtime": 35.225,
|
6 |
+
"eval_samples": 2,
|
7 |
+
"eval_samples_per_second": 0.057,
|
8 |
+
"eval_steps_per_second": 0.057,
|
9 |
+
"total_flos": 652677122304.0,
|
10 |
+
"train_loss": 4.660510063171387,
|
11 |
+
"train_runtime": 26.9263,
|
12 |
+
"train_samples": 8,
|
13 |
+
"train_samples_per_second": 1.188,
|
14 |
+
"train_steps_per_second": 0.149
|
15 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"eval_clap": 0.12032415717840195,
|
4 |
+
"eval_loss": 2.694244861602783,
|
5 |
+
"eval_runtime": 35.225,
|
6 |
+
"eval_samples": 2,
|
7 |
+
"eval_samples_per_second": 0.057,
|
8 |
+
"eval_steps_per_second": 0.057
|
9 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"total_flos": 652677122304.0,
|
4 |
+
"train_loss": 4.660510063171387,
|
5 |
+
"train_runtime": 26.9263,
|
6 |
+
"train_samples": 8,
|
7 |
+
"train_samples_per_second": 1.188,
|
8 |
+
"train_steps_per_second": 0.149
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.0,
|
5 |
+
"eval_steps": 25,
|
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": 1.0,
|
13 |
+
"grad_norm": 2.864440679550171,
|
14 |
+
"learning_rate": 0.00015000000000000001,
|
15 |
+
"loss": 4.9451,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 2.0,
|
20 |
+
"grad_norm": 2.771547317504883,
|
21 |
+
"learning_rate": 0.0001,
|
22 |
+
"loss": 4.7639,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 3.0,
|
27 |
+
"grad_norm": 2.7337377071380615,
|
28 |
+
"learning_rate": 5e-05,
|
29 |
+
"loss": 4.5808,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 4.0,
|
34 |
+
"grad_norm": 2.805464267730713,
|
35 |
+
"learning_rate": 0.0,
|
36 |
+
"loss": 4.3522,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 4.0,
|
41 |
+
"step": 4,
|
42 |
+
"total_flos": 652677122304.0,
|
43 |
+
"train_loss": 4.660510063171387,
|
44 |
+
"train_runtime": 26.9263,
|
45 |
+
"train_samples_per_second": 1.188,
|
46 |
+
"train_steps_per_second": 0.149
|
47 |
+
}
|
48 |
+
],
|
49 |
+
"logging_steps": 1.0,
|
50 |
+
"max_steps": 4,
|
51 |
+
"num_input_tokens_seen": 0,
|
52 |
+
"num_train_epochs": 4,
|
53 |
+
"save_steps": 500,
|
54 |
+
"stateful_callbacks": {
|
55 |
+
"TrainerControl": {
|
56 |
+
"args": {
|
57 |
+
"should_epoch_stop": false,
|
58 |
+
"should_evaluate": false,
|
59 |
+
"should_log": false,
|
60 |
+
"should_save": true,
|
61 |
+
"should_training_stop": true
|
62 |
+
},
|
63 |
+
"attributes": {}
|
64 |
+
}
|
65 |
+
},
|
66 |
+
"total_flos": 652677122304.0,
|
67 |
+
"train_batch_size": 2,
|
68 |
+
"trial_name": null,
|
69 |
+
"trial_params": null
|
70 |
+
}
|