End of training
Browse files- README.md +3 -1
- trainer_state.json +35 -14
README.md
CHANGED
@@ -3,6 +3,8 @@ base_model: facebook/musicgen-large
|
|
3 |
library_name: peft
|
4 |
license: cc-by-nc-4.0
|
5 |
tags:
|
|
|
|
|
6 |
- generated_from_trainer
|
7 |
model-index:
|
8 |
- name: musicgen-large-lora-trance_3ep_30da-colab
|
@@ -14,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
# musicgen-large-lora-trance_3ep_30da-colab
|
16 |
|
17 |
-
This model is a fine-tuned version of [facebook/musicgen-large](https://huggingface.co/facebook/musicgen-large) on
|
18 |
|
19 |
## Model description
|
20 |
|
|
|
3 |
library_name: peft
|
4 |
license: cc-by-nc-4.0
|
5 |
tags:
|
6 |
+
- text-to-audio
|
7 |
+
- trance_clips
|
8 |
- generated_from_trainer
|
9 |
model-index:
|
10 |
- name: musicgen-large-lora-trance_3ep_30da-colab
|
|
|
16 |
|
17 |
# musicgen-large-lora-trance_3ep_30da-colab
|
18 |
|
19 |
+
This model is a fine-tuned version of [facebook/musicgen-large](https://huggingface.co/facebook/musicgen-large) on the ShaySha/trance_clips dataset.
|
20 |
|
21 |
## Model description
|
22 |
|
trainer_state.json
CHANGED
@@ -1,27 +1,48 @@
|
|
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,
|
13 |
-
"
|
14 |
-
"
|
15 |
-
"
|
16 |
-
"
|
17 |
-
|
18 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
}
|
20 |
],
|
21 |
"logging_steps": 1,
|
22 |
-
"max_steps":
|
23 |
"num_input_tokens_seen": 0,
|
24 |
-
"num_train_epochs":
|
25 |
"save_steps": 500,
|
26 |
"stateful_callbacks": {
|
27 |
"TrainerControl": {
|
@@ -29,13 +50,13 @@
|
|
29 |
"should_epoch_stop": false,
|
30 |
"should_evaluate": false,
|
31 |
"should_log": false,
|
32 |
-
"should_save":
|
33 |
-
"should_training_stop":
|
34 |
},
|
35 |
"attributes": {}
|
36 |
}
|
37 |
},
|
38 |
-
"total_flos":
|
39 |
"train_batch_size": 2,
|
40 |
"trial_name": null,
|
41 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.533333333333333,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 3,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.5333333333333333,
|
13 |
+
"grad_norm": 1.0211135149002075,
|
14 |
+
"learning_rate": 0.00013333333333333334,
|
15 |
+
"loss": 8.9053,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.5333333333333332,
|
20 |
+
"grad_norm": 1.9195276498794556,
|
21 |
+
"learning_rate": 6.666666666666667e-05,
|
22 |
+
"loss": 15.5624,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 2.533333333333333,
|
27 |
+
"grad_norm": 3.327542543411255,
|
28 |
+
"learning_rate": 0.0,
|
29 |
+
"loss": 15.4835,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 2.533333333333333,
|
34 |
+
"step": 3,
|
35 |
+
"total_flos": 14231678474352.0,
|
36 |
+
"train_loss": 13.31708844502767,
|
37 |
+
"train_runtime": 37.7347,
|
38 |
+
"train_samples_per_second": 2.385,
|
39 |
+
"train_steps_per_second": 0.08
|
40 |
}
|
41 |
],
|
42 |
"logging_steps": 1,
|
43 |
+
"max_steps": 3,
|
44 |
"num_input_tokens_seen": 0,
|
45 |
+
"num_train_epochs": 3,
|
46 |
"save_steps": 500,
|
47 |
"stateful_callbacks": {
|
48 |
"TrainerControl": {
|
|
|
50 |
"should_epoch_stop": false,
|
51 |
"should_evaluate": false,
|
52 |
"should_log": false,
|
53 |
+
"should_save": true,
|
54 |
+
"should_training_stop": true
|
55 |
},
|
56 |
"attributes": {}
|
57 |
}
|
58 |
},
|
59 |
+
"total_flos": 14231678474352.0,
|
60 |
"train_batch_size": 2,
|
61 |
"trial_name": null,
|
62 |
"trial_params": null
|