Training in progress, step 12
Browse files- adapter_config.json +46 -0
- adapter_model.safetensors +3 -0
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +49 -0
- training_args.bin +1 -1
adapter_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": {
|
| 4 |
+
"base_model_class": "MusicgenForConditionalGeneration",
|
| 5 |
+
"parent_library": "transformers.models.musicgen.modeling_musicgen"
|
| 6 |
+
},
|
| 7 |
+
"base_model_name_or_path": "facebook/musicgen-small",
|
| 8 |
+
"bias": "none",
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 16,
|
| 17 |
+
"lora_dropout": 0.05,
|
| 18 |
+
"megatron_config": null,
|
| 19 |
+
"megatron_core": "megatron.core",
|
| 20 |
+
"modules_to_save": null,
|
| 21 |
+
"peft_type": "LORA",
|
| 22 |
+
"r": 32,
|
| 23 |
+
"rank_pattern": {},
|
| 24 |
+
"revision": null,
|
| 25 |
+
"target_modules": [
|
| 26 |
+
"fc2",
|
| 27 |
+
"embed_tokens.2",
|
| 28 |
+
"lm_heads.0",
|
| 29 |
+
"k_proj",
|
| 30 |
+
"enc_to_dec_proj",
|
| 31 |
+
"lm_heads.2",
|
| 32 |
+
"embed_tokens.1",
|
| 33 |
+
"q_proj",
|
| 34 |
+
"audio_enc_to_dec_proj",
|
| 35 |
+
"lm_heads.3",
|
| 36 |
+
"embed_tokens.0",
|
| 37 |
+
"embed_tokens.3",
|
| 38 |
+
"v_proj",
|
| 39 |
+
"lm_heads.1",
|
| 40 |
+
"out_proj",
|
| 41 |
+
"fc1"
|
| 42 |
+
],
|
| 43 |
+
"task_type": null,
|
| 44 |
+
"use_dora": false,
|
| 45 |
+
"use_rslora": false
|
| 46 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a1140c66270323fd2bd7b8565dd87bdb71e767cb253cf70c0d77bffebc70b07
|
| 3 |
+
size 85238600
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.8,
|
| 3 |
+
"total_flos": 3295460764752.0,
|
| 4 |
+
"train_loss": 10.123604774475098,
|
| 5 |
+
"train_runtime": 9.2915,
|
| 6 |
+
"train_samples": 20,
|
| 7 |
+
"train_samples_per_second": 2.153,
|
| 8 |
+
"train_steps_per_second": 0.108
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.8,
|
| 3 |
+
"total_flos": 3295460764752.0,
|
| 4 |
+
"train_loss": 10.123604774475098,
|
| 5 |
+
"train_runtime": 9.2915,
|
| 6 |
+
"train_samples": 20,
|
| 7 |
+
"train_samples_per_second": 2.153,
|
| 8 |
+
"train_steps_per_second": 0.108
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.8,
|
| 5 |
+
"eval_steps": 25,
|
| 6 |
+
"global_step": 1,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.8,
|
| 13 |
+
"grad_norm": Infinity,
|
| 14 |
+
"learning_rate": 0.0002,
|
| 15 |
+
"loss": 10.1236,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.8,
|
| 20 |
+
"step": 1,
|
| 21 |
+
"total_flos": 3295460764752.0,
|
| 22 |
+
"train_loss": 10.123604774475098,
|
| 23 |
+
"train_runtime": 9.2915,
|
| 24 |
+
"train_samples_per_second": 2.153,
|
| 25 |
+
"train_steps_per_second": 0.108
|
| 26 |
+
}
|
| 27 |
+
],
|
| 28 |
+
"logging_steps": 1.0,
|
| 29 |
+
"max_steps": 1,
|
| 30 |
+
"num_input_tokens_seen": 0,
|
| 31 |
+
"num_train_epochs": 1,
|
| 32 |
+
"save_steps": 500,
|
| 33 |
+
"stateful_callbacks": {
|
| 34 |
+
"TrainerControl": {
|
| 35 |
+
"args": {
|
| 36 |
+
"should_epoch_stop": false,
|
| 37 |
+
"should_evaluate": false,
|
| 38 |
+
"should_log": false,
|
| 39 |
+
"should_save": true,
|
| 40 |
+
"should_training_stop": true
|
| 41 |
+
},
|
| 42 |
+
"attributes": {}
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"total_flos": 3295460764752.0,
|
| 46 |
+
"train_batch_size": 1,
|
| 47 |
+
"trial_name": null,
|
| 48 |
+
"trial_params": null
|
| 49 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5496
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ff2f849e7eefc5afba4b07dad74bbe23e7f1c5570e7a1382aa0b517cc30dd16
|
| 3 |
size 5496
|