Ygr avsr #13
Closed
Ygr avsr #13
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
ddlBoJack
reviewed
Dec 15, 2023
| @@ -33,8 +34,33 @@ class custom_dataset: | |||
| train_split: str = "train" | |||
| test_split: str = "validation" | |||
| data_path: str = NotImplemented | |||
| max_words: int = NotImplemented | |||
ddlBoJack
reviewed
Dec 15, 2023
| TRAIN_LRS3_MODEL_FILE: str = "/nfs/yangguanrou.ygr/AVSR/train-step_0108-wer_0.058.ckpt" # "/home/oss/yangguanrou.ygr/AVSR/train-step_0108-wer_0.058.ckpt" #单一模态是这个 | ||
| TRAINED_AO_FILE : str = "/nfs/yangguanrou.ygr/AVSR/check/train-step_0604-wer_0.054.ckpt" #"/home/oss/yangguanrou.ygr/AVSR/check/train-step_0604-wer_0.054.ckpt" | ||
| TRAINED_VO_FILE: str = "/nfs/yangguanrou.ygr/AVSR/check/train-step_1191-wer_0.674.ckpt" #"/home/oss/yangguanrou.ygr/AVSR/check/train-step_1191-wer_0.674.ckpt" |
There was a problem hiding this comment.
maybe we can customize each model config, instead of merge all model together.
@LauraGPT Can this be resolved with hydra?
ddlBoJack
reviewed
Dec 15, 2023
| @@ -222,7 +222,7 @@ def main(**kwargs): | |||
| lr=train_config.lr, | |||
| weight_decay=train_config.weight_decay, | |||
| ) | |||
| scheduler = StepLR(optimizer, step_size=1, gamma=train_config.gamma) | |||
| scheduler = StepLR(optimizer, step_size=1/root/SLAM-LLM/src/llama_recipes/models, gamma=train_config.gamma) | |||
ddlBoJack
reviewed
Dec 15, 2023
| logger.info("model_config: {}".format(model_config)) | ||
|
|
||
|
|
||
|
|
ddlBoJack
reviewed
Dec 15, 2023
| [2023-12-15 16:38:36][root][INFO] - --> Training Set Length = 280879 | ||
| [2023-12-15 16:38:36][root][INFO] - --> Validation Set Length = 2864 | ||
| [2023-12-15 16:38:36][llama_recipes.utils.config_utils][INFO] - Using batching strategy: custom | ||
| [2023-12-15 16:38:36][llama_recipes.utils.config_utils][INFO] - Using batching strategy: custom |
ddlBoJack
reviewed
Dec 15, 2023
| try: | ||
| #loss = model(**batch).loss | ||
| outputs, *rest = model(**batch) | ||
| except Exception as e: |
ddlBoJack
requested changes
Dec 15, 2023
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
add log&wandb