-
Notifications
You must be signed in to change notification settings - Fork 43
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Add multiGPU finetuning tests for granite, llama and mixtral models
- Loading branch information
1 parent
d82f293
commit 095c68e
Showing
9 changed files
with
210 additions
and
104 deletions.
There are no files selected for viewing
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
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
13 changes: 5 additions & 8 deletions
13
tests/kfto/core/config_GPU.json → ...ore/config_granite_20b_code_instruct.json
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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,22 +1,19 @@ | ||
{ | ||
"model_name_or_path": "/tmp/model/bloom-560m", | ||
"training_data_path": "/tmp/dataset/alpaca_data.json", | ||
"output_dir": "/tmp/out", | ||
"model_name_or_path": "ibm-granite/granite-20b-code-instruct", | ||
"training_data_path": "/mnt/scratch/dataset/alpaca_data.json", | ||
"output_dir": "/mnt/output/model", | ||
"num_train_epochs": 1.0, | ||
"per_device_train_batch_size": 4, | ||
"per_device_train_batch_size": 1, | ||
"per_device_eval_batch_size": 4, | ||
"gradient_accumulation_steps": 4, | ||
"evaluation_strategy": "no", | ||
"save_strategy": "epoch", | ||
"learning_rate": 1e-5, | ||
"weight_decay": 0.0, | ||
"lr_scheduler_type": "cosine", | ||
"logging_steps": 1.0, | ||
"packing": false, | ||
"include_tokens_per_second": true, | ||
"response_template": "\n### Response:", | ||
"dataset_text_field": "output", | ||
"use_flash_attn": false, | ||
"torch_dtype": "float32", | ||
"tokenizer_name_or_path": "/tmp/model/bloom-560m" | ||
"tokenizer_name_or_path": "ibm-granite/granite-20b-code-instruct" | ||
} |
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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,19 @@ | ||
{ | ||
"model_name_or_path": "meta-llama/Llama-2-13b-chat-hf", | ||
"training_data_path": "/mnt/scratch/dataset/alpaca_data.json", | ||
"output_dir": "/mnt/output/model", | ||
"num_train_epochs": 1.0, | ||
"per_device_train_batch_size": 1, | ||
"per_device_eval_batch_size": 4, | ||
"gradient_accumulation_steps": 4, | ||
"evaluation_strategy": "no", | ||
"save_strategy": "epoch", | ||
"learning_rate": 1e-5, | ||
"weight_decay": 0.0, | ||
"lr_scheduler_type": "cosine", | ||
"include_tokens_per_second": true, | ||
"response_template": "\n### Response:", | ||
"dataset_text_field": "output", | ||
"use_flash_attn": false, | ||
"tokenizer_name_or_path": "meta-llama/Llama-2-13b-chat-hf" | ||
} |
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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,20 @@ | ||
{ | ||
"model_name_or_path": "meta-llama/Meta-Llama-3-70B-Instruct", | ||
"training_data_path": "/mnt/scratch/dataset/alpaca_data.json", | ||
"output_dir": "/mnt/output/model", | ||
"num_train_epochs": 1.0, | ||
"per_device_train_batch_size": 1, | ||
"per_device_eval_batch_size": 4, | ||
"gradient_accumulation_steps": 4, | ||
"evaluation_strategy": "no", | ||
"save_strategy": "epoch", | ||
"learning_rate": 1e-5, | ||
"weight_decay": 0.0, | ||
"lr_scheduler_type": "cosine", | ||
"include_tokens_per_second": true, | ||
"response_template": "\n### Response:", | ||
"dataset_text_field": "output", | ||
"use_flash_attn": false, | ||
"tokenizer_name_or_path": "meta-llama/Meta-Llama-3-70B-Instruct", | ||
"peft_method": "lora" | ||
} |
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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,19 @@ | ||
{ | ||
"model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct", | ||
"training_data_path": "/mnt/scratch/dataset/alpaca_data.json", | ||
"output_dir": "/mnt/output/model", | ||
"num_train_epochs": 1.0, | ||
"per_device_train_batch_size": 1, | ||
"per_device_eval_batch_size": 4, | ||
"gradient_accumulation_steps": 4, | ||
"evaluation_strategy": "no", | ||
"save_strategy": "epoch", | ||
"learning_rate": 1e-5, | ||
"weight_decay": 0.0, | ||
"lr_scheduler_type": "cosine", | ||
"include_tokens_per_second": true, | ||
"response_template": "\n### Response:", | ||
"dataset_text_field": "output", | ||
"use_flash_attn": false, | ||
"tokenizer_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct" | ||
} |
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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,20 @@ | ||
{ | ||
"model_name_or_path": "mistralai/Mixtral-8x7B-Instruct-v0.1", | ||
"training_data_path": "/mnt/scratch/dataset/alpaca_data.json", | ||
"output_dir": "/mnt/output/model", | ||
"num_train_epochs": 1.0, | ||
"per_device_train_batch_size": 1, | ||
"per_device_eval_batch_size": 4, | ||
"gradient_accumulation_steps": 1, | ||
"evaluation_strategy": "no", | ||
"save_strategy": "epoch", | ||
"learning_rate": 1e-5, | ||
"weight_decay": 0.0, | ||
"lr_scheduler_type": "cosine", | ||
"include_tokens_per_second": true, | ||
"response_template": "\n### Response:", | ||
"dataset_text_field": "output", | ||
"use_flash_attn": false, | ||
"tokenizer_name_or_path": "mistralai/Mixtral-8x7B-Instruct-v0.1" | ||
} | ||
|
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
Oops, something went wrong.