nielsbantilan commited on
Commit
1d5a566
1 Parent(s): 85f3f44

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. README.md +31 -13
  2. flyte_training_config.json +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -1,16 +1,34 @@
1
  ---
2
- datasets:
3
- - yahma/alpaca-cleaned
4
- language:
5
- - en
6
- license: apache-2.0
7
- tags:
8
- - pytorch
9
- - causal-lm
10
- - llama2
11
- - fine-tuning
12
- - alpaca
13
-
14
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
 
16
- # Llama-2-7b fine-tuned on LoRA alpaca-cleaned
 
1
  ---
2
+ library_name: peft
 
 
 
 
 
 
 
 
 
 
 
3
  ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - quant_method: bitsandbytes
9
+ - load_in_8bit: False
10
+ - load_in_4bit: True
11
+ - llm_int8_threshold: 6.0
12
+ - llm_int8_skip_modules: None
13
+ - llm_int8_enable_fp32_cpu_offload: True
14
+ - llm_int8_has_fp16_weight: False
15
+ - bnb_4bit_quant_type: nf4
16
+ - bnb_4bit_use_double_quant: True
17
+ - bnb_4bit_compute_dtype: bfloat16
18
+
19
+ The following `bitsandbytes` quantization config was used during training:
20
+ - quant_method: bitsandbytes
21
+ - load_in_8bit: False
22
+ - load_in_4bit: True
23
+ - llm_int8_threshold: 6.0
24
+ - llm_int8_skip_modules: None
25
+ - llm_int8_enable_fp32_cpu_offload: True
26
+ - llm_int8_has_fp16_weight: False
27
+ - bnb_4bit_quant_type: nf4
28
+ - bnb_4bit_use_double_quant: True
29
+ - bnb_4bit_compute_dtype: bfloat16
30
+ ### Framework versions
31
+
32
+ - PEFT 0.5.0.dev0
33
 
34
+ - PEFT 0.5.0.dev0
flyte_training_config.json CHANGED
@@ -1 +1 @@
1
- {"base_model": "meta-llama/Llama-2-7b-hf", "data_path": "yahma/alpaca-cleaned", "instruction_key": "instruction", "input_key": "input", "output_key": "output", "output_dir": "./output", "device_map": "auto", "batch_size": 32, "micro_batch_size": 8, "num_epochs": 1, "max_steps": 300, "eval_steps": 200, "save_steps": 50, "learning_rate": 0.0003, "cutoff_len": 512, "val_set_size": 0, "lora_r": 8, "lora_alpha": 16, "lora_dropout": 0.05, "weight_decay": 0.02, "warmup_ratio": 0.03, "lr_scheduler_type": "cosine", "lora_target_modules": ["q_proj", "k_proj", "v_proj"], "train_on_inputs": true, "add_eos_token": true, "group_by_length": true, "resume_from_checkpoint": null, "wandb_project": "unionai-llm-fine-tuning", "wandb_run_name": "", "wandb_watch": "", "wandb_log_model": "", "debug_mode": false, "debug_train_data_size": 1024}
 
1
+ {"base_model": "meta-llama/Llama-2-7b-hf", "data_path": "yahma/alpaca-cleaned", "instruction_key": "instruction", "input_key": "input", "output_key": "output", "output_dir": "./output", "device_map": "auto", "batch_size": 32, "micro_batch_size": 16, "num_epochs": 1, "max_steps": 50, "eval_steps": 5, "save_steps": 500, "learning_rate": 3e-08, "cutoff_len": 512, "val_set_size": 1000, "lora_r": 8, "lora_alpha": 16, "lora_dropout": 0.05, "weight_decay": 0.02, "warmup_ratio": 0.03, "lr_scheduler_type": "cosine", "lora_target_modules": ["q_proj", "k_proj", "v_proj"], "train_on_inputs": true, "add_eos_token": true, "group_by_length": false, "resume_from_checkpoint": null, "wandb_project": "unionai-llm-fine-tuning", "wandb_run_name": "", "wandb_watch": "", "wandb_log_model": "", "debug_mode": false, "debug_train_data_size": 1024}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7404ccd2db3be9b05a3dc59889c92771351aab687ad0c14878fca9a50c2c646
3
  size 4027
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0018f2fe57030840f1adb0dd94cc28a1803425bcce15c72278fbfb5f07984334
3
  size 4027