update model card README.md
Browse files
README.md
CHANGED
|
@@ -5,7 +5,6 @@ tags:
|
|
| 5 |
model-index:
|
| 6 |
- name: falcon-7b-sharded_finetuned_codealpaca_20k
|
| 7 |
results: []
|
| 8 |
-
library_name: peft
|
| 9 |
---
|
| 10 |
|
| 11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -29,25 +28,14 @@ More information needed
|
|
| 29 |
|
| 30 |
## Training procedure
|
| 31 |
|
| 32 |
-
|
| 33 |
-
The following `bitsandbytes` quantization config was used during training:
|
| 34 |
-
- load_in_8bit: False
|
| 35 |
-
- load_in_4bit: True
|
| 36 |
-
- llm_int8_threshold: 6.0
|
| 37 |
-
- llm_int8_skip_modules: None
|
| 38 |
-
- llm_int8_enable_fp32_cpu_offload: False
|
| 39 |
-
- llm_int8_has_fp16_weight: False
|
| 40 |
-
- bnb_4bit_quant_type: nf4
|
| 41 |
-
- bnb_4bit_use_double_quant: False
|
| 42 |
-
- bnb_4bit_compute_dtype: float16
|
| 43 |
### Training hyperparameters
|
| 44 |
|
| 45 |
The following hyperparameters were used during training:
|
| 46 |
- learning_rate: 0.0002
|
| 47 |
-
- train_batch_size:
|
| 48 |
- eval_batch_size: 8
|
| 49 |
- seed: 42
|
| 50 |
-
- gradient_accumulation_steps:
|
| 51 |
- total_train_batch_size: 64
|
| 52 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 53 |
- lr_scheduler_type: cosine
|
|
@@ -60,7 +48,6 @@ The following hyperparameters were used during training:
|
|
| 60 |
|
| 61 |
### Framework versions
|
| 62 |
|
| 63 |
-
- PEFT 0.4.0
|
| 64 |
- Transformers 4.31.0
|
| 65 |
- Pytorch 2.0.1+cu118
|
| 66 |
- Datasets 2.13.0
|
|
|
|
| 5 |
model-index:
|
| 6 |
- name: falcon-7b-sharded_finetuned_codealpaca_20k
|
| 7 |
results: []
|
|
|
|
| 8 |
---
|
| 9 |
|
| 10 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 28 |
|
| 29 |
## Training procedure
|
| 30 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
### Training hyperparameters
|
| 32 |
|
| 33 |
The following hyperparameters were used during training:
|
| 34 |
- learning_rate: 0.0002
|
| 35 |
+
- train_batch_size: 8
|
| 36 |
- eval_batch_size: 8
|
| 37 |
- seed: 42
|
| 38 |
+
- gradient_accumulation_steps: 8
|
| 39 |
- total_train_batch_size: 64
|
| 40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
- lr_scheduler_type: cosine
|
|
|
|
| 48 |
|
| 49 |
### Framework versions
|
| 50 |
|
|
|
|
| 51 |
- Transformers 4.31.0
|
| 52 |
- Pytorch 2.0.1+cu118
|
| 53 |
- Datasets 2.13.0
|