Model save
Browse files
README.md
CHANGED
|
@@ -5,9 +5,9 @@ tags:
|
|
| 5 |
- trl
|
| 6 |
- sft
|
| 7 |
- generated_from_trainer
|
|
|
|
| 8 |
datasets:
|
| 9 |
- generator
|
| 10 |
-
base_model: codellama/CodeLlama-7b-hf
|
| 11 |
model-index:
|
| 12 |
- name: code-llama-7b-text-to-sql
|
| 13 |
results: []
|
|
@@ -38,11 +38,11 @@ More information needed
|
|
| 38 |
|
| 39 |
The following hyperparameters were used during training:
|
| 40 |
- learning_rate: 0.0002
|
| 41 |
-
- train_batch_size:
|
| 42 |
- eval_batch_size: 8
|
| 43 |
- seed: 42
|
| 44 |
- gradient_accumulation_steps: 2
|
| 45 |
-
- total_train_batch_size:
|
| 46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
- lr_scheduler_type: constant
|
| 48 |
- lr_scheduler_warmup_ratio: 0.03
|
|
@@ -55,7 +55,7 @@ The following hyperparameters were used during training:
|
|
| 55 |
### Framework versions
|
| 56 |
|
| 57 |
- PEFT 0.7.2.dev0
|
| 58 |
-
- Transformers 4.
|
| 59 |
-
- Pytorch 2.1
|
| 60 |
- Datasets 2.16.1
|
| 61 |
-
- Tokenizers 0.15.
|
|
|
|
| 5 |
- trl
|
| 6 |
- sft
|
| 7 |
- generated_from_trainer
|
| 8 |
+
base_model: codellama/CodeLlama-7b-hf
|
| 9 |
datasets:
|
| 10 |
- generator
|
|
|
|
| 11 |
model-index:
|
| 12 |
- name: code-llama-7b-text-to-sql
|
| 13 |
results: []
|
|
|
|
| 38 |
|
| 39 |
The following hyperparameters were used during training:
|
| 40 |
- learning_rate: 0.0002
|
| 41 |
+
- train_batch_size: 2
|
| 42 |
- eval_batch_size: 8
|
| 43 |
- seed: 42
|
| 44 |
- gradient_accumulation_steps: 2
|
| 45 |
+
- total_train_batch_size: 4
|
| 46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
- lr_scheduler_type: constant
|
| 48 |
- lr_scheduler_warmup_ratio: 0.03
|
|
|
|
| 55 |
### Framework versions
|
| 56 |
|
| 57 |
- PEFT 0.7.2.dev0
|
| 58 |
+
- Transformers 4.38.2
|
| 59 |
+
- Pytorch 2.2.1+cu121
|
| 60 |
- Datasets 2.16.1
|
| 61 |
+
- Tokenizers 0.15.2
|