Model save
Browse files- README.md +71 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- trl
|
| 4 |
+
- sft
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: COK
|
| 8 |
+
results: []
|
| 9 |
+
library_name: peft
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# COK
|
| 16 |
+
|
| 17 |
+
This model was trained from scratch on an unknown dataset.
|
| 18 |
+
|
| 19 |
+
## Model description
|
| 20 |
+
|
| 21 |
+
More information needed
|
| 22 |
+
|
| 23 |
+
## Intended uses & limitations
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Training and evaluation data
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training procedure
|
| 32 |
+
|
| 33 |
+
|
| 34 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 35 |
+
- quant_method: bitsandbytes
|
| 36 |
+
- _load_in_8bit: True
|
| 37 |
+
- _load_in_4bit: False
|
| 38 |
+
- llm_int8_threshold: 6.0
|
| 39 |
+
- llm_int8_skip_modules: None
|
| 40 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 41 |
+
- llm_int8_has_fp16_weight: False
|
| 42 |
+
- bnb_4bit_quant_type: fp4
|
| 43 |
+
- bnb_4bit_use_double_quant: False
|
| 44 |
+
- bnb_4bit_compute_dtype: float32
|
| 45 |
+
- bnb_4bit_quant_storage: uint8
|
| 46 |
+
- load_in_4bit: False
|
| 47 |
+
- load_in_8bit: True
|
| 48 |
+
### Training hyperparameters
|
| 49 |
+
|
| 50 |
+
The following hyperparameters were used during training:
|
| 51 |
+
- learning_rate: 1.41e-05
|
| 52 |
+
- train_batch_size: 1
|
| 53 |
+
- eval_batch_size: 8
|
| 54 |
+
- seed: 42
|
| 55 |
+
- gradient_accumulation_steps: 2
|
| 56 |
+
- total_train_batch_size: 2
|
| 57 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 58 |
+
- lr_scheduler_type: linear
|
| 59 |
+
- num_epochs: 3
|
| 60 |
+
|
| 61 |
+
### Training results
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
### Framework versions
|
| 66 |
+
|
| 67 |
+
- PEFT 0.5.0
|
| 68 |
+
- Transformers 4.40.1
|
| 69 |
+
- Pytorch 2.0.1+cu117
|
| 70 |
+
- Datasets 2.14.5
|
| 71 |
+
- Tokenizers 0.19.1
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 109069176
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02bc5f18ccb751e6307b96a167cf4652b9aa95ecbe6159d9ac7c7cd71d9ae6d7
|
| 3 |
size 109069176
|