Upload model

README.md

@@ -1,76 +1,21 @@
 ---
-base_model: meta-llama/Llama-2-13b-hf
-tags:
-- generated_from_trainer
-model-index:
-- name: Llama-2-13b-hf-eli5-wiki-1024_qlora
-  results: []
+library_name: peft
 ---
-
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
-
-# Llama-2-13b-hf-eli5-wiki-1024_qlora
-
-This model is a fine-tuned version of [meta-llama/Llama-2-13b-hf](https://huggingface.co/meta-llama/Llama-2-13b-hf) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 1.3339
-
-## Model description
-
-More information needed
-
-## Intended uses & limitations
-
-More information needed
-
-## Training and evaluation data
-
-More information needed
-
 ## Training procedure
 
-### Training hyperparameters
-
-The following hyperparameters were used during training:
-- learning_rate: 0.0002
-- train_batch_size: 16
-- eval_batch_size: 16
-- seed: 42
-- gradient_accumulation_steps: 8
-- total_train_batch_size: 128
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- lr_scheduler_warmup_ratio: 0.03
-- num_epochs: 3
-
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 1.5071        | 0.15  | 125  | 1.3593          |
-| 1.5606        | 0.3   | 250  | 1.3514          |
-| 1.452         | 0.45  | 375  | 1.3441          |
-| 1.5435        | 0.6   | 500  | 1.3423          |
-| 1.4355        | 0.75  | 625  | 1.3373          |
-| 1.5407        | 0.9   | 750  | 1.3371          |
-| 1.1397        | 1.05  | 875  | 1.3361          |
-| 1.4666        | 1.2   | 1000 | 1.3383          |
-| 1.1651        | 1.35  | 1125 | 1.3374          |
-| 1.4819        | 1.5   | 1250 | 1.3372          |
-| 1.1667        | 1.65  | 1375 | 1.3361          |
-| 1.4585        | 1.8   | 1500 | 1.3348          |
-| 1.138         | 1.95  | 1625 | 1.3339          |
-| 1.069         | 2.1   | 1750 | 1.3474          |
-| 1.7055        | 2.25  | 1875 | 1.3596          |
-| 1.0747        | 2.4   | 2000 | 1.3498          |
-| 1.7118        | 2.55  | 2125 | 1.3580          |
-| 1.0339        | 2.7   | 2250 | 1.3502          |
-
 
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
 ### Framework versions
 
-- Transformers 4.34.0.dev0
-- Pytorch 2.0.1+cu118
-- Datasets 2.14.5
-- Tokenizers 0.13.3
+
+- PEFT 0.6.0.dev0

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9422f1c5e2358c61a4b8905e8941d050cf4d7a47c2fc7e13a20e19521080bbf0
+size 1001465824