End of training

README.md

@@ -0,0 +1,157 @@
+---
+license: llama3
+library_name: peft
+tags:
+- axolotl
+- generated_from_trainer
+base_model: meta-llama/Meta-Llama-3-8B
+model-index:
+- name: llama3-8b-hermes-sandals-100
+  results: []
+---
+
+<!-- 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. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.0`
+```yaml
+base_model: meta-llama/Meta-Llama-3-8B
+model_type: LlamaForCausalLM
+tokenizer_type: AutoTokenizer
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+datasets:
+  - path: ./data/openhermes2_5_first_100.jsonl
+    type: sharegpt
+    conversation: llama3
+dataset_prepared_path: 
+val_set_size: 0.05
+output_dir: ./outputs_lora-out
+hub_model_id: venetis/llama3-8b-hermes-sandals-100
+
+chat_template: llama3
+adapter: lora
+lora_model_dir:
+lora_r: 32
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_linear: true
+lora_fan_in_fan_out:
+
+
+sequence_len: 4096
+sample_packing: false
+pad_to_sequence_len: true
+wandb_project: llama-3-8b-hermes-sandals-first100
+wandb_entity: venetispall
+
+gradient_accumulation_steps: 4
+micro_batch_size: 2
+num_epochs: 4
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 2e-4
+
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: false
+
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+s2_attention:
+
+
+warmup_steps: 10
+evals_per_epoch: 4
+eval_table_size:
+eval_max_new_tokens: 128
+saves_per_epoch: 1
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+   pad_token: <|end_of_text|>
+
+```
+
+</details><br>
+
+# llama3-8b-hermes-sandals-100
+
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6973
+
+## 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: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.1059        | 0.0833 | 1    | 0.9750          |
+| 0.7822        | 0.25   | 3    | 0.9658          |
+| 0.9619        | 0.5    | 6    | 0.8441          |
+| 0.9988        | 0.75   | 9    | 0.7469          |
+| 1.0968        | 1.0    | 12   | 0.7146          |
+| 0.9651        | 1.25   | 15   | 0.6966          |
+| 1.0208        | 1.5    | 18   | 0.6926          |
+| 0.6837        | 1.75   | 21   | 0.7035          |
+| 0.8704        | 2.0    | 24   | 0.6958          |
+| 0.4346        | 2.25   | 27   | 0.6800          |
+| 0.5709        | 2.5    | 30   | 0.6885          |
+| 0.331         | 2.75   | 33   | 0.6952          |
+| 0.5077        | 3.0    | 36   | 0.6953          |
+| 0.6047        | 3.25   | 39   | 0.6939          |
+| 0.5974        | 3.5    | 42   | 0.6961          |
+| 0.5238        | 3.75   | 45   | 0.6963          |
+| 0.7728        | 4.0    | 48   | 0.6973          |
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.40.2
+- Pytorch 2.1.2+cu118
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0ff7401a6dc3aa95a53ca2d5d6e0a5a7052c4f8390449f39ce2d1a8ec5eabf6
+size 167934026