End of training

README.md

@@ -0,0 +1,166 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: NousResearch/Yarn-Solar-10b-32k
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: 3ba86d79-b7fc-41ce-97d1-ca4829a23719
+  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/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.1`
+```yaml
+adapter: lora
+base_model: NousResearch/Yarn-Solar-10b-32k
+bf16: auto
+chat_template: llama3
+dataset_prepared_path: null
+datasets:
+- data_files:
+  - 7271f119bcc5d989_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/7271f119bcc5d989_train_data.json
+  type:
+    field_input: context
+    field_instruction: question
+    field_output: answer
+    format: '{instruction} {input}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+debug: null
+deepspeed: null
+early_stopping_patience: null
+eval_max_new_tokens: 128
+eval_table_size: null
+evals_per_epoch: 4
+flash_attention: true
+fp16: null
+fsdp: null
+fsdp_config: null
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+gradient_clipping: 1.0
+group_by_length: false
+hub_model_id: sn56m5/3ba86d79-b7fc-41ce-97d1-ca4829a23719
+hub_repo: null
+hub_strategy: checkpoint
+hub_token: null
+learning_rate: 5.0e-05
+load_in_4bit: false
+load_in_8bit: false
+local_rank: 0
+logging_steps: 3
+lora_alpha: 32
+lora_dropout: 0.05
+lora_fan_in_fan_out: null
+lora_model_dir: null
+lora_r: 16
+lora_target_linear: true
+lr_scheduler: cosine
+max_steps: 500
+micro_batch_size: 8
+mlflow_experiment_name: /tmp/7271f119bcc5d989_train_data.json
+model_type: AutoModelForCausalLM
+num_epochs: 3
+optimizer: adamw_bnb_8bit
+output_dir: miner_id_24
+pad_to_sequence_len: true
+resume_from_checkpoint: null
+s2_attention: null
+sample_packing: false
+saves_per_epoch: 4
+sequence_len: 1024
+special_tokens:
+  pad_token: </s>
+strict: false
+tf32: false
+tokenizer_type: AutoTokenizer
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 0.05
+wandb_entity: sn56-miner
+wandb_mode: disabled
+wandb_name: null
+wandb_project: god
+wandb_run: o0f6
+wandb_runid: null
+warmup_steps: 10
+weight_decay: 0.01
+xformers_attention: null
+
+```
+
+</details><br>
+
+# 3ba86d79-b7fc-41ce-97d1-ca4829a23719
+
+This model is a fine-tuned version of [NousResearch/Yarn-Solar-10b-32k](https://huggingface.co/NousResearch/Yarn-Solar-10b-32k) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1280
+
+## 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: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- total_eval_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- training_steps: 500
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| No log        | 0.0035 | 1    | 0.7139          |
+| 0.6722        | 0.1479 | 42   | 0.1650          |
+| 0.6329        | 0.2958 | 84   | 0.1505          |
+| 0.5936        | 0.4437 | 126  | 0.1457          |
+| 0.5783        | 0.5915 | 168  | 0.1405          |
+| 0.5684        | 0.7394 | 210  | 0.1381          |
+| 0.5662        | 0.8873 | 252  | 0.1334          |
+| 0.4207        | 1.0352 | 294  | 0.1316          |
+| 0.4356        | 1.1831 | 336  | 0.1303          |
+| 0.4508        | 1.3310 | 378  | 0.1292          |
+| 0.4651        | 1.4789 | 420  | 0.1286          |
+| 0.4505        | 1.6268 | 462  | 0.1280          |
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.46.0
+- Pytorch 2.5.0+cu124
+- Datasets 3.0.1
+- Tokenizers 0.20.1

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14a9aacaf06a90b0cb5928b0a8853c34467acb051700f6299fb2a48f26db2c7b
+size 251901130