End of training

README.md

@@ -0,0 +1,187 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: 01-ai/Yi-1.5-9B-Chat-16K
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: 9b1a4180-c1b9-48ca-aff1-fa203a8dcd00
+  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
+auto_find_batch_size: true
+base_model: 01-ai/Yi-1.5-9B-Chat-16K
+bf16: auto
+chat_template: llama3
+dataloader_num_workers: 12
+dataset_prepared_path: null
+datasets:
+- data_files:
+  - 86439f2f93cdf4d4_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/86439f2f93cdf4d4_train_data.json
+  type:
+    field_input: input
+    field_instruction: instruction
+    field_output: system
+    format: '{instruction} {input}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+debug: null
+deepspeed: null
+early_stopping_patience: 3
+early_stopping_threshold: 0.001
+eval_max_new_tokens: 128
+eval_steps: 20
+flash_attention: false
+fp16: null
+fsdp: null
+fsdp_config: null
+gradient_accumulation_steps: 2
+gradient_checkpointing: false
+group_by_length: false
+hub_model_id: mrferr3t/9b1a4180-c1b9-48ca-aff1-fa203a8dcd00
+hub_repo: null
+hub_strategy: checkpoint
+hub_token: null
+learning_rate: 0.0003
+load_in_4bit: false
+load_in_8bit: false
+local_rank: null
+logging_steps: 100
+lora_alpha: 16
+lora_dropout: 0.05
+lora_fan_in_fan_out: null
+lora_model_dir: null
+lora_r: 8
+lora_target_linear: true
+lr_scheduler: cosine
+micro_batch_size: 32
+mlflow_experiment_name: /tmp/86439f2f93cdf4d4_train_data.json
+model_type: AutoModelForCausalLM
+num_epochs: 5
+optimizer: adamw_bnb_8bit
+output_dir: miner_id_24
+pad_to_sequence_len: true
+s2_attention: null
+sample_packing: false
+save_steps: 20
+saves_per_epoch: 0
+sequence_len: 512
+strict: false
+tf32: false
+tokenizer_type: AutoTokenizer
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 0.05
+wandb_entity: null
+wandb_mode: online
+wandb_name: ae2946b7-5a83-4c68-97f5-b0524b77f261
+wandb_project: Gradients-On-Demand
+wandb_run: your_name
+wandb_runid: ae2946b7-5a83-4c68-97f5-b0524b77f261
+warmup_ratio: 0.05
+weight_decay: 0.0
+xformers_attention: null
+
+```
+
+</details><br>
+
+# 9b1a4180-c1b9-48ca-aff1-fa203a8dcd00
+
+This model is a fine-tuned version of [01-ai/Yi-1.5-9B-Chat-16K](https://huggingface.co/01-ai/Yi-1.5-9B-Chat-16K) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0000
+
+## 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: 0.0003
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 64
+- optimizer: Use adamw_bnb_8bit 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: 9
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| No log        | 0.0067 | 1    | 0.4763          |
+| No log        | 0.1347 | 20   | 0.0001          |
+| No log        | 0.2694 | 40   | 0.0000          |
+| No log        | 0.4040 | 60   | 0.0000          |
+| No log        | 0.5387 | 80   | 0.0000          |
+| 0.0221        | 0.6734 | 100  | 0.0000          |
+| 0.0221        | 0.8081 | 120  | 0.0000          |
+| 0.0221        | 0.9428 | 140  | 0.0000          |
+| 0.0221        | 1.0774 | 160  | 0.0000          |
+| 0.0221        | 1.2121 | 180  | 0.0000          |
+| 0.0           | 1.3468 | 200  | 0.0000          |
+| 0.0           | 1.4815 | 220  | 0.0000          |
+| 0.0           | 1.6162 | 240  | 0.0000          |
+| 0.0           | 1.7508 | 260  | 0.0000          |
+| 0.0           | 1.8855 | 280  | 0.0000          |
+| 0.0           | 2.0202 | 300  | 0.0000          |
+| 0.0           | 2.1549 | 320  | 0.0000          |
+| 0.0           | 2.2896 | 340  | 0.0000          |
+| 0.0           | 2.4242 | 360  | 0.0000          |
+| 0.0           | 2.5589 | 380  | 0.0000          |
+| 0.0           | 2.6936 | 400  | 0.0000          |
+| 0.0           | 2.8283 | 420  | 0.0000          |
+| 0.0           | 2.9630 | 440  | 0.0000          |
+| 0.0           | 3.0976 | 460  | 0.0000          |
+| 0.0           | 3.2323 | 480  | 0.0000          |
+| 0.0           | 3.3670 | 500  | 0.0000          |
+| 0.0           | 3.5017 | 520  | 0.0000          |
+| 0.0           | 3.6364 | 540  | 0.0000          |
+| 0.0           | 3.7710 | 560  | 0.0000          |
+| 0.0           | 3.9057 | 580  | 0.0000          |
+| 0.0           | 4.0404 | 600  | 0.0000          |
+| 0.0           | 4.1751 | 620  | 0.0000          |
+| 0.0           | 4.3098 | 640  | 0.0000          |
+| 0.0           | 4.4444 | 660  | 0.0000          |
+| 0.0           | 4.5791 | 680  | 0.0000          |
+| 0.0           | 4.7138 | 700  | 0.0000          |
+| 0.0           | 4.8485 | 720  | 0.0000          |
+| 0.0           | 4.9832 | 740  | 0.0000          |
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.46.0
+- Pytorch 2.3.1+cu121
+- Datasets 3.0.1
+- Tokenizers 0.20.1

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88a6d29bced12c3f2d8c64f87df6f6b7177c866fedf1a142e107910fc9b77753
+size 109162826