End of training

README.md

@@ -0,0 +1,148 @@
+---
+library_name: transformers
+base_model: minpeter/tiny-ko-124m-base
+tags:
+- axolotl
+- generated_from_trainer
+datasets:
+- lemon-mint/smol-koreantalk
+model-index:
+- name: tiny-ko-124m-sft
+  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: `0.11.0.dev0`
+```yaml
+base_model: minpeter/tiny-ko-124m-base
+
+hub_model_id: minpeter/tiny-ko-124m-sft
+output_dir: ./outputs/tiny-ko-124m-sft
+wandb_project: "axolotl"
+wandb_entity: "kasfiekfs-e"
+
+model_type: LlamaForCausalLM
+tokenizer_type: AutoTokenizer
+
+strict: false
+
+chat_template: chatml
+datasets:
+  - path: lemon-mint/smol-koreantalk
+    type: chat_template
+    split: train
+    field_messages: messages
+    message_property_mappings:
+      role: role
+      content: content
+
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.001
+save_safetensors: true
+sequence_len: 2048
+sample_packing: false
+pad_to_sequence_len: false
+use_pose: true
+pose_max_context_len: 65536
+
+overrides_of_model_config:
+  rope_theta: 10000.0
+  max_position_embeddings: 65536
+
+gradient_accumulation_steps: 8
+micro_batch_size: 32
+num_epochs: 1
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 3e-4
+
+train_on_inputs: false
+group_by_length: false
+bf16: true
+fp16:
+tf32: true
+
+gradient_checkpointing: false
+gradient_checkpointing_kwargs:
+  use_reentrant: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+sdp_attention:
+s2_attention:
+
+save_steps: 200
+warmup_steps: 20
+eval_steps: 200
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+
+```
+
+</details><br>
+
+# tiny-ko-124m-sft
+
+This model is a fine-tuned version of [minpeter/tiny-ko-124m-base](https://huggingface.co/minpeter/tiny-ko-124m-base) on the lemon-mint/smol-koreantalk dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.8151
+
+## 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
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 512
+- total_eval_batch_size: 64
+- 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: 20
+- training_steps: 887
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| No log        | 0      | 0    | 2.8035          |
+| 2.0195        | 0.2256 | 200  | 1.9871          |
+| 1.8857        | 0.4513 | 400  | 1.8815          |
+| 1.8013        | 0.6769 | 600  | 1.8270          |
+| 1.8489        | 0.9026 | 800  | 1.8151          |
+
+
+### Framework versions
+
+- Transformers 4.52.4
+- Pytorch 2.6.0+cu124
+- Datasets 3.6.0
+- Tokenizers 0.21.1