End of training

README.md

@@ -0,0 +1,158 @@
+---
+library_name: peft
+license: llama3
+base_model: tokyotech-llm/Llama-3-Swallow-8B-v0.1
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: 8cad90b9-d437-42b4-afb4-e51b67e64e50
+  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: tokyotech-llm/Llama-3-Swallow-8B-v0.1
+bf16: false
+chat_template: llama3
+dataset_prepared_path: null
+datasets:
+- data_files:
+  - 3f72bc6633b04dfb_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/3f72bc6633b04dfb_train_data.json
+  type:
+    field_input: titles
+    field_instruction: instructions
+    field_output: essays
+    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: true
+fsdp: null
+fsdp_config: null
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+group_by_length: false
+hub_model_id: lesso/8cad90b9-d437-42b4-afb4-e51b67e64e50
+hub_repo: null
+hub_strategy: checkpoint
+hub_token: null
+learning_rate: 0.0002
+load_in_4bit: false
+load_in_8bit: false
+local_rank: null
+logging_steps: 1
+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
+max_steps: 10
+micro_batch_size: 1
+mlflow_experiment_name: /tmp/3f72bc6633b04dfb_train_data.json
+model_type: AutoModelForCausalLM
+num_epochs: 1
+optimizer: adamw_hf
+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: <|end_of_text|>
+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: 8cad90b9-d437-42b4-afb4-e51b67e64e50
+wandb_project: Gradients-On-Demand
+wandb_run: your_name
+wandb_runid: 8cad90b9-d437-42b4-afb4-e51b67e64e50
+warmup_steps: 10
+weight_decay: 0.0
+xformers_attention: null
+
+```
+
+</details><br>
+
+# 8cad90b9-d437-42b4-afb4-e51b67e64e50
+
+This model is a fine-tuned version of [tokyotech-llm/Llama-3-Swallow-8B-v0.1](https://huggingface.co/tokyotech-llm/Llama-3-Swallow-8B-v0.1) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.1792
+
+## 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: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- total_eval_batch_size: 2
+- optimizer: Use OptimizerNames.ADAMW_HF 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: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 2.3204        | 0.0054 | 1    | 2.2009          |
+| 2.2241        | 0.0162 | 3    | 2.1992          |
+| 2.4093        | 0.0324 | 6    | 2.1916          |
+| 2.2467        | 0.0486 | 9    | 2.1792          |
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.46.0
+- Pytorch 2.5.0+cu124
+- Datasets 3.0.1
+- Tokenizers 0.20.1

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
+    "v_proj",
     "up_proj",
     "o_proj",
-    "q_proj",
     "down_proj",
-    "k_proj",
-    "v_proj"
+    "q_proj",
+    "gate_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dd44e7c4608b202bc0f01c2f4a3f50f7ecd28e7fd03c4c0097240dbaadfaf2b
+size 84047370

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:096d0d1306c228ce8c01652e2e9dc22fbfdf66e56fe1c3cc3c3f3341baa59e44
+oid sha256:dd8d602b8c8217d2bad01c439cf265d8636e230eef9088012f7f0abb56d28cf2
 size 83945296

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd961290b5c1511222dcde7c5274eeb95e8e3143dbf3b403d7a4f50c5202a8b5
+oid sha256:46bccd6964f4291101ddc4731a06bfcf4544fcbb608a5a0128bc2068c8364f7b
 size 6776