Training in progress, step 360

284c3982-7bc3-4e42-a78c-849f03798c5f.yml

@@ -0,0 +1,51 @@
+base_model: unsloth/Qwen2-7B-Instruct
+batch_size: 32
+bf16: true
+chat_template: tokenizer_default_fallback_alpaca
+datasets:
+- data_files:
+  - 3e306f9221b79797_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/3e306f9221b79797_train_data.json
+  type:
+    field_input: dialogue
+    field_instruction: rendered_input
+    field_output: summary
+    format: '{instruction} {input}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+eval_steps: 20
+flash_attention: true
+gpu_memory_limit: 80GiB
+gradient_checkpointing: true
+group_by_length: true
+hub_model_id: willtensora/f3c9c6cc-5806-45b4-aab9-d03de6022b3a
+hub_strategy: checkpoint
+learning_rate: 0.0002
+logging_steps: 10
+lr_scheduler: cosine
+max_steps: 2500
+micro_batch_size: 4
+model_type: AutoModelForCausalLM
+optimizer: adamw_bnb_8bit
+output_dir: /workspace/axolotl/configs
+pad_to_sequence_len: true
+resize_token_embeddings_to_32x: false
+sample_packing: false
+save_steps: 40
+save_total_limit: 1
+sequence_len: 2048
+tokenizer_type: Qwen2TokenizerFast
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 0.1
+wandb_entity: ''
+wandb_mode: online
+wandb_name: unsloth/Qwen2-7B-Instruct-/workspace/input_data/3e306f9221b79797_train_data.json
+wandb_project: Gradients-On-Demand
+wandb_run: your_name
+wandb_runid: default
+warmup_ratio: 0.05
+xformers_attention: true

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36f4d7f40c1dfe0aa7d2a4231f75acffd5b79eac451b993d900c03c6ce59780c
+oid sha256:3a5e585476bd5cc6203124e4cba581a60d5b891d3f5443648d4f675341248b47
 size 988097824