Updating for A100 training

02-autotrain.ipynb

@@ -50,7 +50,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "928f44f483504b438e0fdbd4df3d7dd5",
+       "model_id": "b5b27c90c4e849e6aa04587d526e108f",
        "version_major": 2,
        "version_minor": 0
       },
@@ -111,10 +111,10 @@
     "        },\n",
     "    \"params\": {\n",
     "        \"block_size\": 512,\n",
-    "        \"model_max_length\": 1500,\n",
+    "        \"model_max_length\": 1750,\n",
     "        \"epochs\": 4,\n",
     "        \"batch_size\": 8,\n",
-    "        \"lr\": 1e-6,\n",
+    "        \"lr\": 5e-5,\n",
     "        \"peft\": True,\n",
     "        \"quantization\": \"int4\",\n",
     "        \"target_modules\": \"all-linear\",\n",
@@ -191,55 +191,55 @@
      "output_type": "stream",
      "text": [
       "Running autotrain with config: ./autotrain_configs/conversation_RFA_gpt3_5.yml\n",
-      "INFO     | 2025-01-08 14:33:16 | autotrain.cli.autotrain:main:58 - Using AutoTrain configuration: ./autotrain_configs/conversation_RFA_gpt3_5.yml\n",
-      "INFO     | 2025-01-08 14:33:16 | autotrain.parser:__post_init__:165 - Running task: lm_training\n",
-      "INFO     | 2025-01-08 14:33:16 | autotrain.parser:__post_init__:166 - Using backend: spaces-l4x1\n",
-      "INFO     | 2025-01-08 14:33:16 | autotrain.parser:run:224 - {'model': 'tiiuae/Falcon3-7B-Instruct', 'project_name': 'falcon-v03-poe-RFA-gpt3-5', 'data_path': 'derek-thomas/labeled-multiple-choice-explained-falcon-tokenized', 'train_split': 'train', 'valid_split': None, 'add_eos_token': True, 'block_size': 512, 'model_max_length': 1500, 'padding': 'right', 'trainer': 'sft', 'use_flash_attention_2': False, 'log': 'tensorboard', 'disable_gradient_checkpointing': False, 'logging_steps': -1, 'eval_strategy': 'epoch', 'save_total_limit': 1, 'auto_find_batch_size': False, 'mixed_precision': 'bf16', 'lr': 3e-07, 'epochs': 4, 'batch_size': 1, 'warmup_ratio': 0.1, 'gradient_accumulation': 8, 'optimizer': 'adamw_torch', 'scheduler': 'linear', 'weight_decay': 0.0, 'max_grad_norm': 1.0, 'seed': 42, 'chat_template': 'tokenizer', 'quantization': 'int4', 'target_modules': 'all-linear', 'merge_adapter': False, 'peft': True, 'lora_r': 16, 'lora_alpha': 32, 'lora_dropout': 0.05, 'model_ref': None, 'dpo_beta': 0.1, 'max_prompt_length': 128, 'max_completion_length': None, 'prompt_text_column': None, 'text_column': 'conversation_RFA_gpt3_5', 'rejected_text_column': None, 'push_to_hub': True, 'username': 'derek-thomas', 'token': '*****', 'unsloth': False, 'distributed_backend': None}\n",
-      "INFO     | 2025-01-08 14:33:23 | autotrain.parser:run:229 - Job ID: derek-thomas/autotrain-falcon-v03-poe-RFA-gpt3-5\n",
+      "INFO     | 2025-01-10 13:45:51 | autotrain.cli.autotrain:main:58 - Using AutoTrain configuration: ./autotrain_configs/conversation_RFA_gpt3_5.yml\n",
+      "INFO     | 2025-01-10 13:45:51 | autotrain.parser:__post_init__:165 - Running task: lm_training\n",
+      "INFO     | 2025-01-10 13:45:51 | autotrain.parser:__post_init__:166 - Using backend: spaces-a100-large\n",
+      "INFO     | 2025-01-10 13:45:51 | autotrain.parser:run:224 - {'model': 'tiiuae/Falcon3-7B-Instruct', 'project_name': 'falcon-v03-poe-RFA-gpt3-5', 'data_path': 'derek-thomas/labeled-multiple-choice-explained-falcon-tokenized', 'train_split': 'train', 'valid_split': None, 'add_eos_token': True, 'block_size': 512, 'model_max_length': 1750, 'padding': 'right', 'trainer': 'sft', 'use_flash_attention_2': False, 'log': 'tensorboard', 'disable_gradient_checkpointing': False, 'logging_steps': -1, 'eval_strategy': 'epoch', 'save_total_limit': 1, 'auto_find_batch_size': False, 'mixed_precision': 'bf16', 'lr': 5e-05, 'epochs': 4, 'batch_size': 8, 'warmup_ratio': 0.1, 'gradient_accumulation': 8, 'optimizer': 'adamw_torch', 'scheduler': 'linear', 'weight_decay': 0.0, 'max_grad_norm': 1.0, 'seed': 42, 'chat_template': 'tokenizer', 'quantization': 'int4', 'target_modules': 'all-linear', 'merge_adapter': False, 'peft': True, 'lora_r': 16, 'lora_alpha': 32, 'lora_dropout': 0.05, 'model_ref': None, 'dpo_beta': 0.1, 'max_prompt_length': 128, 'max_completion_length': None, 'prompt_text_column': None, 'text_column': 'conversation_RFA_gpt3_5', 'rejected_text_column': None, 'push_to_hub': True, 'username': 'derek-thomas', 'token': '*****', 'unsloth': False, 'distributed_backend': None}\n",
+      "INFO     | 2025-01-10 13:45:54 | autotrain.parser:run:229 - Job ID: derek-thomas/autotrain-falcon-v03-poe-RFA-gpt3-5\n",
       "\n",
       "---\n",
       "https://huggingface.co/spaces/derek-thomas/autotrain-falcon-v03-poe-RFA-gpt3-5\n",
       "---\n",
       "\n",
       "Running autotrain with config: ./autotrain_configs/conversation_RFA_falcon.yml\n",
-      "INFO     | 2025-01-08 14:33:26 | autotrain.cli.autotrain:main:58 - Using AutoTrain configuration: ./autotrain_configs/conversation_RFA_falcon.yml\n",
-      "INFO     | 2025-01-08 14:33:26 | autotrain.parser:__post_init__:165 - Running task: lm_training\n",
-      "INFO     | 2025-01-08 14:33:26 | autotrain.parser:__post_init__:166 - Using backend: spaces-l4x1\n",
-      "INFO     | 2025-01-08 14:33:26 | autotrain.parser:run:224 - {'model': 'tiiuae/Falcon3-7B-Instruct', 'project_name': 'falcon-v03-poe-RFA-falcon', 'data_path': 'derek-thomas/labeled-multiple-choice-explained-falcon-tokenized', 'train_split': 'train', 'valid_split': None, 'add_eos_token': True, 'block_size': 512, 'model_max_length': 1500, 'padding': 'right', 'trainer': 'sft', 'use_flash_attention_2': False, 'log': 'tensorboard', 'disable_gradient_checkpointing': False, 'logging_steps': -1, 'eval_strategy': 'epoch', 'save_total_limit': 1, 'auto_find_batch_size': False, 'mixed_precision': 'bf16', 'lr': 3e-07, 'epochs': 4, 'batch_size': 1, 'warmup_ratio': 0.1, 'gradient_accumulation': 8, 'optimizer': 'adamw_torch', 'scheduler': 'linear', 'weight_decay': 0.0, 'max_grad_norm': 1.0, 'seed': 42, 'chat_template': 'tokenizer', 'quantization': 'int4', 'target_modules': 'all-linear', 'merge_adapter': False, 'peft': True, 'lora_r': 16, 'lora_alpha': 32, 'lora_dropout': 0.05, 'model_ref': None, 'dpo_beta': 0.1, 'max_prompt_length': 128, 'max_completion_length': None, 'prompt_text_column': None, 'text_column': 'conversation_RFA_falcon', 'rejected_text_column': None, 'push_to_hub': True, 'username': 'derek-thomas', 'token': '*****', 'unsloth': False, 'distributed_backend': None}\n",
-      "INFO     | 2025-01-08 14:33:32 | autotrain.parser:run:229 - Job ID: derek-thomas/autotrain-falcon-v03-poe-RFA-falcon\n",
+      "INFO     | 2025-01-10 13:45:58 | autotrain.cli.autotrain:main:58 - Using AutoTrain configuration: ./autotrain_configs/conversation_RFA_falcon.yml\n",
+      "INFO     | 2025-01-10 13:45:58 | autotrain.parser:__post_init__:165 - Running task: lm_training\n",
+      "INFO     | 2025-01-10 13:45:58 | autotrain.parser:__post_init__:166 - Using backend: spaces-a100-large\n",
+      "INFO     | 2025-01-10 13:45:58 | autotrain.parser:run:224 - {'model': 'tiiuae/Falcon3-7B-Instruct', 'project_name': 'falcon-v03-poe-RFA-falcon', 'data_path': 'derek-thomas/labeled-multiple-choice-explained-falcon-tokenized', 'train_split': 'train', 'valid_split': None, 'add_eos_token': True, 'block_size': 512, 'model_max_length': 1750, 'padding': 'right', 'trainer': 'sft', 'use_flash_attention_2': False, 'log': 'tensorboard', 'disable_gradient_checkpointing': False, 'logging_steps': -1, 'eval_strategy': 'epoch', 'save_total_limit': 1, 'auto_find_batch_size': False, 'mixed_precision': 'bf16', 'lr': 5e-05, 'epochs': 4, 'batch_size': 8, 'warmup_ratio': 0.1, 'gradient_accumulation': 8, 'optimizer': 'adamw_torch', 'scheduler': 'linear', 'weight_decay': 0.0, 'max_grad_norm': 1.0, 'seed': 42, 'chat_template': 'tokenizer', 'quantization': 'int4', 'target_modules': 'all-linear', 'merge_adapter': False, 'peft': True, 'lora_r': 16, 'lora_alpha': 32, 'lora_dropout': 0.05, 'model_ref': None, 'dpo_beta': 0.1, 'max_prompt_length': 128, 'max_completion_length': None, 'prompt_text_column': None, 'text_column': 'conversation_RFA_falcon', 'rejected_text_column': None, 'push_to_hub': True, 'username': 'derek-thomas', 'token': '*****', 'unsloth': False, 'distributed_backend': None}\n",
+      "INFO     | 2025-01-10 13:46:01 | autotrain.parser:run:229 - Job ID: derek-thomas/autotrain-falcon-v03-poe-RFA-falcon\n",
       "\n",
       "---\n",
       "https://huggingface.co/spaces/derek-thomas/autotrain-falcon-v03-poe-RFA-falcon\n",
       "---\n",
       "\n",
       "Running autotrain with config: ./autotrain_configs/conversation_FAR_gpt3_5.yml\n",
-      "INFO     | 2025-01-08 14:33:36 | autotrain.cli.autotrain:main:58 - Using AutoTrain configuration: ./autotrain_configs/conversation_FAR_gpt3_5.yml\n",
-      "INFO     | 2025-01-08 14:33:36 | autotrain.parser:__post_init__:165 - Running task: lm_training\n",
-      "INFO     | 2025-01-08 14:33:36 | autotrain.parser:__post_init__:166 - Using backend: spaces-l4x1\n",
-      "INFO     | 2025-01-08 14:33:36 | autotrain.parser:run:224 - {'model': 'tiiuae/Falcon3-7B-Instruct', 'project_name': 'falcon-v03-poe-FAR-gpt3-5', 'data_path': 'derek-thomas/labeled-multiple-choice-explained-falcon-tokenized', 'train_split': 'train', 'valid_split': None, 'add_eos_token': True, 'block_size': 512, 'model_max_length': 1500, 'padding': 'right', 'trainer': 'sft', 'use_flash_attention_2': False, 'log': 'tensorboard', 'disable_gradient_checkpointing': False, 'logging_steps': -1, 'eval_strategy': 'epoch', 'save_total_limit': 1, 'auto_find_batch_size': False, 'mixed_precision': 'bf16', 'lr': 3e-07, 'epochs': 4, 'batch_size': 1, 'warmup_ratio': 0.1, 'gradient_accumulation': 8, 'optimizer': 'adamw_torch', 'scheduler': 'linear', 'weight_decay': 0.0, 'max_grad_norm': 1.0, 'seed': 42, 'chat_template': 'tokenizer', 'quantization': 'int4', 'target_modules': 'all-linear', 'merge_adapter': False, 'peft': True, 'lora_r': 16, 'lora_alpha': 32, 'lora_dropout': 0.05, 'model_ref': None, 'dpo_beta': 0.1, 'max_prompt_length': 128, 'max_completion_length': None, 'prompt_text_column': None, 'text_column': 'conversation_FAR_gpt3_5', 'rejected_text_column': None, 'push_to_hub': True, 'username': 'derek-thomas', 'token': '*****', 'unsloth': False, 'distributed_backend': None}\n",
-      "INFO     | 2025-01-08 14:33:41 | autotrain.parser:run:229 - Job ID: derek-thomas/autotrain-falcon-v03-poe-FAR-gpt3-5\n",
+      "INFO     | 2025-01-10 13:46:05 | autotrain.cli.autotrain:main:58 - Using AutoTrain configuration: ./autotrain_configs/conversation_FAR_gpt3_5.yml\n",
+      "INFO     | 2025-01-10 13:46:05 | autotrain.parser:__post_init__:165 - Running task: lm_training\n",
+      "INFO     | 2025-01-10 13:46:05 | autotrain.parser:__post_init__:166 - Using backend: spaces-a100-large\n",
+      "INFO     | 2025-01-10 13:46:05 | autotrain.parser:run:224 - {'model': 'tiiuae/Falcon3-7B-Instruct', 'project_name': 'falcon-v03-poe-FAR-gpt3-5', 'data_path': 'derek-thomas/labeled-multiple-choice-explained-falcon-tokenized', 'train_split': 'train', 'valid_split': None, 'add_eos_token': True, 'block_size': 512, 'model_max_length': 1750, 'padding': 'right', 'trainer': 'sft', 'use_flash_attention_2': False, 'log': 'tensorboard', 'disable_gradient_checkpointing': False, 'logging_steps': -1, 'eval_strategy': 'epoch', 'save_total_limit': 1, 'auto_find_batch_size': False, 'mixed_precision': 'bf16', 'lr': 5e-05, 'epochs': 4, 'batch_size': 8, 'warmup_ratio': 0.1, 'gradient_accumulation': 8, 'optimizer': 'adamw_torch', 'scheduler': 'linear', 'weight_decay': 0.0, 'max_grad_norm': 1.0, 'seed': 42, 'chat_template': 'tokenizer', 'quantization': 'int4', 'target_modules': 'all-linear', 'merge_adapter': False, 'peft': True, 'lora_r': 16, 'lora_alpha': 32, 'lora_dropout': 0.05, 'model_ref': None, 'dpo_beta': 0.1, 'max_prompt_length': 128, 'max_completion_length': None, 'prompt_text_column': None, 'text_column': 'conversation_FAR_gpt3_5', 'rejected_text_column': None, 'push_to_hub': True, 'username': 'derek-thomas', 'token': '*****', 'unsloth': False, 'distributed_backend': None}\n",
+      "INFO     | 2025-01-10 13:46:08 | autotrain.parser:run:229 - Job ID: derek-thomas/autotrain-falcon-v03-poe-FAR-gpt3-5\n",
       "\n",
       "---\n",
       "https://huggingface.co/spaces/derek-thomas/autotrain-falcon-v03-poe-FAR-gpt3-5\n",
       "---\n",
       "\n",
       "Running autotrain with config: ./autotrain_configs/conversation_FAR_falcon.yml\n",
-      "INFO     | 2025-01-08 14:33:45 | autotrain.cli.autotrain:main:58 - Using AutoTrain configuration: ./autotrain_configs/conversation_FAR_falcon.yml\n",
-      "INFO     | 2025-01-08 14:33:45 | autotrain.parser:__post_init__:165 - Running task: lm_training\n",
-      "INFO     | 2025-01-08 14:33:45 | autotrain.parser:__post_init__:166 - Using backend: spaces-l4x1\n",
-      "INFO     | 2025-01-08 14:33:45 | autotrain.parser:run:224 - {'model': 'tiiuae/Falcon3-7B-Instruct', 'project_name': 'falcon-v03-poe-FAR-falcon', 'data_path': 'derek-thomas/labeled-multiple-choice-explained-falcon-tokenized', 'train_split': 'train', 'valid_split': None, 'add_eos_token': True, 'block_size': 512, 'model_max_length': 1500, 'padding': 'right', 'trainer': 'sft', 'use_flash_attention_2': False, 'log': 'tensorboard', 'disable_gradient_checkpointing': False, 'logging_steps': -1, 'eval_strategy': 'epoch', 'save_total_limit': 1, 'auto_find_batch_size': False, 'mixed_precision': 'bf16', 'lr': 3e-07, 'epochs': 4, 'batch_size': 1, 'warmup_ratio': 0.1, 'gradient_accumulation': 8, 'optimizer': 'adamw_torch', 'scheduler': 'linear', 'weight_decay': 0.0, 'max_grad_norm': 1.0, 'seed': 42, 'chat_template': 'tokenizer', 'quantization': 'int4', 'target_modules': 'all-linear', 'merge_adapter': False, 'peft': True, 'lora_r': 16, 'lora_alpha': 32, 'lora_dropout': 0.05, 'model_ref': None, 'dpo_beta': 0.1, 'max_prompt_length': 128, 'max_completion_length': None, 'prompt_text_column': None, 'text_column': 'conversation_FAR_falcon', 'rejected_text_column': None, 'push_to_hub': True, 'username': 'derek-thomas', 'token': '*****', 'unsloth': False, 'distributed_backend': None}\n",
-      "INFO     | 2025-01-08 14:33:51 | autotrain.parser:run:229 - Job ID: derek-thomas/autotrain-falcon-v03-poe-FAR-falcon\n",
+      "INFO     | 2025-01-10 13:46:13 | autotrain.cli.autotrain:main:58 - Using AutoTrain configuration: ./autotrain_configs/conversation_FAR_falcon.yml\n",
+      "INFO     | 2025-01-10 13:46:13 | autotrain.parser:__post_init__:165 - Running task: lm_training\n",
+      "INFO     | 2025-01-10 13:46:13 | autotrain.parser:__post_init__:166 - Using backend: spaces-a100-large\n",
+      "INFO     | 2025-01-10 13:46:13 | autotrain.parser:run:224 - {'model': 'tiiuae/Falcon3-7B-Instruct', 'project_name': 'falcon-v03-poe-FAR-falcon', 'data_path': 'derek-thomas/labeled-multiple-choice-explained-falcon-tokenized', 'train_split': 'train', 'valid_split': None, 'add_eos_token': True, 'block_size': 512, 'model_max_length': 1750, 'padding': 'right', 'trainer': 'sft', 'use_flash_attention_2': False, 'log': 'tensorboard', 'disable_gradient_checkpointing': False, 'logging_steps': -1, 'eval_strategy': 'epoch', 'save_total_limit': 1, 'auto_find_batch_size': False, 'mixed_precision': 'bf16', 'lr': 5e-05, 'epochs': 4, 'batch_size': 8, 'warmup_ratio': 0.1, 'gradient_accumulation': 8, 'optimizer': 'adamw_torch', 'scheduler': 'linear', 'weight_decay': 0.0, 'max_grad_norm': 1.0, 'seed': 42, 'chat_template': 'tokenizer', 'quantization': 'int4', 'target_modules': 'all-linear', 'merge_adapter': False, 'peft': True, 'lora_r': 16, 'lora_alpha': 32, 'lora_dropout': 0.05, 'model_ref': None, 'dpo_beta': 0.1, 'max_prompt_length': 128, 'max_completion_length': None, 'prompt_text_column': None, 'text_column': 'conversation_FAR_falcon', 'rejected_text_column': None, 'push_to_hub': True, 'username': 'derek-thomas', 'token': '*****', 'unsloth': False, 'distributed_backend': None}\n",
+      "INFO     | 2025-01-10 13:46:16 | autotrain.parser:run:229 - Job ID: derek-thomas/autotrain-falcon-v03-poe-FAR-falcon\n",
       "\n",
       "---\n",
       "https://huggingface.co/spaces/derek-thomas/autotrain-falcon-v03-poe-FAR-falcon\n",
       "---\n",
       "\n",
       "Running autotrain with config: ./autotrain_configs/conversation_FA.yml\n",
-      "INFO     | 2025-01-08 14:33:54 | autotrain.cli.autotrain:main:58 - Using AutoTrain configuration: ./autotrain_configs/conversation_FA.yml\n",
-      "INFO     | 2025-01-08 14:33:54 | autotrain.parser:__post_init__:165 - Running task: lm_training\n",
-      "INFO     | 2025-01-08 14:33:54 | autotrain.parser:__post_init__:166 - Using backend: spaces-l4x1\n",
-      "INFO     | 2025-01-08 14:33:54 | autotrain.parser:run:224 - {'model': 'tiiuae/Falcon3-7B-Instruct', 'project_name': 'falcon-v03-poe-FA', 'data_path': 'derek-thomas/labeled-multiple-choice-explained-falcon-tokenized', 'train_split': 'train', 'valid_split': None, 'add_eos_token': True, 'block_size': 512, 'model_max_length': 1500, 'padding': 'right', 'trainer': 'sft', 'use_flash_attention_2': False, 'log': 'tensorboard', 'disable_gradient_checkpointing': False, 'logging_steps': -1, 'eval_strategy': 'epoch', 'save_total_limit': 1, 'auto_find_batch_size': False, 'mixed_precision': 'bf16', 'lr': 3e-07, 'epochs': 4, 'batch_size': 1, 'warmup_ratio': 0.1, 'gradient_accumulation': 8, 'optimizer': 'adamw_torch', 'scheduler': 'linear', 'weight_decay': 0.0, 'max_grad_norm': 1.0, 'seed': 42, 'chat_template': 'tokenizer', 'quantization': 'int4', 'target_modules': 'all-linear', 'merge_adapter': False, 'peft': True, 'lora_r': 16, 'lora_alpha': 32, 'lora_dropout': 0.05, 'model_ref': None, 'dpo_beta': 0.1, 'max_prompt_length': 128, 'max_completion_length': None, 'prompt_text_column': None, 'text_column': 'conversation_FA', 'rejected_text_column': None, 'push_to_hub': True, 'username': 'derek-thomas', 'token': '*****', 'unsloth': False, 'distributed_backend': None}\n",
-      "INFO     | 2025-01-08 14:34:00 | autotrain.parser:run:229 - Job ID: derek-thomas/autotrain-falcon-v03-poe-FA\n",
+      "INFO     | 2025-01-10 13:46:20 | autotrain.cli.autotrain:main:58 - Using AutoTrain configuration: ./autotrain_configs/conversation_FA.yml\n",
+      "INFO     | 2025-01-10 13:46:20 | autotrain.parser:__post_init__:165 - Running task: lm_training\n",
+      "INFO     | 2025-01-10 13:46:20 | autotrain.parser:__post_init__:166 - Using backend: spaces-a100-large\n",
+      "INFO     | 2025-01-10 13:46:20 | autotrain.parser:run:224 - {'model': 'tiiuae/Falcon3-7B-Instruct', 'project_name': 'falcon-v03-poe-FA', 'data_path': 'derek-thomas/labeled-multiple-choice-explained-falcon-tokenized', 'train_split': 'train', 'valid_split': None, 'add_eos_token': True, 'block_size': 512, 'model_max_length': 1750, 'padding': 'right', 'trainer': 'sft', 'use_flash_attention_2': False, 'log': 'tensorboard', 'disable_gradient_checkpointing': False, 'logging_steps': -1, 'eval_strategy': 'epoch', 'save_total_limit': 1, 'auto_find_batch_size': False, 'mixed_precision': 'bf16', 'lr': 5e-05, 'epochs': 4, 'batch_size': 8, 'warmup_ratio': 0.1, 'gradient_accumulation': 8, 'optimizer': 'adamw_torch', 'scheduler': 'linear', 'weight_decay': 0.0, 'max_grad_norm': 1.0, 'seed': 42, 'chat_template': 'tokenizer', 'quantization': 'int4', 'target_modules': 'all-linear', 'merge_adapter': False, 'peft': True, 'lora_r': 16, 'lora_alpha': 32, 'lora_dropout': 0.05, 'model_ref': None, 'dpo_beta': 0.1, 'max_prompt_length': 128, 'max_completion_length': None, 'prompt_text_column': None, 'text_column': 'conversation_FA', 'rejected_text_column': None, 'push_to_hub': True, 'username': 'derek-thomas', 'token': '*****', 'unsloth': False, 'distributed_backend': None}\n",
+      "INFO     | 2025-01-10 13:46:23 | autotrain.parser:run:229 - Job ID: derek-thomas/autotrain-falcon-v03-poe-FA\n",
       "\n",
       "---\n",
       "https://huggingface.co/spaces/derek-thomas/autotrain-falcon-v03-poe-FA\n",
@@ -284,7 +284,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 9,
    "id": "adf09687-ab1e-4f1e-8bf9-317cc928467a",
    "metadata": {},
    "outputs": [],
@@ -295,7 +295,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 7,
    "id": "19d80d26-cda4-41fb-a125-06060c3f90ce",
    "metadata": {},
    "outputs": [
@@ -335,10 +335,82 @@
    ]
   },
   {
-   "metadata": {},
    "cell_type": "code",
-   "outputs": [],
-   "execution_count": null,
+   "execution_count": 10,
+   "id": "de150f086f1c72fa",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdin",
+     "output_type": "stream",
+     "text": [
+      "Are you sure you want to delete the space 'derek-thomas/autotrain-falcon-v03-poe-RFA-gpt3-5'? (y/n):  y\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Deleted derek-thomas/autotrain-falcon-v03-poe-RFA-gpt3-5\n"
+     ]
+    },
+    {
+     "name": "stdin",
+     "output_type": "stream",
+     "text": [
+      "Are you sure you want to delete the space 'derek-thomas/autotrain-falcon-v03-poe-RFA-falcon'? (y/n):  y\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Deleted derek-thomas/autotrain-falcon-v03-poe-RFA-falcon\n"
+     ]
+    },
+    {
+     "name": "stdin",
+     "output_type": "stream",
+     "text": [
+      "Are you sure you want to delete the space 'derek-thomas/autotrain-falcon-v03-poe-FAR-gpt3-5'? (y/n):  y\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Deleted derek-thomas/autotrain-falcon-v03-poe-FAR-gpt3-5\n"
+     ]
+    },
+    {
+     "name": "stdin",
+     "output_type": "stream",
+     "text": [
+      "Are you sure you want to delete the space 'derek-thomas/autotrain-falcon-v03-poe-FAR-falcon'? (y/n):  y\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Deleted derek-thomas/autotrain-falcon-v03-poe-FAR-falcon\n"
+     ]
+    },
+    {
+     "name": "stdin",
+     "output_type": "stream",
+     "text": [
+      "Are you sure you want to delete the space 'derek-thomas/autotrain-falcon-v03-poe-FA'? (y/n):  y\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Deleted derek-thomas/autotrain-falcon-v03-poe-FA\n"
+     ]
+    }
+   ],
    "source": [
     "for space in autotrain_spaces:\n",
     "    confirm = input(f\"Are you sure you want to delete the space '{space}'? (y/n): \")\n",
@@ -347,35 +419,105 @@
     "        print(f\"Deleted {space}\")\n",
     "    else:\n",
     "        print(f\"Skipped {space}\")\n"
-   ],
-   "id": "de150f086f1c72fa"
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "markdown",
+   "id": "e6aa4788fe8b0297",
+   "metadata": {},
    "source": [
     "<span style=\"color:red; font-size:20px; font-weight:bold;\">\n",
     "ONLY RUN THIS IF YOU NEED TO RESTART FROM SCRATCH\n",
     "THIS WILL DELETE YOUR MODELS\n",
     "</span>\n"
-   ],
-   "id": "e6aa4788fe8b0297"
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "code",
-   "outputs": [],
-   "execution_count": null,
-   "source": [
-    "# for model in autotrain_models:\n",
-    "#     confirm = input(f\"Are you sure you want to delete the model '{model}'? (y/n): \")\n",
-    "#     if confirm.lower() == 'y':\n",
-    "#         api.delete_repo(model, repo_type='model')\n",
-    "#         print(f\"Deleted {model}\")\n",
-    "#     else:\n",
-    "#         print(f\"Skipped {model}\")\n"
+   "execution_count": 11,
+   "id": "c887e61558785e69",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdin",
+     "output_type": "stream",
+     "text": [
+      "Are you sure you want to delete the model 'derek-thomas/falcon-v03-poe-RFA-gpt3-5'? (y/n):  y\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Deleted derek-thomas/falcon-v03-poe-RFA-gpt3-5\n"
+     ]
+    },
+    {
+     "name": "stdin",
+     "output_type": "stream",
+     "text": [
+      "Are you sure you want to delete the model 'derek-thomas/falcon-v03-poe-RFA-falcon'? (y/n):  y\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Deleted derek-thomas/falcon-v03-poe-RFA-falcon\n"
+     ]
+    },
+    {
+     "name": "stdin",
+     "output_type": "stream",
+     "text": [
+      "Are you sure you want to delete the model 'derek-thomas/falcon-v03-poe-FAR-gpt3-5'? (y/n):  y\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Deleted derek-thomas/falcon-v03-poe-FAR-gpt3-5\n"
+     ]
+    },
+    {
+     "name": "stdin",
+     "output_type": "stream",
+     "text": [
+      "Are you sure you want to delete the model 'derek-thomas/falcon-v03-poe-FAR-falcon'? (y/n):  y\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Deleted derek-thomas/falcon-v03-poe-FAR-falcon\n"
+     ]
+    },
+    {
+     "name": "stdin",
+     "output_type": "stream",
+     "text": [
+      "Are you sure you want to delete the model 'derek-thomas/falcon-v03-poe-FA'? (y/n):  y\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Deleted derek-thomas/falcon-v03-poe-FA\n"
+     ]
+    }
    ],
-   "id": "c887e61558785e69"
+   "source": [
+    "for model in autotrain_models:\n",
+    "    confirm = input(f\"Are you sure you want to delete the model '{model}'? (y/n): \")\n",
+    "    if confirm.lower() == 'y':\n",
+    "        api.delete_repo(model, repo_type='model')\n",
+    "        print(f\"Deleted {model}\")\n",
+    "    else:\n",
+    "        print(f\"Skipped {model}\")\n"
+   ]
   },
   {
    "cell_type": "code",