Add dataset_info

README.md

@@ -25,7 +25,7 @@ set CUDA_VISIBLE_DEVICES=0 && llamafactory-cli train --stage sft --do_train True
 
 Stage B: Continued, `orpo`
 ```
-set CUDA_VISIBLE_DEVICES=0 && llamafactory-cli train --stage dpo --do_train True --model_name_or_path meta-llama/Meta-Llama-3.1-8B-Instruct --preprocessing_num_workers 1 --finetuning_type lora --template alpaca --rope_scaling linear --flash_attn fa2 --dataset_dir data --dataset orca_dpo_de --cutoff_len 4000 --learning_rate 5e-05 --num_train_epochs 1.0 --max_samples 100000 --per_device_train_batch_size 1 --gradient_accumulation_steps 1 --lr_scheduler_type cosine --max_grad_norm 1.0 --logging_steps 10 --save_steps 1000 --warmup_steps 0 --neftune_noise_alpha 5 --optim adamw_8bit --packing True --report_to none --output_dir saves\LLaMA3.1-8B-Chat\lora\Llama-3.1-8B-German-ORPO --bf16 True --plot_loss True --ddp_timeout 180000000 --include_num_input_tokens_seen True --quantization_bit 4 --quantization_method bitsandbytes --lora_rank 32 --lora_alpha 64 --lora_dropout 0.35 --lora_target all --pref_beta 0.1 --pref_ftx 0 --pref_loss orpo --adapter_name_or_path saves\LLaMA3.1-8B-Chat\lora\Llama-3.1-8B-German
+set CUDA_VISIBLE_DEVICES=0 && llamafactory-cli train --stage dpo --do_train True --model_name_or_path meta-llama/Meta-Llama-3.1-8B-Instruct --preprocessing_num_workers 1 --finetuning_type lora --template alpaca --rope_scaling linear --flash_attn fa2 --dataset_dir data --dataset fix_orca_dpo_de --cutoff_len 4000 --learning_rate 5e-05 --num_train_epochs 1.0 --max_samples 100000 --per_device_train_batch_size 1 --gradient_accumulation_steps 1 --lr_scheduler_type cosine --max_grad_norm 1.0 --logging_steps 10 --save_steps 1000 --warmup_steps 0 --neftune_noise_alpha 5 --optim adamw_8bit --packing True --report_to none --output_dir saves\LLaMA3.1-8B-Chat\lora\Llama-3.1-8B-German-ORPO --bf16 True --plot_loss True --ddp_timeout 180000000 --include_num_input_tokens_seen True --quantization_bit 4 --quantization_method bitsandbytes --lora_rank 32 --lora_alpha 64 --lora_dropout 0.35 --lora_target all --pref_beta 0.1 --pref_ftx 0 --pref_loss orpo --adapter_name_or_path saves\LLaMA3.1-8B-Chat\lora\Llama-3.1-8B-German
 ```
 
 
@@ -34,7 +34,86 @@ set CUDA_VISIBLE_DEVICES=0 && llamafactory-cli train --stage dpo --do_train True
 
 `dataset_info.json`:
 ```json
-...
+  "oasst_de": {
+    "hf_hub_url": "mayflowergmbh/oasst_de"
+  },
+  "dolly_15k_de": {
+    "hf_hub_url": "mayflowergmbh/dolly-15k_de"
+  },
+  "alpaca-gpt4_de": {
+    "hf_hub_url": "mayflowergmbh/alpaca-gpt4_de"
+  },
+  "openschnabeltier_de": {
+    "hf_hub_url": "mayflowergmbh/openschnabeltier_de"
+  },
+  "evol_instruct_de": {
+    "hf_hub_url": "mayflowergmbh/evol-instruct_de"
+  },
+  "dolphin_de": {
+    "hf_hub_url": "mayflowergmbh/dolphin_de"
+  },
+  "booksum_de": {
+    "hf_hub_url": "mayflowergmbh/booksum_de"
+  },
+  "airoboros_de": {
+    "hf_hub_url": "mayflowergmbh/airoboros-3.0_de"
+  },
+  "ultrachat_de": {
+    "hf_hub_url": "mayflowergmbh/ultra-chat_de"
+  },
+  "German_Songs": {
+    "file_name": "German_Songs.json",
+    "file_sha1": "3ec36066a19debd1b138020b293e05f21264c352",
+    "columns": {
+      "prompt": "prompt",
+      "query": "analysis_prompt",
+      "response": "song",
+      "history": "analysis",
+      "system": "topic"
+    }
+  },
+  "German_Poems": {
+    "file_name": "German_Poems.json",
+    "file_sha1": "f0f4bbea3b8cbc378afb640f4ff4dcd11132263c",
+    "columns": {
+      "prompt": "prompt",
+      "query": "topic", 
+      "response": "poem"
+    }
+  },
+  "bjoernp_ultrachat_de": {
+    "file_name": "ultrachat_de.json",
+    "file_sha1": "4e2b6dba1c387b3fa439c33ab35281403c39e973",
+    "formatting": "sharegpt",
+    "columns": {
+      "messages": "conversations"
+    },
+    "tags": {
+      "role_tag": "from",
+      "content_tag": "value",
+      "user_tag": "human",
+      "assistant_tag": "gpt",
+      "system_tag": "system"
+    }
+  },
+  "OpenSchnabeltier": {
+    "file_name": "OpenSchnabeltier.json",
+    "columns": {
+      "prompt": "instruction_de",
+      "response": "output_de"
+    }
+  },
+  "fix_orca_dpo_de": {
+    "file_name": "fix_intel_orca_dpo_pairs_de.json",
+    "ranking": true,
+    "columns": {
+      "prompt": "instruction",
+      "query": "input",
+      "chosen": "chosen",
+      "rejected": "rejected"
+    }
+  }
+}
 ```
 </details>