Upload folder using huggingface_hub

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/data/miaopeng/workplace/LLaMA-Factory/hugging_cache/Mistral-7B-Instruct-v0.2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "up_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e0f794fe0665cbc316bde2902b95e4becfa1e18eb62440cd0c3a6908096c0a5
+size 83945296

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:960cd654d5c6336dc1a44585020e759f4cc57260ccc22eb223e38bbb6594dd81
+size 168149074

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34bcae41c589c7e4cab7b2ef263b878c90c2741404a6af11994dc31537b2319b
+size 14512

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d05dc84075e8f7dd1191c36f3be9dda12073208e12f7d2cef433c38d6336774a
+size 14512

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a49179b74fb5d6b191d8c0051d07258d7e45e50267e50dfc5fb0c364ea0e6562
+size 1064

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content'] %}\n    {%- set loop_messages = messages[1:] %}\n{%- else %}\n    {%- set loop_messages = messages %}\n{%- endif %}\n\n{{- bos_token }}\n{%- for message in loop_messages %}\n    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}\n        {{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}\n    {%- endif %}\n    {%- if message['role'] == 'user' %}\n        {%- if loop.first and system_message is defined %}\n            {{- ' [INST] ' + system_message + '\\n\\n' + message['content'] + ' [/INST]' }}\n        {%- else %}\n            {{- ' [INST] ' + message['content'] + ' [/INST]' }}\n        {%- endif %}\n    {%- elif message['role'] == 'assistant' %}\n        {{- ' ' + message['content'] + eos_token}}\n    {%- else %}\n        {{- raise_exception('Only user and assistant roles are supported, with the exception of an initial optional system message!') }}\n    {%- endif %}\n{%- endfor %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,123 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.869565217391304,
+  "eval_steps": 500,
+  "global_step": 33,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.43478260869565216,
+      "grad_norm": 34.87980270385742,
+      "learning_rate": 4.985344892885899e-06,
+      "logits/chosen": -2.584322214126587,
+      "logits/rejected": -2.617506265640259,
+      "logps/chosen": -174.532958984375,
+      "logps/rejected": -184.2425994873047,
+      "loss": 0.6893,
+      "rewards/accuracies": 0.3500000238418579,
+      "rewards/chosen": 0.011605634354054928,
+      "rewards/margins": 0.008320190012454987,
+      "rewards/rejected": 0.003285445272922516,
+      "step": 5
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 38.83084487915039,
+      "learning_rate": 4.49023266426411e-06,
+      "logits/chosen": -2.530242919921875,
+      "logits/rejected": -2.510067939758301,
+      "logps/chosen": -242.34451293945312,
+      "logps/rejected": -242.54403686523438,
+      "loss": 0.692,
+      "rewards/accuracies": 0.550000011920929,
+      "rewards/chosen": -0.0007201525731943548,
+      "rewards/margins": 0.003676743945106864,
+      "rewards/rejected": -0.004396896343678236,
+      "step": 10
+    },
+    {
+      "epoch": 1.3043478260869565,
+      "grad_norm": 30.36626434326172,
+      "learning_rate": 3.425345388349787e-06,
+      "logits/chosen": -2.5426576137542725,
+      "logits/rejected": -2.5685505867004395,
+      "logps/chosen": -190.65333557128906,
+      "logps/rejected": -173.3209991455078,
+      "loss": 0.6321,
+      "rewards/accuracies": 0.9500000476837158,
+      "rewards/chosen": 0.0738275945186615,
+      "rewards/margins": 0.1280260980129242,
+      "rewards/rejected": -0.05419851467013359,
+      "step": 15
+    },
+    {
+      "epoch": 1.7391304347826086,
+      "grad_norm": 35.945823669433594,
+      "learning_rate": 2.0955450086180883e-06,
+      "logits/chosen": -2.534226894378662,
+      "logits/rejected": -2.5561437606811523,
+      "logps/chosen": -194.49790954589844,
+      "logps/rejected": -207.09521484375,
+      "loss": 0.6019,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.0849701538681984,
+      "rewards/margins": 0.19348573684692383,
+      "rewards/rejected": -0.10851557552814484,
+      "step": 20
+    },
+    {
+      "epoch": 2.1739130434782608,
+      "grad_norm": 31.386171340942383,
+      "learning_rate": 8.815342880454312e-07,
+      "logits/chosen": -2.5661137104034424,
+      "logits/rejected": -2.5473780632019043,
+      "logps/chosen": -220.97113037109375,
+      "logps/rejected": -215.14369201660156,
+      "loss": 0.5646,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.12264734506607056,
+      "rewards/margins": 0.2811417579650879,
+      "rewards/rejected": -0.15849439799785614,
+      "step": 25
+    },
+    {
+      "epoch": 2.608695652173913,
+      "grad_norm": 30.438610076904297,
+      "learning_rate": 1.3086707204299415e-07,
+      "logits/chosen": -2.565887928009033,
+      "logits/rejected": -2.572723388671875,
+      "logps/chosen": -226.0846710205078,
+      "logps/rejected": -220.2860565185547,
+      "loss": 0.5412,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.1668781042098999,
+      "rewards/margins": 0.3352271318435669,
+      "rewards/rejected": -0.16834904253482819,
+      "step": 30
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 33,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6055611024277504.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee5a8a8afe1eca9b394b2d16fa02fbcfa7b099ec5f8178c4814d059ec16f8c96
+size 5496