first commit

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "/root/autodl-tmp/panel/model/llama2-13b-Chinese-chat/llama2-13B-sharegpt_cn-epoch2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.07,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 36,
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "down_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba4b99904d26979b93a940060efef7d3a7bc37ae751104edcbdf7229f4c7068a
+size 563483981

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,112 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.3964949843384481,
+  "global_step": 5000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 5e-06,
+      "loss": 0.7497,
+      "step": 300
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1e-05,
+      "loss": 0.7216,
+      "step": 600
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.7234,
+      "step": 900
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2e-05,
+      "loss": 0.7101,
+      "step": 1200
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9965904738461534e-05,
+      "loss": 0.7076,
+      "step": 1500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9864303873200655e-05,
+      "loss": 0.7049,
+      "step": 1800
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9695211009121407e-05,
+      "loss": 0.7015,
+      "step": 2100
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.946000599403684e-05,
+      "loss": 0.7053,
+      "step": 2400
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9160292703247836e-05,
+      "loss": 0.7002,
+      "step": 2700
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.8798114897361602e-05,
+      "loss": 0.6937,
+      "step": 3000
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.8375942285781164e-05,
+      "loss": 0.6946,
+      "step": 3300
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.7896653685627762e-05,
+      "loss": 0.696,
+      "step": 3600
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.736351739093632e-05,
+      "loss": 0.6872,
+      "step": 3900
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.678016888598748e-05,
+      "loss": 0.6893,
+      "step": 4200
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.6150586054750085e-05,
+      "loss": 0.6893,
+      "step": 4500
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.5479062055482384e-05,
+      "loss": 0.6888,
+      "step": 4800
+    }
+  ],
+  "max_steps": 12610,
+  "num_train_epochs": 1,
+  "total_flos": 2.872350690204713e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcf0a0bddb6c9a9f308c73c454c7697a3cbe5ae7eac879099232dac126d76a62
+size 4091