checkpoint v20240208

README.md

@@ -0,0 +1,24 @@
+---
+library_name: peft
+---
+
+见[nenekochan/Yi-6B-yoruno](https://huggingface.co/nenekochan/Yi-6B-yoruno)
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: QuantizationMethod.BITS_AND_BYTES
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+### Framework versions
+
+
+- PEFT 0.4.0

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "01-ai/Yi-6B",
+  "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": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fcb742278673bbf4e7c2bdac7069baa33b8a9edba410e985940259bbc0a5b50
+size 580971544

trainer_state.json

@@ -0,0 +1,57 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.23076923076923,
+  "eval_steps": 500,
+  "global_step": 60,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.54,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 3.3839,
+      "step": 10
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 2.6213,
+      "step": 20
+    },
+    {
+      "epoch": 4.62,
+      "learning_rate": 0.0002,
+      "loss": 2.0735,
+      "step": 30
+    },
+    {
+      "epoch": 6.15,
+      "learning_rate": 0.0002,
+      "loss": 1.9831,
+      "step": 40
+    },
+    {
+      "epoch": 7.69,
+      "learning_rate": 0.0002,
+      "loss": 1.8401,
+      "step": 50
+    },
+    {
+      "epoch": 9.23,
+      "learning_rate": 0.0002,
+      "loss": 1.6224,
+      "step": 60
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 150,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 25,
+  "save_steps": 30,
+  "total_flos": 1.3765767134016307e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db50ffac89d2c62c8b6ef8b45b06383951648b9ded85d6159c1a97042288fef3
+size 4728