Upload 9 files

README.md

@@ -1,3 +1,20 @@
 ---
-license: cc-by-4.0
+library_name: peft
 ---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- 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 0.5.0.dev0

adapter_config.json

@@ -0,0 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-13b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32.0,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52b32431c82de7724d85c8f2b834f34e7afef6062f472a4a2c5a0ee138cda5d5
+size 26269517

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 1.053490692918951,
+    "train_runtime": 628.5043,
+    "train_samples_per_second": 2.247,
+    "train_steps_per_second": 0.14
+}

finetuning_args.json

@@ -0,0 +1,13 @@
+{
+  "finetuning_type": "lora",
+  "lora_alpha": 32.0,
+  "lora_dropout": 0.1,
+  "lora_rank": 8,
+  "lora_target": [
+    "q_proj",
+    "v_proj"
+  ],
+  "name_module_trainable": "mlp",
+  "num_hidden_layers": 32,
+  "num_layer_trainable": 3
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 1.053490692918951,
+    "train_runtime": 628.5043,
+    "train_samples_per_second": 2.247,
+    "train_steps_per_second": 0.14
+}

trainer_state.json

@@ -0,0 +1,73 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9971671388101983,
+  "global_step": 88,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.936949724999762e-05,
+      "loss": 1.1665,
+      "step": 10
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7557495743542586e-05,
+      "loss": 1.1156,
+      "step": 20
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.479248986720057e-05,
+      "loss": 1.0721,
+      "step": 30
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.1423148382732854e-05,
+      "loss": 1.0383,
+      "step": 40
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 7.874347104470234e-06,
+      "loss": 1.0421,
+      "step": 50
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.593591825444028e-06,
+      "loss": 1.0273,
+      "step": 60
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.994587590756397e-06,
+      "loss": 1.004,
+      "step": 70
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.0507026385502747e-07,
+      "loss": 0.9901,
+      "step": 80
+    },
+    {
+      "epoch": 1.0,
+      "step": 88,
+      "total_flos": 1.29608516683776e+16,
+      "train_loss": 1.053490692918951,
+      "train_runtime": 628.5043,
+      "train_samples_per_second": 2.247,
+      "train_steps_per_second": 0.14
+    }
+  ],
+  "max_steps": 88,
+  "num_train_epochs": 1,
+  "total_flos": 1.29608516683776e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92bf9afb6506438b2c6093e5a34af126ee23b5a5f9fe5f21573589cf045d9e50
+size 3368