Upload 12 files

adapter_config.json

@@ -0,0 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "../llama/Llama-2-7b-chat-hf",
+  "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": 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:e5e1621f48d9ad8feb1d6d31050275f0aafd080c5c07153301fe2f48411f4406
+size 443

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd16b8c75f3e7e556fd52e53e88f96b9aef80f7e832753ceca3be89a90617ca3
+size 33661637

checkpoint-200/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a158a696c728dca13dc19f2f6c84bfc9ff5a0ec166d376e6ff855fffaeb350a3
+size 16822989

checkpoint-200/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f955e8b723c0bd507cf6341f78d0c6a540f3ae53063393f3627678e991209f7
+size 17655

checkpoint-200/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0000935a5581a79c4dfef1a0fe45c0d4f4c84083d5cefb34d49137f5ad871be
+size 17655

checkpoint-200/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7d8f164390d97d9fef7e429ddb9d1497a333691c3f2cfc255a75033f4bff2e7
+size 17655

checkpoint-200/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1119d3ca34e229b81c46cbbdb28bddd801cf2233f24084b80bb71c04bbd9a68
+size 17655

checkpoint-200/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fccf0f9be1bb8f24861e4393745b3e09cc2687125a69e3757955fb0f0925ea5
+size 557

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05f69199de0a003a34b84089ccbd585e488c50b86661943d92e30983641d0181
+size 627

checkpoint-200/trainer_state.json

@@ -0,0 +1,144 @@
+{
+  "best_metric": 0.8395341634750366,
+  "best_model_checkpoint": "../outputs/7b_chat_lora_ar/checkpoint-200",
+  "epoch": 0.7662835249042146,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 2.0671,
+      "step": 10
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 1.9822,
+      "step": 20
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 1.731,
+      "step": 30
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 1.439,
+      "step": 40
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00015,
+      "loss": 1.2119,
+      "step": 50
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 1.0864,
+      "step": 60
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 1.0386,
+      "step": 70
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 0.9894,
+      "step": 80
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00027,
+      "loss": 0.9454,
+      "step": 90
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.9238,
+      "step": 100
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00028136645962732916,
+      "loss": 0.9011,
+      "step": 110
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00026273291925465835,
+      "loss": 0.8916,
+      "step": 120
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00024409937888198756,
+      "loss": 0.8839,
+      "step": 130
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00022546583850931675,
+      "loss": 0.8757,
+      "step": 140
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00020683229813664593,
+      "loss": 0.8617,
+      "step": 150
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00018819875776397512,
+      "loss": 0.8598,
+      "step": 160
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00016956521739130433,
+      "loss": 0.8515,
+      "step": 170
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00015093167701863352,
+      "loss": 0.8523,
+      "step": 180
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00013229813664596273,
+      "loss": 0.8419,
+      "step": 190
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00011366459627329192,
+      "loss": 0.8356,
+      "step": 200
+    },
+    {
+      "epoch": 0.77,
+      "eval_loss": 0.8395341634750366,
+      "eval_runtime": 25.8353,
+      "eval_samples_per_second": 77.414,
+      "eval_steps_per_second": 2.439,
+      "step": 200
+    }
+  ],
+  "max_steps": 261,
+  "num_train_epochs": 1,
+  "total_flos": 3.8996439031873536e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b59afc2078ace1c05c9d410a43914619b81cbef0604edd7582771c3c08d4d5bc
+size 3899