Upload folder using huggingface_hub

adapter_config.json

@@ -14,13 +14,13 @@
   "r": 64,
   "revision": null,
   "target_modules": [
+    "q_proj",
     "up_proj",
-    "down_proj",
-    "v_proj",
+    "o_proj",
     "k_proj",
+    "down_proj",
     "gate_proj",
-    "o_proj",
-    "q_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6cdd50744bdd0187ef74f63033e373aedda4c10768963245424e90b63b8e85a
+oid sha256:4590eccec48a795c79c444a5e95a4897a5e1fd17be423ccb30c2452c03c56f0f
 size 639792909

adapter_model/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyPixel/Llama-2-7B-bf16-sharded",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16.0,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "k_proj",
+    "down_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e4116d3f32577ecef8b6114563278b1e981034f6e619c6024c25251ea75aca5
-size 175079062
+oid sha256:4590eccec48a795c79c444a5e95a4897a5e1fd17be423ccb30c2452c03c56f0f
+size 639792909

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da46423194ed38a0e436c518a9bec15976c71aede09eabf05b09e03b4d2107a0
+oid sha256:cd9ccc53819f905b62767339beeda3cf066988a317e3f2305ec00e20759a9907
 size 1279539525

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a7bd131b478223910aa63dcd22b0dafd3c52112e49fb85d9750f1813c6cc619
+oid sha256:e614bccb1a8ef816bb038432b434c3b616bc3cc1d34ce452da7fcf26bfcd14fb
 size 14511

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c11fb283cf3e4b97ac923c1ffa6de0c0ce17563d0234b23425c5d68bd12f790
+oid sha256:d98c4ed03f69fb5fab6228cdb31470eee8f856f271fa65776fdc56518749e9f1
 size 627

trainer_state.json

@@ -1,166 +1,46 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09068238494672409,
-  "global_step": 50,
+  "epoch": 0.03627295397868964,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.0,
-      "learning_rate": 0.0001,
-      "loss": 1.3698,
+      "epoch": 0.01,
+      "learning_rate": 2e-05,
+      "loss": 1.4096,
       "step": 2
     },
     {
       "epoch": 0.01,
-      "learning_rate": 0.0001,
-      "loss": 1.2409,
+      "learning_rate": 2e-05,
+      "loss": 1.3036,
       "step": 4
     },
-    {
-      "epoch": 0.01,
-      "learning_rate": 0.0001,
-      "loss": 1.1957,
-      "step": 6
-    },
-    {
-      "epoch": 0.01,
-      "learning_rate": 0.0001,
-      "loss": 1.2257,
-      "step": 8
-    },
     {
       "epoch": 0.02,
-      "learning_rate": 0.0001,
-      "loss": 1.3086,
-      "step": 10
-    },
-    {
-      "epoch": 0.02,
-      "learning_rate": 0.0001,
-      "loss": 1.3006,
-      "step": 12
-    },
-    {
-      "epoch": 0.03,
-      "learning_rate": 0.0001,
-      "loss": 1.254,
-      "step": 14
-    },
-    {
-      "epoch": 0.03,
-      "learning_rate": 0.0001,
-      "loss": 1.1302,
-      "step": 16
+      "learning_rate": 2e-05,
+      "loss": 1.3123,
+      "step": 6
     },
     {
       "epoch": 0.03,
-      "learning_rate": 0.0001,
-      "loss": 1.1735,
-      "step": 18
-    },
-    {
-      "epoch": 0.04,
-      "learning_rate": 0.0001,
-      "loss": 1.1811,
-      "step": 20
-    },
-    {
-      "epoch": 0.04,
-      "learning_rate": 0.0001,
-      "loss": 1.1911,
-      "step": 22
+      "learning_rate": 2e-05,
+      "loss": 1.3386,
+      "step": 8
     },
     {
       "epoch": 0.04,
-      "learning_rate": 0.0001,
-      "loss": 1.3651,
-      "step": 24
-    },
-    {
-      "epoch": 0.05,
-      "learning_rate": 0.0001,
-      "loss": 1.1776,
-      "step": 26
-    },
-    {
-      "epoch": 0.05,
-      "learning_rate": 0.0001,
-      "loss": 1.2349,
-      "step": 28
-    },
-    {
-      "epoch": 0.05,
-      "learning_rate": 0.0001,
-      "loss": 1.397,
-      "step": 30
-    },
-    {
-      "epoch": 0.06,
-      "learning_rate": 0.0001,
-      "loss": 1.3597,
-      "step": 32
-    },
-    {
-      "epoch": 0.06,
-      "learning_rate": 0.0001,
-      "loss": 1.4713,
-      "step": 34
-    },
-    {
-      "epoch": 0.07,
-      "learning_rate": 0.0001,
-      "loss": 1.5044,
-      "step": 36
-    },
-    {
-      "epoch": 0.07,
-      "learning_rate": 0.0001,
-      "loss": 1.4494,
-      "step": 38
-    },
-    {
-      "epoch": 0.07,
-      "learning_rate": 0.0001,
-      "loss": 1.4663,
-      "step": 40
-    },
-    {
-      "epoch": 0.08,
-      "learning_rate": 0.0001,
-      "loss": 1.4471,
-      "step": 42
-    },
-    {
-      "epoch": 0.08,
-      "learning_rate": 0.0001,
-      "loss": 1.4528,
-      "step": 44
-    },
-    {
-      "epoch": 0.08,
-      "learning_rate": 0.0001,
-      "loss": 1.5861,
-      "step": 46
-    },
-    {
-      "epoch": 0.09,
-      "learning_rate": 0.0001,
-      "loss": 1.4502,
-      "step": 48
-    },
-    {
-      "epoch": 0.09,
-      "learning_rate": 0.0001,
-      "loss": 1.4986,
-      "step": 50
+      "learning_rate": 2e-05,
+      "loss": 1.3342,
+      "step": 10
     }
   ],
   "max_steps": 1000,
-  "num_train_epochs": 2,
-  "total_flos": 5795675526709248.0,
+  "num_train_epochs": 4,
+  "total_flos": 3476088198856704.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daf4265965e10cc9d642d2d1187c1167f2ce8e9622861d30ff6fbc03bdb2fbda
-size 5755
+oid sha256:b9a0a46c7cfa60235583101b3ab0112a1794f2418dc4cea13c87968e1699eb02
+size 5691