Upload folder using huggingface_hub

adapter_config.json

@@ -16,14 +16,14 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "lm_head",
     "k_proj",
+    "v_proj",
+    "q_proj",
+    "lm_head",
     "o_proj",
-    "up_proj",
-    "gate_proj",
     "down_proj",
-    "q_proj",
-    "v_proj"
+    "up_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3de4953061370a63e932ab9adef3d1b37a5e265460e924e74f17ca025920c147
-size 5031039
+oid sha256:b6bac0fe4393fb334aa3f0c9d417e30a9a3d89300be07d4634893d07f4327a25
+size 5031484

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b79a623491a90333d1ce22b9d9de2a35bcb25c991ac6e28b032ff67f8daec5b8
-size 2525407
+oid sha256:d8d12cc31694a253150fb4b864dd9db0fd34d6085684fd2b497291115cd92e47
+size 2525844

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:465720dc59f05c874da3430080ff334622b516143a99546883486e56c8841221
-size 14575
+oid sha256:2d9b97ed8e6c4eaad8cb1ef6ae1e3ca5ff2f998cbd086280107ebe6396171944
+size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d6a51cd429314aae6c96ca15be43ce2d4ced57459a1e34e51c06283906510b4
-size 627
+oid sha256:eedfec4bc6f5a00a07b48568793720af057cf404e35f584cd69e8f806039a34d
+size 1064

trainer_state.json

@@ -1,31 +1,139 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04828002414001207,
+  "epoch": 0.9656004828002414,
   "eval_steps": 500,
-  "global_step": 20,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
-    {
-      "epoch": 0.02,
-      "learning_rate": 1.3333333333333333e-05,
-      "loss": 1.8743,
-      "step": 10
-    },
     {
       "epoch": 0.05,
-      "learning_rate": 0.0,
-      "loss": 1.8553,
+      "learning_rate": 1.9325842696629215e-05,
+      "loss": 1.8646,
       "step": 20
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.8426966292134835e-05,
+      "loss": 1.9283,
+      "step": 40
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.752808988764045e-05,
+      "loss": 1.9027,
+      "step": 60
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.662921348314607e-05,
+      "loss": 1.8583,
+      "step": 80
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.5730337078651687e-05,
+      "loss": 1.8618,
+      "step": 100
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.4831460674157305e-05,
+      "loss": 1.8233,
+      "step": 120
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.3932584269662923e-05,
+      "loss": 1.9046,
+      "step": 140
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.303370786516854e-05,
+      "loss": 1.8505,
+      "step": 160
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.213483146067416e-05,
+      "loss": 1.8608,
+      "step": 180
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1235955056179778e-05,
+      "loss": 1.7992,
+      "step": 200
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.0337078651685396e-05,
+      "loss": 1.8869,
+      "step": 220
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 9.438202247191012e-06,
+      "loss": 1.839,
+      "step": 240
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 8.53932584269663e-06,
+      "loss": 1.8787,
+      "step": 260
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 7.640449438202247e-06,
+      "loss": 1.8828,
+      "step": 280
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 6.741573033707865e-06,
+      "loss": 1.8479,
+      "step": 300
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 5.842696629213483e-06,
+      "loss": 1.9063,
+      "step": 320
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 4.943820224719101e-06,
+      "loss": 1.8693,
+      "step": 340
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 4.04494382022472e-06,
+      "loss": 1.827,
+      "step": 360
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.146067415730337e-06,
+      "loss": 1.8259,
+      "step": 380
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.2471910112359554e-06,
+      "loss": 1.8419,
+      "step": 400
     }
   ],
-  "logging_steps": 10,
-  "max_steps": 20,
-  "num_train_epochs": 1,
-  "save_steps": 10,
-  "total_flos": 1.393049758334976e+16,
+  "logging_steps": 20,
+  "max_steps": 450,
+  "num_train_epochs": 2,
+  "save_steps": 20,
+  "total_flos": 2.786099516669952e+17,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e9f8e5ad467430e401cff9fca7527f5ec3d19e2a691d6c74591579cb046ba0f
-size 4027
+oid sha256:050755ce01080bd5005c27dae5043cd1a94e5e57b091a9a27315291e7463c9fb
+size 4472