Upload folder using huggingface_hub

adapter_config.json

@@ -29,13 +29,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "q_proj",
-    "up_proj",
     "o_proj",
+    "q_proj",
+    "down_proj",
     "v_proj",
     "gate_proj",
-    "down_proj"
+    "up_proj",
+    "k_proj"
   ],
   "target_parameters": null,
   "task_type": "SEQ_CLS",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edd631c5036ee04697cc781e0080e4ceeeec4dca3c8f5b8dbc4e037e50058c05
-size 664593800
+oid sha256:64dd9b803586bb8a80e10f6d915bc9074d37b5545bbc9be6a6e0941ec5982ca0
+size 664603016

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71a59bebe794f1a808bca018d70f99f505319403c07240cd87156b7425e16bee
-size 1329396842
+oid sha256:790d597629cb916df27a771e70599d10a2ce72255c8ee695b47e80b8d160d7d1
+size 1329415274

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2adb2436d8231356dbef633a9b00f9c997d3d088cde9229bafc340f774707d36
+oid sha256:d43788e4fdd49a910adde6e956129a90a4b56e5ced8ed62f8b6e1c0cb844b3e7
 size 14645

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c70c8af470d16cae8adab12055155c2988464b9af430aed08af74c6c7f742ad5
+oid sha256:f1bea375e784db877b5f714bc6aaefba3577522e040195e1831e996a0014e30d
 size 1465

trainer_state.json

@@ -1,64 +1,81 @@
 {
-  "best_global_step": 60,
-  "best_metric": 0.7314814814814815,
-  "best_model_checkpoint": "/content/gemma_lora_imb/checkpoint-60",
-  "epoch": 1.1764705882352942,
+  "best_global_step": 80,
+  "best_metric": 0.6859903381642513,
+  "best_model_checkpoint": "/content/gemma_lora_imb/checkpoint-80",
+  "epoch": 1.5686274509803921,
   "eval_steps": 20,
-  "global_step": 60,
+  "global_step": 80,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.39215686274509803,
-      "grad_norm": 33.80354309082031,
+      "grad_norm": 24.230987548828125,
       "learning_rate": 8.137254901960784e-06,
-      "loss": 1.2953,
+      "loss": 1.1665,
       "step": 20
     },
     {
       "epoch": 0.39215686274509803,
-      "eval_accuracy": 0.645320197044335,
-      "eval_f1": 0.6326530612244898,
-      "eval_loss": 0.9012272357940674,
-      "eval_runtime": 1.3299,
-      "eval_samples_per_second": 152.646,
-      "eval_steps_per_second": 5.264,
+      "eval_accuracy": 0.6206896551724138,
+      "eval_f1": 0.631578947368421,
+      "eval_loss": 1.0547616481781006,
+      "eval_runtime": 34.5129,
+      "eval_samples_per_second": 5.882,
+      "eval_steps_per_second": 0.203,
       "step": 20
     },
     {
       "epoch": 0.7843137254901961,
-      "grad_norm": 21.962677001953125,
+      "grad_norm": 26.34092140197754,
       "learning_rate": 6.176470588235295e-06,
-      "loss": 0.7861,
+      "loss": 0.8846,
       "step": 40
     },
     {
       "epoch": 0.7843137254901961,
-      "eval_accuracy": 0.6847290640394089,
-      "eval_f1": 0.6923076923076923,
-      "eval_loss": 0.764927089214325,
-      "eval_runtime": 1.3089,
-      "eval_samples_per_second": 155.088,
-      "eval_steps_per_second": 5.348,
+      "eval_accuracy": 0.6551724137931034,
+      "eval_f1": 0.6634615384615384,
+      "eval_loss": 0.8848929405212402,
+      "eval_runtime": 34.4309,
+      "eval_samples_per_second": 5.896,
+      "eval_steps_per_second": 0.203,
       "step": 40
     },
     {
       "epoch": 1.1764705882352942,
-      "grad_norm": 39.092864990234375,
+      "grad_norm": 28.944477081298828,
       "learning_rate": 4.215686274509805e-06,
-      "loss": 0.4942,
+      "loss": 0.5412,
       "step": 60
     },
     {
       "epoch": 1.1764705882352942,
-      "eval_accuracy": 0.7142857142857143,
-      "eval_f1": 0.7314814814814815,
-      "eval_loss": 0.7433407306671143,
-      "eval_runtime": 1.3004,
-      "eval_samples_per_second": 156.101,
-      "eval_steps_per_second": 5.383,
+      "eval_accuracy": 0.6699507389162561,
+      "eval_f1": 0.6824644549763034,
+      "eval_loss": 0.8630681037902832,
+      "eval_runtime": 34.3671,
+      "eval_samples_per_second": 5.907,
+      "eval_steps_per_second": 0.204,
       "step": 60
+    },
+    {
+      "epoch": 1.5686274509803921,
+      "grad_norm": 14.226760864257812,
+      "learning_rate": 2.254901960784314e-06,
+      "loss": 0.3088,
+      "step": 80
+    },
+    {
+      "epoch": 1.5686274509803921,
+      "eval_accuracy": 0.6798029556650246,
+      "eval_f1": 0.6859903381642513,
+      "eval_loss": 0.8230202794075012,
+      "eval_runtime": 34.5725,
+      "eval_samples_per_second": 5.872,
+      "eval_steps_per_second": 0.202,
+      "step": 80
     }
   ],
   "logging_steps": 20,
@@ -78,7 +95,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3346006641030144.0,
+  "total_flos": 4553569010414592.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c7796473a527b84a6f77258264c10212e0e9d41d86534b20e066486b8bf6013
+oid sha256:0ea7b0406c4d7142b34f920ec82ea3a1f32915f9c273c789d19ddd7b5d0cd3c4
 size 5905