Upload folder using huggingface_hub

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89daabbba6e8fbb223ea2dadd6cafc0473e7831b6a8a31965fd25a932502f63a
+oid sha256:3161508c0505b1add3d5708f8dcbe8451ca9f16d9c4da4eb15f72f0213ea5ab3
 size 369133600

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53b455474ae0967c9dc13e4a970734e024e902b0e0593a5ebcb87d06c41d8d84
+oid sha256:f2de0050503da4c1dfedc106d96c40be2c5e711da4076acf99032873e9af7004
 size 738413771

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:532826bfd6ab0d9c120628c9ba8dbb5c027e661038baccc2d23e0946927a6e4b
+oid sha256:e961bd000aad0805f4df299e9e54c009416c83b5abff201439df38b2efb708fc
 size 14645

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2692bc6d8e85cffcbf5a9395fe1431563b67e6de43846a9570babfa256843214
+oid sha256:3ba3ad0939c5c784a2980c55ea2ede819b84a24d205e18f93e06504838daa120
 size 1465

trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 50,
-  "best_metric": 0.6460065841674805,
+  "best_global_step": 59,
+  "best_metric": 0.6262253522872925,
   "best_model_checkpoint": "/content/drive/MyDrive/lora_model/outputs/task15_microsoft/Phi-4-mini-instruct/checkpoint-50",
-  "epoch": 2.6315789473684212,
+  "epoch": 3.1578947368421053,
   "eval_steps": 1,
-  "global_step": 50,
+  "global_step": 60,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -758,6 +758,156 @@
       "eval_samples_per_second": 8.905,
       "eval_steps_per_second": 1.187,
       "step": 50
+    },
+    {
+      "epoch": 2.6842105263157894,
+      "grad_norm": 0.6689581871032715,
+      "learning_rate": 5.848888922025553e-05,
+      "loss": 0.6803,
+      "step": 51
+    },
+    {
+      "epoch": 2.6842105263157894,
+      "eval_loss": 0.6413608193397522,
+      "eval_runtime": 3.3668,
+      "eval_samples_per_second": 8.911,
+      "eval_steps_per_second": 1.188,
+      "step": 51
+    },
+    {
+      "epoch": 2.736842105263158,
+      "grad_norm": 0.5473130941390991,
+      "learning_rate": 4.7745751406263163e-05,
+      "loss": 0.6535,
+      "step": 52
+    },
+    {
+      "epoch": 2.736842105263158,
+      "eval_loss": 0.6371581554412842,
+      "eval_runtime": 3.371,
+      "eval_samples_per_second": 8.9,
+      "eval_steps_per_second": 1.187,
+      "step": 52
+    },
+    {
+      "epoch": 2.7894736842105265,
+      "grad_norm": 0.6696008443832397,
+      "learning_rate": 3.798797596089351e-05,
+      "loss": 0.744,
+      "step": 53
+    },
+    {
+      "epoch": 2.7894736842105265,
+      "eval_loss": 0.6349052786827087,
+      "eval_runtime": 3.3769,
+      "eval_samples_per_second": 8.884,
+      "eval_steps_per_second": 1.185,
+      "step": 53
+    },
+    {
+      "epoch": 2.8421052631578947,
+      "grad_norm": 0.5501115918159485,
+      "learning_rate": 2.9263101785268254e-05,
+      "loss": 0.6701,
+      "step": 54
+    },
+    {
+      "epoch": 2.8421052631578947,
+      "eval_loss": 0.6328269839286804,
+      "eval_runtime": 3.3789,
+      "eval_samples_per_second": 8.879,
+      "eval_steps_per_second": 1.184,
+      "step": 54
+    },
+    {
+      "epoch": 2.8947368421052633,
+      "grad_norm": 0.4939638078212738,
+      "learning_rate": 2.1613635589349755e-05,
+      "loss": 0.6646,
+      "step": 55
+    },
+    {
+      "epoch": 2.8947368421052633,
+      "eval_loss": 0.6300433278083801,
+      "eval_runtime": 3.3726,
+      "eval_samples_per_second": 8.895,
+      "eval_steps_per_second": 1.186,
+      "step": 55
+    },
+    {
+      "epoch": 2.9473684210526314,
+      "grad_norm": 0.61789470911026,
+      "learning_rate": 1.5076844803522921e-05,
+      "loss": 0.7293,
+      "step": 56
+    },
+    {
+      "epoch": 2.9473684210526314,
+      "eval_loss": 0.6280367374420166,
+      "eval_runtime": 3.3765,
+      "eval_samples_per_second": 8.885,
+      "eval_steps_per_second": 1.185,
+      "step": 56
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.5384323000907898,
+      "learning_rate": 9.684576015420277e-06,
+      "loss": 0.6898,
+      "step": 57
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6272571086883545,
+      "eval_runtime": 3.3704,
+      "eval_samples_per_second": 8.901,
+      "eval_steps_per_second": 1.187,
+      "step": 57
+    },
+    {
+      "epoch": 3.0526315789473686,
+      "grad_norm": 0.5376719236373901,
+      "learning_rate": 5.463099816548578e-06,
+      "loss": 0.6448,
+      "step": 58
+    },
+    {
+      "epoch": 3.0526315789473686,
+      "eval_loss": 0.6269372701644897,
+      "eval_runtime": 3.3667,
+      "eval_samples_per_second": 8.911,
+      "eval_steps_per_second": 1.188,
+      "step": 58
+    },
+    {
+      "epoch": 3.1052631578947367,
+      "grad_norm": 0.515751838684082,
+      "learning_rate": 2.4329828146074094e-06,
+      "loss": 0.7027,
+      "step": 59
+    },
+    {
+      "epoch": 3.1052631578947367,
+      "eval_loss": 0.6262253522872925,
+      "eval_runtime": 3.3654,
+      "eval_samples_per_second": 8.914,
+      "eval_steps_per_second": 1.189,
+      "step": 59
+    },
+    {
+      "epoch": 3.1578947368421053,
+      "grad_norm": 0.5370931029319763,
+      "learning_rate": 6.089874350439506e-07,
+      "loss": 0.6594,
+      "step": 60
+    },
+    {
+      "epoch": 3.1578947368421053,
+      "eval_loss": 0.6268424391746521,
+      "eval_runtime": 3.3618,
+      "eval_samples_per_second": 8.924,
+      "eval_steps_per_second": 1.19,
+      "step": 60
     }
   ],
   "logging_steps": 1,
@@ -772,12 +922,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2071824550963200.0,
+  "total_flos": 2488197563258880.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null