Upload folder using huggingface_hub

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60cddb0b8a51baae7ac39f5c131c6e5d5ca1923905a0722867d9c0ecf9871b58
+oid sha256:35a10693e1787343ac352742f8056750f0ac3a12868daaf18b0918e27b34fa1d
 size 369133600

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9588fde0e17ea6c2c5918e5ed6b3717a4c29046a1c9c3d836cd39d4bb1689c37
+oid sha256:c242f7f75f01bdd5efda8f041fb44b200816c61d4350bc0f7d14d85cae7feb68
 size 738413771

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dac12bb05bd98136abee56099db4e75eadb476f00ee51aa0f7db3f3de1cccf51
+oid sha256:4485c82a37971afa1989881a7c670bc00a34ca98f97cf8ff55f29491f3f7f15f
 size 14645

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:432fe31cc8feaadc988ff87816d3eb23d869c5008676f20a3367d6de19e5cf4c
+oid sha256:b6a0ceb4b88e220a982844159be33a142d353b4617ed2e8cbafc7dcba9bd25b9
 size 1465

trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 140,
-  "best_metric": 0.06147347763180733,
-  "best_model_checkpoint": "/content/drive/MyDrive/lora_model/outputs/task15_microsoft/Phi-4-mini-instruct/checkpoint-140",
-  "epoch": 7.368421052631579,
+  "best_global_step": 150,
+  "best_metric": 0.02963736467063427,
+  "best_model_checkpoint": "/content/drive/MyDrive/lora_model/outputs/task15_microsoft/Phi-4-mini-instruct/checkpoint-150",
+  "epoch": 7.894736842105263,
   "eval_steps": 1,
-  "global_step": 140,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2108,6 +2108,156 @@
       "eval_samples_per_second": 8.9,
       "eval_steps_per_second": 1.187,
       "step": 140
+    },
+    {
+      "epoch": 7.421052631578947,
+      "grad_norm": 0.6074717044830322,
+      "learning_rate": 0.0002249760770939754,
+      "loss": 0.0494,
+      "step": 141
+    },
+    {
+      "epoch": 7.421052631578947,
+      "eval_loss": 0.06366048008203506,
+      "eval_runtime": 3.3644,
+      "eval_samples_per_second": 8.917,
+      "eval_steps_per_second": 1.189,
+      "step": 141
+    },
+    {
+      "epoch": 7.473684210526316,
+      "grad_norm": 0.5519073009490967,
+      "learning_rate": 0.0002216530770986795,
+      "loss": 0.0569,
+      "step": 142
+    },
+    {
+      "epoch": 7.473684210526316,
+      "eval_loss": 0.060868822038173676,
+      "eval_runtime": 3.3772,
+      "eval_samples_per_second": 8.883,
+      "eval_steps_per_second": 1.184,
+      "step": 142
+    },
+    {
+      "epoch": 7.526315789473684,
+      "grad_norm": 0.5936044454574585,
+      "learning_rate": 0.0002183351430834358,
+      "loss": 0.0529,
+      "step": 143
+    },
+    {
+      "epoch": 7.526315789473684,
+      "eval_loss": 0.060183968394994736,
+      "eval_runtime": 3.3842,
+      "eval_samples_per_second": 8.865,
+      "eval_steps_per_second": 1.182,
+      "step": 143
+    },
+    {
+      "epoch": 7.578947368421053,
+      "grad_norm": 0.4775611162185669,
+      "learning_rate": 0.0002150228680081079,
+      "loss": 0.0606,
+      "step": 144
+    },
+    {
+      "epoch": 7.578947368421053,
+      "eval_loss": 0.060147836804389954,
+      "eval_runtime": 3.377,
+      "eval_samples_per_second": 8.884,
+      "eval_steps_per_second": 1.184,
+      "step": 144
+    },
+    {
+      "epoch": 7.631578947368421,
+      "grad_norm": 0.5507313013076782,
+      "learning_rate": 0.00021171684382123,
+      "loss": 0.0515,
+      "step": 145
+    },
+    {
+      "epoch": 7.631578947368421,
+      "eval_loss": 0.05933203548192978,
+      "eval_runtime": 3.3739,
+      "eval_samples_per_second": 8.892,
+      "eval_steps_per_second": 1.186,
+      "step": 145
+    },
+    {
+      "epoch": 7.684210526315789,
+      "grad_norm": 0.6271359324455261,
+      "learning_rate": 0.0002084176613542175,
+      "loss": 0.0768,
+      "step": 146
+    },
+    {
+      "epoch": 7.684210526315789,
+      "eval_loss": 0.05137402191758156,
+      "eval_runtime": 3.3705,
+      "eval_samples_per_second": 8.901,
+      "eval_steps_per_second": 1.187,
+      "step": 146
+    },
+    {
+      "epoch": 7.7368421052631575,
+      "grad_norm": 0.511416494846344,
+      "learning_rate": 0.00020512591021577773,
+      "loss": 0.0559,
+      "step": 147
+    },
+    {
+      "epoch": 7.7368421052631575,
+      "eval_loss": 0.04617203772068024,
+      "eval_runtime": 3.3685,
+      "eval_samples_per_second": 8.906,
+      "eval_steps_per_second": 1.187,
+      "step": 147
+    },
+    {
+      "epoch": 7.7894736842105265,
+      "grad_norm": 0.43504372239112854,
+      "learning_rate": 0.00020184217868653867,
+      "loss": 0.0495,
+      "step": 148
+    },
+    {
+      "epoch": 7.7894736842105265,
+      "eval_loss": 0.039726559072732925,
+      "eval_runtime": 3.3679,
+      "eval_samples_per_second": 8.907,
+      "eval_steps_per_second": 1.188,
+      "step": 148
+    },
+    {
+      "epoch": 7.842105263157895,
+      "grad_norm": 0.5811814069747925,
+      "learning_rate": 0.0001985670536139151,
+      "loss": 0.0741,
+      "step": 149
+    },
+    {
+      "epoch": 7.842105263157895,
+      "eval_loss": 0.03227859362959862,
+      "eval_runtime": 3.3641,
+      "eval_samples_per_second": 8.918,
+      "eval_steps_per_second": 1.189,
+      "step": 149
+    },
+    {
+      "epoch": 7.894736842105263,
+      "grad_norm": 0.41861817240715027,
+      "learning_rate": 0.0001953011203072312,
+      "loss": 0.0477,
+      "step": 150
+    },
+    {
+      "epoch": 7.894736842105263,
+      "eval_loss": 0.02963736467063427,
+      "eval_runtime": 3.3713,
+      "eval_samples_per_second": 8.899,
+      "eval_steps_per_second": 1.186,
+      "step": 150
     }
   ],
   "logging_steps": 1,
@@ -2127,7 +2277,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5806655876229120.0,
+  "total_flos": 6215871296870400.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null