Training in progress, epoch 5

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3746e89ab4ed2d2714cec87011941709b73dd81893768c249c061126dbe2aff0
+oid sha256:e2cdf6b8ff2ed5025ff0c141ca9629fd45083802f135bd9851b20be92936eb0c
 size 498625128

run-1/checkpoint-1410/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:990205f242b0ec2efe39dbc3eb01f20f27d4e8e5f2fac9bd31e6196f3777bab8
+oid sha256:e2cdf6b8ff2ed5025ff0c141ca9629fd45083802f135bd9851b20be92936eb0c
 size 498625128

run-1/checkpoint-1410/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3845a8d67428319e44a880d5e03f4185aca323658755031fab87ba7904b6d17a
+oid sha256:46b3759dd02fa45bacbcb76c638409a044d6ea09c4338d42a999101dd40fba89
 size 997370106

run-1/checkpoint-1410/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fcbae34d469657b5d0c79b5675615c71134bf171f73d10deae62819e085a38e
+oid sha256:1109faa5d519e0ba6fa6da43b365f9d91004bad11954e21938c57bfb5e879ffc
 size 14244

run-1/checkpoint-1410/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c3699141451f13435bbff84239896053f36e79abab9b017911318554f619a55
+oid sha256:c71d890c343978e0041c92ab2f2bbdc890104bc3347d7041a917da94b694ae4b
 size 1064

run-1/checkpoint-1410/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6285243252934658,
+  "best_metric": 0.626596640291279,
   "best_model_checkpoint": "students_scores_model/run-1/checkpoint-1128",
   "epoch": 5.0,
   "eval_steps": 500,
@@ -10,61 +10,61 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_f1": 0.5135559583730447,
-      "eval_loss": 1.0615456104278564,
-      "eval_runtime": 37.678,
-      "eval_samples_per_second": 59.716,
-      "eval_steps_per_second": 7.484,
+      "eval_f1": 0.49162421787585286,
+      "eval_loss": 1.09846031665802,
+      "eval_runtime": 37.7448,
+      "eval_samples_per_second": 59.611,
+      "eval_steps_per_second": 7.471,
       "step": 282
     },
     {
       "epoch": 1.773049645390071,
-      "grad_norm": 11.819360733032227,
-      "learning_rate": 8.537794225405964e-06,
-      "loss": 1.0289,
+      "grad_norm": 8.43077564239502,
+      "learning_rate": 1.4687315682489477e-05,
+      "loss": 1.0146,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_f1": 0.5853742204012189,
-      "eval_loss": 0.9459031224250793,
-      "eval_runtime": 37.7163,
-      "eval_samples_per_second": 59.656,
-      "eval_steps_per_second": 7.477,
+      "eval_f1": 0.5968612549522194,
+      "eval_loss": 0.9038913249969482,
+      "eval_runtime": 37.6284,
+      "eval_samples_per_second": 59.795,
+      "eval_steps_per_second": 7.494,
       "step": 564
     },
     {
       "epoch": 3.0,
-      "eval_f1": 0.6179112498233506,
-      "eval_loss": 0.8894566893577576,
-      "eval_runtime": 37.6552,
-      "eval_samples_per_second": 59.753,
-      "eval_steps_per_second": 7.489,
+      "eval_f1": 0.60670227423826,
+      "eval_loss": 0.919843316078186,
+      "eval_runtime": 37.6908,
+      "eval_samples_per_second": 59.696,
+      "eval_steps_per_second": 7.482,
       "step": 846
     },
     {
       "epoch": 3.546099290780142,
-      "grad_norm": 19.25679588317871,
-      "learning_rate": 3.8466984971609285e-06,
-      "loss": 0.8051,
+      "grad_norm": 27.95517349243164,
+      "learning_rate": 6.617362010791962e-06,
+      "loss": 0.7766,
       "step": 1000
     },
     {
       "epoch": 4.0,
-      "eval_f1": 0.6285243252934658,
-      "eval_loss": 0.8603602647781372,
-      "eval_runtime": 37.769,
-      "eval_samples_per_second": 59.573,
-      "eval_steps_per_second": 7.466,
+      "eval_f1": 0.626596640291279,
+      "eval_loss": 0.8775350451469421,
+      "eval_runtime": 37.7332,
+      "eval_samples_per_second": 59.629,
+      "eval_steps_per_second": 7.474,
       "step": 1128
     },
     {
       "epoch": 5.0,
-      "eval_f1": 0.6176495736574765,
-      "eval_loss": 0.893376886844635,
-      "eval_runtime": 38.2772,
-      "eval_samples_per_second": 58.782,
-      "eval_steps_per_second": 7.367,
+      "eval_f1": 0.6117912548573106,
+      "eval_loss": 0.9414774179458618,
+      "eval_runtime": 38.817,
+      "eval_samples_per_second": 57.964,
+      "eval_steps_per_second": 7.265,
       "step": 1410
     }
   ],
@@ -89,9 +89,9 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 1.3228889953650998e-05,
+    "learning_rate": 2.275726935418699e-05,
     "num_train_epochs": 5,
     "per_device_train_batch_size": 32,
-    "weight_decay": 0.0004860339799795757
+    "weight_decay": 0.0002055903667746397
   }
 }

run-1/checkpoint-1410/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b6c0e80228b83305d52c2ecaa5e9378ae485930e09ca765409ad7f4e4465fdb
+oid sha256:5170867ff483caf9169cfca440571d2f9bf4863737851b36e8f14b28d996f499
 size 5368