Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5acafaf993f20fe8ecc99b137a9581aa92a1830a8aad296a68d9a12b415288c6
+oid sha256:4348799078dfa4432623f79104a6129b81719f49b8ae62ffde9bbfc51b83c5df
 size 498625128

run-2/checkpoint-564/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e8042e8a66f779111574edb23e8d5c38834f4cacdb9af33887881eabf06c385
+oid sha256:4348799078dfa4432623f79104a6129b81719f49b8ae62ffde9bbfc51b83c5df
 size 498625128

run-2/checkpoint-564/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:833abf2e23baab43469bf7282f52f6e13902a574e8528f912d771b88defd198c
+oid sha256:f2aa806efabfc3e31021aa0526dd9c5e9acad66f1280b6d16977efa4a3030d49
 size 997370106

run-2/checkpoint-564/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24e4d5dbef331533ce0b6d9eae278e064359e90705ddd2a51dc79103f3942777
+oid sha256:1add1b9ed3eff7b450376fbbaa59b072d71b8bf40a722fdbb19017aaf4c76378
 size 1064

run-2/checkpoint-564/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.597013961740708,
+  "best_metric": 0.59608556088931,
   "best_model_checkpoint": "students_scores_model/run-2/checkpoint-564",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -10,27 +10,27 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_f1": 0.5280922046056804,
-      "eval_loss": 1.0346653461456299,
-      "eval_runtime": 37.6542,
-      "eval_samples_per_second": 59.754,
-      "eval_steps_per_second": 7.489,
+      "eval_f1": 0.5542424468942035,
+      "eval_loss": 0.9836739301681519,
+      "eval_runtime": 37.7933,
+      "eval_samples_per_second": 59.534,
+      "eval_steps_per_second": 7.462,
       "step": 282
     },
     {
       "epoch": 1.773049645390071,
-      "grad_norm": 15.857311248779297,
-      "learning_rate": 4.500003283675112e-06,
-      "loss": 1.0255,
+      "grad_norm": 13.297893524169922,
+      "learning_rate": 4.297481786070467e-06,
+      "loss": 1.0267,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_f1": 0.597013961740708,
-      "eval_loss": 0.9119309782981873,
-      "eval_runtime": 37.6531,
-      "eval_samples_per_second": 59.756,
-      "eval_steps_per_second": 7.489,
+      "eval_f1": 0.59608556088931,
+      "eval_loss": 0.9071515798568726,
+      "eval_runtime": 37.9029,
+      "eval_samples_per_second": 59.362,
+      "eval_steps_per_second": 7.44,
       "step": 564
     }
   ],
@@ -55,9 +55,9 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 1.1002898202280765e-05,
+    "learning_rate": 1.0507715580969985e-05,
     "num_train_epochs": 3,
     "per_device_train_batch_size": 32,
-    "weight_decay": 0.008293142825111385
+    "weight_decay": 5.2295860944350256e-05
   }
 }

run-2/checkpoint-564/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92eed261d071d88405c0cc7cdc0b8eceb2628d134f07932409e8529a92610828
+oid sha256:615ef351bfbb5cca691b7c9012c2ac8eac8d1f93a3c743c6a15dbc7c75ffeb0b
 size 5368

runs/Dec09_12-41-02_ea67bac3fd95/events.out.tfevents.1733752918.ea67bac3fd95.23.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a16175e219e7c4781a9674db030267ffe56e060bcd5e8c24c085f1608fc2261a
-size 5673
+oid sha256:25ddbe5a672808da6065177f50bb2f4f5dfa20fdad5a9303c61121ad418d9743
+size 6201