Training in progress, epoch 1

logs/events.out.tfevents.1709699344.a2333cf40ebd.21010.9

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d11f8656f960a8d66413d3f027d70c316fa595c20289fc0899ff6623b4aff68
-size 5315
+oid sha256:a915fc24599d0118bd0ce3f4c2df13cb9694a0c6ec2e9ab10020c882d0aefc18
+size 5998

logs/events.out.tfevents.1709699573.a2333cf40ebd.21010.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74a80c0d3ab62a0fa626e8b75d0139975fbfc23c421938b426ea598551984455
+size 5314

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d8d6934d852376a5bc13fbfb17016d4c3adcd7b7bdd42a9aab8b9b5d9f62a1b
+oid sha256:4e79087651dbe07597bcc519c0603106d4238d761309189dc1d8c49bbe9fbdd0
 size 17549312

run-10/checkpoint-96/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3735ea28e3d6cd1886c3e5c7b2785a2ab71ac55d4b90d7f42c9458c9b695f9ba
+oid sha256:4e79087651dbe07597bcc519c0603106d4238d761309189dc1d8c49bbe9fbdd0
 size 17549312

run-10/checkpoint-96/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bce6830ac8b5a9392d5fdf74c2ac9c0069f48622b95ea10f88257a2f7bea411
+oid sha256:3771f7ce5a1e746e27d5b4f30b62b81054ea67cf657063408de78b4fac6385f5
 size 35122746

run-10/checkpoint-96/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36e71e872b9193820685ba7498cf93679ddf638b478b2d60f14aa587fd2c9678
+oid sha256:35ad384a49732bbba66f365d68a02bf664cf1489238a42c775ec81b19b0b82fa
 size 1064

run-10/checkpoint-96/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.799412915851272,
+  "best_metric": 0.7524461839530333,
   "best_model_checkpoint": "tiny-bert-sst2-distilled/run-10/checkpoint-96",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,36 +10,36 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 1.9170680046081543,
-      "learning_rate": 0.0005212663608648181,
-      "loss": 0.5641,
+      "grad_norm": 2.535670757293701,
+      "learning_rate": 0.00048723007690763744,
+      "loss": 0.5767,
       "step": 96
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.799412915851272,
-      "eval_f1": 0.8197009674582234,
-      "eval_loss": 0.47259676456451416,
-      "eval_precision": 0.744408945686901,
-      "eval_recall": 0.9119373776908023,
-      "eval_runtime": 30.8424,
-      "eval_samples_per_second": 33.136,
-      "eval_steps_per_second": 1.038,
+      "eval_accuracy": 0.7524461839530333,
+      "eval_f1": 0.7924528301886793,
+      "eval_loss": 0.4912106394767761,
+      "eval_precision": 0.6822033898305084,
+      "eval_recall": 0.9452054794520548,
+      "eval_runtime": 30.3562,
+      "eval_samples_per_second": 33.667,
+      "eval_steps_per_second": 1.054,
       "step": 96
     }
   ],
   "logging_steps": 500,
-  "max_steps": 288,
+  "max_steps": 192,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 2,
   "save_steps": 500,
   "total_flos": 235695197280.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.9610512963031814,
-    "learning_rate": 0.0007818995412972273,
-    "num_train_epochs": 3,
-    "temperature": 24
+    "alpha": 0.964566953098255,
+    "learning_rate": 0.0009744601538152749,
+    "num_train_epochs": 2,
+    "temperature": 30
   }
 }

run-10/checkpoint-96/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c48cb920a64a7322ad1d6d741321a643be4ed10af970a24a154150a0def2990
+oid sha256:b603cc11f59a882aaaffb8f9536f958187e41d9698ff3658445388c161757421
 size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c88ab003cb8d443d320a7d2a50b7663500e4bdf0605d3f2691a06db8acbcf72
+oid sha256:b603cc11f59a882aaaffb8f9536f958187e41d9698ff3658445388c161757421
 size 4920