Training in progress, epoch 2

logs/events.out.tfevents.1709737211.1dcff7455174.7719.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c9e523b45bc117c2c3cbadd311f9ddb670d13903eeffafd785984849a8ace2c
-size 5315
+oid sha256:547e623b37b94297fc4f9d015128dc831f3e7facd17e094ec7db4df88b330c86
+size 5998

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3f23050b635f2ea8a6ebefacc76753049fc76bd03375e3fb8a1a592289d0966
+oid sha256:c642993344e263148d52e3762d7218229a1a4de0cf8c7436e66df1f5d38f3a4f
 size 17549312

run-0/checkpoint-192/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fac498d151f564f026ebdcb0f781b4b2dc2327d2729864aab262ef38e75065c6
+oid sha256:c642993344e263148d52e3762d7218229a1a4de0cf8c7436e66df1f5d38f3a4f
 size 17549312

run-0/checkpoint-192/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:890533f860bb158939f2613dec488d84b5f23e30542a076271136da9999ad3d2
+oid sha256:6e0b4f12ad26192b122df11dd226cc942b218559913ed2adca76f5b40e64a426
 size 35122746

run-0/checkpoint-192/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0dceefc4088426eab0a6cd2c8414d5fde11cbc28af862e6894c4fdda8fbdac0a
+oid sha256:5b9e831b3911c6c80242ce95b2ad6684d935d06321253e703acca588b4b16bf6
 size 1064

run-0/checkpoint-192/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.541095890410959,
+  "best_metric": 0.7798434442270059,
   "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-192",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -10,55 +10,55 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 0.22234170138835907,
-      "learning_rate": 0.0005297032666879207,
-      "loss": 0.151,
+      "grad_norm": 1.6740443706512451,
+      "learning_rate": 0.0001218354408608861,
+      "loss": 0.4816,
       "step": 96
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5371819960861057,
-      "eval_f1": 0.19420783645655879,
-      "eval_loss": 0.13462358713150024,
-      "eval_precision": 0.75,
-      "eval_recall": 0.11154598825831702,
-      "eval_runtime": 28.032,
-      "eval_samples_per_second": 36.458,
-      "eval_steps_per_second": 1.142,
+      "eval_accuracy": 0.7514677103718199,
+      "eval_f1": 0.7519531250000001,
+      "eval_loss": 0.41538161039352417,
+      "eval_precision": 0.7504873294346979,
+      "eval_recall": 0.7534246575342466,
+      "eval_runtime": 26.5175,
+      "eval_samples_per_second": 38.541,
+      "eval_steps_per_second": 1.207,
       "step": 96
     },
     {
       "epoch": 2.0,
-      "grad_norm": 1.0766675472259521,
-      "learning_rate": 0.00026485163334396037,
-      "loss": 0.1364,
+      "grad_norm": 1.7866544723510742,
+      "learning_rate": 9.137658064566457e-05,
+      "loss": 0.4182,
       "step": 192
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.541095890410959,
-      "eval_f1": 0.20373514431239387,
-      "eval_loss": 0.1334332674741745,
-      "eval_precision": 0.7692307692307693,
-      "eval_recall": 0.11741682974559686,
-      "eval_runtime": 28.1007,
-      "eval_samples_per_second": 36.369,
-      "eval_steps_per_second": 1.139,
+      "eval_accuracy": 0.7798434442270059,
+      "eval_f1": 0.7817652764306499,
+      "eval_loss": 0.3980446457862854,
+      "eval_precision": 0.775,
+      "eval_recall": 0.7886497064579256,
+      "eval_runtime": 25.5088,
+      "eval_samples_per_second": 40.065,
+      "eval_steps_per_second": 1.254,
       "step": 192
     }
   ],
   "logging_steps": 500,
-  "max_steps": 288,
+  "max_steps": 480,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 5,
   "save_steps": 500,
   "total_flos": 471390394560.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.1651966098176283,
-    "learning_rate": 0.0007945549000318812,
-    "num_train_epochs": 3,
-    "temperature": 11
+    "alpha": 0.679174768290245,
+    "learning_rate": 0.00015229430107610762,
+    "num_train_epochs": 5,
+    "temperature": 27
   }
 }

run-0/checkpoint-192/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fe0685d5e12b4cb4c1d100949a8512440a8bd16b57988e693e8d02aacd0fe72
+oid sha256:1873f3a503b2d5b3f7200baa33f737ba864dd65edb3834d85c5b8e40b6b72f07
 size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c234fefe2007f16535ef723e1425baa7c9b3f0aec93243168de7f22031da2d1
+oid sha256:1873f3a503b2d5b3f7200baa33f737ba864dd65edb3834d85c5b8e40b6b72f07
 size 4920