Training in progress, epoch 1

logs/events.out.tfevents.1709699417.adc675a344d5.5455.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6aa5d40f4733f7329c2eee62380ce682f95ca3db0b1857980bbbea454a06e0a
-size 10777
+oid sha256:d91c25c1041976eff58a49ac7864af5ca1d5afb914980af5a0901c514ff20343
+size 11814

logs/events.out.tfevents.1709701849.adc675a344d5.5455.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f17cea2e9947009500120825d917932ab211e3cf3fbb891f9661b2669b04247
+size 5315

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9628db760a85b15894d4aa208e314342d04ac194ff8d5a02d56dd80820e542b
+oid sha256:436c1223e40cc411f216b7a6eb698829ee74318f91d2f9ee826e701f17df37dd
 size 17549312

run-0/checkpoint-96/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3322fefd393b5e39a1386d42857ae3f53f9365d91bd853f467c24c433fc3e870
+oid sha256:436c1223e40cc411f216b7a6eb698829ee74318f91d2f9ee826e701f17df37dd
 size 17549312

run-0/checkpoint-96/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38aac3231dcb829688385aa1ceb0271c9ce2dde158f2559329e2bd0a5cef2adc
+oid sha256:14bc0388b3bb04b006cead065a5f3631ae5c4ff9034a98aaaa7d3d7bb6d3b660
 size 35122746

run-0/checkpoint-96/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc0f31cde557c801b0007fc552a4c92b93986f2a4117411aa9b0c6b121e1a852
+oid sha256:98396641528716b08d59d05e7221ff89e68ef8805fd0936c83a7ab0df7e80e0c
 size 1064

run-0/checkpoint-96/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.5,
+  "best_metric": 0.7436399217221135,
   "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-96",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,36 +10,36 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 0.4804088771343231,
-      "learning_rate": 2.9818131608660274e-05,
-      "loss": 0.4786,
+      "grad_norm": 1.8004393577575684,
+      "learning_rate": 0.0007697157586205755,
+      "loss": 0.4935,
       "step": 96
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5,
-      "eval_f1": 0.0,
-      "eval_loss": 0.4664871394634247,
-      "eval_precision": 0.0,
-      "eval_recall": 0.0,
-      "eval_runtime": 28.9797,
-      "eval_samples_per_second": 35.266,
-      "eval_steps_per_second": 1.104,
+      "eval_accuracy": 0.7436399217221135,
+      "eval_f1": 0.7689594356261024,
+      "eval_loss": 0.448881596326828,
+      "eval_precision": 0.6998394863563403,
+      "eval_recall": 0.8532289628180039,
+      "eval_runtime": 28.6476,
+      "eval_samples_per_second": 35.675,
+      "eval_steps_per_second": 1.117,
       "step": 96
     }
   ],
   "logging_steps": 500,
-  "max_steps": 384,
+  "max_steps": 960,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 4,
+  "num_train_epochs": 10,
   "save_steps": 500,
   "total_flos": 235695197280.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.6186723691968887,
-    "learning_rate": 3.975750881154703e-05,
-    "num_train_epochs": 4,
-    "temperature": 6
+    "alpha": 0.735211359802956,
+    "learning_rate": 0.0008552397318006393,
+    "num_train_epochs": 10,
+    "temperature": 25
   }
 }

run-0/checkpoint-96/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3aa29ea69dd18a01982daa5b87211d303a5144b609fb7e84569d6d408da8e995
+oid sha256:23804eaaa0feed30486319d2982557f65dce708f7d788864c811c20b2e8c33b4
 size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eca285e074f5751b46e77605d55ec46cae8a3b205f294ab4811aec331d54f279
+oid sha256:23804eaaa0feed30486319d2982557f65dce708f7d788864c811c20b2e8c33b4
 size 4920