Training in progress, epoch 1

logs/events.out.tfevents.1711265559.73e3a81c01ef.413.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c360d659b9598e9424aca54f91f2d5cf27de071ff70f1c0cc9c41e4d90ba052
+size 4184

logs/events.out.tfevents.1711265653.73e3a81c01ef.4225.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29328cc7547f41743a4985f8d99faf99f508f44dea209ce91b456a7d804ef40f
+size 5407

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29082dbaea3f8e47cfcc31c6e16d3679b1f3daafed858d8b69e14033805c58b9
+oid sha256:70b7f7f1a78e0b340b57dfae4e8a71ef78a3dbee8319a311f6096e6cf4233908
 size 17549312

run-0/checkpoint-192/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ad0bd06080c9950cf0b32ccbbbcf6703c55e10377efa299383ee3e5fbe872af
+oid sha256:70b7f7f1a78e0b340b57dfae4e8a71ef78a3dbee8319a311f6096e6cf4233908
 size 17549312

run-0/checkpoint-192/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:010a84581763e78e630b72ef20feb9007b160dc66fe58d5b5e40e5c8dce9d715
+oid sha256:356dee3ad756ad1b2b75bf326a1853ce70012cbc769d26f68477c7f9a8c9d542
 size 35122746

run-0/checkpoint-192/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c58c0607d97c986e9d4c30b0aa74b33350e0c7e86978aaaaadda4ebb78f21ad
+oid sha256:ee09ea0d216727b799a80771850b95d7d61b646360702c64b2ec889cdc725399
 size 14054

run-0/checkpoint-192/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae35fc790746b06c7bed32afc0cf4fb21caaf6a541d31f420d923a2b79458e53
+oid sha256:b5203618527782331a9cff178ca211eed05dd20856984abcc56b6a5b95a15783
 size 1064

run-0/checkpoint-192/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.5,
+  "best_metric": 0.6976516634050881,
   "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-192",
-  "epoch": 2.0,
+  "epoch": 1.0,
   "eval_steps": 500,
   "global_step": 192,
   "is_hyper_param_search": true,
@@ -10,55 +10,38 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 0.8380242586135864,
-      "learning_rate": 8.6265645867868e-06,
-      "loss": 0.6538,
-      "step": 96
-    },
-    {
-      "epoch": 1.0,
-      "eval_accuracy": 0.4980430528375734,
-      "eval_f1": 0.06215722120658134,
-      "eval_loss": 0.6460775136947632,
-      "eval_precision": 0.4722222222222222,
-      "eval_recall": 0.033268101761252444,
-      "eval_runtime": 32.7473,
-      "eval_samples_per_second": 31.209,
-      "eval_steps_per_second": 0.977,
-      "step": 96
-    },
-    {
-      "epoch": 2.0,
-      "grad_norm": 1.982408046722412,
-      "learning_rate": 6.901251669429439e-06,
-      "loss": 0.6453,
+      "grad_norm": 1.7846055030822754,
+      "learning_rate": 4.610177667546352e-05,
+      "loss": 0.4587,
       "step": 192
     },
     {
-      "epoch": 2.0,
-      "eval_accuracy": 0.5,
-      "eval_f1": 0.019193857965451058,
-      "eval_loss": 0.6427881717681885,
-      "eval_precision": 0.5,
-      "eval_recall": 0.009784735812133072,
-      "eval_runtime": 30.8528,
-      "eval_samples_per_second": 33.125,
-      "eval_steps_per_second": 1.037,
+      "epoch": 1.0,
+      "eval_accuracy": 0.6976516634050881,
+      "eval_f1": 0.6419466975666281,
+      "eval_loss": 0.4008609354496002,
+      "eval_mcc": 0.41595144404027,
+      "eval_precision": 0.7869318181818182,
+      "eval_recall": 0.5420743639921722,
+      "eval_runtime": 66.5688,
+      "eval_samples_per_second": 15.353,
+      "eval_steps_per_second": 0.481,
       "step": 192
     }
   ],
   "logging_steps": 500,
-  "max_steps": 576,
+  "max_steps": 1920,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 6,
+  "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 471390394560.0,
-  "train_batch_size": 32,
+  "total_flos": 235695197280.0,
+  "train_batch_size": 16,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.9136100763812092,
-    "learning_rate": 1.035187750414416e-05,
-    "num_train_epochs": 6,
-    "temperature": 5
+    "alpha": 0.6226480553446316,
+    "learning_rate": 5.122419630607058e-05,
+    "num_train_epochs": 10,
+    "per_device_train_batch_size": 16,
+    "temperature": 20
   }
 }

run-0/checkpoint-192/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebe7dd3c3e257754c6583ea668a830f19b3dc80cb7982abc3ddecb0dac8e92b5
-size 4920
+oid sha256:dbca9cde0b156ba25d74ee6bc6ea4c2fa160afa3570e75ccc73231ac4a159c49
+size 4984

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c0967cc1aebc72646b1634b2a505d0131b61790f8449416683fb0b8bf534fc0
-size 4920
+oid sha256:dbca9cde0b156ba25d74ee6bc6ea4c2fa160afa3570e75ccc73231ac4a159c49
+size 4984