Training in progress, epoch 1

logs/events.out.tfevents.1711203362.a08db75a0e93.4335.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71fe8ea276034d50ea2662487d33044c22d787b07263563c26bc2054c6a3ae66
-size 17642
+oid sha256:6fe9be7ab2d5b1bc79a7e0d52c51ede7b7d10f52b4d484c8856134da3a874770
+size 18679

logs/events.out.tfevents.1711205777.a08db75a0e93.4335.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78b630a9e465aa30be443299a34b49e6b081b0ba8d18c6b2ce1ee8f872140993
+size 5346

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d5b5c121b1eac187d043c4e323d50eadad9d5980290a5238c92477d7e0cdce8
+oid sha256:2b076bb533559423580ae70c17097e396f62387c173c74e541e335bac8e7e180
 size 17549312

run-0/checkpoint-96/config.json

@@ -27,7 +27,7 @@
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.39.1",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

run-0/checkpoint-96/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9deaf7b9483814e8658af2bd540c9c428e1d9d74902b8546da37c62a418f2b8
+oid sha256:2b076bb533559423580ae70c17097e396f62387c173c74e541e335bac8e7e180
 size 17549312

run-0/checkpoint-96/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e8f5ef6ee86d49f7eb75c8214eefcb88b1a2166ac8c9a098a261f23125fce34
+oid sha256:33b703a05840ff22d318422c0edd034a5683303adcf0be6a9f507ceb8211b739
 size 35122746

run-0/checkpoint-96/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bc13e09b59a62b6fb29cad756bfeefcce6f512c71a9054cc39e336db0b532a5
+oid sha256:24aa86019b8aea1c551cc1adaf38c4db2fc01de75a22af312230f6b592e0fd81
 size 14054

run-0/checkpoint-96/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bd902627d0c1d565c70987837a95a63c8ee21875132d3259ea0ce69d0e7372a
+oid sha256:1deff0f11257c2d691ece1057908e736422281f9c02aff1f44118d31a5fc6ba2
 size 1064

run-0/checkpoint-96/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.5,
-  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-48",
-  "epoch": 2.0,
+  "best_metric": 0.4980430528375734,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-96",
+  "epoch": 1.0,
   "eval_steps": 500,
   "global_step": 96,
   "is_hyper_param_search": true,
@@ -10,55 +10,36 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 1.7277214527130127,
-      "learning_rate": 7.1080634981543736e-06,
-      "loss": 0.4421,
-      "step": 48
-    },
-    {
-      "epoch": 1.0,
-      "eval_accuracy": 0.5,
-      "eval_f1": 0.0,
-      "eval_loss": 0.4095905125141144,
-      "eval_precision": 0.0,
-      "eval_recall": 0.0,
-      "eval_runtime": 28.1077,
-      "eval_samples_per_second": 36.36,
-      "eval_steps_per_second": 0.569,
-      "step": 48
-    },
-    {
-      "epoch": 2.0,
-      "grad_norm": 0.3527555465698242,
-      "learning_rate": 3.5540317490771868e-06,
-      "loss": 0.4039,
+      "grad_norm": 0.8380242586135864,
+      "learning_rate": 8.6265645867868e-06,
+      "loss": 0.6538,
       "step": 96
     },
     {
-      "epoch": 2.0,
-      "eval_accuracy": 0.5,
-      "eval_f1": 0.0,
-      "eval_loss": 0.39591261744499207,
-      "eval_precision": 0.0,
-      "eval_recall": 0.0,
-      "eval_runtime": 27.762,
-      "eval_samples_per_second": 36.813,
-      "eval_steps_per_second": 0.576,
+      "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
     }
   ],
   "logging_steps": 500,
-  "max_steps": 144,
+  "max_steps": 576,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 6,
   "save_steps": 500,
-  "total_flos": 471390394560.0,
-  "train_batch_size": 64,
+  "total_flos": 235695197280.0,
+  "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.48386139243976256,
-    "learning_rate": 1.066209524723156e-05,
-    "num_train_epochs": 3,
-    "temperature": 23
+    "alpha": 0.9136100763812092,
+    "learning_rate": 1.035187750414416e-05,
+    "num_train_epochs": 6,
+    "temperature": 5
   }
 }

run-0/checkpoint-96/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:103518af05e87893001984e8fe4e4fbdef270179595accd70434e2248c87999d
+oid sha256:ebe7dd3c3e257754c6583ea668a830f19b3dc80cb7982abc3ddecb0dac8e92b5
 size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c0967cc1aebc72646b1634b2a505d0131b61790f8449416683fb0b8bf534fc0
+oid sha256:ebe7dd3c3e257754c6583ea668a830f19b3dc80cb7982abc3ddecb0dac8e92b5
 size 4920