Training in progress, epoch 1

logs/events.out.tfevents.1711296275.73e3a81c01ef.4225.25

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36845eae388a6e0f6493946025661fd9d30d4f19ddb6df88e7d95ecf8884d710
-size 6136
+oid sha256:640031df7bf3c366316b0bbd9dacf62195711aa34c91df0b2fcc3f9913577fef
+size 6866

logs/events.out.tfevents.1711297125.73e3a81c01ef.4225.26

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07fbea6ccc8ef7eda5e716999bad57bb45834cef318989b6309cbdd2bf2cf28b
+size 5406

logs/events.out.tfevents.1711297410.73e3a81c01ef.4225.27

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7b0640749892c869765e6d4160dec75b04b75c952170e5ebc7e226900e45291
+size 5406

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe9367c1c7d0b1c40f98f59a8a71dcda0d81f0972aa6410e57b3d855d1c6a816
+oid sha256:0357fb092c644e21a7a496383ce1471a9bb139c8cf8b29278061531e65ee0497
 size 17549312

run-27/checkpoint-192/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-27/checkpoint-192/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70f46e894f9b0d216b3b5de9d8b88ee883b27a75cfdadf6a0918c1494e2aca8c
+oid sha256:0357fb092c644e21a7a496383ce1471a9bb139c8cf8b29278061531e65ee0497
 size 17549312

run-27/checkpoint-192/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bdfd1008daf4099dedd9cbf754cb7cad1fa3a2504bb9b686c9fe61071b72e36
+oid sha256:0299ded21cb640edd148b4e3911ebee16415e4c1c9628f5a4256c1a7e49db08e
 size 35122746

run-27/checkpoint-192/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d267b33c0df8c744bb62ca8fc0e243d0ddded8c46ea62639c56f51d1dc7a548
+oid sha256:ee09ea0d216727b799a80771850b95d7d61b646360702c64b2ec889cdc725399
 size 14054

run-27/checkpoint-192/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ded7e8a2a22247cab1714b65e628b0eec06f8edd07dced724345ece707cd3b67
+oid sha256:f63cfbfe1806434dcecbe337fe128cd5bf1be8d0d5dc307ff642ddd6652c3280
 size 1064

run-27/checkpoint-192/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.8228962818003914,
+  "best_metric": 0.799412915851272,
   "best_model_checkpoint": "tiny-bert-sst2-distilled/run-27/checkpoint-192",
-  "epoch": 4.0,
+  "epoch": 1.0,
   "eval_steps": 500,
   "global_step": 192,
   "is_hyper_param_search": true,
@@ -10,93 +10,38 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 3.0442044734954834,
-      "learning_rate": 0.00047720243978875736,
-      "loss": 0.5494,
-      "step": 48
-    },
-    {
-      "epoch": 1.0,
-      "eval_accuracy": 0.7270058708414873,
-      "eval_f1": 0.7787470261697065,
-      "eval_loss": 0.4914495050907135,
-      "eval_precision": 0.6546666666666666,
-      "eval_recall": 0.9608610567514677,
-      "eval_runtime": 28.018,
-      "eval_samples_per_second": 36.476,
-      "eval_steps_per_second": 0.571,
-      "step": 48
-    },
-    {
-      "epoch": 2.0,
-      "grad_norm": 1.9368475675582886,
-      "learning_rate": 0.000357901829841568,
-      "loss": 0.4641,
-      "step": 96
-    },
-    {
-      "epoch": 2.0,
-      "eval_accuracy": 0.7720156555772995,
-      "eval_f1": 0.8059950041631974,
-      "eval_loss": 0.4658460021018982,
-      "eval_precision": 0.7014492753623188,
-      "eval_recall": 0.9471624266144814,
-      "eval_runtime": 27.3749,
-      "eval_samples_per_second": 37.333,
-      "eval_steps_per_second": 0.584,
-      "step": 96
-    },
-    {
-      "epoch": 3.0,
-      "grad_norm": 3.3749494552612305,
-      "learning_rate": 0.00023860121989437868,
-      "loss": 0.4456,
-      "step": 144
-    },
-    {
-      "epoch": 3.0,
-      "eval_accuracy": 0.8189823874755382,
-      "eval_f1": 0.8262910798122065,
-      "eval_loss": 0.4206434190273285,
-      "eval_precision": 0.7942238267148014,
-      "eval_recall": 0.8610567514677103,
-      "eval_runtime": 27.471,
-      "eval_samples_per_second": 37.203,
-      "eval_steps_per_second": 0.582,
-      "step": 144
-    },
-    {
-      "epoch": 4.0,
-      "grad_norm": 3.301919937133789,
-      "learning_rate": 0.00011930060994718934,
-      "loss": 0.4162,
+      "grad_norm": 5.356992244720459,
+      "learning_rate": 8.28536608591822e-05,
+      "loss": 0.547,
       "step": 192
     },
     {
-      "epoch": 4.0,
-      "eval_accuracy": 0.8228962818003914,
-      "eval_f1": 0.8281101614434948,
-      "eval_loss": 0.4116476774215698,
-      "eval_precision": 0.8044280442804428,
-      "eval_recall": 0.8532289628180039,
-      "eval_runtime": 27.5336,
-      "eval_samples_per_second": 37.118,
-      "eval_steps_per_second": 0.581,
+      "epoch": 1.0,
+      "eval_accuracy": 0.799412915851272,
+      "eval_f1": 0.820647419072616,
+      "eval_loss": 0.4454892873764038,
+      "eval_mcc": 0.6163545180480211,
+      "eval_precision": 0.7420886075949367,
+      "eval_recall": 0.9178082191780822,
+      "eval_runtime": 66.9011,
+      "eval_samples_per_second": 15.276,
+      "eval_steps_per_second": 0.478,
       "step": 192
     }
   ],
   "logging_steps": 500,
-  "max_steps": 240,
+  "max_steps": 576,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 942780789120.0,
-  "train_batch_size": 64,
+  "total_flos": 235695197280.0,
+  "train_batch_size": 16,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.8647030881639047,
-    "learning_rate": 0.0005965030497359467,
-    "num_train_epochs": 5,
-    "temperature": 29
+    "alpha": 0.8507816113188046,
+    "learning_rate": 0.0001242804912887733,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "temperature": 24
   }
 }

run-27/checkpoint-192/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ad319ae4dbd5526fdc9ef9369914cfa0da7582e34b1f498bfcaa68cc341085f
-size 4920
+oid sha256:f91d80d8fa16254fc8cafbdb71abffe2e808a53378473794805afa08c4e2bbeb
+size 4984

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2f00f9e41c59dd180c45edf27f2b5cce7facf08fcb4e44e2c4108d00dc05a63
-size 4920
+oid sha256:f91d80d8fa16254fc8cafbdb71abffe2e808a53378473794805afa08c4e2bbeb
+size 4984