Training in progress, epoch 2

logs/events.out.tfevents.1706267654.A-FVFFG2C4Q05P.18450.25

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52e8a45c581fb5b3516f4cb4889b959907d751513b182ded83870e5a483005e9
-size 4916
+oid sha256:7b747605f0133808a1c3fb7171fd8d456496eafe3abfe5be2883f33c808489f6
+size 5396

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87568c0afc5ae5e4ff718507f68ad4943997f13f2f2353ed7480c5872143ba54
+oid sha256:a8ca26b38440b24ac09b4108e4fad32a203e7fb86f22a35fb7ee11404f1a1e04
 size 17549312

run-1/checkpoint-1054/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a48f92c46c7e5026b38f2b3bf26873dd3ae9f5952ec78dfa9724da5d9e0ab0c2
+oid sha256:a8ca26b38440b24ac09b4108e4fad32a203e7fb86f22a35fb7ee11404f1a1e04
 size 17549312

run-1/checkpoint-1054/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b28bbcc0546d31f0198832865f505c9cf6e29ab2fd20d07ff939ad80196014e
+oid sha256:6a833337f09e72dc86573785f7bcf879bfb8368c000dfb8bc8fad2aef129deb2
 size 35122373

run-1/checkpoint-1054/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7ac61b823b02e9f174aebe61188f30c7365422c82ea4dfaaa2d4e8479e62b71
+oid sha256:11d09bc903f95d6f79c61520bda6bb10b74f15510dab87c8eabb5924934da6f3
 size 627

run-1/checkpoint-1054/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6995412844036697,
+  "best_metric": 0.8130733944954128,
   "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-1054",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -10,47 +10,47 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "learning_rate": 5.34694014828574e-06,
-      "loss": 4.485,
+      "learning_rate": 0.0006875917567735723,
+      "loss": 0.9069,
       "step": 527
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6513761467889908,
-      "eval_loss": 3.9686293601989746,
-      "eval_runtime": 9.1719,
-      "eval_samples_per_second": 95.073,
-      "eval_steps_per_second": 0.763,
+      "eval_accuracy": 0.801605504587156,
+      "eval_loss": 1.1160032749176025,
+      "eval_runtime": 9.4507,
+      "eval_samples_per_second": 92.269,
+      "eval_steps_per_second": 0.741,
       "step": 527
     },
     {
       "epoch": 2.0,
-      "learning_rate": 0.0,
-      "loss": 4.0805,
+      "learning_rate": 0.0006111926726876199,
+      "loss": 0.4218,
       "step": 1054
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6995412844036697,
-      "eval_loss": 3.6462810039520264,
-      "eval_runtime": 9.4456,
-      "eval_samples_per_second": 92.318,
-      "eval_steps_per_second": 0.741,
+      "eval_accuracy": 0.8130733944954128,
+      "eval_loss": 1.181414246559143,
+      "eval_runtime": 9.1074,
+      "eval_samples_per_second": 95.746,
+      "eval_steps_per_second": 0.769,
       "step": 1054
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1054,
+  "max_steps": 5270,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
+  "num_train_epochs": 10,
   "save_steps": 500,
   "total_flos": 16162868129520.0,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.10705118382199963,
-    "learning_rate": 1.069388029657148e-05,
-    "num_train_epochs": 2,
-    "temperature": 16
+    "alpha": 0.5682681228180307,
+    "learning_rate": 0.0007639908408595248,
+    "num_train_epochs": 10,
+    "temperature": 8
   }
 }

run-1/checkpoint-1054/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70d09d03f84ec5e6f07e718b975ff8effb1d82efe0ca25ef5c8642902ec419c8
+oid sha256:d99816c97dcbe7250039b2fe72e8bb2c24840867dcd296d9eb6598b2afd2670d
 size 4283