Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2ad2c39211fbc204817af62eefaa7eceac8c9136c0ddcea09a9f3cfebd16bea
+oid sha256:61328080f228eddcdc74604c14b976fa7e02d5f04c872d80d4612da9e66e9b5b
 size 267832560

run-1/checkpoint-2138/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c10a863d2024a16eabdb38f36ff1b877741cf800f424ffde7bb1d789ce6bf2a
+oid sha256:61328080f228eddcdc74604c14b976fa7e02d5f04c872d80d4612da9e66e9b5b
 size 267832560

run-1/checkpoint-2138/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f47b6f83d386fa4d034def2f98d698fca4112195349f9da0f8e12e89e085d120
+oid sha256:5619b277bff481f9a59d230787ad34b3ced4b55d730897d0c29bcc85689af966
 size 535727290

run-1/checkpoint-2138/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93a2e16f1ea1471458175c4ba68043637f6d6ee28de6970ff4bfa08e7a6ad823
+oid sha256:4d70f1d78643ce09fb76f143eed50fbc04d6c0cecbcc32f76fcb57c4e04cf238
 size 14244

run-1/checkpoint-2138/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7324550fd6a275553df67d00fca12195160f5d5c7b8404c97821cb10ff18545
+oid sha256:05d6545c67fdba48fe949eb310e3e3415e570befeafea63f143797b2955b546b
 size 1064

run-1/checkpoint-2138/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.4854632779262472,
+  "best_metric": 0.4535057217805826,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-2138",
-  "epoch": 2.0,
+  "epoch": 1.0,
   "eval_steps": 500,
   "global_step": 2138,
   "is_hyper_param_search": true,
@@ -9,60 +9,51 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.47,
-      "learning_rate": 2.972945030670128e-05,
-      "loss": 0.5666,
+      "epoch": 0.23,
+      "learning_rate": 1.8468801055818304e-05,
+      "loss": 0.6002,
       "step": 500
     },
     {
-      "epoch": 0.94,
-      "learning_rate": 2.0654526525656932e-05,
-      "loss": 0.5211,
+      "epoch": 0.47,
+      "learning_rate": 1.2831193895922604e-05,
+      "loss": 0.5626,
       "step": 1000
     },
     {
-      "epoch": 1.0,
-      "eval_loss": 0.5038339495658875,
-      "eval_matthews_correlation": 0.4051130128677346,
-      "eval_runtime": 0.7912,
-      "eval_samples_per_second": 1318.257,
-      "eval_steps_per_second": 83.418,
-      "step": 1069
-    },
-    {
-      "epoch": 1.4,
-      "learning_rate": 1.1579602744612585e-05,
-      "loss": 0.3564,
+      "epoch": 0.7,
+      "learning_rate": 7.193586736026908e-06,
+      "loss": 0.5724,
       "step": 1500
     },
     {
-      "epoch": 1.87,
-      "learning_rate": 2.50467896356824e-06,
-      "loss": 0.3321,
+      "epoch": 0.94,
+      "learning_rate": 1.5559795761312122e-06,
+      "loss": 0.521,
       "step": 2000
     },
     {
-      "epoch": 2.0,
-      "eval_loss": 0.6782745122909546,
-      "eval_matthews_correlation": 0.4854632779262472,
-      "eval_runtime": 0.7525,
-      "eval_samples_per_second": 1386.109,
-      "eval_steps_per_second": 87.712,
+      "epoch": 1.0,
+      "eval_loss": 0.5128270387649536,
+      "eval_matthews_correlation": 0.4535057217805826,
+      "eval_runtime": 0.734,
+      "eval_samples_per_second": 1421.029,
+      "eval_steps_per_second": 89.921,
       "step": 2138
     }
   ],
   "logging_steps": 500,
   "max_steps": 2138,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
+  "num_train_epochs": 1,
   "save_steps": 500,
-  "total_flos": 75607578860628.0,
-  "train_batch_size": 8,
+  "total_flos": 32718412566480.0,
+  "train_batch_size": 4,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 3.8804374087745627e-05,
-    "num_train_epochs": 2,
-    "per_device_train_batch_size": 8,
-    "seed": 18
+    "learning_rate": 2.4106408215713998e-05,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 4,
+    "seed": 23
   }
 }

run-1/checkpoint-2138/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:909fa524061d6512cdc9000093fba071240645db37ca2a337df7a8b6661c2561
+oid sha256:0402ba3f82d56fed257a16dd5baa2c1f121aecba5ac06c06660cf3d0d370a49e
 size 4792

runs/Dec23_01-09-39_cab176ec49ea/events.out.tfevents.1703294400.cab176ec49ea.681.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98cada0d4043c3e0e7eac573a4355a44318c50a72505b86b100e593bd6f64607
+size 5658

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0819cb158943ae09f3b80bb459146d75a549846361b972033a0ddb1fc169aaf
+oid sha256:0402ba3f82d56fed257a16dd5baa2c1f121aecba5ac06c06660cf3d0d370a49e
 size 4792