Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f3d39af8eaf5db8c9342afd21b6daca84a6b7eb421a18e1ded6fe0fb9e1769a
+oid sha256:ff3df08caa0c5e98037019b5d56d98eaa6fe11a9bcdae02bfbde5be20fba20e5
 size 267832560

run-1/checkpoint-2138/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cec4ce1d2b9f76db5a8dedca630e6f833ee08905c7efdc3173e0d174c1130648
+oid sha256:ff3df08caa0c5e98037019b5d56d98eaa6fe11a9bcdae02bfbde5be20fba20e5
 size 267832560

run-1/checkpoint-2138/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6de591f08904fd53e4c847c659bc95a41069c1f0c2b910487b6da18ed83ff7a
+oid sha256:3f5de18039268471c399f67329cc78a085cd09bdf8fec86f67845f9f58d830fc
 size 535724410

run-1/checkpoint-2138/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e37bb18caef6eb447741eff7ae91dfd3fcfa8bc8a63135e1f691bb2da338921c
-size 14054
+oid sha256:a19465d7b8e06894de84f452a1f87d9245fba61d92f8e977f1a67c420bf19cf1
+size 13990

run-1/checkpoint-2138/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6da3a89515b59dff37c5a264b589ef20e97716e0f62e87efd04721694227d277
+oid sha256:852437654a4d4832fb56156864b4d8a03fff01279bd2bbb67d8c37e6da2245c0
 size 1064

run-1/checkpoint-2138/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.4546806571399457,
+  "best_metric": 0.3084289905217366,
   "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,
@@ -9,64 +9,55 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.4677268475210477,
-      "grad_norm": 2.976968765258789,
-      "learning_rate": 5.1710250568684506e-05,
-      "loss": 0.5872,
+      "epoch": 0.23386342376052385,
+      "grad_norm": 3.146369218826294,
+      "learning_rate": 1.653715321124928e-06,
+      "loss": 0.6079,
       "step": 500
     },
     {
-      "epoch": 0.9354536950420954,
-      "grad_norm": 3.4058539867401123,
-      "learning_rate": 3.592568079802378e-05,
-      "loss": 0.5491,
+      "epoch": 0.4677268475210477,
+      "grad_norm": 5.078900337219238,
+      "learning_rate": 1.5725712916291023e-06,
+      "loss": 0.6126,
       "step": 1000
     },
     {
-      "epoch": 1.0,
-      "eval_loss": 0.5090050101280212,
-      "eval_matthews_correlation": 0.3611067385212146,
-      "eval_runtime": 28.3466,
-      "eval_samples_per_second": 36.794,
-      "eval_steps_per_second": 2.328,
-      "step": 1069
-    },
-    {
-      "epoch": 1.4031805425631432,
-      "grad_norm": 5.668572902679443,
-      "learning_rate": 2.014111102736307e-05,
-      "loss": 0.3878,
+      "epoch": 0.7015902712815716,
+      "grad_norm": 7.2771897315979,
+      "learning_rate": 1.4914272621332766e-06,
+      "loss": 0.5551,
       "step": 1500
     },
     {
-      "epoch": 1.8709073900841908,
-      "grad_norm": 1.8915776014328003,
-      "learning_rate": 4.3565412567023575e-06,
-      "loss": 0.3562,
+      "epoch": 0.9354536950420954,
+      "grad_norm": 22.494115829467773,
+      "learning_rate": 1.4102832326374508e-06,
+      "loss": 0.523,
       "step": 2000
     },
     {
-      "epoch": 2.0,
-      "eval_loss": 0.5790878534317017,
-      "eval_matthews_correlation": 0.4546806571399457,
-      "eval_runtime": 29.1964,
-      "eval_samples_per_second": 35.724,
-      "eval_steps_per_second": 2.261,
+      "epoch": 1.0,
+      "eval_loss": 0.5956234335899353,
+      "eval_matthews_correlation": 0.3084289905217366,
+      "eval_runtime": 31.6888,
+      "eval_samples_per_second": 32.914,
+      "eval_steps_per_second": 2.083,
       "step": 2138
     }
   ],
   "logging_steps": 500,
-  "max_steps": 2138,
+  "max_steps": 10690,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
+  "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 75350923275732.0,
-  "train_batch_size": 8,
+  "total_flos": 32670807095088.0,
+  "train_batch_size": 4,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 6.749482033934521e-05,
-    "num_train_epochs": 2,
-    "per_device_train_batch_size": 8,
-    "seed": 25
+    "learning_rate": 1.7348593506207536e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 22
   }
 }

run-1/checkpoint-2138/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86af0a103816c5520416e0097dd89d50a07cbde39cfa749f0effccd48467f774
+oid sha256:7b505570bfabe2b3954b5c415db50fe70c16c7616859b303999126f730738b08
 size 5048

runs/Apr23_21-08-52_949a71f95aca/events.out.tfevents.1713915632.949a71f95aca.1272.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cd1541b8f500be6968b250517007aad975c46818332b10b5fac09afa0274ac6
+size 5829

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dacdab469fdcefaf9db3c5881569ed8f6809388c6a56ea9627c14d9ffaa0fc76
+oid sha256:7b505570bfabe2b3954b5c415db50fe70c16c7616859b303999126f730738b08
 size 5048