Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c045372f29e6a3f37f3f88e140fc38258f54572ecc9ac94f101c483b9cc8c37a
+oid sha256:951f38e98d13e21dc75cc9bd9b2cdeaa5a6f08f0892623ca0324878e99204599
 size 267832560

run-1/checkpoint-428/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f5e5e12cac969229af19d5cc7e20d9dd28b58d83480d2f3f341a4edb226f21e
+oid sha256:8220f206622c6f496381eba1d07bd6ca75d91e74d50afa7e44799ad9c5be7d7d
 size 267832560

run-1/checkpoint-428/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eadb1fadb61f6a7641544ddbe29956168ba4da83b036b9363f9861969ced5ba0
+oid sha256:4e02fdb1e8930d0fc3489386465b2180991e69247221cc87c1151b1dbd15512a
 size 535727290

run-1/checkpoint-428/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd01b2476b9fd2a1c227088b0c96b8416829b65b2617d2ef2215b5bf1d325ff4
+oid sha256:e87fe3c36d691ac6c42bca874c74ed014eefdbb6108564f8658fb9e5b9febc83
 size 14244

run-1/checkpoint-428/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d27394d0580c0938e9e973527b4d373c693291de7929426d26b8c19e9b62200
+oid sha256:3c25e2e9cf1ce0cd951d12d306061617bdab3f567ca512f75957cae4f113da48
 size 1064

run-1/checkpoint-428/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.3432921557472473,
+  "best_metric": 0.3005246361638528,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-428",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -10,35 +10,35 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.5924310088157654,
-      "eval_matthews_correlation": 0.06558874629318973,
-      "eval_runtime": 0.7705,
-      "eval_samples_per_second": 1353.67,
-      "eval_steps_per_second": 85.659,
+      "eval_loss": 0.6478912234306335,
+      "eval_matthews_correlation": 0.18118799119487816,
+      "eval_runtime": 0.7571,
+      "eval_samples_per_second": 1377.58,
+      "eval_steps_per_second": 87.172,
       "step": 214
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.5929568409919739,
-      "eval_matthews_correlation": 0.3432921557472473,
-      "eval_runtime": 1.2272,
-      "eval_samples_per_second": 849.906,
-      "eval_steps_per_second": 53.781,
+      "eval_loss": 0.9094101190567017,
+      "eval_matthews_correlation": 0.3005246361638528,
+      "eval_runtime": 1.0485,
+      "eval_samples_per_second": 994.768,
+      "eval_steps_per_second": 62.948,
       "step": 428
     }
   ],
   "logging_steps": 500,
-  "max_steps": 856,
+  "max_steps": 428,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 4,
+  "num_train_epochs": 2,
   "save_steps": 500,
   "total_flos": 0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 1.674218791607766e-05,
-    "num_train_epochs": 4,
+    "learning_rate": 3.45845102664945e-05,
+    "num_train_epochs": 2,
     "per_device_train_batch_size": 4,
-    "seed": 16
+    "seed": 15
   }
 }

run-1/checkpoint-428/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36613bcef60bcf7fd2c5bce911434f81154fc143b65a8b57de2003769014ca00
+oid sha256:f8bfed4abe7904aebfa29146a26419ad532e218a199dc08365bb4ca5a35eafdb
 size 4984

run-2/checkpoint-54/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa0fee7546ff58c6ec3390bde5cecd927681e055eef69980256766b8e949510b
+oid sha256:951f38e98d13e21dc75cc9bd9b2cdeaa5a6f08f0892623ca0324878e99204599
 size 267832560

run-2/checkpoint-54/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79f7f242c330bc7344d80b82b5a5744020478114d6b0ddd5297974b2c9489275
+oid sha256:5740171fee8b11d2fbb61832c047c97d81240537dace9d499fca0fe4dddff88c
 size 535727290

run-2/checkpoint-54/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56e134a945a8c09dbe3c3e74ec36d9a17c0f35f9759b7fc9e96fefe249cf37f0
+oid sha256:df090108457d96817be2199667108a02455609ad929d99fa814d2ee7bd50d185
 size 14244

run-2/checkpoint-54/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9afcab2bcd613780244f936803a32ad4b09ef30bad1a438d264ad9700e3668e0
+oid sha256:303844bf75ccfc607f59353a7880410a50503f4e94b34d2f10013216f0e88a2a
 size 1064

run-2/checkpoint-54/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.2712686505720511,
+  "best_metric": 0.0,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-54",
-  "epoch": 2.0,
+  "epoch": 1.0,
   "eval_steps": 500,
   "global_step": 54,
   "is_hyper_param_search": true,
@@ -10,35 +10,26 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.5924028158187866,
+      "eval_loss": 0.5896052122116089,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.7139,
-      "eval_samples_per_second": 1460.954,
-      "eval_steps_per_second": 92.448,
-      "step": 27
-    },
-    {
-      "epoch": 2.0,
-      "eval_loss": 0.5790226459503174,
-      "eval_matthews_correlation": 0.2712686505720511,
-      "eval_runtime": 0.7744,
-      "eval_samples_per_second": 1346.766,
-      "eval_steps_per_second": 85.222,
+      "eval_runtime": 0.7382,
+      "eval_samples_per_second": 1412.91,
+      "eval_steps_per_second": 89.408,
       "step": 54
     }
   ],
   "logging_steps": 500,
-  "max_steps": 135,
+  "max_steps": 162,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 3,
   "save_steps": 500,
   "total_flos": 0,
-  "train_batch_size": 32,
+  "train_batch_size": 16,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 3.196781434256157e-05,
-    "num_train_epochs": 5,
-    "per_device_train_batch_size": 32,
-    "seed": 15
+    "learning_rate": 4.44263313595678e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "seed": 36
   }
 }

run-2/checkpoint-54/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69153e9bbab207ff12f995d64fcbc179aebf9c056495013eeb831a9bd3f09fb4
+oid sha256:64b88362824c828734d46d9219cae04a83c937724d8224d58b37d769b6b5a4e8
 size 4984

runs/Feb28_18-10-00_5620ed9b2fff/events.out.tfevents.1709144639.5620ed9b2fff.209.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aab91ac1e0a164f942e98bb69c1148a4711749f1e19200cf9e8d0d19bf3edfcc
+size 5888

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8bfed4abe7904aebfa29146a26419ad532e218a199dc08365bb4ca5a35eafdb
+oid sha256:64b88362824c828734d46d9219cae04a83c937724d8224d58b37d769b6b5a4e8
 size 4984