Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8c8a388e36e0bf6ad2319a1bef8deb3da83e87730116e7d0d4866a53317ad9e
+oid sha256:9152e90a3c9e77ecea6ba6c66be674c5ca7f0f34362bd74db83fdba3b54eb72b
 size 267832560

run-4/checkpoint-28/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b38f3f108b688e85145e94b5b56a28c00f9561110ded714c3d71987fe8f0b4c
+oid sha256:9152e90a3c9e77ecea6ba6c66be674c5ca7f0f34362bd74db83fdba3b54eb72b
 size 267832560

run-4/checkpoint-28/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19eebd242c4f4c63f900985a41c9d65e824eccbf34e3e8ae3ee3d9b967b2201f
-size 535727290
+oid sha256:2e6e76dbd95bcf89c812762cd490a47012995a4214960b0a6410cde9f2c1485c
+size 535724410

run-4/checkpoint-28/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0271999a8810dd52694b83db2238813229da6d77696350886a6251a48fcf498
-size 14244
+oid sha256:a2366e2958c2c2ad740ca53c6e5742ec8e1b272e9023b397e1a6fe941d5a09ab
+size 13990

run-4/checkpoint-28/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c4bd2dc9fbe87657ae6126fbf1791044201ea88bf50f33bc11e6c4201643f66
+oid sha256:9626fc9fc55c7eb7261b08007e5e50efdeca4c253581bb30368005a3a08c872f
 size 1064

run-4/checkpoint-28/trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.0,
-  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-28",
+  "best_metric": 0.0463559874942472,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-14",
   "epoch": 2.0,
   "eval_steps": 500,
   "global_step": 28,
@@ -10,20 +10,20 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.6748577952384949,
-      "eval_matthews_correlation": -0.02339059069282274,
-      "eval_runtime": 0.5175,
-      "eval_samples_per_second": 2015.397,
-      "eval_steps_per_second": 127.532,
+      "eval_loss": 0.6544817686080933,
+      "eval_matthews_correlation": 0.0463559874942472,
+      "eval_runtime": 9.8012,
+      "eval_samples_per_second": 106.416,
+      "eval_steps_per_second": 6.734,
       "step": 14
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.6442534923553467,
+      "eval_loss": 0.6357603669166565,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.5351,
-      "eval_samples_per_second": 1949.087,
-      "eval_steps_per_second": 123.336,
+      "eval_runtime": 9.3026,
+      "eval_samples_per_second": 112.119,
+      "eval_steps_per_second": 7.095,
       "step": 28
     }
   ],
@@ -36,9 +36,9 @@
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 9.275459477508523e-06,
+    "learning_rate": 6.226187573987636e-06,
     "num_train_epochs": 2,
     "per_device_train_batch_size": 64,
-    "seed": 19
+    "seed": 27
   }
 }

run-4/checkpoint-28/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f215b8d0a2d3f4dfd3304f2a727dab785e1a5bd6316594447c1595a03c7703c
+oid sha256:b4c0d3a0c467db322c0006765e467b1f7b3e3b026673cc6b57936f072d505de9
 size 4984

runs/Mar06_18-56-30_6942db43b48a/events.out.tfevents.1709753908.6942db43b48a.1479.6

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd449f0b576fdd2fd939d53d4f97de790a7cbcd483b3c6b64ee877373ffe39db
-size 4871
+oid sha256:6139d0d6c258a60d4513e7f90ebe41df5f32ec49cf3219f0a103607ef2b39290
+size 5548