Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca0dc6ea72694ff54a88f458db9aff463c496bd6d83166f6fb57a4e51c5bb172
+oid sha256:b5b3ada415323df4681659f8a3c19121e9379a2b0c7922cade957c3cc9526017
 size 409103316

run-0/checkpoint-534/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2c26a4990298c617435add4fef099a107381df4b5d4dd2ceb1932c28c743541
+oid sha256:b5b3ada415323df4681659f8a3c19121e9379a2b0c7922cade957c3cc9526017
 size 409103316

run-0/checkpoint-534/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7c82d05f4ce26f22c9acaa7998473a49f5f6cbfcd52e5fa856d9f347b60ad8c
+oid sha256:01fc13bfd901a55e2ac038444bc5950e036e98be6e0fb3c7670e6e8a5cef840f
 size 818327802

run-0/checkpoint-534/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dda5eab8086c3361f01b6da1d0d501e5d7ffcc15041db5c9a3384c00b843300f
+oid sha256:8a56050495e1938ae70b239ae8ece3c43ac800b58f0a6e02bd7ed6cd1669797d
 size 1064

run-0/checkpoint-534/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.5817901492118835,
+  "best_metric": 0.6037774682044983,
   "best_model_checkpoint": "BERT-WMM/run-0/checkpoint-534",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -10,39 +10,39 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7563380281690141,
-      "eval_loss": 0.6019130349159241,
-      "eval_runtime": 2.4228,
-      "eval_samples_per_second": 879.158,
-      "eval_steps_per_second": 55.309,
+      "eval_accuracy": 0.7530516431924883,
+      "eval_loss": 0.6065725684165955,
+      "eval_runtime": 2.5073,
+      "eval_samples_per_second": 849.524,
+      "eval_steps_per_second": 53.444,
       "step": 267
     },
     {
       "epoch": 1.87,
-      "grad_norm": 9.674468994140625,
-      "learning_rate": 5.7987153604787005e-06,
-      "loss": 0.6061,
+      "grad_norm": 9.447751998901367,
+      "learning_rate": 9.825065893169892e-07,
+      "loss": 0.6083,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.7619718309859155,
-      "eval_loss": 0.5817901492118835,
-      "eval_runtime": 2.4333,
-      "eval_samples_per_second": 875.37,
-      "eval_steps_per_second": 55.07,
+      "eval_accuracy": 0.7615023474178404,
+      "eval_loss": 0.6037774682044983,
+      "eval_runtime": 2.4998,
+      "eval_samples_per_second": 852.081,
+      "eval_steps_per_second": 53.605,
       "step": 534
     }
   ],
   "logging_steps": 500,
-  "max_steps": 801,
+  "max_steps": 534,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 2,
   "save_steps": 500,
   "total_flos": 349221394826640.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "num_train_epochs": 3
+    "weight_decay": 9.670788404941036e-05
   }
 }

run-0/checkpoint-534/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11f7c65747bd635b8f0e76f611e224f7ef08b5428ba70dd1530c26977be68e0b
+oid sha256:de07fd0528e0ec401b749f0d80d28e850e36f7e66780675fb859022ed638d382
 size 4856

runs/Apr19_10-19-01_dcdaa3e6ec43/events.out.tfevents.1713521944.dcdaa3e6ec43.789.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6f0b3002c4418729fd7ca23e6ae9fc9e8fac9d2478d4a388d69ecd8d2385060
-size 5234
+oid sha256:fee924e67051849fdffd25dac35c063461003059dc4fd9c69d77b70a0171a73d
+size 6122