Training in progress, step 1000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:272d2902a0945322b1098e2370c32c855495b60f146a82a0560640b3ab47d30e
+oid sha256:b048f2f6b54d60fa72f2a3164d1367da71e0e65aa96125890f1438b85e42a3bd
 size 267906392

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0363580c9aec52148e73233c0c10a7e3aba961c3d2c84bd54d368bef6fe0d04c
+oid sha256:362d86dd1a8695f7ddfeaf505e181802734cbf2cd7a52bc5791e278dbe7d3d5f
 size 535874874

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:683fad27550de1ffc9b0cc6c790b518e58ed323e4f2ac3633bf01ad829ce6017
+oid sha256:ad5ec4194439653dbe58e434c457cf95f96cb11af503c2275d1ed57edb8f9bb6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:215ffe1bec7733c0fb3f3e9bb274c5f02ff2056776126fa80e3e4a6ddd3853be
+oid sha256:5c0d22cc62c0cba538eed7b95bffd66002292cff6960e5cd2e1548a5d3e45dd6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.4708317220211029,
-  "best_model_checkpoint": "/kaggle/working/results/checkpoint-500",
-  "epoch": 0.19047619047619047,
+  "best_metric": 0.4669652283191681,
+  "best_model_checkpoint": "/kaggle/working/results/checkpoint-1000",
+  "epoch": 0.38095238095238093,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -22,6 +22,21 @@
       "eval_samples_per_second": 106.896,
       "eval_steps_per_second": 0.838,
       "step": 500
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 232334.46875,
+      "learning_rate": 3.047619047619048e-05,
+      "loss": 0.418,
+      "step": 1000
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "eval_loss": 0.4669652283191681,
+      "eval_runtime": 244.726,
+      "eval_samples_per_second": 106.858,
+      "eval_steps_per_second": 0.838,
+      "step": 1000
     }
   ],
   "logging_steps": 500,
@@ -41,7 +56,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3999047105445888.0,
+  "total_flos": 6119432633253888.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null