Training in progress, epoch 6, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4edcaa9878838fd6cba6bbe68e29c9c32a723f75eaeebdbddc4db2f79e4c9e04
+oid sha256:23746a7620b5136a66401d5f96e0ea05ec82a1e20a2d9ba6c073a2115d51aae5
 size 737722356

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2537d0dea7dcc79617ba45301f4d1fe3a40489ca2e7c0a2fa8bf9b0d56aea40d
+oid sha256:e4d440d763da6639fb3e8ddcc63bdee0021603baea8513c68fea369b3eda3261
 size 1475564538

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01b1ef99b79bf162fdcfc6d98dbaf87c13c9ce1977824524538f4f936cc70630
+oid sha256:f139f42632372cea8d0db01b7b8ab87daad9d5bcb35431e47c8491cc521019ea
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6491af318b1c80d880dc12e80ac041c57092dca8e1473d08121d7239a717b443
+oid sha256:fe9cd7bdbd735686cf42c7853c76c322de4831c1ff5af82514b8acdb8ca46cd0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.2747629944426283,
   "best_model_checkpoint": "debertalarge-medical-classifier/checkpoint-366",
-  "epoch": 5.0,
+  "epoch": 6.0,
   "eval_steps": 500,
-  "global_step": 915,
+  "global_step": 1098,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -115,6 +115,22 @@
       "eval_samples_per_second": 7.052,
       "eval_steps_per_second": 3.526,
       "step": 915
+    },
+    {
+      "epoch": 5.46448087431694,
+      "grad_norm": 4.914717674255371,
+      "learning_rate": 3.9071038251366124e-05,
+      "loss": 1.0869,
+      "step": 1000
+    },
+    {
+      "epoch": 6.0,
+      "eval_f1": 0.2747629944426283,
+      "eval_loss": 1.1109999418258667,
+      "eval_runtime": 13.0453,
+      "eval_samples_per_second": 7.052,
+      "eval_steps_per_second": 3.526,
+      "step": 1098
     }
   ],
   "logging_steps": 100,
@@ -134,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2438467884450000.0,
+  "total_flos": 2926161461340000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null