Training in progress, epoch 21, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bab9b9ff143148c2eb48ab0eb01cb1c0039ed21a628f016dbb3ec7062b11276
+oid sha256:1ca8c84488dd6202f0546fff851509759128aa5016770978313aeee3e6bc01b2
 size 737722356

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f348c4a8be5e1a3517a82a9723a92ba5912c931847e8ed5fe32e865ec1bcb5d
+oid sha256:ce97e611ed60cf89405bb2166ca9446b30640593428120effb97319f0028acf6
 size 1475564538

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35bfabf194d35621153f637e9571c8e75877c760faefb1ae4f0569d288d288e9
+oid sha256:36d7c6bf5fd3f1bcb0581401457e89aa2a045b729c1d5c6c785ebb770b3c1a98
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d34b63a4c17f1a4f74c70ccf71f8613ced085ca4a8ea826051df9e4a623355a
+oid sha256:c770044305d507c80511da6fed303b03f94f5214835f3ef90360cc9ddd1927a5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.2747629944426283,
   "best_model_checkpoint": "debertalarge-medical-classifier/checkpoint-366",
-  "epoch": 20.0,
+  "epoch": 21.0,
   "eval_steps": 500,
-  "global_step": 3660,
+  "global_step": 3843,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -439,6 +439,29 @@
       "eval_samples_per_second": 7.031,
       "eval_steps_per_second": 3.516,
       "step": 3660
+    },
+    {
+      "epoch": 20.218579234972676,
+      "grad_norm": 6.329209327697754,
+      "learning_rate": 9.562841530054644e-06,
+      "loss": 1.0009,
+      "step": 3700
+    },
+    {
+      "epoch": 20.76502732240437,
+      "grad_norm": 7.754738807678223,
+      "learning_rate": 8.469945355191257e-06,
+      "loss": 1.0893,
+      "step": 3800
+    },
+    {
+      "epoch": 21.0,
+      "eval_f1": 0.2747629944426283,
+      "eval_loss": 1.1135228872299194,
+      "eval_runtime": 13.0668,
+      "eval_samples_per_second": 7.041,
+      "eval_steps_per_second": 3.52,
+      "step": 3843
     }
   ],
   "logging_steps": 100,
@@ -458,7 +481,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9753871537800000.0,
+  "total_flos": 1.024156511469e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null