Training in progress, epoch 22, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ca8c84488dd6202f0546fff851509759128aa5016770978313aeee3e6bc01b2
+oid sha256:15f1c4a971e099d512cec1774d57f70e9333774ad38e327c5943af0639d4fc47
 size 737722356

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce97e611ed60cf89405bb2166ca9446b30640593428120effb97319f0028acf6
+oid sha256:465b2322bddc359b3425d427e8459035ea00fc73d12c9db66fe95d412662c41f
 size 1475564538

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36d7c6bf5fd3f1bcb0581401457e89aa2a045b729c1d5c6c785ebb770b3c1a98
+oid sha256:590d7c172aabf42d21104329afbc496ff5ad235378fe2c2c64f88973507188a9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c770044305d507c80511da6fed303b03f94f5214835f3ef90360cc9ddd1927a5
+oid sha256:6943e5b148bc6f89e0cfac1ee67940b9e73bd19b65da33d10f190eccc49b708e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.2747629944426283,
   "best_model_checkpoint": "debertalarge-medical-classifier/checkpoint-366",
-  "epoch": 21.0,
+  "epoch": 22.0,
   "eval_steps": 500,
-  "global_step": 3843,
+  "global_step": 4026,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -462,6 +462,29 @@
       "eval_samples_per_second": 7.041,
       "eval_steps_per_second": 3.52,
       "step": 3843
+    },
+    {
+      "epoch": 21.311475409836067,
+      "grad_norm": 5.315028190612793,
+      "learning_rate": 7.3770491803278695e-06,
+      "loss": 1.0579,
+      "step": 3900
+    },
+    {
+      "epoch": 21.85792349726776,
+      "grad_norm": 5.136527061462402,
+      "learning_rate": 6.284153005464481e-06,
+      "loss": 1.0686,
+      "step": 4000
+    },
+    {
+      "epoch": 22.0,
+      "eval_f1": 0.2747629944426283,
+      "eval_loss": 1.1142159700393677,
+      "eval_runtime": 13.0603,
+      "eval_samples_per_second": 7.044,
+      "eval_steps_per_second": 3.522,
+      "step": 4026
     }
   ],
   "logging_steps": 100,
@@ -481,7 +504,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.024156511469e+16,
+  "total_flos": 1.072925869158e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null