Training in progress, epoch 10, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a7e6fc04deb6bdcd6980d2ae11996fa46b5057f077912ff527397b73b8d8921
+oid sha256:0bdc41551b933d2fe35ea88d82d13eed280c2522e7af67d11f12c0282ae42fc0
 size 737722356

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c410e9ecac85e7278a75c47ca1bddded3160da7379ac44622ac0d67b41c6bc6a
+oid sha256:6d6c397791ac92763f9e205e8ef510b47ad59bb375050c4e30ca36015500cc44
 size 1475564538

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2044a73980cd22113b15a50f74750aaca26011bd55b22f37985441a2bdc0f1e
+oid sha256:be99df8b3f53af28592d8cdccf7f2c01662135503a2081ac70bb1f25ea2abfac
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58b535628edbac2f1b6fda2e4366aba365d2efb86443bc470b3a3499eefd3781
+oid sha256:86ccb6d05c02edfe77c4f50beefff43ca85a79779bf84844c9dc8a1cdba8b680
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.2747629944426283,
   "best_model_checkpoint": "debertalarge-medical-classifier/checkpoint-366",
-  "epoch": 9.0,
+  "epoch": 10.0,
   "eval_steps": 500,
-  "global_step": 1647,
+  "global_step": 1830,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -200,6 +200,29 @@
       "eval_samples_per_second": 7.044,
       "eval_steps_per_second": 3.522,
       "step": 1647
+    },
+    {
+      "epoch": 9.289617486338798,
+      "grad_norm": 2.8257970809936523,
+      "learning_rate": 3.142076502732241e-05,
+      "loss": 0.9989,
+      "step": 1700
+    },
+    {
+      "epoch": 9.836065573770492,
+      "grad_norm": 4.843544960021973,
+      "learning_rate": 3.0327868852459017e-05,
+      "loss": 1.1366,
+      "step": 1800
+    },
+    {
+      "epoch": 10.0,
+      "eval_f1": 0.2747629944426283,
+      "eval_loss": 1.1037259101867676,
+      "eval_runtime": 13.0719,
+      "eval_samples_per_second": 7.038,
+      "eval_steps_per_second": 3.519,
+      "step": 1830
     }
   ],
   "logging_steps": 100,
@@ -219,7 +242,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4389242192010000.0,
+  "total_flos": 4876935768900000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null