Training in progress, epoch 9, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a2018d54a34012ba4546bb4f9b7c9529b6614e668d8606d353645d3586c3045
+oid sha256:2a7e6fc04deb6bdcd6980d2ae11996fa46b5057f077912ff527397b73b8d8921
 size 737722356

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0715101da8193f8171b69d9fe96bc57f88b295c344d0606585b7cacf3554b7a2
+oid sha256:c410e9ecac85e7278a75c47ca1bddded3160da7379ac44622ac0d67b41c6bc6a
 size 1475564538

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d55807819bdae9e8fbe453685136e22fbf0013e7f27fc4b2e8b261bbf5cae4ef
+oid sha256:c2044a73980cd22113b15a50f74750aaca26011bd55b22f37985441a2bdc0f1e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58cf2bfb447415b2597ec64c77694929e3d11b1375ad51d86c88386c6a7dc6e2
+oid sha256:58b535628edbac2f1b6fda2e4366aba365d2efb86443bc470b3a3499eefd3781
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.2747629944426283,
   "best_model_checkpoint": "debertalarge-medical-classifier/checkpoint-366",
-  "epoch": 8.0,
+  "epoch": 9.0,
   "eval_steps": 500,
-  "global_step": 1464,
+  "global_step": 1647,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -177,6 +177,29 @@
       "eval_samples_per_second": 7.043,
       "eval_steps_per_second": 3.522,
       "step": 1464
+    },
+    {
+      "epoch": 8.19672131147541,
+      "grad_norm": 2.7967240810394287,
+      "learning_rate": 3.360655737704918e-05,
+      "loss": 1.0848,
+      "step": 1500
+    },
+    {
+      "epoch": 8.743169398907105,
+      "grad_norm": 5.457353115081787,
+      "learning_rate": 3.251366120218579e-05,
+      "loss": 1.0525,
+      "step": 1600
+    },
+    {
+      "epoch": 9.0,
+      "eval_f1": 0.2747629944426283,
+      "eval_loss": 1.1294028759002686,
+      "eval_runtime": 13.0615,
+      "eval_samples_per_second": 7.044,
+      "eval_steps_per_second": 3.522,
+      "step": 1647
     }
   ],
   "logging_steps": 100,
@@ -196,7 +219,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3901548615120000.0,
+  "total_flos": 4389242192010000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null