Training in progress, epoch 8, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b0ff0d2efae69a63c4480e31b3e0f95982bc222a8480dcc53f28de19b7aa366
+oid sha256:0a2018d54a34012ba4546bb4f9b7c9529b6614e668d8606d353645d3586c3045
 size 737722356

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f11b81e206a0fb0ba631637ddc19a9ee68a5208e792c8bed8108a92f5a88f883
+oid sha256:0715101da8193f8171b69d9fe96bc57f88b295c344d0606585b7cacf3554b7a2
 size 1475564538

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f415da0cb308c9dae6ffd1aaf4430c8311f998460c9c29a4be9af8a552a3a81c
+oid sha256:d55807819bdae9e8fbe453685136e22fbf0013e7f27fc4b2e8b261bbf5cae4ef
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4512033475c77e3052594c5f3b7b6b276c78cc2ab4b304f66f8e700255ff821a
+oid sha256:58cf2bfb447415b2597ec64c77694929e3d11b1375ad51d86c88386c6a7dc6e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.2747629944426283,
   "best_model_checkpoint": "debertalarge-medical-classifier/checkpoint-366",
-  "epoch": 7.0,
+  "epoch": 8.0,
   "eval_steps": 500,
-  "global_step": 1281,
+  "global_step": 1464,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -154,6 +154,29 @@
       "eval_samples_per_second": 7.049,
       "eval_steps_per_second": 3.525,
       "step": 1281
+    },
+    {
+      "epoch": 7.103825136612022,
+      "grad_norm": 2.940361499786377,
+      "learning_rate": 3.579234972677596e-05,
+      "loss": 1.1085,
+      "step": 1300
+    },
+    {
+      "epoch": 7.6502732240437155,
+      "grad_norm": 5.258467674255371,
+      "learning_rate": 3.469945355191257e-05,
+      "loss": 1.0989,
+      "step": 1400
+    },
+    {
+      "epoch": 8.0,
+      "eval_f1": 0.2747629944426283,
+      "eval_loss": 1.0947765111923218,
+      "eval_runtime": 13.0622,
+      "eval_samples_per_second": 7.043,
+      "eval_steps_per_second": 3.522,
+      "step": 1464
     }
   ],
   "logging_steps": 100,
@@ -173,7 +196,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3413855038230000.0,
+  "total_flos": 3901548615120000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null