Training in progress, epoch 24, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f632a47dc0c30788796a8dba61a612ecf8317dcea16bdcb15010a80ce0260d4
+oid sha256:26757196176bb3ec4fa9eea66af0b0dfe2068b26532b2956952e3eb2630984ab
 size 737722356

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ceaccb5dd5c1b7a308ff896ee95096f4baf6ce2613c023c121468b409d5750b5
+oid sha256:31c92e0696ce2f24d81c5647cb7318bb2b0dfb5b926fa43b868869c973ae659a
 size 1475564538

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27fe2f6c19f1d393961e1a1f2e3da92a7f6540c77a0c3480b24c8f9b30e7be57
+oid sha256:ab48d2b47abcf3862b9afad11c799581d64eb9c0c79293833348cfa34b1f1e74
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9d352d54511c127cc9deb5ec7e7c87112ff76a5828dda59f37bc325e32cd6aa
+oid sha256:b9e6c373ef8f4f5af14afe06af61797af9aed9e7e2f2397b6448ba535ca55214
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.2747629944426283,
   "best_model_checkpoint": "debertalarge-medical-classifier/checkpoint-366",
-  "epoch": 23.0,
+  "epoch": 24.0,
   "eval_steps": 500,
-  "global_step": 4209,
+  "global_step": 4392,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -508,6 +508,22 @@
       "eval_samples_per_second": 7.047,
       "eval_steps_per_second": 3.523,
       "step": 4209
+    },
+    {
+      "epoch": 23.497267759562842,
+      "grad_norm": 4.816049098968506,
+      "learning_rate": 3.005464480874317e-06,
+      "loss": 1.0524,
+      "step": 4300
+    },
+    {
+      "epoch": 24.0,
+      "eval_f1": 0.2747629944426283,
+      "eval_loss": 1.1108192205429077,
+      "eval_runtime": 13.0475,
+      "eval_samples_per_second": 7.051,
+      "eval_steps_per_second": 3.526,
+      "step": 4392
     }
   ],
   "logging_steps": 100,
@@ -527,7 +543,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.121695226847e+16,
+  "total_flos": 1.170464584536e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null