Training in progress, epoch 5, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75fab14feb35b6eacf7f265a98c52fa832be876d3adad6c881e114337bd89cef
+oid sha256:4edcaa9878838fd6cba6bbe68e29c9c32a723f75eaeebdbddc4db2f79e4c9e04
 size 737722356

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c82d93eb831f5d3e03ac9ee2e5cc10bec306dbb330b880ae7713263b8835a2b5
+oid sha256:2537d0dea7dcc79617ba45301f4d1fe3a40489ca2e7c0a2fa8bf9b0d56aea40d
 size 1475564538

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1330c6d36a4799a8630c102246619f318be16fe9e0d437a473bf59adfdbf823
+oid sha256:01b1ef99b79bf162fdcfc6d98dbaf87c13c9ce1977824524538f4f936cc70630
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b73273c461bfd5a00bbd32e679f302efaa2fe2d4547e13b7d8c7afd31d365b11
+oid sha256:6491af318b1c80d880dc12e80ac041c57092dca8e1473d08121d7239a717b443
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.2747629944426283,
   "best_model_checkpoint": "debertalarge-medical-classifier/checkpoint-366",
-  "epoch": 4.0,
+  "epoch": 5.0,
   "eval_steps": 500,
-  "global_step": 732,
+  "global_step": 915,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -92,6 +92,29 @@
       "eval_samples_per_second": 7.043,
       "eval_steps_per_second": 3.522,
       "step": 732
+    },
+    {
+      "epoch": 4.371584699453552,
+      "grad_norm": 3.6401052474975586,
+      "learning_rate": 4.12568306010929e-05,
+      "loss": 1.0741,
+      "step": 800
+    },
+    {
+      "epoch": 4.918032786885246,
+      "grad_norm": 5.5951972007751465,
+      "learning_rate": 4.016393442622951e-05,
+      "loss": 1.0916,
+      "step": 900
+    },
+    {
+      "epoch": 5.0,
+      "eval_f1": 0.1245394252026529,
+      "eval_loss": 1.142012357711792,
+      "eval_runtime": 13.0456,
+      "eval_samples_per_second": 7.052,
+      "eval_steps_per_second": 3.526,
+      "step": 915
     }
   ],
   "logging_steps": 100,
@@ -111,7 +134,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1950774307560000.0,
+  "total_flos": 2438467884450000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null