Training in progress, epoch 4, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:580d8e77c729fb4984bb9c9f51741452e2c136d0b60a11bba8b9f64157672a12
+oid sha256:75fab14feb35b6eacf7f265a98c52fa832be876d3adad6c881e114337bd89cef
 size 737722356

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:147b8b3258a91181e6bb5318fa147074f926aa9b71090481f152f0ad3e713204
+oid sha256:c82d93eb831f5d3e03ac9ee2e5cc10bec306dbb330b880ae7713263b8835a2b5
 size 1475564538

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6a056d1576b9dd130e0a0e9c22395f596c7172e1bbcd7620c2ad7b8513a2fc3
+oid sha256:f1330c6d36a4799a8630c102246619f318be16fe9e0d437a473bf59adfdbf823
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c742a8bcd183a765dd0e9c362a3881e8009e8d1f29a5268e888484a18d7415ea
+oid sha256:b73273c461bfd5a00bbd32e679f302efaa2fe2d4547e13b7d8c7afd31d365b11
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.2747629944426283,
   "best_model_checkpoint": "debertalarge-medical-classifier/checkpoint-366",
-  "epoch": 3.0,
+  "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 549,
+  "global_step": 732,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -69,6 +69,29 @@
       "eval_samples_per_second": 7.049,
       "eval_steps_per_second": 3.524,
       "step": 549
+    },
+    {
+      "epoch": 3.278688524590164,
+      "grad_norm": 2.7470598220825195,
+      "learning_rate": 4.3442622950819674e-05,
+      "loss": 1.0524,
+      "step": 600
+    },
+    {
+      "epoch": 3.8251366120218577,
+      "grad_norm": 2.554631233215332,
+      "learning_rate": 4.234972677595629e-05,
+      "loss": 1.073,
+      "step": 700
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.2747629944426283,
+      "eval_loss": 1.1285173892974854,
+      "eval_runtime": 13.0619,
+      "eval_samples_per_second": 7.043,
+      "eval_steps_per_second": 3.522,
+      "step": 732
     }
   ],
   "logging_steps": 100,
@@ -88,7 +111,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1463080730670000.0,
+  "total_flos": 1950774307560000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null