Training in progress, epoch 16, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fda8a3a0cfe96a5a51e15c0690d5e1c48857832e5d77678267e42e6fa3a1817f
+oid sha256:657ca3021e5b6baff883b9156c24a243272d9ecbbb03b48fafaad921c72c3310
 size 737722356

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9df2f5f97e9f862467508980e69acf0eb0956f6b4e75ecc2902800e27e088f7
+oid sha256:91959ee2247f551a280486183f80d9acc6e81bee811aba741ba2d237950de18b
 size 1475564538

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2971d2339194afcfd80aff922bc915204e0778014c7d2e047351d6f30e3bd3fc
+oid sha256:20616955913563c641cbdf6bd0c2164643c9c28e79d9473d76717848b530b4b5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:091031ae22eb7d8dfa24111bac44553b71f40bb7016aeefd4960b0ea3e4c04a6
+oid sha256:0098baefc5d839aa49a31b29141de8bb1790117b396c3d13f4b14674b6b436f2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.2747629944426283,
   "best_model_checkpoint": "debertalarge-medical-classifier/checkpoint-366",
-  "epoch": 15.0,
+  "epoch": 16.0,
   "eval_steps": 500,
-  "global_step": 2745,
+  "global_step": 2928,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -331,6 +331,29 @@
       "eval_samples_per_second": 7.047,
       "eval_steps_per_second": 3.524,
       "step": 2745
+    },
+    {
+      "epoch": 15.300546448087431,
+      "grad_norm": 4.447215557098389,
+      "learning_rate": 1.9398907103825135e-05,
+      "loss": 1.0086,
+      "step": 2800
+    },
+    {
+      "epoch": 15.846994535519126,
+      "grad_norm": 3.9617857933044434,
+      "learning_rate": 1.830601092896175e-05,
+      "loss": 1.0938,
+      "step": 2900
+    },
+    {
+      "epoch": 16.0,
+      "eval_f1": 0.2747629944426283,
+      "eval_loss": 1.1148039102554321,
+      "eval_runtime": 13.0531,
+      "eval_samples_per_second": 7.048,
+      "eval_steps_per_second": 3.524,
+      "step": 2928
     }
   ],
   "logging_steps": 100,
@@ -350,7 +373,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7315403653350000.0,
+  "total_flos": 7803097230240000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null