Training in progress, epoch 17, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:657ca3021e5b6baff883b9156c24a243272d9ecbbb03b48fafaad921c72c3310
+oid sha256:47e2acf1a516b89ef3ac486410bd891b1eb4c2f07ff0811e7bedaf2c93821c60
 size 737722356

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91959ee2247f551a280486183f80d9acc6e81bee811aba741ba2d237950de18b
+oid sha256:c6084d5e39532668a29a9a7adfc8f7e6d954178d10523bcc4bb14b505beebe42
 size 1475564538

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20616955913563c641cbdf6bd0c2164643c9c28e79d9473d76717848b530b4b5
+oid sha256:177f4600c463df4ac0fab58eca4d20530489d85799600cbe5c332b74b2834cd3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0098baefc5d839aa49a31b29141de8bb1790117b396c3d13f4b14674b6b436f2
+oid sha256:52d9926229eece8ee772f15833f4e38d9c72b87fe1d5554bff5cd38f9587a548
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.2747629944426283,
   "best_model_checkpoint": "debertalarge-medical-classifier/checkpoint-366",
-  "epoch": 16.0,
+  "epoch": 17.0,
   "eval_steps": 500,
-  "global_step": 2928,
+  "global_step": 3111,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -354,6 +354,29 @@
       "eval_samples_per_second": 7.048,
       "eval_steps_per_second": 3.524,
       "step": 2928
+    },
+    {
+      "epoch": 16.39344262295082,
+      "grad_norm": 4.644863605499268,
+      "learning_rate": 1.721311475409836e-05,
+      "loss": 1.021,
+      "step": 3000
+    },
+    {
+      "epoch": 16.939890710382514,
+      "grad_norm": 4.022730827331543,
+      "learning_rate": 1.6120218579234975e-05,
+      "loss": 1.0961,
+      "step": 3100
+    },
+    {
+      "epoch": 17.0,
+      "eval_f1": 0.2747629944426283,
+      "eval_loss": 1.0970044136047363,
+      "eval_runtime": 13.0521,
+      "eval_samples_per_second": 7.049,
+      "eval_steps_per_second": 3.524,
+      "step": 3111
     }
   ],
   "logging_steps": 100,
@@ -373,7 +396,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7803097230240000.0,
+  "total_flos": 8290790807130000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null