Training in progress, epoch 25, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26757196176bb3ec4fa9eea66af0b0dfe2068b26532b2956952e3eb2630984ab
+oid sha256:c60aab2808e0b6ff5c3044ddc4a383615587c02b8fb170ec5b7bd46ceda4d67b
 size 737722356

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31c92e0696ce2f24d81c5647cb7318bb2b0dfb5b926fa43b868869c973ae659a
+oid sha256:bb141463b53f69fc963e09ea0da9ba5fda33860798b350c5ab616411d738cbc5
 size 1475564538

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab48d2b47abcf3862b9afad11c799581d64eb9c0c79293833348cfa34b1f1e74
+oid sha256:e4e98addb3c7bd9c7af5f26d56711fb35e9c46bbafadffb4d522578bf67cacbf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9e6c373ef8f4f5af14afe06af61797af9aed9e7e2f2397b6448ba535ca55214
+oid sha256:200656733f889023bd664e4c06b18d14315fef4336b3371d1fb8d8effa5df415
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.2747629944426283,
   "best_model_checkpoint": "debertalarge-medical-classifier/checkpoint-366",
-  "epoch": 24.0,
+  "epoch": 25.0,
   "eval_steps": 500,
-  "global_step": 4392,
+  "global_step": 4575,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -524,6 +524,29 @@
       "eval_samples_per_second": 7.051,
       "eval_steps_per_second": 3.526,
       "step": 4392
+    },
+    {
+      "epoch": 24.043715846994534,
+      "grad_norm": 4.936235427856445,
+      "learning_rate": 1.912568306010929e-06,
+      "loss": 1.0767,
+      "step": 4400
+    },
+    {
+      "epoch": 24.59016393442623,
+      "grad_norm": 4.7811665534973145,
+      "learning_rate": 8.19672131147541e-07,
+      "loss": 1.0675,
+      "step": 4500
+    },
+    {
+      "epoch": 25.0,
+      "eval_f1": 0.2747629944426283,
+      "eval_loss": 1.1084977388381958,
+      "eval_runtime": 13.1143,
+      "eval_samples_per_second": 7.015,
+      "eval_steps_per_second": 3.508,
+      "step": 4575
     }
   ],
   "logging_steps": 100,
@@ -538,12 +561,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.170464584536e+16,
+  "total_flos": 1.219233942225e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null