Training in progress, epoch 13, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e725f21bf5e9e86c88f80c57e3bb2704cf1eb07e29d0c579587b5032b0691e76
+oid sha256:bb6099b26484dcdc5882c934997be8ef652f09f24e4e3c8b9259641204db7271
 size 737722356

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af46f8dedd17a334921f28292e8c85822fc33f297652c8536b53d32b54f2073c
+oid sha256:42d7c22f3db24f63a9818736fbcbfc342409bf9ddaa7c1800e579be44c7b72a1
 size 1475564538

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a622f6a101cea5ef2f690e821b18ab364a3198cabaabf2a361e8317a9501bb4
+oid sha256:40105344871e6865600e248503be12c043bc99c76811b1b10664961dd30b5937
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7a0e59c63e2086f8607dd910ba9145cdf868d634af5bc4d4ce1666a51f2c790
+oid sha256:2be7dc1d219acbd2f0efe1381e52b307e7734916897f0a941960c9fecdf13a99
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.2747629944426283,
   "best_model_checkpoint": "debertalarge-medical-classifier/checkpoint-366",
-  "epoch": 12.0,
+  "epoch": 13.0,
   "eval_steps": 500,
-  "global_step": 2196,
+  "global_step": 2379,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -262,6 +262,29 @@
       "eval_samples_per_second": 7.047,
       "eval_steps_per_second": 3.523,
       "step": 2196
+    },
+    {
+      "epoch": 12.021857923497267,
+      "grad_norm": 4.95583963394165,
+      "learning_rate": 2.5956284153005467e-05,
+      "loss": 1.0431,
+      "step": 2200
+    },
+    {
+      "epoch": 12.568306010928962,
+      "grad_norm": 6.593821048736572,
+      "learning_rate": 2.4863387978142078e-05,
+      "loss": 1.0925,
+      "step": 2300
+    },
+    {
+      "epoch": 13.0,
+      "eval_f1": 0.2747629944426283,
+      "eval_loss": 1.1049476861953735,
+      "eval_runtime": 13.0607,
+      "eval_samples_per_second": 7.044,
+      "eval_steps_per_second": 3.522,
+      "step": 2379
     }
   ],
   "logging_steps": 100,
@@ -281,7 +304,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5852322922680000.0,
+  "total_flos": 6340016499570000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null