End of training

README.md

@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.7765
+- Loss: 1.5599
 
 ## Model description
 

logs/events.out.tfevents.1705756331.73c15bc94ff8.26.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4668362ec170285ecb52f1339e4b97ff9f0f3cef687ce3330272e76d46f9c112
-size 1717786
+oid sha256:08bcc5ca3fd9e08fae4d0deea68c5b22cc565a2bbc8d69e305635c77e90e9d14
+size 1718214

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b1b6632dcf8924ae2f679831ef1b53986009f7be9340d896fd6f3631757431f
+oid sha256:f5824014e2f2d6012298be55eae3b3b728030b2573a78059b8bc1b4fcdb8ba7f
 size 535667604

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.558716893196106,
   "best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-4500",
-  "epoch": 9.096328730212193,
+  "epoch": 10.106769956214213,
   "eval_steps": 750,
-  "global_step": 6750,
+  "global_step": 7500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -142,6 +142,20 @@
       "eval_samples_per_second": 59.093,
       "eval_steps_per_second": 0.934,
       "step": 6750
+    },
+    {
+      "epoch": 10.11,
+      "learning_rate": 4.696900269541779e-05,
+      "loss": 1.4372,
+      "step": 7500
+    },
+    {
+      "epoch": 10.11,
+      "eval_loss": 1.5598968267440796,
+      "eval_runtime": 84.6222,
+      "eval_samples_per_second": 59.086,
+      "eval_steps_per_second": 0.934,
+      "step": 7500
     }
   ],
   "logging_steps": 750,
@@ -149,7 +163,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 50,
   "save_steps": 750,
-  "total_flos": 2.921414053891277e+17,
+  "total_flos": 3.2460126096420864e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null