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: 1.8179
+- Loss: 1.5888
 
 ## Model description
 

logs/events.out.tfevents.1706094350.f329f175c73d.27.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3b5e82da3b80a716343d560e291f2f6b76a81cb739da3ca4c69cba42b592e63
-size 1717366
+oid sha256:2991293247af2759b3ca3c56758cc67d2225483f1b1e8c6834627a8ceb8cc4b2
+size 1717802

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:613cb6d14e837438e147a82e700afe18cfce98be7e6368c03c61e66858490071
+oid sha256:3655a7f16558f4dfaeeccee155d4f5d54251f78ecb72aca1c0ed8cde887bf5c1
 size 535667604

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.3940773010253906,
   "best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-18000",
-  "epoch": 26.27989221960256,
+  "epoch": 27.29033344560458,
   "eval_steps": 750,
-  "global_step": 19500,
+  "global_step": 20250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -380,6 +380,20 @@
       "eval_samples_per_second": 59.02,
       "eval_steps_per_second": 0.933,
       "step": 19500
+    },
+    {
+      "epoch": 27.29,
+      "learning_rate": 4.7979784366576826e-05,
+      "loss": 1.1042,
+      "step": 20250
+    },
+    {
+      "epoch": 27.29,
+      "eval_loss": 1.5888350009918213,
+      "eval_runtime": 84.3483,
+      "eval_samples_per_second": 59.278,
+      "eval_steps_per_second": 0.937,
+      "step": 20250
     }
   ],
   "logging_steps": 750,
@@ -387,7 +401,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 50,
   "save_steps": 750,
-  "total_flos": 8.43958950165504e+17,
+  "total_flos": 8.76418805740585e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null