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: 1.8303
+- Loss: 1.5852
 
 ## Model description
 

logs/events.out.tfevents.1706460461.2106b1bddca9.27.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d15e4faf6f10d412caa19e0ac4ddf0ad91a252888b05620e50964e4bbe94bd0
-size 1717366
+oid sha256:ef363147cc745d7ac0eea878b3ad2d52ee167935f8ba5fcc592bdfa0e81bba69
+size 1717802

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5a12f522f79c0de9db88cc997f0bdb2896dc7bd75c4f385f1c012f38f05b47d
+oid sha256:89bbf2b4f786a5d9c1a884636487f5e3006dce4168d95f9ca0e422e39b6c762b
 size 535667604

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.3940773010253906,
   "best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-18000",
-  "epoch": 32.34456045806669,
+  "epoch": 33.35500168406871,
   "eval_steps": 750,
-  "global_step": 24000,
+  "global_step": 24750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -464,6 +464,20 @@
       "eval_samples_per_second": 59.241,
       "eval_steps_per_second": 0.936,
       "step": 24000
+    },
+    {
+      "epoch": 33.36,
+      "learning_rate": 4.7979784366576826e-05,
+      "loss": 1.0061,
+      "step": 24750
+    },
+    {
+      "epoch": 33.36,
+      "eval_loss": 1.585161566734314,
+      "eval_runtime": 84.0634,
+      "eval_samples_per_second": 59.479,
+      "eval_steps_per_second": 0.94,
+      "step": 24750
     }
   ],
   "logging_steps": 750,
@@ -471,7 +485,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 50,
   "save_steps": 750,
-  "total_flos": 1.0387180836159898e+18,
+  "total_flos": 1.0711779391910707e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null