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: 1.5852
+- Loss: 1.5000
 
 ## Model description
 

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef363147cc745d7ac0eea878b3ad2d52ee167935f8ba5fcc592bdfa0e81bba69
-size 1717802
+oid sha256:928a89ae6792e55483bc39d0180105b3d33fbeb904d386da17efc25f687ba413
+size 1718238

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89bbf2b4f786a5d9c1a884636487f5e3006dce4168d95f9ca0e422e39b6c762b
+oid sha256:7f084df875164e58b6b1ab6f9b417cb4033bf485760d7eb9c0e2d7346e08de52
 size 535667604

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.3940773010253906,
   "best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-18000",
-  "epoch": 33.35500168406871,
+  "epoch": 34.36544291007073,
   "eval_steps": 750,
-  "global_step": 24750,
+  "global_step": 25500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -478,6 +478,20 @@
       "eval_samples_per_second": 59.479,
       "eval_steps_per_second": 0.94,
       "step": 24750
+    },
+    {
+      "epoch": 34.37,
+      "learning_rate": 4.696900269541779e-05,
+      "loss": 0.7859,
+      "step": 25500
+    },
+    {
+      "epoch": 34.37,
+      "eval_loss": 1.5000197887420654,
+      "eval_runtime": 83.979,
+      "eval_samples_per_second": 59.539,
+      "eval_steps_per_second": 0.941,
+      "step": 25500
     }
   ],
   "logging_steps": 750,
@@ -485,7 +499,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 50,
   "save_steps": 750,
-  "total_flos": 1.0711779391910707e+18,
+  "total_flos": 1.1036377947661517e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null