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: 1.5137
+- Loss: 1.4940
 
 ## Model description
 

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7d771f264308ce7f35b8c3fb7fc29a362ec651d69bc2c461ae286c91a6b795e
-size 1718238
+oid sha256:2cfdcc94989579f866346edbd46c9f4c4d038380d950ef1f882bed8765fdfeef
+size 1718674

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4303eb70dddfc16e4d1d002afc24f25e477d757511b8782fb6ce277d5d9a5432
+oid sha256:ae13bd05e5e5647407d8a00ec0028f95ee1428af7e437fb3f93c62e3f6fd2546
 size 535667604

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.3940773010253906,
   "best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-18000",
-  "epoch": 28.3007746716066,
+  "epoch": 29.311215897608623,
   "eval_steps": 750,
-  "global_step": 21000,
+  "global_step": 21750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -408,6 +408,20 @@
       "eval_samples_per_second": 59.318,
       "eval_steps_per_second": 0.937,
       "step": 21000
+    },
+    {
+      "epoch": 29.31,
+      "learning_rate": 4.595822102425876e-05,
+      "loss": 0.7273,
+      "step": 21750
+    },
+    {
+      "epoch": 29.31,
+      "eval_loss": 1.4939533472061157,
+      "eval_runtime": 84.3697,
+      "eval_samples_per_second": 59.263,
+      "eval_steps_per_second": 0.936,
+      "step": 21750
     }
   ],
   "logging_steps": 750,
@@ -415,7 +429,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 50,
   "save_steps": 750,
-  "total_flos": 9.088786613156659e+17,
+  "total_flos": 9.413385168907469e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null