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: 1.3941
+- Loss: 1.4438
 
 ## Model description
 

logs/events.out.tfevents.1705984080.5feecac333ed.26.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:640f79d9ce439566510e95dc62e9d60412190b6e40704c736213706c4c003a6c
-size 1719094
+oid sha256:8f705281c4c99fad418aab9863bc0b2be061424e50651ed065837dcfcbefb8f1
+size 1719530

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78099c76677f8173282faa015f1a643d6a78bf8f9ab8b0ef1bb7eac563132094
+oid sha256:aabc4282b7369a5c1ca89409329716b42d8d9e24786d2390550f81bf1bd07651
 size 535667604

trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4253113269805908,
-  "best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-13500",
-  "epoch": 24.256988885146512,
+  "best_metric": 1.3940773010253906,
+  "best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-18000",
+  "epoch": 25.267430111148535,
   "eval_steps": 750,
-  "global_step": 18000,
+  "global_step": 18750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -352,6 +352,20 @@
       "eval_samples_per_second": 59.642,
       "eval_steps_per_second": 0.942,
       "step": 18000
+    },
+    {
+      "epoch": 25.27,
+      "learning_rate": 4.3938005390835576e-05,
+      "loss": 0.633,
+      "step": 18750
+    },
+    {
+      "epoch": 25.27,
+      "eval_loss": 1.443783164024353,
+      "eval_runtime": 83.8619,
+      "eval_samples_per_second": 59.622,
+      "eval_steps_per_second": 0.942,
+      "step": 18750
     }
   ],
   "logging_steps": 750,
@@ -359,7 +373,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 50,
   "save_steps": 750,
-  "total_flos": 7.790392390153421e+17,
+  "total_flos": 8.11499094590423e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null