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: 1.5000
+- Loss: 1.4848
 
 ## Model description
 

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:928a89ae6792e55483bc39d0180105b3d33fbeb904d386da17efc25f687ba413
-size 1718238
+oid sha256:dd6065e03fe9ba5171e1c5dbae7998b3ea3c522c184c1da6c8db9f00a501888b
+size 1718674

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f084df875164e58b6b1ab6f9b417cb4033bf485760d7eb9c0e2d7346e08de52
+oid sha256:1fe05ee95d9afea4822b9659bc67843eb383bd0cc59a8188327a110b6ad63514
 size 535667604

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.3940773010253906,
   "best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-18000",
-  "epoch": 34.36544291007073,
+  "epoch": 35.37588413607275,
   "eval_steps": 750,
-  "global_step": 25500,
+  "global_step": 26250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -492,6 +492,20 @@
       "eval_samples_per_second": 59.539,
       "eval_steps_per_second": 0.941,
       "step": 25500
+    },
+    {
+      "epoch": 35.38,
+      "learning_rate": 4.595956873315364e-05,
+      "loss": 0.6611,
+      "step": 26250
+    },
+    {
+      "epoch": 35.38,
+      "eval_loss": 1.4847756624221802,
+      "eval_runtime": 84.066,
+      "eval_samples_per_second": 59.477,
+      "eval_steps_per_second": 0.94,
+      "step": 26250
     }
   ],
   "logging_steps": 750,
@@ -499,7 +513,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 50,
   "save_steps": 750,
-  "total_flos": 1.1036377947661517e+18,
+  "total_flos": 1.1360976503412326e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null