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: 1.4809
+- Loss: 1.5037
 
 ## Model description
 

logs/events.out.tfevents.1706529108.663d6886d228.26.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed7b9a43275b40fa123d56033c632a0d7cc8653ac0078653224f5ef5a81bf303
-size 1719110
+oid sha256:c396dde31a0ce4e4ce8086147bdab4291556e16dcfb0a8a502e6d83b0135aca5
+size 1719546

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e6fcc28cd855433938670fb6fa5b08f2c469f7340def1cdd66133fd9f9ccdca
+oid sha256:05ebacde0003e34edf452bf7624bdd0eead5542451e0a563e0d67fc5c380950e
 size 535667604

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.3940773010253906,
   "best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-18000",
-  "epoch": 42.4509936005389,
+  "epoch": 43.46143482654092,
   "eval_steps": 750,
-  "global_step": 31500,
+  "global_step": 32250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -604,6 +604,20 @@
       "eval_samples_per_second": 58.698,
       "eval_steps_per_second": 0.927,
       "step": 31500
+    },
+    {
+      "epoch": 43.46,
+      "learning_rate": 4.3938005390835576e-05,
+      "loss": 0.4453,
+      "step": 32250
+    },
+    {
+      "epoch": 43.46,
+      "eval_loss": 1.5037322044372559,
+      "eval_runtime": 85.2811,
+      "eval_samples_per_second": 58.63,
+      "eval_steps_per_second": 0.926,
+      "step": 32250
     }
   ],
   "logging_steps": 750,
@@ -611,7 +625,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 50,
   "save_steps": 750,
-  "total_flos": 1.3633166393667994e+18,
+  "total_flos": 1.3957764949418803e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null