End of training

README.md

@@ -15,12 +15,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 1.6346
-- eval_runtime: 84.1885
-- eval_samples_per_second: 59.391
+- eval_loss: 1.5282
+- eval_runtime: 84.2371
+- eval_samples_per_second: 59.356
 - eval_steps_per_second: 0.938
-- epoch: 5.05
-- step: 3750
+- epoch: 6.06
+- step: 4500
 
 ## Model description
 

logs/events.out.tfevents.1704595715.d90d7534d98a.27.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8d45a240d79fa10662a8e657ca92eeba18416366edf302b7a040f9e1f0f7c72
-size 1718978
+oid sha256:f9e5da318c8357d485ab966bddd11dfa836bee503cf9e23ca4e623074805d1fb
+size 1719406

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a19c266842a4f6fc6a546e469f6bd827b62053c727ec8b3d9817b7cbbb3d1ac2
+oid sha256:ae13ecd9fc839ef94736671faab0dcc0acd342d63ac53d36f3f434917fb712b3
 size 535667604

trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.9211012125015259,
-  "best_model_checkpoint": "ner-bert-ingredients/checkpoint-3000",
-  "epoch": 5.052206130010104,
+  "best_metric": 1.6346299648284912,
+  "best_model_checkpoint": "ner-bert-ingredients/checkpoint-3750",
+  "epoch": 6.062647356012126,
   "eval_steps": 750,
-  "global_step": 3750,
+  "global_step": 4500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -77,6 +77,20 @@
       "eval_samples_per_second": 59.391,
       "eval_steps_per_second": 0.938,
       "step": 3750
+    },
+    {
+      "epoch": 6.06,
+      "learning_rate": 4.696900269541779e-05,
+      "loss": 1.437,
+      "step": 4500
+    },
+    {
+      "epoch": 6.06,
+      "eval_loss": 1.5281634330749512,
+      "eval_runtime": 84.2371,
+      "eval_samples_per_second": 59.356,
+      "eval_steps_per_second": 0.938,
+      "step": 4500
     }
   ],
   "logging_steps": 750,
@@ -84,7 +98,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 100,
   "save_steps": 750,
-  "total_flos": 1.622992778754048e+17,
+  "total_flos": 1.9475913345048576e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null