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: 2.6926
-- eval_runtime: 84.8728
-- eval_samples_per_second: 58.912
-- eval_steps_per_second: 0.931
-- epoch: 2.02
-- step: 1500
+- eval_loss: 2.2497
+- eval_runtime: 84.957
+- eval_samples_per_second: 58.853
+- eval_steps_per_second: 0.93
+- epoch: 3.03
+- step: 2250
 
 ## Model description
 

logs/events.out.tfevents.1704536554.9585f193967c.27.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afeb77457c9c4a545df5f0b806ae6c76b9b834e73473956e5904c8600ad8ec18
-size 1717694
+oid sha256:e89f989e4955a50cfddc7bb8a3e3e14075d0d2392f143925f36db9b0fa5f9b21
+size 1718122

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5977be66008ccbf3a905fc1702f6f36943ba6cce85352db22c1b3a5d7cd17879
+oid sha256:fe652302c6ea5bdc5124482be6693e70ebf49976b2a5d02a862f5b5ca6f4acdc
 size 535667604

trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 4.010455131530762,
-  "best_model_checkpoint": "ner-bert-ingredients/checkpoint-750",
-  "epoch": 2.0208824520040416,
+  "best_metric": 2.692633867263794,
+  "best_model_checkpoint": "ner-bert-ingredients/checkpoint-1500",
+  "epoch": 3.031323678006063,
   "eval_steps": 750,
-  "global_step": 1500,
+  "global_step": 2250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -35,6 +35,20 @@
       "eval_samples_per_second": 58.912,
       "eval_steps_per_second": 0.931,
       "step": 1500
+    },
+    {
+      "epoch": 3.03,
+      "learning_rate": 4.84845013477089e-05,
+      "loss": 2.4396,
+      "step": 2250
+    },
+    {
+      "epoch": 3.03,
+      "eval_loss": 2.2496654987335205,
+      "eval_runtime": 84.957,
+      "eval_samples_per_second": 58.853,
+      "eval_steps_per_second": 0.93,
+      "step": 2250
     }
   ],
   "logging_steps": 750,
@@ -42,7 +56,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 100,
   "save_steps": 750,
-  "total_flos": 6.491971115016192e+16,
+  "total_flos": 9.737956672524288e+16,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null