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: 1.6640
-- eval_runtime: 84.9276
-- eval_samples_per_second: 58.874
-- eval_steps_per_second: 0.93
-- epoch: 5.05
-- step: 3750
+- eval_loss: 1.6010
+- eval_runtime: 84.8998
+- eval_samples_per_second: 58.893
+- eval_steps_per_second: 0.931
+- epoch: 6.06
+- step: 4500
 
 ## Model description
 

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d83d6fc119e58280f1128f3d74a66d0c94b379ca4d5b9687b867687ecad5aa10
-size 1718978
+oid sha256:dfea933dcc6f64906384902ed63ab9a77a6489669cf0fcb6761f7859e66ba7df
+size 1719406

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7e35f50c51b07ebf94faeccd1579b2538bcb1feb61746d76c1001c57dcf223b
+oid sha256:ca494bdc7c7097726f187ca048bf114765ed27cc0040b6e6ad524a9873ab935e
 size 535667604

trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.9068394899368286,
-  "best_model_checkpoint": "ner-bert-ingredients/checkpoint-3000",
-  "epoch": 5.052206130010104,
+  "best_metric": 1.6639649868011475,
+  "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": 58.874,
       "eval_steps_per_second": 0.93,
       "step": 3750
+    },
+    {
+      "epoch": 6.06,
+      "learning_rate": 4.696900269541779e-05,
+      "loss": 1.4061,
+      "step": 4500
+    },
+    {
+      "epoch": 6.06,
+      "eval_loss": 1.6010338068008423,
+      "eval_runtime": 84.8998,
+      "eval_samples_per_second": 58.893,
+      "eval_steps_per_second": 0.931,
+      "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