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: 1.8944
+- Loss: 1.6254
 
 ## Model description
 

logs/events.out.tfevents.1705984080.5feecac333ed.26.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb105d7fd8e0be1fdc31867ede7628f2c39631839d76b9bff390eebd98dcc602
-size 1717358
+oid sha256:57864e7d774dd90890e57684c4e349f6d59c2e1cc3bcf5af6595fc3c859a94c5
+size 1717786

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a16459f696ebed20a3fc02c36617a6e235a7ebfa18c8b483e6d7ba31457959c
+oid sha256:cd4d73487f9eb01d6fdc49152e53eea267ad8bef8c7745897d2af1cfb06186d1
 size 535667604

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.4253113269805908,
   "best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-13500",
-  "epoch": 20.21522398113843,
+  "epoch": 21.22566520714045,
   "eval_steps": 750,
-  "global_step": 15000,
+  "global_step": 15750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -296,6 +296,20 @@
       "eval_samples_per_second": 59.412,
       "eval_steps_per_second": 0.939,
       "step": 15000
+    },
+    {
+      "epoch": 21.23,
+      "learning_rate": 4.7979784366576826e-05,
+      "loss": 1.2528,
+      "step": 15750
+    },
+    {
+      "epoch": 21.23,
+      "eval_loss": 1.6253798007965088,
+      "eval_runtime": 83.8622,
+      "eval_samples_per_second": 59.622,
+      "eval_steps_per_second": 0.942,
+      "step": 15750
     }
   ],
   "logging_steps": 750,
@@ -303,7 +317,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 50,
   "save_steps": 750,
-  "total_flos": 6.491998167150182e+17,
+  "total_flos": 6.816596722900992e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null