End of training

README.md

@@ -13,12 +13,12 @@ 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:
-- eval_loss: 1.4049
-- eval_runtime: 83.6632
-- eval_samples_per_second: 59.763
+- eval_loss: 1.3497
+- eval_runtime: 83.6712
+- eval_samples_per_second: 59.758
 - eval_steps_per_second: 0.944
-- epoch: 11.12
-- step: 8250
+- epoch: 12.13
+- step: 9000
 
 ## Model description
 

logs/events.out.tfevents.1704638284.80d534b5f596.26.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c77705a0b57703517c0dfc835be23cda0c723da30c798c1386d77ecee016b71
-size 1719036
+oid sha256:1df804bbce7176c17a9b7e2ffd0f90760d52812288260894052a638a82249907
+size 1719464

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ed0df3b133c6dbbafda39cd4c9518e71bc9320376ba66771d842ead44921003
+oid sha256:ee869e69f26d6b5af04157d2668f1392049dcc8bc28677868a1cd397756c694a
 size 535667604

trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4776005744934082,
-  "best_model_checkpoint": "ner-bert-ingredients/checkpoint-7500",
-  "epoch": 11.116874368474233,
+  "best_metric": 1.4048632383346558,
+  "best_model_checkpoint": "ner-bert-ingredients/checkpoint-8250",
+  "epoch": 12.127315594476254,
   "eval_steps": 750,
-  "global_step": 8250,
+  "global_step": 9000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -161,6 +161,20 @@
       "eval_samples_per_second": 59.763,
       "eval_steps_per_second": 0.944,
       "step": 8250
+    },
+    {
+      "epoch": 12.13,
+      "learning_rate": 4.696900269541779e-05,
+      "loss": 0.9469,
+      "step": 9000
+    },
+    {
+      "epoch": 12.13,
+      "eval_loss": 1.349704384803772,
+      "eval_runtime": 83.6712,
+      "eval_samples_per_second": 59.758,
+      "eval_steps_per_second": 0.944,
+      "step": 9000
     }
   ],
   "logging_steps": 750,
@@ -168,7 +182,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 100,
   "save_steps": 750,
-  "total_flos": 3.5705841132589056e+17,
+  "total_flos": 3.895182669009715e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null