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: 1.4940
+- Loss: 1.4075
 
 ## Model description
 

logs/events.out.tfevents.1706094350.f329f175c73d.27.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cfdcc94989579f866346edbd46c9f4c4d038380d950ef1f882bed8765fdfeef
-size 1718674
+oid sha256:1b978678a5bfa88c552c340ea38321eccb93f5026e6584ccb7c317d95a4efa8b
+size 1719110

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae13bd05e5e5647407d8a00ec0028f95ee1428af7e437fb3f93c62e3f6fd2546
+oid sha256:136ec0a13ad6ab3edb0074ad3fb89f92f9207f0b0b9a7103444757ea429abe34
 size 535667604

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.3940773010253906,
   "best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-18000",
-  "epoch": 29.311215897608623,
+  "epoch": 30.321657123610642,
   "eval_steps": 750,
-  "global_step": 21750,
+  "global_step": 22500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -422,6 +422,20 @@
       "eval_samples_per_second": 59.263,
       "eval_steps_per_second": 0.936,
       "step": 21750
+    },
+    {
+      "epoch": 30.32,
+      "learning_rate": 4.4948787061994616e-05,
+      "loss": 0.6283,
+      "step": 22500
+    },
+    {
+      "epoch": 30.32,
+      "eval_loss": 1.4074889421463013,
+      "eval_runtime": 84.3283,
+      "eval_samples_per_second": 59.292,
+      "eval_steps_per_second": 0.937,
+      "step": 22500
     }
   ],
   "logging_steps": 750,
@@ -429,7 +443,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 50,
   "save_steps": 750,
-  "total_flos": 9.413385168907469e+17,
+  "total_flos": 9.737983724658278e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null