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: 1.5663
+- Loss: 1.5644
 
 ## Model description
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3203539df8bd53bbb4ad2c506be1977fda3a01e8ec3aca8b34857d4c6c497baf
+oid sha256:c4f9a6b5be81e6e01f9e7bc2170a3a47af08176934245e294625a7cb9be52fd9
 size 535667604

runs/Jan30_10-22-15_1f29a6e67489/events.out.tfevents.1706610136.1f29a6e67489.26.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cabe5b15966dcde4de08bb692914287043bf565a1448cabc714582e8c1e2609e
-size 1718270
+oid sha256:b4fcd878326982413fb5709db134e537b6020b36e7e1860f27940bb878fa585a
+size 1718706

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.3940773010253906,
   "best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-18000",
-  "epoch": 46.49477938699899,
+  "epoch": 47.50522061300101,
   "eval_steps": 750,
-  "global_step": 34500,
+  "global_step": 35250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -660,6 +660,20 @@
       "eval_samples_per_second": 59.249,
       "eval_steps_per_second": 0.936,
       "step": 34500
+    },
+    {
+      "epoch": 47.51,
+      "learning_rate": 4.7979784366576826e-05,
+      "loss": 0.5584,
+      "step": 35250
+    },
+    {
+      "epoch": 47.51,
+      "eval_loss": 1.5644365549087524,
+      "eval_runtime": 84.4556,
+      "eval_samples_per_second": 59.203,
+      "eval_steps_per_second": 0.935,
+      "step": 35250
     }
   ],
   "logging_steps": 750,
@@ -667,7 +681,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 100,
   "save_steps": 750,
-  "total_flos": 1.4931560616671232e+18,
+  "total_flos": 1.5256159172422042e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null