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: 1.6010
+- Loss: 1.4926
 
 ## Model description
 

logs/events.out.tfevents.1706529108.663d6886d228.26.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a52b619f7894675d3b2eafa71cd2918b11eae4115297d2c5ab6e358082492316
-size 1717802
+oid sha256:8872e8beb6f19a00a3dd9e1ead9bbe2cacd381a94bbb75e788eea2b0bf5b15c4
+size 1718238

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4967d7bc56de2cbee407d67abaeb4baa4d73d4f7148fb77f65b7a25a5eff7644
+oid sha256:7fd27cc956e4162c815ae1e0c25b2f933b06f14f8ab7cb1f1de1f296fde5de41
 size 535667604

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.3940773010253906,
   "best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-18000",
-  "epoch": 39.41966992253284,
+  "epoch": 40.43011114853486,
   "eval_steps": 750,
-  "global_step": 29250,
+  "global_step": 30000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -562,6 +562,20 @@
       "eval_samples_per_second": 58.752,
       "eval_steps_per_second": 0.928,
       "step": 29250
+    },
+    {
+      "epoch": 40.43,
+      "learning_rate": 4.696900269541779e-05,
+      "loss": 0.7137,
+      "step": 30000
+    },
+    {
+      "epoch": 40.43,
+      "eval_loss": 1.4925891160964966,
+      "eval_runtime": 85.1688,
+      "eval_samples_per_second": 58.707,
+      "eval_steps_per_second": 0.928,
+      "step": 30000
     }
   ],
   "logging_steps": 750,
@@ -569,7 +583,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 50,
   "save_steps": 750,
-  "total_flos": 1.2659370726415565e+18,
+  "total_flos": 1.2983969282166374e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null