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: 2.3138
+- Loss: 1.7765
 
 ## Model description
 

logs/events.out.tfevents.1705756331.73c15bc94ff8.26.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:693326dcf3bcf1378a7e6ba4e554f1683e3754ff1cff9af1a9f17d57b44640d4
-size 1717358
+oid sha256:4668362ec170285ecb52f1339e4b97ff9f0f3cef687ce3330272e76d46f9c112
+size 1717786

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ead591b05effc8d3de0b0f74fa7c18d2f2811cd76be06282f70a34e529edabe1
+oid sha256:3b1b6632dcf8924ae2f679831ef1b53986009f7be9340d896fd6f3631757431f
 size 535667604

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.558716893196106,
   "best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-4500",
-  "epoch": 8.085887504210172,
+  "epoch": 9.096328730212193,
   "eval_steps": 750,
-  "global_step": 6000,
+  "global_step": 6750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -128,6 +128,20 @@
       "eval_samples_per_second": 58.739,
       "eval_steps_per_second": 0.928,
       "step": 6000
+    },
+    {
+      "epoch": 9.1,
+      "learning_rate": 4.7979784366576826e-05,
+      "loss": 1.8488,
+      "step": 6750
+    },
+    {
+      "epoch": 9.1,
+      "eval_loss": 1.7765036821365356,
+      "eval_runtime": 84.6118,
+      "eval_samples_per_second": 59.093,
+      "eval_steps_per_second": 0.934,
+      "step": 6750
     }
   ],
   "logging_steps": 750,
@@ -135,7 +149,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 50,
   "save_steps": 750,
-  "total_flos": 2.5968154981404672e+17,
+  "total_flos": 2.921414053891277e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null