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: 2.0050
+- Loss: 1.6688
 
 ## Model description
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e39b8df1cbb99fffe7efe5e8ace9235204c42cf176944966f84611a6e266e7d6
+oid sha256:3259915083e1ecce9885b9cd06762ad8b35f83a24fabe145b16ba73ff609831c
 size 535667604

runs/Jan22_02-43-32_fbf1b033956c/events.out.tfevents.1705891414.fbf1b033956c.26.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:722c6890eb6f5d56b877a66688db33d3be7b63d17d0d8045a51a8731c0562d1a
-size 1717390
+oid sha256:30aa48091683d8951d7db8abdbec6369d8757f148f5787495eceaea1d7f05438
+size 1717818

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.4617092609405518,
   "best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-9000",
-  "epoch": 14.150555742674301,
+  "epoch": 15.160996968676322,
   "eval_steps": 750,
-  "global_step": 10500,
+  "global_step": 11250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -212,6 +212,20 @@
       "eval_samples_per_second": 58.913,
       "eval_steps_per_second": 0.931,
       "step": 10500
+    },
+    {
+      "epoch": 15.16,
+      "learning_rate": 4.898989218328841e-05,
+      "loss": 1.4983,
+      "step": 11250
+    },
+    {
+      "epoch": 15.16,
+      "eval_loss": 1.668813705444336,
+      "eval_runtime": 84.5947,
+      "eval_samples_per_second": 59.105,
+      "eval_steps_per_second": 0.934,
+      "step": 11250
     }
   ],
   "logging_steps": 750,
@@ -219,7 +233,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 100,
   "save_steps": 750,
-  "total_flos": 4.544406832645325e+17,
+  "total_flos": 4.8690053883961344e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null