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: 1.4848
+- Loss: 1.4603
 
 ## Model description
 

logs/events.out.tfevents.1706460461.2106b1bddca9.27.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd6065e03fe9ba5171e1c5dbae7998b3ea3c522c184c1da6c8db9f00a501888b
-size 1718674
+oid sha256:c46ca864d773aa62a13f9b06c16a216fd22a776175caf966f6fe0680ae3d6167
+size 1719110

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fe05ee95d9afea4822b9659bc67843eb383bd0cc59a8188327a110b6ad63514
+oid sha256:8b0f7ff93ca3c1ceb872c8b559a0eb85282e539e93b213803ca9c85442eb01e0
 size 535667604

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.3940773010253906,
   "best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-18000",
-  "epoch": 35.37588413607275,
+  "epoch": 36.38632536207477,
   "eval_steps": 750,
-  "global_step": 26250,
+  "global_step": 27000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -506,6 +506,20 @@
       "eval_samples_per_second": 59.477,
       "eval_steps_per_second": 0.94,
       "step": 26250
+    },
+    {
+      "epoch": 36.39,
+      "learning_rate": 4.4948787061994616e-05,
+      "loss": 0.571,
+      "step": 27000
+    },
+    {
+      "epoch": 36.39,
+      "eval_loss": 1.4602794647216797,
+      "eval_runtime": 84.1634,
+      "eval_samples_per_second": 59.408,
+      "eval_steps_per_second": 0.939,
+      "step": 27000
     }
   ],
   "logging_steps": 750,
@@ -513,7 +527,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 50,
   "save_steps": 750,
-  "total_flos": 1.1360976503412326e+18,
+  "total_flos": 1.1685575059163136e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null