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: 1.4617
+- Loss: 1.3601
 
 ## Model description
 

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:821ed8e08a7f9198f8fc15ca4b56cf190bcf714b3eed85480d11ec86eec5d52e
-size 1719070
+oid sha256:dd484e4229c7e130206425c71db3486119da7efdf7ec1291ce7bd4adef4d6446
+size 1719498

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d50cb9ae99c2c04d44d00182ea4a48b1068afd1769a4b2153f7c32a99ca3525
+oid sha256:192542153436042bee50de991c19209c78b1a24d1d47df54fc052fa1da0e1fa5
 size 535667604

trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4957914352416992,
-  "best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-8250",
-  "epoch": 12.127652408218255,
+  "best_metric": 1.4617092609405518,
+  "best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-9000",
+  "epoch": 13.138093634220276,
   "eval_steps": 750,
-  "global_step": 9000,
+  "global_step": 9750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -184,6 +184,20 @@
       "eval_samples_per_second": 59.229,
       "eval_steps_per_second": 0.936,
       "step": 9000
+    },
+    {
+      "epoch": 13.14,
+      "learning_rate": 4.39366576819407e-05,
+      "loss": 0.922,
+      "step": 9750
+    },
+    {
+      "epoch": 13.14,
+      "eval_loss": 1.3600549697875977,
+      "eval_runtime": 84.2691,
+      "eval_samples_per_second": 59.334,
+      "eval_steps_per_second": 0.937,
+      "step": 9750
     }
   ],
   "logging_steps": 750,
@@ -191,7 +205,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 50,
   "save_steps": 750,
-  "total_flos": 3.8952097211437056e+17,
+  "total_flos": 4.219808276894515e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null