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: 1.4603
+- Loss: 1.4159
 
 ## Model description
 

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c46ca864d773aa62a13f9b06c16a216fd22a776175caf966f6fe0680ae3d6167
-size 1719110
+oid sha256:eaa2fd3f0d0367cf1ff8d1671d10a6489972c798f0b3f33b996287b67fb695d1
+size 1719546

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b0f7ff93ca3c1ceb872c8b559a0eb85282e539e93b213803ca9c85442eb01e0
+oid sha256:af39bb1cb3b4fe0593ef476784182e216b667ed1f09bf30cbb05981752213a90
 size 535667604

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.3940773010253906,
   "best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-18000",
-  "epoch": 36.38632536207477,
+  "epoch": 37.396766588076794,
   "eval_steps": 750,
-  "global_step": 27000,
+  "global_step": 27750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -520,6 +520,20 @@
       "eval_samples_per_second": 59.408,
       "eval_steps_per_second": 0.939,
       "step": 27000
+    },
+    {
+      "epoch": 37.4,
+      "learning_rate": 4.3938005390835576e-05,
+      "loss": 0.5044,
+      "step": 27750
+    },
+    {
+      "epoch": 37.4,
+      "eval_loss": 1.4159477949142456,
+      "eval_runtime": 84.0529,
+      "eval_samples_per_second": 59.486,
+      "eval_steps_per_second": 0.94,
+      "step": 27750
     }
   ],
   "logging_steps": 750,
@@ -527,7 +541,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 50,
   "save_steps": 750,
-  "total_flos": 1.1685575059163136e+18,
+  "total_flos": 1.2010173614913946e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null