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: 3.2860
+- Loss: 2.4815
 
 ## Model description
 

logs/events.out.tfevents.1705498568.ed78651fcb5b.26.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f137b2c4f982df40b1835165df2efb0b8d6ecb9c0e36684e7019bb5f066d085
-size 1717786
+oid sha256:695082ab22efaef9ae2a297e5a205acc1918b02972150fb6ff7ad1f538045453
+size 1718214

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa878307e27c74d382612902a7b9e4c7ff9c804b946271146df2ac84b664ed5d
+oid sha256:312cf3588bb2cc38a8915a7119b0def981af42e9748073c024ef0e663cd9602c
 size 535667604

trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 9.694682121276855,
-  "best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-750",
-  "epoch": 2.0212192657460424,
+  "best_metric": 3.2859976291656494,
+  "best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-1500",
+  "epoch": 3.031660491748063,
   "eval_steps": 750,
-  "global_step": 1500,
+  "global_step": 2250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,20 @@
       "eval_samples_per_second": 59.268,
       "eval_steps_per_second": 0.936,
       "step": 1500
+    },
+    {
+      "epoch": 3.03,
+      "learning_rate": 4.796900269541779e-05,
+      "loss": 2.8798,
+      "step": 2250
+    },
+    {
+      "epoch": 3.03,
+      "eval_loss": 2.4815261363983154,
+      "eval_runtime": 84.3896,
+      "eval_samples_per_second": 59.249,
+      "eval_steps_per_second": 0.936,
+      "step": 2250
     }
   ],
   "logging_steps": 750,
@@ -51,7 +65,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 50,
   "save_steps": 750,
-  "total_flos": 6.492241636356096e+16,
+  "total_flos": 9.738227193864192e+16,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null