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: 1.7986
+- Loss: 1.6345
 
 ## Model description
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:125fce126a25a7d7cbdf7cbe65207dd07d79df1754cc739915dc184993d63706
+oid sha256:30aabd01a16f311467534f05247ea6db3d09109d729f6ff46abd712cdf7bcebf
 size 535667604

runs/Jan30_10-22-15_1f29a6e67489/events.out.tfevents.1706610136.1f29a6e67489.26.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbc944516ada237f33d0a8f407c0314ae56c10ad8063ec7aa747d2df76f1bb8c
-size 1717398
+oid sha256:001a241be45eeb597d377359704f6df7987a17ad27e4af97a38dd5fd94031b77
+size 1717834

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.3940773010253906,
   "best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-18000",
-  "epoch": 44.47389693499495,
+  "epoch": 45.48433816099697,
   "eval_steps": 750,
-  "global_step": 33000,
+  "global_step": 33750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -632,6 +632,20 @@
       "eval_samples_per_second": 59.036,
       "eval_steps_per_second": 0.933,
       "step": 33000
+    },
+    {
+      "epoch": 45.48,
+      "learning_rate": 4.898989218328841e-05,
+      "loss": 0.8625,
+      "step": 33750
+    },
+    {
+      "epoch": 45.48,
+      "eval_loss": 1.6345179080963135,
+      "eval_runtime": 84.4707,
+      "eval_samples_per_second": 59.192,
+      "eval_steps_per_second": 0.935,
+      "step": 33750
     }
   ],
   "logging_steps": 750,
@@ -639,7 +653,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 100,
   "save_steps": 750,
-  "total_flos": 1.4282363505169613e+18,
+  "total_flos": 1.4606962060920422e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null