End of training

README.md

@@ -13,12 +13,12 @@ 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:
-- eval_loss: 4.9241
-- eval_runtime: 0.0183
-- eval_samples_per_second: 54.52
-- eval_steps_per_second: 54.52
-- epoch: 20.0
-- step: 20
+- eval_loss: 5.0407
+- eval_runtime: 0.0178
+- eval_samples_per_second: 56.023
+- eval_steps_per_second: 56.023
+- epoch: 30.0
+- step: 30
 
 ## Model description
 

logs/events.out.tfevents.1705983321.70e47a1f5afe.42.14

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f6f005cc9bd58b6b64b38c2e50dd6a68c1318b90114ba87fe296773e4abf580
-size 7086
+oid sha256:483cc885342b5846234cda30542e668374a4b33ff1c0068d3a2eca0c60033fdf
+size 7506

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b682db66b454975faf7da3a053ad47ae19381e41248c218350c29f4e02d2c921
+oid sha256:2031e42e4c65f6842de54d7f3dca23b0e9524e255c1325c040c9d41980c05d15
 size 435756040

trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 20.0,
+  "best_metric": 4.924107074737549,
+  "best_model_checkpoint": "ner-bert-ingredients/checkpoint-20",
+  "epoch": 30.0,
   "eval_steps": 10,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -35,6 +35,20 @@
       "eval_samples_per_second": 54.52,
       "eval_steps_per_second": 54.52,
       "step": 20
+    },
+    {
+      "epoch": 30.0,
+      "learning_rate": 3e-05,
+      "loss": 0.01,
+      "step": 30
+    },
+    {
+      "epoch": 30.0,
+      "eval_loss": 5.040736675262451,
+      "eval_runtime": 0.0178,
+      "eval_samples_per_second": 56.023,
+      "eval_steps_per_second": 56.023,
+      "step": 30
     }
   ],
   "logging_steps": 10,
@@ -42,7 +56,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 50,
   "save_steps": 10,
-  "total_flos": 13142461915440.0,
+  "total_flos": 19713692873160.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null