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: 5.0407
-- eval_runtime: 0.0178
-- eval_samples_per_second: 56.023
-- eval_steps_per_second: 56.023
-- epoch: 30.0
-- step: 30
+- eval_loss: 5.1613
+- eval_runtime: 0.0185
+- eval_samples_per_second: 54.098
+- eval_steps_per_second: 54.098
+- epoch: 40.0
+- step: 40
 
 ## Model description
 

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:483cc885342b5846234cda30542e668374a4b33ff1c0068d3a2eca0c60033fdf
-size 7506
+oid sha256:b7be002b7d8d9897cb295b10981fa697d7903eb1ce42c45272ce37bf76fd78b3
+size 7926

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2031e42e4c65f6842de54d7f3dca23b0e9524e255c1325c040c9d41980c05d15
+oid sha256:6115bd197b37a0b28faf2a02c12abf2551cd1d4c4d2fbf23fb47032e2a8d914f
 size 435756040

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 4.924107074737549,
   "best_model_checkpoint": "ner-bert-ingredients/checkpoint-20",
-  "epoch": 30.0,
+  "epoch": 40.0,
   "eval_steps": 10,
-  "global_step": 30,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -49,6 +49,20 @@
       "eval_samples_per_second": 56.023,
       "eval_steps_per_second": 56.023,
       "step": 30
+    },
+    {
+      "epoch": 40.0,
+      "learning_rate": 2e-05,
+      "loss": 0.0063,
+      "step": 40
+    },
+    {
+      "epoch": 40.0,
+      "eval_loss": 5.1612725257873535,
+      "eval_runtime": 0.0185,
+      "eval_samples_per_second": 54.098,
+      "eval_steps_per_second": 54.098,
+      "step": 40
     }
   ],
   "logging_steps": 10,
@@ -56,7 +70,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 50,
   "save_steps": 10,
-  "total_flos": 19713692873160.0,
+  "total_flos": 26284923830880.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null