End of training

README.md

@@ -15,12 +15,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 4.4464
-- eval_runtime: 0.0184
-- eval_samples_per_second: 54.288
-- eval_steps_per_second: 54.288
-- epoch: 10.0
-- step: 10
+- eval_loss: 4.5212
+- eval_runtime: 0.018
+- eval_samples_per_second: 55.574
+- eval_steps_per_second: 55.574
+- epoch: 20.0
+- step: 20
 
 ## Model description
 

logs/events.out.tfevents.1705983189.70e47a1f5afe.42.12

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f551b9e27c17ebfa551fc7d1e14ed51a482b4bc22699aa35a77795af53bf867
-size 7028
+oid sha256:105cdc3c944add4cdb009f7f6f527894351990ee32cfccca9dfbe4436997c167
+size 7448

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1f2ed33d49476ecdf341fac292ec64b65edf6c4f0c485b9fcbbab100d62d596
+oid sha256:4e14093528daec4025eb3a97e7cbc6cf1404e08fb4a5aa0d3616739091c40424
 size 435756040

trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 10.0,
+  "best_metric": 4.4464287757873535,
+  "best_model_checkpoint": "ner-bert-ingredients/checkpoint-10",
+  "epoch": 20.0,
   "eval_steps": 10,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -21,6 +21,20 @@
       "eval_samples_per_second": 54.288,
       "eval_steps_per_second": 54.288,
       "step": 10
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 3e-05,
+      "loss": 0.207,
+      "step": 20
+    },
+    {
+      "epoch": 20.0,
+      "eval_loss": 4.521205425262451,
+      "eval_runtime": 0.018,
+      "eval_samples_per_second": 55.574,
+      "eval_steps_per_second": 55.574,
+      "step": 20
     }
   ],
   "logging_steps": 10,
@@ -28,7 +42,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 50,
   "save_steps": 10,
-  "total_flos": 6571230957720.0,
+  "total_flos": 13142461915440.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null