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: 1.3803
-- eval_runtime: 83.8966
-- eval_samples_per_second: 59.597
+- eval_loss: 1.3330
+- eval_runtime: 83.8879
+- eval_samples_per_second: 59.603
 - eval_steps_per_second: 0.942
-- epoch: 17.18
-- step: 12750
+- epoch: 18.19
+- step: 13500
 
 ## Model description
 

logs/events.out.tfevents.1704684118.c9f3f47f1977.26.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:744b3329cc2991eee89d1ac9d7144d06b50bba8b618011fc0f1e90b38ff6148d
-size 1719036
+oid sha256:9b710b4ae801ddf799c0012b6a5e1d50e653b6509c9ce8f0e1a66805e4b4b784
+size 1719464

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4853e6ea033ef7d62e5022742fe79728c5cff75122838aa45cd49e31deea886f
+oid sha256:a785e2c88f8ed9ee8652fa9430e459d33b10cbf45a1d482a0e8ca5da6dcdf371
 size 535667604

trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4048632383346558,
-  "best_model_checkpoint": "ner-bert-ingredients/checkpoint-8250",
-  "epoch": 17.181542606938365,
+  "best_metric": 1.3803095817565918,
+  "best_model_checkpoint": "ner-bert-ingredients/checkpoint-12750",
+  "epoch": 18.191983832940384,
   "eval_steps": 750,
-  "global_step": 12750,
+  "global_step": 13500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -245,6 +245,20 @@
       "eval_samples_per_second": 59.597,
       "eval_steps_per_second": 0.942,
       "step": 12750
+    },
+    {
+      "epoch": 18.19,
+      "learning_rate": 4.696900269541779e-05,
+      "loss": 0.7554,
+      "step": 13500
+    },
+    {
+      "epoch": 18.19,
+      "eval_loss": 1.3329607248306274,
+      "eval_runtime": 83.8879,
+      "eval_samples_per_second": 59.603,
+      "eval_steps_per_second": 0.942,
+      "step": 13500
     }
   ],
   "logging_steps": 750,
@@ -252,7 +266,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 100,
   "save_steps": 750,
-  "total_flos": 5.518175447763763e+17,
+  "total_flos": 5.842774003514573e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null