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: 1.3392
-- eval_runtime: 83.6972
-- eval_samples_per_second: 59.739
-- eval_steps_per_second: 0.944
-- epoch: 23.25
-- step: 17250
+- eval_loss: 1.3551
+- eval_runtime: 83.7743
+- eval_samples_per_second: 59.684
+- eval_steps_per_second: 0.943
+- epoch: 24.26
+- step: 18000
 
 ## Model description
 

logs/events.out.tfevents.1704794705.1ec128b7e2b3.26.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29079118c6a11ac4b5b72f71a1af8c5378ec3589fb7f1483ef3ae7e960a82f68
-size 1719052
+oid sha256:dd4f528a0cdfa51b985368423bdcb4f040f696c27952c9fc3cb9f88487acbfcb
+size 1719488

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa7dc5a64dc0c9b86eb9ccd1d76caf8c477f33eed6d5cda9dd0b9a0f4e2b5556
+oid sha256:99fd67a82b1777a8bbb4dcfd6c2bda43327b2e79d9caf192697494fc9ebced34
 size 535667604

trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3803095817565918,
-  "best_model_checkpoint": "ner-bert-ingredients/checkpoint-12750",
-  "epoch": 23.24621084540249,
+  "best_metric": 1.3392431735992432,
+  "best_model_checkpoint": "ner-bert-ingredients/checkpoint-17250",
+  "epoch": 24.256652071404513,
   "eval_steps": 750,
-  "global_step": 17250,
+  "global_step": 18000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -329,6 +329,20 @@
       "eval_samples_per_second": 59.739,
       "eval_steps_per_second": 0.944,
       "step": 17250
+    },
+    {
+      "epoch": 24.26,
+      "learning_rate": 4.6969676549865234e-05,
+      "loss": 0.6533,
+      "step": 18000
+    },
+    {
+      "epoch": 24.26,
+      "eval_loss": 1.3550658226013184,
+      "eval_runtime": 83.7743,
+      "eval_samples_per_second": 59.684,
+      "eval_steps_per_second": 0.943,
+      "step": 18000
     }
   ],
   "logging_steps": 750,
@@ -336,7 +350,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 100,
   "save_steps": 750,
-  "total_flos": 7.465766782268621e+17,
+  "total_flos": 7.79036533801943e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null