End of training

README.md

@@ -13,7 +13,7 @@ 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:
-- Loss: 1.5599
+- Loss: 1.4958
 
 ## Model description
 

logs/events.out.tfevents.1705756331.73c15bc94ff8.26.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08bcc5ca3fd9e08fae4d0deea68c5b22cc565a2bbc8d69e305635c77e90e9d14
-size 1718214
+oid sha256:be900d2072744b445761afee7618dc923e675155d12601fc9cfade5dc1afa6a4
+size 1718642

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5824014e2f2d6012298be55eae3b3b728030b2573a78059b8bc1b4fcdb8ba7f
+oid sha256:060061aea4c77414c4ae9a21f6ac3719318a94583c41cfd343e10bd6c0773fa1
 size 535667604

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.558716893196106,
   "best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-4500",
-  "epoch": 10.106769956214213,
+  "epoch": 11.117211182216234,
   "eval_steps": 750,
-  "global_step": 7500,
+  "global_step": 8250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -156,6 +156,20 @@
       "eval_samples_per_second": 59.086,
       "eval_steps_per_second": 0.934,
       "step": 7500
+    },
+    {
+      "epoch": 11.12,
+      "learning_rate": 4.595822102425876e-05,
+      "loss": 1.2011,
+      "step": 8250
+    },
+    {
+      "epoch": 11.12,
+      "eval_loss": 1.4957914352416992,
+      "eval_runtime": 84.6871,
+      "eval_samples_per_second": 59.041,
+      "eval_steps_per_second": 0.933,
+      "step": 8250
     }
   ],
   "logging_steps": 750,
@@ -163,7 +177,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 50,
   "save_steps": 750,
-  "total_flos": 3.2460126096420864e+17,
+  "total_flos": 3.570611165392896e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null