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: 1.5255
+- Loss: 1.4377
 
 ## Model description
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47ba5eceb8f9e87cdb1f103986dbd1995ba6e02107d2e46434a3f3334766ea69
+oid sha256:33572d875c77405045bee1e1b6d196f3275e0230d0283937f3dd3a376f0bc665
 size 535667604

runs/Jan22_02-43-32_fbf1b033956c/events.out.tfevents.1705891414.fbf1b033956c.26.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4265bb71d1e21980073d9be0f5fca5978e1d19a43098ab6b9ad0f7344179bbf9
-size 1718246
+oid sha256:05e58c37b81af20ab189b8b9620c8318b1c4301baa70ed985ad5d8eafe0372f6
+size 1718674

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.4617092609405518,
   "best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-9000",
-  "epoch": 16.17143819467834,
+  "epoch": 17.181879420680364,
   "eval_steps": 750,
-  "global_step": 12000,
+  "global_step": 12750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -240,6 +240,20 @@
       "eval_samples_per_second": 59.118,
       "eval_steps_per_second": 0.934,
       "step": 12000
+    },
+    {
+      "epoch": 17.18,
+      "learning_rate": 4.7979110512129385e-05,
+      "loss": 0.9732,
+      "step": 12750
+    },
+    {
+      "epoch": 17.18,
+      "eval_loss": 1.4376968145370483,
+      "eval_runtime": 84.6742,
+      "eval_samples_per_second": 59.05,
+      "eval_steps_per_second": 0.933,
+      "step": 12750
     }
   ],
   "logging_steps": 750,
@@ -247,7 +261,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 100,
   "save_steps": 750,
-  "total_flos": 5.193603944146944e+17,
+  "total_flos": 5.5182024998977536e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null