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: 1.4926
+- Loss: 1.5096
 
 ## Model description
 

logs/events.out.tfevents.1706529108.663d6886d228.26.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8872e8beb6f19a00a3dd9e1ead9bbe2cacd381a94bbb75e788eea2b0bf5b15c4
-size 1718238
+oid sha256:6cdf6abad5e16c2161560ba88e7e855f6055387a8b6f834dce16336ce41af2d6
+size 1718674

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fd27cc956e4162c815ae1e0c25b2f933b06f14f8ab7cb1f1de1f296fde5de41
+oid sha256:7464dfbee2efb33541cd257e168bf6a40d573e12a6945afa147131fd46de57b1
 size 535667604

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.3940773010253906,
   "best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-18000",
-  "epoch": 40.43011114853486,
+  "epoch": 41.44055237453688,
   "eval_steps": 750,
-  "global_step": 30000,
+  "global_step": 30750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -576,6 +576,20 @@
       "eval_samples_per_second": 58.707,
       "eval_steps_per_second": 0.928,
       "step": 30000
+    },
+    {
+      "epoch": 41.44,
+      "learning_rate": 4.595956873315364e-05,
+      "loss": 0.596,
+      "step": 30750
+    },
+    {
+      "epoch": 41.44,
+      "eval_loss": 1.5095667839050293,
+      "eval_runtime": 85.1603,
+      "eval_samples_per_second": 58.713,
+      "eval_steps_per_second": 0.928,
+      "step": 30750
     }
   ],
   "logging_steps": 750,
@@ -583,7 +597,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 50,
   "save_steps": 750,
-  "total_flos": 1.2983969282166374e+18,
+  "total_flos": 1.3308567837917184e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null