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: 1.4202
+- Loss: 1.8303
 
 ## Model description
 

logs/events.out.tfevents.1706460461.2106b1bddca9.27.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d15e4faf6f10d412caa19e0ac4ddf0ad91a252888b05620e50964e4bbe94bd0
+size 1717366

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78408bc361c088697d6742a9a787eecd40f5b3bf9f7dfe66d0f775ee2a9c3230
+oid sha256:e5a12f522f79c0de9db88cc997f0bdb2896dc7bd75c4f385f1c012f38f05b47d
 size 535667604

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.3940773010253906,
   "best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-18000",
-  "epoch": 31.332098349612664,
+  "epoch": 32.34456045806669,
   "eval_steps": 750,
-  "global_step": 23250,
+  "global_step": 24000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -450,6 +450,20 @@
       "eval_samples_per_second": 59.259,
       "eval_steps_per_second": 0.936,
       "step": 23250
+    },
+    {
+      "epoch": 32.34,
+      "learning_rate": 4.899056603773585e-05,
+      "loss": 2.2264,
+      "step": 24000
+    },
+    {
+      "epoch": 32.34,
+      "eval_loss": 1.830324649810791,
+      "eval_runtime": 84.4012,
+      "eval_samples_per_second": 59.241,
+      "eval_steps_per_second": 0.936,
+      "step": 24000
     }
   ],
   "logging_steps": 750,
@@ -457,7 +471,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 50,
   "save_steps": 750,
-  "total_flos": 1.0062582280409088e+18,
+  "total_flos": 1.0387180836159898e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null