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: 9.6947
+- Loss: 3.2860
 
 ## Model description
 

logs/events.out.tfevents.1705498568.ed78651fcb5b.26.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e03d099642d8c62eed1cd53da6fb61b861d281018436e51b3954e422d17a6500
-size 1717358
+oid sha256:2f137b2c4f982df40b1835165df2efb0b8d6ecb9c0e36684e7019bb5f066d085
+size 1717786

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfb4fb1ece8a9c6c9217b4b1d2a851afb9bf4e9e25fed762c0956c70b2892ef6
+oid sha256:fa878307e27c74d382612902a7b9e4c7ff9c804b946271146df2ac84b664ed5d
 size 535667604

trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 1.0107780397440216,
+  "best_metric": 9.694682121276855,
+  "best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-750",
+  "epoch": 2.0212192657460424,
   "eval_steps": 750,
-  "global_step": 750,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,20 @@
       "eval_samples_per_second": 59.067,
       "eval_steps_per_second": 0.933,
       "step": 750
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 4.897978436657682e-05,
+      "loss": 4.9343,
+      "step": 1500
+    },
+    {
+      "epoch": 2.02,
+      "eval_loss": 3.2859976291656494,
+      "eval_runtime": 84.3631,
+      "eval_samples_per_second": 59.268,
+      "eval_steps_per_second": 0.936,
+      "step": 1500
     }
   ],
   "logging_steps": 750,
@@ -37,7 +51,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 50,
   "save_steps": 750,
-  "total_flos": 3.246256078848e+16,
+  "total_flos": 6.492241636356096e+16,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null