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: 1.4253
+- Loss: 1.3664
 
 ## Model description
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:baa988aac25a6cd2ffcec35178741dbf3b99d56a087e843ffde904ce6c382f78
+oid sha256:74c3ca17b2c4844f31da80a93fa740990ffdfc1bb60232eb8f348ad181478215
 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 sha256:8ec8245ec215e90675fdb097a0d959e29060270edd3d7360bc2ab90074cb9aeb
-size 1719102
+oid sha256:50f7cc07356db6bb190faf8b75c7b609070ddc604fdeba5b10b006fec742e374
+size 1719530

trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4376968145370483,
-  "best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-12750",
-  "epoch": 18.192320646682386,
+  "best_metric": 1.4253113269805908,
+  "best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-13500",
+  "epoch": 19.202761872684405,
   "eval_steps": 750,
-  "global_step": 13500,
+  "global_step": 14250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -268,6 +268,20 @@
       "eval_samples_per_second": 59.123,
       "eval_steps_per_second": 0.934,
       "step": 13500
+    },
+    {
+      "epoch": 19.2,
+      "learning_rate": 4.696900269541779e-05,
+      "loss": 0.7497,
+      "step": 14250
+    },
+    {
+      "epoch": 19.2,
+      "eval_loss": 1.3664312362670898,
+      "eval_runtime": 84.6297,
+      "eval_samples_per_second": 59.081,
+      "eval_steps_per_second": 0.933,
+      "step": 14250
     }
   ],
   "logging_steps": 750,
@@ -275,7 +289,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 100,
   "save_steps": 750,
-  "total_flos": 5.842801055648563e+17,
+  "total_flos": 6.167399611399373e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null