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: 1.3664
+- Loss: 1.8944
 
 ## Model description
 
@@ -40,7 +40,7 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 128
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 100
+- num_epochs: 50
 - mixed_precision_training: Native AMP
 
 ### Training results

logs/events.out.tfevents.1705984080.5feecac333ed.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb105d7fd8e0be1fdc31867ede7628f2c39631839d76b9bff390eebd98dcc602
+size 1717358

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74c3ca17b2c4844f31da80a93fa740990ffdfc1bb60232eb8f348ad181478215
+oid sha256:6a16459f696ebed20a3fc02c36617a6e235a7ebfa18c8b483e6d7ba31457959c
 size 535667604

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.4253113269805908,
   "best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-13500",
-  "epoch": 19.202761872684405,
+  "epoch": 20.21522398113843,
   "eval_steps": 750,
-  "global_step": 14250,
+  "global_step": 15000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -282,14 +282,28 @@
       "eval_samples_per_second": 59.081,
       "eval_steps_per_second": 0.933,
       "step": 14250
+    },
+    {
+      "epoch": 20.22,
+      "learning_rate": 4.899056603773585e-05,
+      "loss": 2.6343,
+      "step": 15000
+    },
+    {
+      "epoch": 20.22,
+      "eval_loss": 1.8943818807601929,
+      "eval_runtime": 84.158,
+      "eval_samples_per_second": 59.412,
+      "eval_steps_per_second": 0.939,
+      "step": 15000
     }
   ],
   "logging_steps": 750,
-  "max_steps": 74200,
+  "max_steps": 37100,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 100,
+  "num_train_epochs": 50,
   "save_steps": 750,
-  "total_flos": 6.167399611399373e+17,
+  "total_flos": 6.491998167150182e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cef0e37aa829d716243e98221dfcba8c8ab13915a644f48844f6e173245a93f
+oid sha256:6d8b2637195f6863cffd1bc8a94e43113975024730eec08107e77fd2d167de4a
 size 4283