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: 1.3601
+- Loss: 2.0050
 
 ## 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: 50
+- num_epochs: 100
 - mixed_precision_training: Native AMP
 
 ### Training results

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:192542153436042bee50de991c19209c78b1a24d1d47df54fc052fa1da0e1fa5
+oid sha256:e39b8df1cbb99fffe7efe5e8ace9235204c42cf176944966f84611a6e266e7d6
 size 535667604

runs/Jan22_02-43-32_fbf1b033956c/events.out.tfevents.1705891414.fbf1b033956c.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:722c6890eb6f5d56b877a66688db33d3be7b63d17d0d8045a51a8731c0562d1a
+size 1717390

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.4617092609405518,
   "best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-9000",
-  "epoch": 13.138093634220276,
+  "epoch": 14.150555742674301,
   "eval_steps": 750,
-  "global_step": 9750,
+  "global_step": 10500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,14 +198,28 @@
       "eval_samples_per_second": 59.334,
       "eval_steps_per_second": 0.937,
       "step": 9750
+    },
+    {
+      "epoch": 14.15,
+      "learning_rate": 4.949528301886793e-05,
+      "loss": 3.0742,
+      "step": 10500
+    },
+    {
+      "epoch": 14.15,
+      "eval_loss": 2.005005359649658,
+      "eval_runtime": 84.8703,
+      "eval_samples_per_second": 58.913,
+      "eval_steps_per_second": 0.931,
+      "step": 10500
     }
   ],
   "logging_steps": 750,
-  "max_steps": 37100,
+  "max_steps": 74200,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 50,
+  "num_train_epochs": 100,
   "save_steps": 750,
-  "total_flos": 4.219808276894515e+17,
+  "total_flos": 4.544406832645325e+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 sha256:6d8b2637195f6863cffd1bc8a94e43113975024730eec08107e77fd2d167de4a
+oid sha256:6cef0e37aa829d716243e98221dfcba8c8ab13915a644f48844f6e173245a93f
 size 4283