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: 1.5037
+- Loss: 1.7986
 
 ## 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 sha256:05ebacde0003e34edf452bf7624bdd0eead5542451e0a563e0d67fc5c380950e
+oid sha256:125fce126a25a7d7cbdf7cbe65207dd07d79df1754cc739915dc184993d63706
 size 535667604

runs/Jan30_10-22-15_1f29a6e67489/events.out.tfevents.1706610136.1f29a6e67489.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbc944516ada237f33d0a8f407c0314ae56c10ad8063ec7aa747d2df76f1bb8c
+size 1717398

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.3940773010253906,
   "best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-18000",
-  "epoch": 43.46143482654092,
+  "epoch": 44.47389693499495,
   "eval_steps": 750,
-  "global_step": 32250,
+  "global_step": 33000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -618,14 +618,28 @@
       "eval_samples_per_second": 58.63,
       "eval_steps_per_second": 0.926,
       "step": 32250
+    },
+    {
+      "epoch": 44.47,
+      "learning_rate": 4.949528301886793e-05,
+      "loss": 2.0138,
+      "step": 33000
+    },
+    {
+      "epoch": 44.47,
+      "eval_loss": 1.798643708229065,
+      "eval_runtime": 84.6945,
+      "eval_samples_per_second": 59.036,
+      "eval_steps_per_second": 0.933,
+      "step": 33000
     }
   ],
   "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": 1.3957764949418803e+18,
+  "total_flos": 1.4282363505169613e+18,
   "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 sha256:66c61243b25605d74b26033db93a069c3b81ee416898c97ff0a455425b8e048d
 size 4283