End of training

README.md

@@ -13,12 +13,12 @@ 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:
-- eval_loss: 1.3497
-- eval_runtime: 83.6712
-- eval_samples_per_second: 59.758
-- eval_steps_per_second: 0.944
-- epoch: 12.13
-- step: 9000
+- eval_loss: 2.0906
+- eval_runtime: 84.2266
+- eval_samples_per_second: 59.364
+- eval_steps_per_second: 0.938
+- epoch: 13.14
+- step: 9750
 
 ## Model description
 

logs/events.out.tfevents.1704684118.c9f3f47f1977.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c0604fcc349ac6ad8e7fd09b8dcb072329f98126a7ce21710f61bb6c723dd8d
+size 1717324

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee869e69f26d6b5af04157d2668f1392049dcc8bc28677868a1cd397756c694a
+oid sha256:f298964c6cfbc416e8a4189f8b3bc68a7621f88d91f851279271189cde5a4b33
 size 535667604

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.4048632383346558,
   "best_model_checkpoint": "ner-bert-ingredients/checkpoint-8250",
-  "epoch": 12.127315594476254,
+  "epoch": 13.13977770293028,
   "eval_steps": 750,
-  "global_step": 9000,
+  "global_step": 9750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -175,6 +175,20 @@
       "eval_samples_per_second": 59.758,
       "eval_steps_per_second": 0.944,
       "step": 9000
+    },
+    {
+      "epoch": 13.14,
+      "learning_rate": 4.949460916442048e-05,
+      "loss": 3.1119,
+      "step": 9750
+    },
+    {
+      "epoch": 13.14,
+      "eval_loss": 2.09057354927063,
+      "eval_runtime": 84.2266,
+      "eval_samples_per_second": 59.364,
+      "eval_steps_per_second": 0.938,
+      "step": 9750
     }
   ],
   "logging_steps": 750,
@@ -182,7 +196,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 100,
   "save_steps": 750,
-  "total_flos": 3.895182669009715e+17,
+  "total_flos": 4.219781224760525e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null