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: 1.4031
-- eval_runtime: 84.5417
-- eval_samples_per_second: 59.142
-- eval_steps_per_second: 0.934
-- epoch: 8.08
-- step: 6000
+- eval_loss: 1.7413
+- eval_runtime: 84.4082
+- eval_samples_per_second: 59.236
+- eval_steps_per_second: 0.936
+- epoch: 10.11
+- step: 7500
 
 ## Model description
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75be812e69caf13a857bdeaff7ac0b9e4b2f649c211974088190696440005bb3
+oid sha256:1df161abd771fcf710eabc03224865fdebcab37a40a5f8579b71911cbd9f9dd1
 size 535667604

runs/Jan06_06-32-59_2e4916cde887/events.out.tfevents.1704522780.2e4916cde887.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be6f10cd74368a90f328235bc92fb27c7adfddfca6f89a2908e0148d93f9389e
+size 1717355

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.63157057762146,
   "best_model_checkpoint": "ner-bert-ingredients/checkpoint-4500",
-  "epoch": 8.084203435500168,
+  "epoch": 10.107106769956214,
   "eval_steps": 1500,
-  "global_step": 6000,
+  "global_step": 7500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -63,6 +63,20 @@
       "eval_samples_per_second": 59.142,
       "eval_steps_per_second": 0.934,
       "step": 6000
+    },
+    {
+      "epoch": 10.11,
+      "learning_rate": 4.8989218328840976e-05,
+      "loss": 2.5862,
+      "step": 7500
+    },
+    {
+      "epoch": 10.11,
+      "eval_loss": 1.7413185834884644,
+      "eval_runtime": 84.4082,
+      "eval_samples_per_second": 59.236,
+      "eval_steps_per_second": 0.936,
+      "step": 7500
     }
   ],
   "logging_steps": 1500,
@@ -70,7 +84,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 100,
   "save_steps": 1500,
-  "total_flos": 2.5967884460064768e+17,
+  "total_flos": 3.245985557508096e+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 sha256:7d04dcf48c1765416300cdabd173191914eeef8cc1092e6e54c54108346d000d
+oid sha256:f593d4ea75754b8c22e75c7f17003f0a08348c63a20a400df9886c12cbeedc59
 size 4283