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: 1.6316
-- eval_runtime: 84.483
-- eval_samples_per_second: 59.183
-- eval_steps_per_second: 0.935
-- epoch: 6.06
-- step: 4500
+- 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
 
 ## Model description
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39dbfa4a734647af92a6c65de31648b6f0d98b630394a4ad2e6a9d539e352512
+oid sha256:75be812e69caf13a857bdeaff7ac0b9e4b2f649c211974088190696440005bb3
 size 535667604

runs/Jan05_15-00-19_ce9c0c92fc28/events.out.tfevents.1704466820.ce9c0c92fc28.26.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:147d7c661e0833a7eb8f2dfbcc11ea2a80be2ae249d5411e548ee4e295d79c1c
-size 1717783
+oid sha256:829c897348edd671b240ce1750975f184c5c8235b98f43c65d5cc761d73c8155
+size 1718211

trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.236969232559204,
-  "best_model_checkpoint": "ner-bert-ingredients/checkpoint-3000",
-  "epoch": 6.063320983496126,
+  "best_metric": 1.63157057762146,
+  "best_model_checkpoint": "ner-bert-ingredients/checkpoint-4500",
+  "epoch": 8.084203435500168,
   "eval_steps": 1500,
-  "global_step": 4500,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -49,6 +49,20 @@
       "eval_samples_per_second": 59.183,
       "eval_steps_per_second": 0.935,
       "step": 4500
+    },
+    {
+      "epoch": 8.08,
+      "learning_rate": 4.696900269541779e-05,
+      "loss": 1.2736,
+      "step": 6000
+    },
+    {
+      "epoch": 8.08,
+      "eval_loss": 1.4030611515045166,
+      "eval_runtime": 84.5417,
+      "eval_samples_per_second": 59.142,
+      "eval_steps_per_second": 0.934,
+      "step": 6000
     }
   ],
   "logging_steps": 1500,
@@ -56,7 +70,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 100,
   "save_steps": 1500,
-  "total_flos": 1.9475913345048576e+17,
+  "total_flos": 2.5967884460064768e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null