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: 1.5660
+- Loss: 1.4842
 
 ## Model description
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01d222c1d4ea9681f87f1c3489a40477fa73d053f1cd19b164ff2ff310b9d508
+oid sha256:a922bc09cad9822c1231705238ef0059f6ad4f08ec088befb62daa91c5699e90
 size 535667604

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bc30ae8710694ce6a82fcc868dda0ee628b318689af1731f158d08c80c1a901
-size 1719142
+oid sha256:6d4217d32fd01f818778456021e1c0a67d0f6bbae4e794e17f31d31eff8aa772
+size 1719578

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.3940773010253906,
   "best_model_checkpoint": "ner-bert-ingredientstesting/checkpoint-18000",
-  "epoch": 48.51566183900303,
+  "epoch": 49.52610306500505,
   "eval_steps": 750,
-  "global_step": 36000,
+  "global_step": 36750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -688,6 +688,20 @@
       "eval_samples_per_second": 59.248,
       "eval_steps_per_second": 0.936,
       "step": 36000
+    },
+    {
+      "epoch": 49.53,
+      "learning_rate": 4.6969676549865234e-05,
+      "loss": 0.4128,
+      "step": 36750
+    },
+    {
+      "epoch": 49.53,
+      "eval_loss": 1.4841716289520264,
+      "eval_runtime": 84.3983,
+      "eval_samples_per_second": 59.243,
+      "eval_steps_per_second": 0.936,
+      "step": 36750
     }
   ],
   "logging_steps": 750,
@@ -695,7 +709,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 100,
   "save_steps": 750,
-  "total_flos": 1.558075772817285e+18,
+  "total_flos": 1.590535628392366e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null