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: 0.8792
-- eval_runtime: 1985.6931
-- eval_samples_per_second: 112.361
-- eval_steps_per_second: 1.756
-- epoch: 22.31
-- step: 1400000
+- eval_loss: 0.8800
+- eval_runtime: 2021.1167
+- eval_samples_per_second: 110.392
+- eval_steps_per_second: 1.725
+- epoch: 23.11
+- step: 1450000
 
 ## Model description
 

logs/events.out.tfevents.1705980498.4c96a83a2518.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cd5a93fd1005b8776d729e04eacaecc520b2121f9fac4ca951575131c0090a2
+size 5099

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a51da105fccd05ac3ab0eab61c0e0cc154cfc86fdfafd085fc53bab26b3187b
+oid sha256:1dbddb86f969282280a65ed4dd2012219eb863ac99138ee0331a62ace913f664
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 22.310401427865692,
+  "epoch": 23.107201478860894,
   "eval_steps": 50000,
-  "global_step": 1400000,
+  "global_step": 1450000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -399,6 +399,20 @@
       "eval_samples_per_second": 112.361,
       "eval_steps_per_second": 1.756,
       "step": 1400000
+    },
+    {
+      "epoch": 23.11,
+      "learning_rate": 4.9920348679702315e-05,
+      "loss": 0.8294,
+      "step": 1450000
+    },
+    {
+      "epoch": 23.11,
+      "eval_loss": 0.8799900412559509,
+      "eval_runtime": 2021.1167,
+      "eval_samples_per_second": 110.392,
+      "eval_steps_per_second": 1.725,
+      "step": 1450000
     }
   ],
   "logging_steps": 50000,
@@ -406,7 +420,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 500,
   "save_steps": 50000,
-  "total_flos": 2.92646357286912e+18,
+  "total_flos": 3.03098005905408e+18,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null