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: 0.8813
-- eval_runtime: 1998.6292
-- eval_samples_per_second: 111.634
-- eval_steps_per_second: 1.745
-- epoch: 16.73
-- step: 1050000
+- eval_loss: 0.8817
+- eval_runtime: 1994.6872
+- eval_samples_per_second: 111.855
+- eval_steps_per_second: 1.748
+- epoch: 17.53
+- step: 1100000
 
 ## Model description
 

logs/events.out.tfevents.1705237173.e6a48c76d057.27.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50f83b41f84e5c1337af46ae676a9df4b6fe89cd1a8737461faa97d83f62b9c9
+size 5099

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d64048d97434bbf88262b43e49df0dcf022c8ce86158dbe84febde128cf6802
+oid sha256:841c215fe5afa81bc942c40d802bbaecf1c6ad8c3cc242dacef4fdfef8fd29cd
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 16.732801070899267,
+  "epoch": 17.529601121894473,
   "eval_steps": 50000,
-  "global_step": 1050000,
+  "global_step": 1100000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -301,6 +301,20 @@
       "eval_samples_per_second": 111.634,
       "eval_steps_per_second": 1.745,
       "step": 1050000
+    },
+    {
+      "epoch": 17.53,
+      "learning_rate": 4.992034708610221e-05,
+      "loss": 0.8427,
+      "step": 1100000
+    },
+    {
+      "epoch": 17.53,
+      "eval_loss": 0.8817498683929443,
+      "eval_runtime": 1994.6872,
+      "eval_samples_per_second": 111.855,
+      "eval_steps_per_second": 1.748,
+      "step": 1100000
     }
   ],
   "logging_steps": 50000,
@@ -308,7 +322,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 500,
   "save_steps": 50000,
-  "total_flos": 2.19484784295936e+18,
+  "total_flos": 2.29936432914432e+18,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null