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: 0.8817
-- eval_runtime: 1994.6872
-- eval_samples_per_second: 111.855
-- eval_steps_per_second: 1.748
-- epoch: 17.53
-- step: 1100000
+- eval_loss: 0.8802
+- eval_runtime: 1993.2844
+- eval_samples_per_second: 111.933
+- eval_steps_per_second: 1.749
+- epoch: 18.33
+- step: 1150000
 
 ## Model description
 

logs/events.out.tfevents.1705326049.0a4578509b3b.27.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:808e08b70ef2eb94b75ff9df36a54fc3352b6f7f040fbebad9c4107a9cef81ee
+size 5099

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:841c215fe5afa81bc942c40d802bbaecf1c6ad8c3cc242dacef4fdfef8fd29cd
+oid sha256:eeff65b8f9080bd84229af9009c4f3ca96ab5b56561ffa57e8bbe58a8cc399fc
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 17.529601121894473,
+  "epoch": 18.326401172889675,
   "eval_steps": 50000,
-  "global_step": 1100000,
+  "global_step": 1150000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -315,6 +315,20 @@
       "eval_samples_per_second": 111.855,
       "eval_steps_per_second": 1.748,
       "step": 1100000
+    },
+    {
+      "epoch": 18.33,
+      "learning_rate": 4.992034549250211e-05,
+      "loss": 0.841,
+      "step": 1150000
+    },
+    {
+      "epoch": 18.33,
+      "eval_loss": 0.8802331686019897,
+      "eval_runtime": 1993.2844,
+      "eval_samples_per_second": 111.933,
+      "eval_steps_per_second": 1.749,
+      "step": 1150000
     }
   ],
   "logging_steps": 50000,
@@ -322,7 +336,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 500,
   "save_steps": 50000,
-  "total_flos": 2.29936432914432e+18,
+  "total_flos": 2.40388081532928e+18,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null