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: 0.9326
-- eval_runtime: 2015.1208
-- eval_samples_per_second: 110.72
-- eval_steps_per_second: 1.73
-- epoch: 3.19
-- step: 200000
+- eval_loss: 0.9212
+- eval_runtime: 2011.4269
+- eval_samples_per_second: 110.924
+- eval_steps_per_second: 1.734
+- epoch: 3.98
+- step: 250000
 
 ## Model description
 

logs/events.out.tfevents.1703258750.d25677ef05c2.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f90bae4c11082be8781d04a26319bf504cd3ca882bbb4b50e4f8450b517cf29c
+size 5099

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a19116bc254cd3ca11b543d86ebe279b8a7068397e584380689d839c15a8fb45
+oid sha256:dfc14b03649696bdba14f3322b521deebadb227eb6e3774484fd33a2f940a700
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.187200203980813,
+  "epoch": 3.9840002549760163,
   "eval_steps": 50000,
-  "global_step": 200000,
+  "global_step": 250000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -63,6 +63,20 @@
       "eval_samples_per_second": 110.72,
       "eval_steps_per_second": 1.73,
       "step": 200000
+    },
+    {
+      "epoch": 3.98,
+      "learning_rate": 4.992035027330242e-05,
+      "loss": 0.9387,
+      "step": 250000
+    },
+    {
+      "epoch": 3.98,
+      "eval_loss": 0.9212433099746704,
+      "eval_runtime": 2011.4269,
+      "eval_samples_per_second": 110.924,
+      "eval_steps_per_second": 1.734,
+      "step": 250000
     }
   ],
   "logging_steps": 50000,
@@ -70,7 +84,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 500,
   "save_steps": 50000,
-  "total_flos": 4.1806627135488e+17,
+  "total_flos": 5.2258308415488e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null