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: 0.9121
-- eval_runtime: 1374.6065
-- eval_samples_per_second: 109.122
-- eval_steps_per_second: 1.705
-- epoch: 13.04
-- step: 550000
+- eval_loss: 0.9102
+- eval_runtime: 1370.4302
+- eval_samples_per_second: 109.455
+- eval_steps_per_second: 1.71
+- epoch: 14.22
+- step: 600000
 
 ## Model description
 

logs/events.out.tfevents.1708534313.ef069b1332b9.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec13d99b79a44c4a0f2c21aeec46b3361a26e8f77ebe1b4f68bc8fa672281dfc
+size 5142

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc26b7156c94261538c66d6f1c986a9445a4c87876cad57acc8a240d957d2680
+oid sha256:a7b47e220e2f1f3ca73055393677e5e1c953e35d8d65d8603755f5e1e048690c
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 13.036882525836731,
+  "epoch": 14.222053664549161,
   "eval_steps": 50000,
-  "global_step": 550000,
+  "global_step": 600000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -161,6 +161,20 @@
       "eval_samples_per_second": 109.122,
       "eval_steps_per_second": 1.705,
       "step": 550000
+    },
+    {
+      "epoch": 14.22,
+      "learning_rate": 4.940762776144876e-05,
+      "loss": 0.8727,
+      "step": 600000
+    },
+    {
+      "epoch": 14.22,
+      "eval_loss": 0.9102199077606201,
+      "eval_runtime": 1370.4302,
+      "eval_samples_per_second": 109.455,
+      "eval_steps_per_second": 1.71,
+      "step": 600000
     }
   ],
   "logging_steps": 50000,
@@ -168,7 +182,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 100,
   "save_steps": 50000,
-  "total_flos": 1.149671353614336e+18,
+  "total_flos": 1.254187121246208e+18,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb10217ea6ee5a53faf925ba15fc624a98562d0ed446408452fcac3eb4a1b18e
+oid sha256:e11847e74c240616571649a97da406725778726648f4a5d5ba652545c0ac20df
 size 4728