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: 0.9071
-- eval_runtime: 1376.6401
-- eval_samples_per_second: 108.961
-- eval_steps_per_second: 1.703
-- epoch: 20.15
-- step: 850000
+- eval_loss: 0.9067
+- eval_runtime: 1378.1375
+- eval_samples_per_second: 108.843
+- eval_steps_per_second: 1.701
+- epoch: 21.33
+- step: 900000
 
 ## Model description
 

logs/events.out.tfevents.1709538402.34d8bbd0f97b.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa2e2ab14339aa47825765627f5db692d6145b68ab9a117b6da268fe73d3666d
+size 5142

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d3193ae0f4607a11d15b4d3fdc2406f7bf17648fafc46cd1c042c0e9b981345
+oid sha256:8c2cdec83bd9e62ade6c7b1d79f75a934bf7aa79979795b153b6a0c2744e6142
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 20.14790935811131,
+  "epoch": 21.33308049682374,
   "eval_steps": 50000,
-  "global_step": 850000,
+  "global_step": 900000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -245,6 +245,20 @@
       "eval_samples_per_second": 108.961,
       "eval_steps_per_second": 1.703,
       "step": 850000
+    },
+    {
+      "epoch": 21.33,
+      "learning_rate": 4.940761590973737e-05,
+      "loss": 0.8407,
+      "step": 900000
+    },
+    {
+      "epoch": 21.33,
+      "eval_loss": 0.906717836856842,
+      "eval_runtime": 1378.1375,
+      "eval_samples_per_second": 108.843,
+      "eval_steps_per_second": 1.701,
+      "step": 900000
     }
   ],
   "logging_steps": 50000,
@@ -252,7 +266,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 100,
   "save_steps": 50000,
-  "total_flos": 1.77676491423744e+18,
+  "total_flos": 1.881280681869312e+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