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: 0.8908
-- eval_runtime: 1991.4984
-- eval_samples_per_second: 112.034
-- eval_steps_per_second: 1.751
-- epoch: 9.56
-- step: 600000
+- eval_loss: 0.8896
+- eval_runtime: 2006.0064
+- eval_samples_per_second: 111.223
+- eval_steps_per_second: 1.738
+- epoch: 10.36
+- step: 650000
 
 ## Model description
 

logs/events.out.tfevents.1704166717.dacfc4e056f2.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d26d64cc3b8803ad7007812f04147b09b326cbfe42e12632230b324db1a46ca
+size 5099

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca580655c792a39d032ebc6a4600b7073b4e0002851ad8702ee605c5e0178e38
+oid sha256:dfd94057aad0373c5507053c75b00b127339bb5015b4f4d88173824b359a0aa9
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.561600611942438,
+  "epoch": 10.358400662937642,
   "eval_steps": 50000,
-  "global_step": 600000,
+  "global_step": 650000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -175,6 +175,20 @@
       "eval_samples_per_second": 112.034,
       "eval_steps_per_second": 1.751,
       "step": 600000
+    },
+    {
+      "epoch": 10.36,
+      "learning_rate": 4.992035346050262e-05,
+      "loss": 0.8763,
+      "step": 650000
+    },
+    {
+      "epoch": 10.36,
+      "eval_loss": 0.8895950317382812,
+      "eval_runtime": 2006.0064,
+      "eval_samples_per_second": 111.223,
+      "eval_steps_per_second": 1.738,
+      "step": 650000
     }
   ],
   "logging_steps": 50000,
@@ -182,7 +196,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 500,
   "save_steps": 50000,
-  "total_flos": 1.25419881406464e+18,
+  "total_flos": 1.3587153002496e+18,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null