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: 0.8834
-- eval_runtime: 2010.1701
-- eval_samples_per_second: 110.993
-- eval_steps_per_second: 1.735
-- epoch: 12.75
-- step: 800000
+- eval_loss: 0.8838
+- eval_runtime: 2005.9725
+- eval_samples_per_second: 111.225
+- eval_steps_per_second: 1.738
+- epoch: 13.55
+- step: 850000
 
 ## Model description
 

logs/events.out.tfevents.1704595968.052fb87a7a0a.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:debf9c06661bf9df642e3b1ade2311e20b967f39c08b8268beaa5b7e4b0b4408
+size 5099

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13d8c2b3d9bd1e34b45401a71877f331f0befb78b5f8c0e889877ab1e0c096dc
+oid sha256:a152f01e2eed2929de814ef9415645fd4bbd68cd7b31bf6c5438a5dc762577da
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 12.748800815923252,
+  "epoch": 13.545600866918456,
   "eval_steps": 50000,
-  "global_step": 800000,
+  "global_step": 850000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -231,6 +231,20 @@
       "eval_samples_per_second": 110.993,
       "eval_steps_per_second": 1.735,
       "step": 800000
+    },
+    {
+      "epoch": 13.55,
+      "learning_rate": 4.9920348679702315e-05,
+      "loss": 0.8599,
+      "step": 850000
+    },
+    {
+      "epoch": 13.55,
+      "eval_loss": 0.883805513381958,
+      "eval_runtime": 2005.9725,
+      "eval_samples_per_second": 111.225,
+      "eval_steps_per_second": 1.738,
+      "step": 850000
     }
   ],
   "logging_steps": 50000,
@@ -238,7 +252,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 500,
   "save_steps": 50000,
-  "total_flos": 1.67226508541952e+18,
+  "total_flos": 1.77678157160448e+18,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null