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: 0.8850
-- eval_runtime: 1989.8507
-- eval_samples_per_second: 112.127
-- eval_steps_per_second: 1.752
-- epoch: 11.95
-- step: 750000
+- 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
 
 ## Model description
 

logs/events.out.tfevents.1704523026.c58ea2b4ca4f.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be42082267a047ff43379f21d63ef425b53e7ef3a19e0d91539353bc558547a0
+size 5099

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67cc4de92fece2c93275b8cf42cc5d73da47e78c9380f833b1086aff847f27bc
+oid sha256:13d8c2b3d9bd1e34b45401a71877f331f0befb78b5f8c0e889877ab1e0c096dc
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 11.95200076492805,
+  "epoch": 12.748800815923252,
   "eval_steps": 50000,
-  "global_step": 750000,
+  "global_step": 800000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -217,6 +217,20 @@
       "eval_samples_per_second": 112.127,
       "eval_steps_per_second": 1.752,
       "step": 750000
+    },
+    {
+      "epoch": 12.75,
+      "learning_rate": 4.992035186690252e-05,
+      "loss": 0.8628,
+      "step": 800000
+    },
+    {
+      "epoch": 12.75,
+      "eval_loss": 0.8833887577056885,
+      "eval_runtime": 2010.1701,
+      "eval_samples_per_second": 110.993,
+      "eval_steps_per_second": 1.735,
+      "step": 800000
     }
   ],
   "logging_steps": 50000,
@@ -224,7 +238,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 500,
   "save_steps": 50000,
-  "total_flos": 1.56774859923456e+18,
+  "total_flos": 1.67226508541952e+18,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null