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: 0.9804
-- eval_runtime: 1376.4724
-- eval_samples_per_second: 108.974
+- eval_loss: 0.9588
+- eval_runtime: 1376.5573
+- eval_samples_per_second: 108.967
 - eval_steps_per_second: 1.703
-- epoch: 2.37
-- step: 100000
+- epoch: 3.56
+- step: 150000
 
 ## Model description
 

logs/events.out.tfevents.1707149028.4c55bcba7827.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de511e2aff8aec50f56506a4d453b836ad0c2e858090c2a7f49c427fc8db70de
+size 5154

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c463344c8cb5f2df488df653b7dba47cd576e06dd4f6531b17bfec7bce0d2f3a
+oid sha256:569bc69dea165d5d6cfe12190fa1b33d3707f544b843c3a41ac3a46c44484a09
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.37034227742486,
+  "epoch": 3.5555134161372903,
   "eval_steps": 50000,
-  "global_step": 100000,
+  "global_step": 150000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -35,6 +35,20 @@
       "eval_samples_per_second": 108.974,
       "eval_steps_per_second": 1.703,
       "step": 100000
+    },
+    {
+      "epoch": 3.56,
+      "learning_rate": 4.940766331658292e-05,
+      "loss": 0.9833,
+      "step": 150000
+    },
+    {
+      "epoch": 3.56,
+      "eval_loss": 0.9588034152984619,
+      "eval_runtime": 1376.5573,
+      "eval_samples_per_second": 108.967,
+      "eval_steps_per_second": 1.703,
+      "step": 150000
     }
   ],
   "logging_steps": 50000,
@@ -42,7 +56,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 100,
   "save_steps": 50000,
-  "total_flos": 2.09031535263744e+17,
+  "total_flos": 3.13547302895616e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null