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: 0.9102
-- eval_runtime: 1370.4302
-- eval_samples_per_second: 109.455
-- eval_steps_per_second: 1.71
-- epoch: 14.22
-- step: 600000
+- eval_loss: 0.9076
+- eval_runtime: 1379.694
+- eval_samples_per_second: 108.72
+- eval_steps_per_second: 1.699
+- epoch: 15.41
+- step: 650000
 
 ## Model description
 

logs/events.out.tfevents.1708590633.624f01aff40e.27.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7981afeb9a7c96521b6f80565900669f7e5913c5b5b95ba5ef7d1f2116f80e59
+size 5142

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7b47e220e2f1f3ca73055393677e5e1c953e35d8d65d8603755f5e1e048690c
+oid sha256:bd5d9238101183379b4f6f7d5f27f1eabe8b3f1bd7d65edce05b27a0a433a821
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 14.222053664549161,
+  "epoch": 15.407224803261592,
   "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": 109.455,
       "eval_steps_per_second": 1.71,
       "step": 600000
+    },
+    {
+      "epoch": 15.41,
+      "learning_rate": 4.940763961316014e-05,
+      "loss": 0.8664,
+      "step": 650000
+    },
+    {
+      "epoch": 15.41,
+      "eval_loss": 0.9076188802719116,
+      "eval_runtime": 1379.694,
+      "eval_samples_per_second": 108.72,
+      "eval_steps_per_second": 1.699,
+      "step": 650000
     }
   ],
   "logging_steps": 50000,
@@ -182,7 +196,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 100,
   "save_steps": 50000,
-  "total_flos": 1.254187121246208e+18,
+  "total_flos": 1.35870288887808e+18,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null