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: 0.9034
-- eval_runtime: 1376.7168
-- eval_samples_per_second: 108.955
+- eval_loss: 0.9071
+- eval_runtime: 1376.6401
+- eval_samples_per_second: 108.961
 - eval_steps_per_second: 1.703
-- epoch: 18.96
-- step: 800000
+- epoch: 20.15
+- step: 850000
 
 ## Model description
 

logs/events.out.tfevents.1709182326.6f3e8825b9ca.27.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55546c8438f3abe1f326db166051de9ea92100eb39a408f3d23d12308b93982e
+size 5154

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a347c18c530d4f57e7d1f7191e6060cd0df8e867924acb29724727579ae0277b
+oid sha256:5d3193ae0f4607a11d15b4d3fdc2406f7bf17648fafc46cd1c042c0e9b981345
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
  "best_metric": null,
  "best_model_checkpoint": null,
- "epoch": 18.96273821939888,
+ "epoch": 20.14790935811131,
  "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": 108.955,
  "eval_steps_per_second": 1.703,
  "step": 800000
+ },
+ {
+ "epoch": 20.15,
+ "learning_rate": 4.940762776144876e-05,
+ "loss": 0.8475,
+ "step": 850000
+ },
+ {
+ "epoch": 20.15,
+ "eval_loss": 0.9070873856544495,
+ "eval_runtime": 1376.6401,
+ "eval_samples_per_second": 108.961,
+ "eval_steps_per_second": 1.703,
+ "step": 850000
  }
  ],
  "logging_steps": 50000,
@@ -238,7 +252,7 @@
  "num_input_tokens_seen": 0,
  "num_train_epochs": 100,
  "save_steps": 50000,
- "total_flos": 1.672250191773696e+18,
+ "total_flos": 1.77676491423744e+18,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null