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: 0.9071
-- eval_runtime: 1366.9659
-- eval_samples_per_second: 109.732
-- eval_steps_per_second: 1.715
-- epoch: 16.59
-- step: 700000
+- eval_loss: 0.9052
+- eval_runtime: 1372.6886
+- eval_samples_per_second: 109.275
+- eval_steps_per_second: 1.708
+- epoch: 17.78
+- step: 750000
 
 ## Model description
 

logs/events.out.tfevents.1708915015.2b77ed4580e3.27.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:632879f94a9617b4774956b467f692fd563b1312e0424fdc77165c739dbf3158
+size 5142

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0d67c2b65ae6e5206dfafc08cce5024ed542ad173cc472520d3bda5967a968c
+oid sha256:d29d6d99a53aea865a135433fe708f41fc80200781badae74d7b36925f8b4142
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
  "best_metric": null,
  "best_model_checkpoint": null,
- "epoch": 16.592395941974022,
+ "epoch": 17.777567080686453,
  "eval_steps": 50000,
- "global_step": 700000,
+ "global_step": 750000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
@@ -203,6 +203,20 @@
  "eval_samples_per_second": 109.732,
  "eval_steps_per_second": 1.715,
  "step": 700000
+ },
+ {
+ "epoch": 17.78,
+ "learning_rate": 4.940761590973737e-05,
+ "loss": 0.8571,
+ "step": 750000
+ },
+ {
+ "epoch": 17.78,
+ "eval_loss": 0.9051714539527893,
+ "eval_runtime": 1372.6886,
+ "eval_samples_per_second": 109.275,
+ "eval_steps_per_second": 1.708,
+ "step": 750000
  }
  ],
  "logging_steps": 50000,
@@ -210,7 +224,7 @@
  "num_input_tokens_seen": 0,
  "num_train_epochs": 100,
  "save_steps": 50000,
- "total_flos": 1.463218656509952e+18,
+ "total_flos": 1.567734424141824e+18,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null