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: 0.9149
-- eval_runtime: 1375.6915
-- eval_samples_per_second: 109.036
-- eval_steps_per_second: 1.704
-- epoch: 10.67
-- step: 450000
+- eval_loss: 0.9112
+- eval_runtime: 1361.672
+- eval_samples_per_second: 110.159
+- eval_steps_per_second: 1.721
+- epoch: 11.85
+- step: 500000
 
 ## Model description
 

logs/events.out.tfevents.1708177060.d7a757208556.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69dd7768d90060fd258e03f09c5cb49f5458593c5c9fb6cb986f98f9614b4f71
+size 5154

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a80fe317d4c5fc702b8ebe10cd504d78022508d5ffbf0eb2ff6e81820878b176
+oid sha256:296515dd3d70398833ab4b19d88b7e46d0b53f16d5b6a86506db5d99c8581642
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
  "best_metric": null,
  "best_model_checkpoint": null,
- "epoch": 10.66654024841187,
+ "epoch": 11.8517113871243,
  "eval_steps": 50000,
- "global_step": 450000,
+ "global_step": 500000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
@@ -133,6 +133,20 @@
  "eval_samples_per_second": 109.036,
  "eval_steps_per_second": 1.704,
  "step": 450000
+ },
+ {
+ "epoch": 11.85,
+ "learning_rate": 4.940763961316014e-05,
+ "loss": 0.8878,
+ "step": 500000
+ },
+ {
+ "epoch": 11.85,
+ "eval_loss": 0.9112315773963928,
+ "eval_runtime": 1361.672,
+ "eval_samples_per_second": 110.159,
+ "eval_steps_per_second": 1.721,
+ "step": 500000
  }
  ],
  "logging_steps": 50000,
@@ -140,7 +154,7 @@
  "num_input_tokens_seen": 0,
  "num_train_epochs": 100,
  "save_steps": 50000,
- "total_flos": 9.4064086351872e+17,
+ "total_flos": 1.045156631150592e+18,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null