End of training

README.md

@@ -1,6 +1,4 @@
 ---
-license: mit
-base_model: gpt2
 tags:
 - generated_from_trainer
 model-index:
@@ -13,14 +11,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 # controlled-food-recipe-generation
 
-This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
+This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 1.0261
-- eval_runtime: 1432.5553
-- eval_samples_per_second: 104.708
-- eval_steps_per_second: 1.636
-- epoch: 1.19
-- step: 50000
+- eval_loss: 0.9804
+- eval_runtime: 1376.4724
+- eval_samples_per_second: 108.974
+- eval_steps_per_second: 1.703
+- epoch: 2.37
+- step: 100000
 
 ## Model description
 

config.json

@@ -1,5 +1,5 @@
 {
- "_name_or_path": "gpt2",
+ "_name_or_path": "/kaggle/working/controlled-food-recipe-generation",
  "activation_function": "gelu_new",
  "architectures": [
  "GPT2LMHeadModel"

logs/events.out.tfevents.1707102026.2f58af33d3db.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:347dd1c2c3debc6a8720f970d8c810dd55f20054ed1295e0429bba74aea735c9
+size 5154

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:167443881e7d10287201ffedb2a2f6354b36719d8c5ceb86c2538e5de6b97c7b
+oid sha256:c463344c8cb5f2df488df653b7dba47cd576e06dd4f6531b17bfec7bce0d2f3a
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
  "best_metric": null,
  "best_model_checkpoint": null,
- "epoch": 1.18517113871243,
+ "epoch": 2.37034227742486,
  "eval_steps": 50000,
- "global_step": 50000,
+ "global_step": 100000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
@@ -21,6 +21,20 @@
  "eval_samples_per_second": 104.708,
  "eval_steps_per_second": 1.636,
  "step": 50000
+ },
+ {
+ "epoch": 2.37,
+ "learning_rate": 4.940763961316014e-05,
+ "loss": 1.0237,
+ "step": 100000
+ },
+ {
+ "epoch": 2.37,
+ "eval_loss": 0.9803563356399536,
+ "eval_runtime": 1376.4724,
+ "eval_samples_per_second": 108.974,
+ "eval_steps_per_second": 1.703,
+ "step": 100000
  }
  ],
  "logging_steps": 50000,
@@ -28,7 +42,7 @@
  "num_input_tokens_seen": 0,
  "num_train_epochs": 100,
  "save_steps": 50000,
- "total_flos": 1.04515767631872e+17,
+ "total_flos": 2.09031535263744e+17,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null