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: 6.9974
-- eval_runtime: 0.0211
-- eval_samples_per_second: 47.457
-- eval_steps_per_second: 47.457
-- epoch: 15.0
-- step: 15
+- eval_loss: 4.0246
+- eval_runtime: 0.0201
+- eval_samples_per_second: 49.72
+- eval_steps_per_second: 49.72
+- epoch: 17.0
+- step: 17
 
 ## 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.1707026005.d77ab3a64c5c.34.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ba3d6e581aab74637b693922b066f79ffe151620bbe2904e337fe6d48bb02b4
-size 10933
+oid sha256:da95de961c5fb3d0a3f1731fe1c2359a0c7bf25b33787bc95384f23fe090c360
+size 11353

logs/events.out.tfevents.1707026588.d77ab3a64c5c.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85d7d859600c3d05c0805bb0af742fd93e2d4b0b623fcfe47c886bb73a46fc60
+size 5126

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f0f5d17dafec3300164ff2ba0d1d63fbe9d86331d49f4e267f4f76e9f82cadf
+oid sha256:5c5c324b6aa17b080b6e2d404e011302113fe31203e74eff5f0ef92d145c737b
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
- "best_metric": 9.170014381408691,
- "best_model_checkpoint": "controlled-food-recipe-generation/checkpoint-14",
- "epoch": 15.0,
+ "best_metric": 6.997350215911865,
+ "best_model_checkpoint": "controlled-food-recipe-generation/checkpoint-15",
+ "epoch": 17.0,
  "eval_steps": 1,
- "global_step": 15,
+ "global_step": 17,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
@@ -217,6 +217,34 @@
  "eval_samples_per_second": 47.457,
  "eval_steps_per_second": 47.457,
  "step": 15
+ },
+ {
+ "epoch": 16.0,
+ "learning_rate": 4.600000000000001e-05,
+ "loss": 5.6621,
+ "step": 16
+ },
+ {
+ "epoch": 16.0,
+ "eval_loss": 4.715316295623779,
+ "eval_runtime": 0.0208,
+ "eval_samples_per_second": 48.084,
+ "eval_steps_per_second": 48.084,
+ "step": 16
+ },
+ {
+ "epoch": 17.0,
+ "learning_rate": 5e-05,
+ "loss": 5.8038,
+ "step": 17
+ },
+ {
+ "epoch": 17.0,
+ "eval_loss": 4.024607181549072,
+ "eval_runtime": 0.0201,
+ "eval_samples_per_second": 49.72,
+ "eval_steps_per_second": 49.72,
+ "step": 17
  }
  ],
  "logging_steps": 1,
@@ -224,7 +252,7 @@
  "num_input_tokens_seen": 0,
  "num_train_epochs": 100,
  "save_steps": 1,
- "total_flos": 8818606080000.0,
+ "total_flos": 9994420224000.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null