Hugging Face's logo

Alqayed2024
/
gpt2-cpt-dutch

Text Generation
Transformers
Safetensors
gpt2
Generated from Trainer
alignment-handbook
trl
sft
text-generation-inference
Inference Endpoints
Model card Files Community
Alqayed2024 commited on
Commit
11474d9
•
1 Parent(s): 8ee8fba

Model save

Browse files
Files changed (5) hide show
  1. README.md +1 -1
  2. all_results.json +3 -3
  3. train_results.json +3 -3
  4. trainer_state.json +3 -3
  5. training_args.bin +1 -1
README.md CHANGED
@@ -27,7 +27,7 @@ print(output["generated_text"])
27
 
28
  ## Training procedure
29
 
30
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/ahmed-alhammadi-technology-innovation-institute/huggingface/runs/m9rtyo80)
31
 
32
  This model was trained with SFT.
33
 
 
27
 
28
  ## Training procedure
29
 
30
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/ahmed-alhammadi-technology-innovation-institute/huggingface/runs/kuloss31)
31
 
32
  This model was trained with SFT.
33
 
all_results.json CHANGED
@@ -2,8 +2,8 @@
2
  "epoch": 1.0,
3
  "total_flos": 2783887138750464.0,
4
  "train_loss": 0.0,
5
- "train_runtime": 2.4947,
6
  "train_samples": 12593,
7
- "train_samples_per_second": 4258.631,
8
- "train_steps_per_second": 66.541
9
  }
 
2
  "epoch": 1.0,
3
  "total_flos": 2783887138750464.0,
4
  "train_loss": 0.0,
5
+ "train_runtime": 3.0865,
6
  "train_samples": 12593,
7
+ "train_samples_per_second": 3442.1,
8
+ "train_steps_per_second": 53.783
9
  }
train_results.json CHANGED
@@ -2,8 +2,8 @@
2
  "epoch": 1.0,
3
  "total_flos": 2783887138750464.0,
4
  "train_loss": 0.0,
5
- "train_runtime": 2.4947,
6
  "train_samples": 12593,
7
- "train_samples_per_second": 4258.631,
8
- "train_steps_per_second": 66.541
9
  }
 
2
  "epoch": 1.0,
3
  "total_flos": 2783887138750464.0,
4
  "train_loss": 0.0,
5
+ "train_runtime": 3.0865,
6
  "train_samples": 12593,
7
+ "train_samples_per_second": 3442.1,
8
+ "train_steps_per_second": 53.783
9
  }
trainer_state.json CHANGED
@@ -251,9 +251,9 @@
251
  "step": 166,
252
  "total_flos": 2783887138750464.0,
253
  "train_loss": 0.0,
254
- "train_runtime": 2.4947,
255
- "train_samples_per_second": 4258.631,
256
- "train_steps_per_second": 66.541
257
  }
258
  ],
259
  "logging_steps": 5,
 
251
  "step": 166,
252
  "total_flos": 2783887138750464.0,
253
  "train_loss": 0.0,
254
+ "train_runtime": 3.0865,
255
+ "train_samples_per_second": 3442.1,
256
+ "train_steps_per_second": 53.783
257
  }
258
  ],
259
  "logging_steps": 5,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27a1c4496a36f2593baa01bee487602817a25dc954a948b3d926e503aaa72419
3
  size 5752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a2ac786c119edcf71e838842bade47846fc52ca8fe529429a15dee2f8e02ad9
3
  size 5752