Hugging Face's logo

KotshinZ
/
gpt2-RMT-2

Transformers
PyTorch
Safetensors
rmt_gpt2
Generated from Trainer
open-r1
trl
sft
Model card Files
xet
Community
KotshinZ commited on
Commit
65048b8
·
verified ·
1 Parent(s): ae820d4

Model save

Browse files
Files changed (6) hide show
  1. README.md +2 -4
  2. all_results.json +4 -4
  3. model.safetensors +1 -1
  4. train_results.json +4 -4
  5. trainer_state.json +0 -0
  6. training_args.bin +1 -1
README.md CHANGED
@@ -1,17 +1,15 @@
1
  ---
2
  base_model: openai-community/gpt2
3
- datasets: HuggingFaceH4/Bespoke-Stratos-17k
4
  library_name: transformers
5
  model_name: gpt2-RMT-2
6
  tags:
7
  - generated_from_trainer
8
- - open-r1
9
  licence: license
10
  ---
11
 
12
  # Model Card for gpt2-RMT-2
13
 
14
- This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on the [HuggingFaceH4/Bespoke-Stratos-17k](https://huggingface.co/datasets/HuggingFaceH4/Bespoke-Stratos-17k) dataset.
15
  It has been trained using [TRL](https://github.com/huggingface/trl).
16
 
17
  ## Quick start
@@ -27,7 +25,7 @@ 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/s18574s18574-/huggingface/runs/ov7s46ya)
31
 
32
 
33
  This model was trained with SFT.
 
1
  ---
2
  base_model: openai-community/gpt2
 
3
  library_name: transformers
4
  model_name: gpt2-RMT-2
5
  tags:
6
  - generated_from_trainer
 
7
  licence: license
8
  ---
9
 
10
  # Model Card for gpt2-RMT-2
11
 
12
+ This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2).
13
  It has been trained using [TRL](https://github.com/huggingface/trl).
14
 
15
  ## Quick start
 
25
 
26
  ## Training procedure
27
 
28
+ [<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/s18574s18574-/huggingface/runs/6c36vz5o)
29
 
30
 
31
  This model was trained with SFT.
all_results.json CHANGED
@@ -4,9 +4,9 @@
4
  "eval_samples_per_second": 263.957,
5
  "eval_steps_per_second": 66.17,
6
  "total_flos": 0.0,
7
- "train_loss": 2.8374191810344827,
8
- "train_runtime": 8.8944,
9
  "train_samples": 16610,
10
- "train_samples_per_second": 103.136,
11
- "train_steps_per_second": 6.521
12
  }
 
4
  "eval_samples_per_second": 263.957,
5
  "eval_steps_per_second": 66.17,
6
  "total_flos": 0.0,
7
+ "train_loss": 2.0137617991367285,
8
+ "train_runtime": 996.2065,
9
  "train_samples": 16610,
10
+ "train_samples_per_second": 92.083,
11
+ "train_steps_per_second": 5.756
12
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69f688ffe91216be05cfd64b0ce40b518c8f32580576fa7393b2e094b090329c
3
  size 326110968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:992d4bcdb3356997a0a168440f993d5c27b000e48ba6ea568caf99b214bf322f
3
  size 326110968
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "total_flos": 0.0,
3
- "train_loss": 2.8374191810344827,
4
- "train_runtime": 8.8944,
5
  "train_samples": 16610,
6
- "train_samples_per_second": 103.136,
7
- "train_steps_per_second": 6.521
8
  }
 
1
  {
2
  "total_flos": 0.0,
3
+ "train_loss": 2.0137617991367285,
4
+ "train_runtime": 996.2065,
5
  "train_samples": 16610,
6
+ "train_samples_per_second": 92.083,
7
+ "train_steps_per_second": 5.756
8
  }
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f5848278ac435ff22cb803cb15c110d68ebe13c30adcb298632fdfa7845ac04
3
  size 7352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdef709c27929e8ae9c8e3a5424f8df2c8a0dc367fd631551cc0f01060414d18
3
  size 7352