Hugging Face's logo

smolagents
/
SmolVLM2-2.2B-Instruct-Agentic-GUI

Any-to-Any
Transformers
Safetensors
smolvlm
Generated from Trainer
open-r1
vision-language
vlm
Model card Files
xet
Community
1
[email protected] commited on
Commit
32624be
·
1 Parent(s): e7129dd

PUSH last checkpoint

Browse files
Files changed (7) hide show
  1. README.md +3 -6
  2. all_results.json +11 -11
  3. eval_results.json +5 -5
  4. model.safetensors +1 -1
  5. train_results.json +6 -6
  6. trainer_state.json +0 -0
  7. training_args.bin +2 -2
README.md CHANGED
@@ -1,18 +1,15 @@
1
  ---
2
  datasets: smolagents/aguvis-stage-2
3
  library_name: transformers
4
- model_name: SmolVLM2-2.2B-Instruct-Agentic-GUI
5
  tags:
6
  - generated_from_trainer
7
  - open-r1
8
  - vision-language
9
  - vlm
10
- - trl
11
- - sft
12
  licence: license
13
  ---
14
 
15
- # Model Card for SmolVLM2-2.2B-Instruct-Agentic-GUI
16
 
17
  This model is a fine-tuned version of [None](https://huggingface.co/None) on the [smolagents/aguvis-stage-2](https://huggingface.co/datasets/smolagents/aguvis-stage-2) dataset.
18
  It has been trained using [TRL](https://github.com/huggingface/trl).
@@ -23,14 +20,14 @@ It has been trained using [TRL](https://github.com/huggingface/trl).
23
  from transformers import pipeline
24
 
25
  question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
26
- generator = pipeline("text-generation", model="smolagents/SmolVLM2-2.2B-Instruct-Agentic-GUI", device="cuda")
27
  output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
28
  print(output["generated_text"])
29
  ```
30
 
31
  ## Training procedure
32
 
33
- [<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/huggingface/smolagents/runs/fafnjj0e)
34
 
35
 
36
  This model was trained with SFT.
 
1
  ---
2
  datasets: smolagents/aguvis-stage-2
3
  library_name: transformers
 
4
  tags:
5
  - generated_from_trainer
6
  - open-r1
7
  - vision-language
8
  - vlm
 
 
9
  licence: license
10
  ---
11
 
12
+ # Model Card for None
13
 
14
  This model is a fine-tuned version of [None](https://huggingface.co/None) on the [smolagents/aguvis-stage-2](https://huggingface.co/datasets/smolagents/aguvis-stage-2) dataset.
15
  It has been trained using [TRL](https://github.com/huggingface/trl).
 
20
  from transformers import pipeline
21
 
22
  question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
23
+ generator = pipeline("text-generation", model="None", device="cuda")
24
  output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
25
  print(output["generated_text"])
26
  ```
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/huggingface/smolagents/runs/9jig6y4c)
31
 
32
 
33
  This model was trained with SFT.
all_results.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
- "eval_loss": 0.6482115983963013,
3
- "eval_runtime": 149.9453,
4
- "eval_samples": 3639,
5
- "eval_samples_per_second": 24.269,
6
- "eval_steps_per_second": 0.76,
7
- "total_flos": 1.0314062938243072e+16,
8
- "train_loss": 0.7184352108531378,
9
- "train_runtime": 49977.4428,
10
- "train_samples": 360255,
11
- "train_samples_per_second": 14.417,
12
- "train_steps_per_second": 0.028
13
  }
 
1
  {
2
+ "eval_loss": 0.4539664685726166,
3
+ "eval_runtime": 141.8302,
4
+ "eval_samples": 3638,
5
+ "eval_samples_per_second": 25.65,
6
+ "eval_steps_per_second": 0.804,
7
+ "total_flos": 9795365997903872.0,
8
+ "train_loss": 0.5166227378120477,
9
+ "train_runtime": 48333.5779,
10
+ "train_samples": 360073,
11
+ "train_samples_per_second": 14.899,
12
+ "train_steps_per_second": 0.029
13
  }
eval_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "eval_loss": 0.6482115983963013,
3
- "eval_runtime": 149.9453,
4
- "eval_samples": 3639,
5
- "eval_samples_per_second": 24.269,
6
- "eval_steps_per_second": 0.76
7
  }
 
1
  {
2
+ "eval_loss": 0.4539664685726166,
3
+ "eval_runtime": 141.8302,
4
+ "eval_samples": 3638,
5
+ "eval_samples_per_second": 25.65,
6
+ "eval_steps_per_second": 0.804
7
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a0cc2775f67a58f2f49f72ee3cda5e75dcec41726d4248ab1590904f3957bac8
3
  size 4493654912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f35a1d63b330152bc12ccb0685c77ca95a832992639eff97e5ec51473d249d5
3
  size 4493654912
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "total_flos": 1.0314062938243072e+16,
3
- "train_loss": 0.7184352108531378,
4
- "train_runtime": 49977.4428,
5
- "train_samples": 360255,
6
- "train_samples_per_second": 14.417,
7
- "train_steps_per_second": 0.028
8
  }
 
1
  {
2
+ "total_flos": 9795365997903872.0,
3
+ "train_loss": 0.5166227378120477,
4
+ "train_runtime": 48333.5779,
5
+ "train_samples": 360073,
6
+ "train_samples_per_second": 14.899,
7
+ "train_steps_per_second": 0.029
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:a8a6aaab234537ac22f6e654d93a1438177e55229767e5163fa09044f87b23b7
3
- size 7544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11aab7e60c1e4b330194483ff537da7366acadb2c5dceb7c17da2174c696abd3
3
+ size 7608