Hugging Face's logo

A-Mahla
/
Qwen2.5-VL-3B-Instruct-Agentic-GUI

Image-to-Text
Transformers
Safetensors
qwen2_5_vl
Generated from Trainer
open-r1
vision-language
vlm
trl
sft
text-generation-inference
Model card Files Community
A-Mahla HF Staff commited on
Commit
caa9e55
·
verified ·
1 Parent(s): cba23e4

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/huggingface/smolagents/runs/6le3ndu5)
31
 
32
 
33
  This model was trained with SFT.
 
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/40go7ytp)
31
 
32
 
33
  This model was trained with SFT.
all_results.json CHANGED
@@ -6,8 +6,8 @@
6
  "eval_steps_per_second": 0.38,
7
  "total_flos": 1.2125984924893184e+16,
8
  "train_loss": 0.0,
9
- "train_runtime": 1.4965,
10
  "train_samples": 360252,
11
- "train_samples_per_second": 240725.021,
12
- "train_steps_per_second": 470.422
13
  }
 
6
  "eval_steps_per_second": 0.38,
7
  "total_flos": 1.2125984924893184e+16,
8
  "train_loss": 0.0,
9
+ "train_runtime": 1.6574,
10
  "train_samples": 360252,
11
+ "train_samples_per_second": 217359.421,
12
+ "train_steps_per_second": 424.761
13
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "total_flos": 1.2125984924893184e+16,
3
  "train_loss": 0.0,
4
- "train_runtime": 1.4965,
5
  "train_samples": 360252,
6
- "train_samples_per_second": 240725.021,
7
- "train_steps_per_second": 470.422
8
  }
 
1
  {
2
  "total_flos": 1.2125984924893184e+16,
3
  "train_loss": 0.0,
4
+ "train_runtime": 1.6574,
5
  "train_samples": 360252,
6
+ "train_samples_per_second": 217359.421,
7
+ "train_steps_per_second": 424.761
8
  }
trainer_state.json CHANGED
@@ -1344,9 +1344,9 @@
1344
  "step": 704,
1345
  "total_flos": 1.2125984924893184e+16,
1346
  "train_loss": 0.0,
1347
- "train_runtime": 1.4965,
1348
- "train_samples_per_second": 240725.021,
1349
- "train_steps_per_second": 470.422
1350
  }
1351
  ],
1352
  "logging_steps": 5,
 
1344
  "step": 704,
1345
  "total_flos": 1.2125984924893184e+16,
1346
  "train_loss": 0.0,
1347
+ "train_runtime": 1.6574,
1348
+ "train_samples_per_second": 217359.421,
1349
+ "train_steps_per_second": 424.761
1350
  }
1351
  ],
1352
  "logging_steps": 5,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9200a5447fbc68c080f36c064447506ad8c2651fb30799814fe17b6d621ddb08
3
  size 7416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4f376cceaf26232285fa3b02a9d163b52905e043f1c9d632aa5e7c812cbedf5
3
  size 7416