Hugging Face's logo

amburger66
/
robometer-4b-lora-robotsmith-task03

Transformers
Safetensors
qwen3_vl
reward_model
rbm
preference_comparisons
Model card Files
xet
 Community
amburger66 commited on
Commit
aea53cd
·
verified ·
1 Parent(s): 79aea5b

LoRA fine-tune on RobotSmith task03 after fixing dataset

Browse files
Files changed (6) hide show
  1. README.md +2 -2
  2. metrics.json +7 -7
  3. model-00001-of-00002.safetensors +1 -1
  4. model-00002-of-00002.safetensors +1 -1
  5. trainer_state.json +0 -0
  6. training_args.bin +1 -1
README.md CHANGED
@@ -17,8 +17,8 @@ library_name: transformers
17
 
18
  ## Training Run
19
 
20
- - **Wandb Run**: [lora_task03](https://wandb.ai/r-pad/rbm-finetune-robotsmith/runs/jo7kron2)
21
- - **Wandb ID**: `jo7kron2`
22
  - **Project**: rbm-finetune-robotsmith
23
  - **Notes**: fine-tuning Robometer on RobotSmith
24
 
 
17
 
18
  ## Training Run
19
 
20
+ - **Wandb Run**: [lora_task03_data_fixed](https://wandb.ai/r-pad/rbm-finetune-robotsmith/runs/6ihsmc6l)
21
+ - **Wandb ID**: `6ihsmc6l`
22
  - **Project**: rbm-finetune-robotsmith
23
  - **Notes**: fine-tuning Robometer on RobotSmith
24
 
metrics.json CHANGED
@@ -1,11 +1,11 @@
1
  {
2
- "step": 1000,
3
  "metrics": {
4
- "eval_rew_align/success_auprc_robotsmith": 0.5676789606136536,
5
- "eval_rew_align/positive_success_acc_robotsmith": 1.0,
6
- "eval_rew_align/negative_success_acc_robotsmith": 0.8295114656031904,
7
- "eval_rew_align/loss_robotsmith": 3.9487876653671266,
8
- "eval_rew_align/pearson_robotsmith": 0.9754855632280524,
9
- "time/custom_evaluations": 34.202012355439365
10
  }
11
  }
 
1
  {
2
+ "step": 450,
3
  "metrics": {
4
+ "eval_rew_align/success_auprc_robotsmith": 0.5288600712338849,
5
+ "eval_rew_align/positive_success_acc_robotsmith": 0.8125,
6
+ "eval_rew_align/negative_success_acc_robotsmith": 0.9348591549295775,
7
+ "eval_rew_align/loss_robotsmith": 4.137787556648254,
8
+ "eval_rew_align/pearson_robotsmith": 0.9885291064855337,
9
+ "time/custom_evaluations": 83.76057602092624
10
  }
11
  }
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d4ce3fa97d1fb4069d4c2ec431b143427a40533974af5726c8da15d36595e89
3
  size 4996131352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e0e6693e838703cc847e2ba66fcae114c3ca7ba1dbc16d751cd78a06c2c15ee
3
  size 4996131352
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6bed5405c80f8a04adc158b63331a92a53e3eca74389f35b4601f4924e1cb4cc
3
  size 4162297688
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fc0035aebba87eeda73b20ead9bc83508b7b9d9e42dd633796c350d11bfc4fd
3
  size 4162297688
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 sha256:5f814638d07915b697b3e6502936a65277de5b1ad82b95c8a249634cf325f732
3
  size 5841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df32aad17cbfc2aa4ad3381b46f28c1a9815a7ed93ec0e8534171090ad2c781b
3
  size 5841