Hugging Face's logo

lewtun
/
Qwen2-0.5B-Reward

Text Classification
Transformers
Safetensors
qwen2
trl
reward-trainer
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
lewtun HF staff commited on
Commit
f52a123
•
1 Parent(s): 0d0c7a3

End of training

Browse files
Files changed (5) hide show
  1. README.md +21 -21
  2. all_results.json +5 -5
  3. eval_results.json +5 -5
  4. model.safetensors +1 -1
  5. training_args.bin +1 -1
README.md CHANGED
@@ -20,8 +20,8 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [Qwen/Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct) on an unknown dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.5139
24
- - Accuracy: 0.723
25
 
26
  ## Model description
27
 
@@ -56,25 +56,25 @@ The following hyperparameters were used during training:
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
58
  |:-------------:|:------:|:----:|:---------------:|:--------:|
59
- | 0.6426 | 0.0516 | 50 | 0.6197 | 0.664 |
60
- | 0.5877 | 0.1032 | 100 | 0.6080 | 0.662 |
61
- | 0.5902 | 0.1548 | 150 | 0.5787 | 0.697 |
62
- | 0.5582 | 0.2064 | 200 | 0.5555 | 0.694 |
63
- | 0.5664 | 0.2580 | 250 | 0.5441 | 0.699 |
64
- | 0.5638 | 0.3096 | 300 | 0.5290 | 0.716 |
65
- | 0.5375 | 0.3612 | 350 | 0.5315 | 0.729 |
66
- | 0.5233 | 0.4128 | 400 | 0.5380 | 0.718 |
67
- | 0.5375 | 0.4644 | 450 | 0.5482 | 0.71 |
68
- | 0.5223 | 0.5160 | 500 | 0.5352 | 0.72 |
69
- | 0.5229 | 0.5676 | 550 | 0.5251 | 0.724 |
70
- | 0.5173 | 0.6192 | 600 | 0.5181 | 0.717 |
71
- | 0.5227 | 0.6708 | 650 | 0.5178 | 0.724 |
72
- | 0.5103 | 0.7224 | 700 | 0.5153 | 0.728 |
73
- | 0.5178 | 0.7740 | 750 | 0.5198 | 0.725 |
74
- | 0.5072 | 0.8256 | 800 | 0.5195 | 0.722 |
75
- | 0.5137 | 0.8772 | 850 | 0.5168 | 0.725 |
76
- | 0.4995 | 0.9288 | 900 | 0.5146 | 0.724 |
77
- | 0.4988 | 0.9804 | 950 | 0.5135 | 0.723 |
78
 
79
 
80
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [Qwen/Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct) on an unknown dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.5212
24
+ - Accuracy: 0.731
25
 
26
  ## Model description
27
 
 
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
58
  |:-------------:|:------:|:----:|:---------------:|:--------:|
59
+ | 0.6316 | 0.0516 | 50 | 0.5943 | 0.666 |
60
+ | 0.573 | 0.1032 | 100 | 0.5857 | 0.698 |
61
+ | 0.5809 | 0.1548 | 150 | 0.5718 | 0.705 |
62
+ | 0.5493 | 0.2064 | 200 | 0.5450 | 0.714 |
63
+ | 0.5649 | 0.2580 | 250 | 0.5483 | 0.713 |
64
+ | 0.5585 | 0.3096 | 300 | 0.5265 | 0.734 |
65
+ | 0.5431 | 0.3612 | 350 | 0.5295 | 0.732 |
66
+ | 0.5209 | 0.4128 | 400 | 0.5334 | 0.735 |
67
+ | 0.5414 | 0.4644 | 450 | 0.5409 | 0.726 |
68
+ | 0.525 | 0.5160 | 500 | 0.5387 | 0.731 |
69
+ | 0.5242 | 0.5676 | 550 | 0.5255 | 0.727 |
70
+ | 0.521 | 0.6192 | 600 | 0.5208 | 0.727 |
71
+ | 0.5227 | 0.6708 | 650 | 0.5191 | 0.736 |
72
+ | 0.5132 | 0.7224 | 700 | 0.5186 | 0.728 |
73
+ | 0.5145 | 0.7740 | 750 | 0.5236 | 0.729 |
74
+ | 0.514 | 0.8256 | 800 | 0.5249 | 0.728 |
75
+ | 0.5087 | 0.8772 | 850 | 0.5261 | 0.725 |
76
+ | 0.5009 | 0.9288 | 900 | 0.5229 | 0.727 |
77
+ | 0.4989 | 0.9804 | 950 | 0.5213 | 0.731 |
78
 
79
 
80
  ### Framework versions
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
- "eval_accuracy": 0.723,
4
- "eval_loss": 0.5138623118400574,
5
- "eval_runtime": 2.0077,
6
- "eval_samples_per_second": 498.086,
7
- "eval_steps_per_second": 7.969
8
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "eval_accuracy": 0.731,
4
+ "eval_loss": 0.5211551785469055,
5
+ "eval_runtime": 2.0022,
6
+ "eval_samples_per_second": 499.448,
7
+ "eval_steps_per_second": 7.991
8
  }
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
- "eval_accuracy": 0.723,
4
- "eval_loss": 0.5138623118400574,
5
- "eval_runtime": 2.0077,
6
- "eval_samples_per_second": 498.086,
7
- "eval_steps_per_second": 7.969
8
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "eval_accuracy": 0.731,
4
+ "eval_loss": 0.5211551785469055,
5
+ "eval_runtime": 2.0022,
6
+ "eval_samples_per_second": 499.448,
7
+ "eval_steps_per_second": 7.991
8
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:df0861428ae56d0926aca933d0a8d4aa61d7eb92bb82d044f698df7907cf9f8c
3
  size 1976167144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c29074e3f3ffe048fd0713eabf76871f1620fb1d7a0e4931019ad00667c8fb96
3
  size 1976167144
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b3fbf44a004ce45641fabec53e0923a0949fc045787bc754a16c82fbf95311f
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc26ccf5708848787f97cf4742af6a5285f87008335dbe6ae6598085d277ec2a
3
  size 5240