Hugging Face's logo

sucharush
/
camel_qwen_sft

Text Generation
Transformers
Safetensors
qwen3
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
sucharush commited on
Commit
28e2dd3
·
verified ·
1 Parent(s): bffdfe6

sucharush/camel_qwen_sft_big

Browse files
Files changed (5) hide show
  1. README.md +11 -9
  2. config.json +1 -1
  3. model.safetensors +1 -1
  4. tokenizer.json +2 -2
  5. training_args.bin +1 -1
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [Qwen/Qwen3-0.6B-Base](https://huggingface.co/Qwen/Qwen3-0.6B-Base) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.5060
20
 
21
  ## Model description
22
 
@@ -39,8 +39,8 @@ The following hyperparameters were used during training:
39
  - train_batch_size: 4
40
  - eval_batch_size: 2
41
  - seed: 42
42
- - gradient_accumulation_steps: 4
43
- - total_train_batch_size: 16
44
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 100
@@ -50,12 +50,14 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:------:|:----:|:---------------:|
53
- | 0.5411 | 0.1616 | 500 | 0.5226 |
54
- | 0.5331 | 0.3232 | 1000 | 0.5140 |
55
- | 0.5182 | 0.4848 | 1500 | 0.5095 |
56
- | 0.5193 | 0.6465 | 2000 | 0.5072 |
57
- | 0.5034 | 0.8081 | 2500 | 0.5062 |
58
- | 0.5079 | 0.9697 | 3000 | 0.5060 |
 
 
59
 
60
 
61
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [Qwen/Qwen3-0.6B-Base](https://huggingface.co/Qwen/Qwen3-0.6B-Base) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.5013
20
 
21
  ## Model description
22
 
 
39
  - train_batch_size: 4
40
  - eval_batch_size: 2
41
  - seed: 42
42
+ - gradient_accumulation_steps: 6
43
+ - total_train_batch_size: 24
44
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 100
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:------:|:----:|:---------------:|
53
+ | 0.5374 | 0.1212 | 500 | 0.5227 |
54
+ | 0.5229 | 0.2424 | 1000 | 0.5129 |
55
+ | 0.5135 | 0.3636 | 1500 | 0.5077 |
56
+ | 0.5113 | 0.4848 | 2000 | 0.5045 |
57
+ | 0.51 | 0.6061 | 2500 | 0.5027 |
58
+ | 0.5119 | 0.7273 | 3000 | 0.5017 |
59
+ | 0.5069 | 0.8485 | 3500 | 0.5014 |
60
+ | 0.508 | 0.9697 | 4000 | 0.5013 |
61
 
62
 
63
  ### Framework versions
config.json CHANGED
@@ -24,7 +24,7 @@
24
  "tie_word_embeddings": true,
25
  "torch_dtype": "bfloat16",
26
  "transformers_version": "4.51.3",
27
- "use_cache": true,
28
  "use_sliding_window": false,
29
  "vocab_size": 151936
30
  }
 
24
  "tie_word_embeddings": true,
25
  "torch_dtype": "bfloat16",
26
  "transformers_version": "4.51.3",
27
+ "use_cache": false,
28
  "use_sliding_window": false,
29
  "vocab_size": 151936
30
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b924b913ac41ff8ed975d3f525587efceae944a9988ef72996faa99180c2d36
3
  size 1192135096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5065157b287e9f868e108bf9056d9ea61ee6f6aff35d2a2dcf8a59a760f7e587
3
  size 1192135096
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae1a036a9837df9caeebb840d09d80e8feef0f6d2bae982970d1ad34f5946aff
3
- size 11422753
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd2cd2a9bc5c9f88974cfd47d915aac319d6590ce29708c2879f2054c92bf383
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f60b83c1bc76bdef9217e9fd62862d94c1a3f50aaa3e119c9541e1b4729fd6c3
3
  size 5240