Hugging Face's logo

guangyangnlp
/
Qwen3-1.7B-SFT-science-2e-5

Text Generation
Transformers
Safetensors
qwen3
llama-factory
full
Generated from Trainer
text-generation-inference
Model card Files
xet
 Community
guangyangnlp commited on
Commit
e04c93f
·
verified ·
1 Parent(s): 0f027ba

Upload folder using huggingface_hub

Browse files
Files changed (11) hide show
  1. .gitattributes +1 -0
  2. README.md +72 -0
  3. all_results.json +12 -0
  4. config.json +63 -0
  5. eval_results.json +7 -0
  6. generation_config.json +12 -0
  7. model.safetensors +3 -0
  8. tokenizer.json +3 -0
  9. tokenizer_config.json +30 -0
  10. train_results.json +8 -0
  11. trainer_state.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: other
4
+ base_model: Qwen/Qwen3-1.7B
5
+ tags:
6
+ - llama-factory
7
+ - full
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: Qwen3-1.7B-SFT-science-2e-5
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # Qwen3-1.7B-SFT-science-2e-5
18
+
19
+ This model is a fine-tuned version of [Qwen/Qwen3-1.7B](https://huggingface.co/Qwen/Qwen3-1.7B) on the dolci_science_train dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.7464
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 2e-05
41
+ - train_batch_size: 2
42
+ - eval_batch_size: 4
43
+ - seed: 42
44
+ - gradient_accumulation_steps: 64
45
+ - total_train_batch_size: 128
46
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
+ - lr_scheduler_type: cosine
48
+ - lr_scheduler_warmup_steps: 0.05
49
+ - num_epochs: 3.0
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss |
54
+ |:-------------:|:------:|:----:|:---------------:|
55
+ | 0.9187 | 0.2985 | 230 | 0.8187 |
56
+ | 0.7641 | 0.5970 | 460 | 0.7886 |
57
+ | 0.7856 | 0.8954 | 690 | 0.7687 |
58
+ | 0.6880 | 1.1934 | 920 | 0.7622 |
59
+ | 0.7079 | 1.4918 | 1150 | 0.7541 |
60
+ | 0.7302 | 1.7903 | 1380 | 0.7464 |
61
+ | 0.6540 | 2.0882 | 1610 | 0.7521 |
62
+ | 0.6004 | 2.3867 | 1840 | 0.7504 |
63
+ | 0.6712 | 2.6852 | 2070 | 0.7492 |
64
+ | 0.6775 | 2.9837 | 2300 | 0.7490 |
65
+
66
+
67
+ ### Framework versions
68
+
69
+ - Transformers 5.0.0
70
+ - Pytorch 2.10.0+cu128
71
+ - Datasets 4.0.0
72
+ - Tokenizers 0.22.2
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 0.7464115023612976,
4
+ "eval_runtime": 140.9584,
5
+ "eval_samples_per_second": 36.834,
6
+ "eval_steps_per_second": 9.208,
7
+ "total_flos": 4.1917370482093916e+18,
8
+ "train_loss": 0.06833103949818527,
9
+ "train_runtime": 3477.4713,
10
+ "train_samples_per_second": 85.09,
11
+ "train_steps_per_second": 0.665
12
+ }
config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": null,
8
+ "dtype": "float32",
9
+ "eos_token_id": 151645,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2048,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 6144,
15
+ "layer_types": [
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention"
44
+ ],
45
+ "max_position_embeddings": 40960,
46
+ "max_window_layers": 28,
47
+ "model_type": "qwen3",
48
+ "num_attention_heads": 16,
49
+ "num_hidden_layers": 28,
50
+ "num_key_value_heads": 8,
51
+ "pad_token_id": 151643,
52
+ "rms_norm_eps": 1e-06,
53
+ "rope_parameters": {
54
+ "rope_theta": 1000000,
55
+ "rope_type": "default"
56
+ },
57
+ "sliding_window": null,
58
+ "tie_word_embeddings": true,
59
+ "transformers_version": "5.0.0",
60
+ "use_cache": false,
61
+ "use_sliding_window": false,
62
+ "vocab_size": 151936
63
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 0.7464115023612976,
4
+ "eval_runtime": 140.9584,
5
+ "eval_samples_per_second": 36.834,
6
+ "eval_steps_per_second": 9.208
7
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": true,
3
+ "eos_token_id": [
4
+ 151645,
5
+ 151643
6
+ ],
7
+ "pad_token_id": 151643,
8
+ "temperature": 0.6,
9
+ "top_k": 20,
10
+ "top_p": 0.95,
11
+ "transformers_version": "5.0.0"
12
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ae44870991a1706b5c32f64c6600f383f4d86ebd856e6381ac26cef7df9bc86
3
+ size 8126995136
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
3
+ size 11422650
tokenizer_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [
9
+ "<|im_start|>",
10
+ "<|im_end|>",
11
+ "<|object_ref_start|>",
12
+ "<|object_ref_end|>",
13
+ "<|box_start|>",
14
+ "<|box_end|>",
15
+ "<|quad_start|>",
16
+ "<|quad_end|>",
17
+ "<|vision_start|>",
18
+ "<|vision_end|>",
19
+ "<|vision_pad|>",
20
+ "<|image_pad|>",
21
+ "<|video_pad|>"
22
+ ],
23
+ "is_local": false,
24
+ "model_max_length": 131072,
25
+ "pad_token": "<|endoftext|>",
26
+ "padding_side": "right",
27
+ "split_special_tokens": false,
28
+ "tokenizer_class": "Qwen2Tokenizer",
29
+ "unk_token": null
30
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 4.1917370482093916e+18,
4
+ "train_loss": 0.06833103949818527,
5
+ "train_runtime": 3477.4713,
6
+ "train_samples_per_second": 85.09,
7
+ "train_steps_per_second": 0.665
8
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff