Hugging Face's logo

ChenDRAG
/
Qwen2.5-1.5B-Open-R1-Distill

Text Generation
Transformers
TensorBoard
Safetensors
qwen2
Generated from Trainer
trl
sft
conversational
text-generation-inference
Model card Files
xet
Metrics Community
1
ChenDRAG commited on
Commit
1735024
·
verified ·
1 Parent(s): 790ffd7

Model save

Browse files
Files changed (7) hide show
  1. README.md +2 -2
  2. all_results.json +7 -6
  3. model.safetensors +1 -1
  4. tokenizer.json +2 -2
  5. train_results.json +7 -6
  6. trainer_state.json +15 -17
  7. training_args.bin +1 -1
README.md CHANGED
@@ -27,14 +27,14 @@ 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/noteam2235/huggingface/runs/4xsgt4nu)
31
 
32
 
33
  This model was trained with SFT.
34
 
35
  ### Framework versions
36
 
37
- - TRL: 0.16.0.dev0
38
  - Transformers: 4.49.0.dev0
39
  - Pytorch: 2.5.1
40
  - Datasets: 3.3.0
 
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/noteam2235/huggingface/runs/0rzfbsdx)
31
 
32
 
33
  This model was trained with SFT.
34
 
35
  ### Framework versions
36
 
37
+ - TRL: 0.14.0
38
  - Transformers: 4.49.0.dev0
39
  - Pytorch: 2.5.1
40
  - Datasets: 3.3.0
all_results.json CHANGED
@@ -1,8 +1,9 @@
1
  {
2
- "total_flos": 1338922500096.0,
3
- "train_loss": 0.8787662982940674,
4
- "train_runtime": 52.0164,
5
- "train_samples": 300,
6
- "train_samples_per_second": 8.44,
7
- "train_steps_per_second": 0.115
 
8
  }
 
1
  {
2
+ "epoch": 1.0,
3
+ "total_flos": 1713227169792.0,
4
+ "train_loss": 0.8339962363243103,
5
+ "train_runtime": 79.6006,
6
+ "train_samples": 512,
7
+ "train_samples_per_second": 6.432,
8
+ "train_steps_per_second": 0.101
9
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d728507d2aa4a648f418b5491e02e84a26af476918a8e9218e9cb369ea3569b
3
  size 3087467144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91e0928e844a28ce46c96756c86abe3dd4866b9e10eeb84b47b40de7ebd7a00e
3
  size 3087467144
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
- size 11421896
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83396048d512ec1f3178af0d7c1f79a226bba041822614b0e26a4fd2d4b55bf7
3
+ size 11421995
train_results.json CHANGED
@@ -1,8 +1,9 @@
1
  {
2
- "total_flos": 1338922500096.0,
3
- "train_loss": 0.8787662982940674,
4
- "train_runtime": 52.0164,
5
- "train_samples": 300,
6
- "train_samples_per_second": 8.44,
7
- "train_steps_per_second": 0.115
 
8
  }
 
1
  {
2
+ "epoch": 1.0,
3
+ "total_flos": 1713227169792.0,
4
+ "train_loss": 0.8339962363243103,
5
+ "train_runtime": 79.6006,
6
+ "train_samples": 512,
7
+ "train_samples_per_second": 6.432,
8
+ "train_steps_per_second": 0.101
9
  }
trainer_state.json CHANGED
@@ -1,34 +1,32 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.8727272727272727,
5
  "eval_steps": 100,
6
- "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.7272727272727273,
13
- "grad_norm": 1.3501643358314308,
14
- "learning_rate": 1.9098300562505266e-06,
15
- "loss": 0.8944,
16
- "mean_token_accuracy": 0.7577449153561558,
17
  "step": 5
18
  },
19
  {
20
- "epoch": 0.8727272727272727,
21
- "mean_token_accuracy": 0.7622872596745417,
22
- "step": 6,
23
- "total_flos": 1338922500096.0,
24
- "train_loss": 0.8787662982940674,
25
- "train_runtime": 52.0164,
26
- "train_samples_per_second": 8.44,
27
- "train_steps_per_second": 0.115
28
  }
29
  ],
30
  "logging_steps": 5,
31
- "max_steps": 6,
32
  "num_input_tokens_seen": 0,
33
  "num_train_epochs": 1,
34
  "save_steps": 500,
@@ -44,7 +42,7 @@
44
  "attributes": {}
45
  }
46
  },
47
- "total_flos": 1338922500096.0,
48
  "train_batch_size": 2,
49
  "trial_name": null,
50
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
  "eval_steps": 100,
6
+ "global_step": 8,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 0.625,
13
+ "grad_norm": 1.2765480627259704,
14
+ "learning_rate": 7.774790660436857e-06,
15
+ "loss": 0.846,
 
16
  "step": 5
17
  },
18
  {
19
+ "epoch": 1.0,
20
+ "step": 8,
21
+ "total_flos": 1713227169792.0,
22
+ "train_loss": 0.8339962363243103,
23
+ "train_runtime": 79.6006,
24
+ "train_samples_per_second": 6.432,
25
+ "train_steps_per_second": 0.101
 
26
  }
27
  ],
28
  "logging_steps": 5,
29
+ "max_steps": 8,
30
  "num_input_tokens_seen": 0,
31
  "num_train_epochs": 1,
32
  "save_steps": 500,
 
42
  "attributes": {}
43
  }
44
  },
45
+ "total_flos": 1713227169792.0,
46
  "train_batch_size": 2,
47
  "trial_name": null,
48
  "trial_params": null
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:deb35b2251125d46ac633df88868293fe4cfef8f450e9b8b8d0d500ffe8c97d6
3
  size 7416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e2b8214a009a973ecaf8845b622ee7cda8a7f25278a76831680805084cf5721
3
  size 7416