Feature Extraction
Transformers
Safetensors
sdar
llama-factory
full
Generated from Trainer
custom_code
Instructions to use autoprogrammer/sdar_4b_trace_sft_openr1math with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use autoprogrammer/sdar_4b_trace_sft_openr1math with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="autoprogrammer/sdar_4b_trace_sft_openr1math", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("autoprogrammer/sdar_4b_trace_sft_openr1math", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 369, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0408997955010225, | |
| "grad_norm": 7.998523235321045, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.5733, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.081799591002045, | |
| "grad_norm": 9.153129577636719, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 0.5196, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12269938650306748, | |
| "grad_norm": 8.34139347076416, | |
| "learning_rate": 9.999225623611208e-06, | |
| "loss": 0.5806, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.16359918200409, | |
| "grad_norm": 7.1141204833984375, | |
| "learning_rate": 9.990516643685222e-06, | |
| "loss": 0.4941, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.20449897750511248, | |
| "grad_norm": 8.44301700592041, | |
| "learning_rate": 9.972147627352593e-06, | |
| "loss": 0.6074, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.24539877300613497, | |
| "grad_norm": 6.837522029876709, | |
| "learning_rate": 9.944154131125643e-06, | |
| "loss": 0.6176, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.28629856850715746, | |
| "grad_norm": 6.722048282623291, | |
| "learning_rate": 9.906590341416725e-06, | |
| "loss": 0.6011, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.32719836400818, | |
| "grad_norm": 6.896355152130127, | |
| "learning_rate": 9.859528969650739e-06, | |
| "loss": 0.5717, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.36809815950920244, | |
| "grad_norm": 7.0612945556640625, | |
| "learning_rate": 9.803061111519188e-06, | |
| "loss": 0.5783, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.40899795501022496, | |
| "grad_norm": 6.113592147827148, | |
| "learning_rate": 9.737296070648187e-06, | |
| "loss": 0.6013, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4498977505112474, | |
| "grad_norm": 6.054924488067627, | |
| "learning_rate": 9.66236114702178e-06, | |
| "loss": 0.612, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.49079754601226994, | |
| "grad_norm": 5.854165554046631, | |
| "learning_rate": 9.57840139057007e-06, | |
| "loss": 0.5835, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5316973415132924, | |
| "grad_norm": 6.945219993591309, | |
| "learning_rate": 9.485579320399184e-06, | |
| "loss": 0.5709, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.5725971370143149, | |
| "grad_norm": 6.699445724487305, | |
| "learning_rate": 9.384074610206495e-06, | |
| "loss": 0.6038, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6134969325153374, | |
| "grad_norm": 6.41201114654541, | |
| "learning_rate": 9.274083740490097e-06, | |
| "loss": 0.6221, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.65439672801636, | |
| "grad_norm": 5.748655796051025, | |
| "learning_rate": 9.155819618225707e-06, | |
| "loss": 0.6027, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.6952965235173824, | |
| "grad_norm": 6.205794334411621, | |
| "learning_rate": 9.029511164747175e-06, | |
| "loss": 0.5737, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.7361963190184049, | |
| "grad_norm": 6.745859622955322, | |
| "learning_rate": 8.895402872628352e-06, | |
| "loss": 0.6281, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.7770961145194274, | |
| "grad_norm": 5.8365302085876465, | |
| "learning_rate": 8.753754332424047e-06, | |
| "loss": 0.5721, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.8179959100204499, | |
| "grad_norm": 6.5638532638549805, | |
| "learning_rate": 8.604839730186125e-06, | |
| "loss": 0.6225, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8588957055214724, | |
| "grad_norm": 9.908438682556152, | |
| "learning_rate": 8.448947316727444e-06, | |
| "loss": 0.6062, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.8997955010224948, | |
| "grad_norm": 7.083659648895264, | |
| "learning_rate": 8.286378849660895e-06, | |
| "loss": 0.5851, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.9406952965235174, | |
| "grad_norm": 5.502669811248779, | |
| "learning_rate": 8.117449009293668e-06, | |
| "loss": 0.5388, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.9815950920245399, | |
| "grad_norm": 5.813559055328369, | |
| "learning_rate": 7.942484789507282e-06, | |
| "loss": 0.6135, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.016359918200409, | |
| "grad_norm": 4.387826442718506, | |
| "learning_rate": 7.76182486480253e-06, | |
| "loss": 0.3565, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.0572597137014315, | |
| "grad_norm": 3.389594793319702, | |
| "learning_rate": 7.57581893473448e-06, | |
| "loss": 0.185, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.098159509202454, | |
| "grad_norm": 3.6928842067718506, | |
| "learning_rate": 7.38482704700653e-06, | |
| "loss": 0.1724, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.1390593047034765, | |
| "grad_norm": 4.740786552429199, | |
| "learning_rate": 7.1892189005337494e-06, | |
| "loss": 0.1397, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.179959100204499, | |
| "grad_norm": 6.11871862411499, | |
| "learning_rate": 6.989373129824605e-06, | |
| "loss": 0.1564, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.2208588957055215, | |
| "grad_norm": 4.457100868225098, | |
| "learning_rate": 6.785676572066225e-06, | |
| "loss": 0.1557, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.261758691206544, | |
| "grad_norm": 4.849860191345215, | |
| "learning_rate": 6.5785235183319266e-06, | |
| "loss": 0.142, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.3026584867075663, | |
| "grad_norm": 4.870535373687744, | |
| "learning_rate": 6.368314950360416e-06, | |
| "loss": 0.1623, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.343558282208589, | |
| "grad_norm": 4.23346471786499, | |
| "learning_rate": 6.155457764384001e-06, | |
| "loss": 0.1615, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.3844580777096114, | |
| "grad_norm": 4.38654088973999, | |
| "learning_rate": 5.940363983508257e-06, | |
| "loss": 0.1759, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.425357873210634, | |
| "grad_norm": 4.874055862426758, | |
| "learning_rate": 5.723449960167703e-06, | |
| "loss": 0.1886, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.4662576687116564, | |
| "grad_norm": 4.817355155944824, | |
| "learning_rate": 5.50513557020129e-06, | |
| "loss": 0.165, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.5071574642126788, | |
| "grad_norm": 4.6559953689575195, | |
| "learning_rate": 5.285843400107722e-06, | |
| "loss": 0.1718, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.5480572597137015, | |
| "grad_norm": 4.32926082611084, | |
| "learning_rate": 5.065997929053795e-06, | |
| "loss": 0.1644, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.588957055214724, | |
| "grad_norm": 4.097021102905273, | |
| "learning_rate": 4.846024707219149e-06, | |
| "loss": 0.1648, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.6298568507157465, | |
| "grad_norm": 5.297605037689209, | |
| "learning_rate": 4.626349532067879e-06, | |
| "loss": 0.1847, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.670756646216769, | |
| "grad_norm": 3.8317348957061768, | |
| "learning_rate": 4.407397624141487e-06, | |
| "loss": 0.1595, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 1.7116564417177913, | |
| "grad_norm": 5.160454750061035, | |
| "learning_rate": 4.1895928039685635e-06, | |
| "loss": 0.1692, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.752556237218814, | |
| "grad_norm": 3.6158623695373535, | |
| "learning_rate": 3.973356671684455e-06, | |
| "loss": 0.1531, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 1.7934560327198366, | |
| "grad_norm": 4.5961503982543945, | |
| "learning_rate": 3.7591077909488817e-06, | |
| "loss": 0.1621, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.834355828220859, | |
| "grad_norm": 4.000308036804199, | |
| "learning_rate": 3.54726087874122e-06, | |
| "loss": 0.1456, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.8752556237218814, | |
| "grad_norm": 4.329658031463623, | |
| "learning_rate": 3.3382260026017027e-06, | |
| "loss": 0.1514, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.9161554192229038, | |
| "grad_norm": 4.9972028732299805, | |
| "learning_rate": 3.132407786872442e-06, | |
| "loss": 0.1659, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 1.9570552147239264, | |
| "grad_norm": 4.748896598815918, | |
| "learning_rate": 2.9302046294747498e-06, | |
| "loss": 0.148, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.997955010224949, | |
| "grad_norm": 5.426475524902344, | |
| "learning_rate": 2.7320079307387788e-06, | |
| "loss": 0.1588, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 2.032719836400818, | |
| "grad_norm": 2.0547497272491455, | |
| "learning_rate": 2.538201335778289e-06, | |
| "loss": 0.0437, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.0736196319018405, | |
| "grad_norm": 1.7896406650543213, | |
| "learning_rate": 2.3491599918769854e-06, | |
| "loss": 0.0408, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 2.114519427402863, | |
| "grad_norm": 3.0377840995788574, | |
| "learning_rate": 2.165249822323943e-06, | |
| "loss": 0.0416, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.1554192229038853, | |
| "grad_norm": 2.5748441219329834, | |
| "learning_rate": 1.9868268181037186e-06, | |
| "loss": 0.039, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 2.196319018404908, | |
| "grad_norm": 3.0743508338928223, | |
| "learning_rate": 1.814236348812211e-06, | |
| "loss": 0.0536, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.2372188139059306, | |
| "grad_norm": 2.9512462615966797, | |
| "learning_rate": 1.6478124941321123e-06, | |
| "loss": 0.0385, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 2.278118609406953, | |
| "grad_norm": 3.284522533416748, | |
| "learning_rate": 1.4878773971620076e-06, | |
| "loss": 0.0348, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.3190184049079754, | |
| "grad_norm": 1.6712443828582764, | |
| "learning_rate": 1.3347406408508695e-06, | |
| "loss": 0.0248, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 2.359918200408998, | |
| "grad_norm": 3.1134347915649414, | |
| "learning_rate": 1.1886986487449476e-06, | |
| "loss": 0.0391, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.40081799591002, | |
| "grad_norm": 2.1109068393707275, | |
| "learning_rate": 1.0500341112070605e-06, | |
| "loss": 0.0369, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 2.441717791411043, | |
| "grad_norm": 2.5719072818756104, | |
| "learning_rate": 9.190154382188921e-07, | |
| "loss": 0.035, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.4826175869120655, | |
| "grad_norm": 2.971503496170044, | |
| "learning_rate": 7.958962398255293e-07, | |
| "loss": 0.0312, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 2.523517382413088, | |
| "grad_norm": 3.7453150749206543, | |
| "learning_rate": 6.809148352279182e-07, | |
| "loss": 0.0381, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.5644171779141103, | |
| "grad_norm": 2.350411891937256, | |
| "learning_rate": 5.742937914734853e-07, | |
| "loss": 0.0317, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 2.6053169734151327, | |
| "grad_norm": 2.607921838760376, | |
| "learning_rate": 4.762394926378477e-07, | |
| "loss": 0.0342, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.6462167689161555, | |
| "grad_norm": 2.516187906265259, | |
| "learning_rate": 3.869417403315856e-07, | |
| "loss": 0.0367, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 2.687116564417178, | |
| "grad_norm": 3.3790230751037598, | |
| "learning_rate": 3.065733863053072e-07, | |
| "loss": 0.0321, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.7280163599182004, | |
| "grad_norm": 1.9204952716827393, | |
| "learning_rate": 2.3528999786421758e-07, | |
| "loss": 0.0251, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 2.7689161554192228, | |
| "grad_norm": 2.1479649543762207, | |
| "learning_rate": 1.7322955673980678e-07, | |
| "loss": 0.0351, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.809815950920245, | |
| "grad_norm": 4.126728057861328, | |
| "learning_rate": 1.2051219200156394e-07, | |
| "loss": 0.0439, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 2.850715746421268, | |
| "grad_norm": 2.021738052368164, | |
| "learning_rate": 7.723994752570463e-08, | |
| "loss": 0.0299, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.8916155419222904, | |
| "grad_norm": 3.108388662338257, | |
| "learning_rate": 4.3496584471016125e-08, | |
| "loss": 0.0396, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 2.932515337423313, | |
| "grad_norm": 2.0311710834503174, | |
| "learning_rate": 1.9347419144180035e-08, | |
| "loss": 0.0291, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.9734151329243352, | |
| "grad_norm": 3.245495557785034, | |
| "learning_rate": 4.839196568388049e-09, | |
| "loss": 0.034, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 369, | |
| "total_flos": 1.1649211674300252e+18, | |
| "train_loss": 0.2605089543634637, | |
| "train_runtime": 3793.9194, | |
| "train_samples_per_second": 3.09, | |
| "train_steps_per_second": 0.097 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 369, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1649211674300252e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |