Instructions to use FormlessAI/Qwen3.5-0.8B-Code-TogetherAI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use FormlessAI/Qwen3.5-0.8B-Code-TogetherAI with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("togethercomputer/Qwen3.5-0.8B") model = PeftModel.from_pretrained(base_model, "FormlessAI/Qwen3.5-0.8B-Code-TogetherAI") - Notebooks
- Google Colab
- Kaggle
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 42, | |
| "global_step": 42, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.047619047619047616, | |
| "grad_norm": 11.711328506469727, | |
| "learning_rate": 1e-05, | |
| "loss": 1.435546875, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.09523809523809523, | |
| "grad_norm": 9.186811447143555, | |
| "learning_rate": 9.986018985905901e-06, | |
| "loss": 1.21875, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.14285714285714285, | |
| "grad_norm": 6.505200386047363, | |
| "learning_rate": 9.944154131125643e-06, | |
| "loss": 1.077880859375, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.19047619047619047, | |
| "grad_norm": 3.609107255935669, | |
| "learning_rate": 9.874639560909118e-06, | |
| "loss": 0.925048828125, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.23809523809523808, | |
| "grad_norm": 2.2253434658050537, | |
| "learning_rate": 9.777864028930705e-06, | |
| "loss": 0.8056640625, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 1.6206773519515991, | |
| "learning_rate": 9.654368743221022e-06, | |
| "loss": 0.7550048828125, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 1.2944828271865845, | |
| "learning_rate": 9.504844339512096e-06, | |
| "loss": 0.7470703125, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "grad_norm": 1.212505578994751, | |
| "learning_rate": 9.330127018922195e-06, | |
| "loss": 0.74267578125, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.42857142857142855, | |
| "grad_norm": 1.0636065006256104, | |
| "learning_rate": 9.131193871579975e-06, | |
| "loss": 0.72100830078125, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.47619047619047616, | |
| "grad_norm": 0.8706919550895691, | |
| "learning_rate": 8.90915741234015e-06, | |
| "loss": 0.65545654296875, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5238095238095238, | |
| "grad_norm": 0.7248157262802124, | |
| "learning_rate": 8.665259359149132e-06, | |
| "loss": 0.694580078125, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 0.6671891808509827, | |
| "learning_rate": 8.400863688854598e-06, | |
| "loss": 0.6015625, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.6190476190476191, | |
| "grad_norm": 0.5413753390312195, | |
| "learning_rate": 8.117449009293668e-06, | |
| "loss": 0.6578369140625, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 0.4379308521747589, | |
| "learning_rate": 7.81660029031811e-06, | |
| "loss": 0.6123046875, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 0.425498902797699, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 0.616943359375, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.7619047619047619, | |
| "grad_norm": 0.35449525713920593, | |
| "learning_rate": 7.169418695587791e-06, | |
| "loss": 0.64208984375, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.8095238095238095, | |
| "grad_norm": 0.35049211978912354, | |
| "learning_rate": 6.8267051218319766e-06, | |
| "loss": 0.64404296875, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 0.39211469888687134, | |
| "learning_rate": 6.473775872054522e-06, | |
| "loss": 0.611572265625, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.9047619047619048, | |
| "grad_norm": 0.3265855610370636, | |
| "learning_rate": 6.112604669781572e-06, | |
| "loss": 0.5914306640625, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.9523809523809523, | |
| "grad_norm": 0.24601729214191437, | |
| "learning_rate": 5.745211330880872e-06, | |
| "loss": 0.5931396484375, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.2900349795818329, | |
| "learning_rate": 5.373650467932122e-06, | |
| "loss": 0.6011962890625, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.0476190476190477, | |
| "grad_norm": 0.29191672801971436, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5892333984375, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.0952380952380953, | |
| "grad_norm": 0.2348019927740097, | |
| "learning_rate": 4.626349532067879e-06, | |
| "loss": 0.5809326171875, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 0.32889172434806824, | |
| "learning_rate": 4.254788669119127e-06, | |
| "loss": 0.5633544921875, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.1904761904761905, | |
| "grad_norm": 0.24565577507019043, | |
| "learning_rate": 3.887395330218429e-06, | |
| "loss": 0.60107421875, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.2380952380952381, | |
| "grad_norm": 0.21797123551368713, | |
| "learning_rate": 3.526224127945479e-06, | |
| "loss": 0.5947265625, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.2857142857142856, | |
| "grad_norm": 0.20814970135688782, | |
| "learning_rate": 3.173294878168025e-06, | |
| "loss": 0.584716796875, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 0.21900132298469543, | |
| "learning_rate": 2.83058130441221e-06, | |
| "loss": 0.59588623046875, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.380952380952381, | |
| "grad_norm": 0.22003313899040222, | |
| "learning_rate": 2.5000000000000015e-06, | |
| "loss": 0.6072998046875, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.4285714285714286, | |
| "grad_norm": 0.25176453590393066, | |
| "learning_rate": 2.1833997096818897e-06, | |
| "loss": 0.60723876953125, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.4761904761904763, | |
| "grad_norm": 0.21191780269145966, | |
| "learning_rate": 1.8825509907063328e-06, | |
| "loss": 0.5780029296875, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.5238095238095237, | |
| "grad_norm": 0.21442794799804688, | |
| "learning_rate": 1.5991363111454023e-06, | |
| "loss": 0.621826171875, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.5714285714285714, | |
| "grad_norm": 0.216970294713974, | |
| "learning_rate": 1.3347406408508695e-06, | |
| "loss": 0.54669189453125, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.619047619047619, | |
| "grad_norm": 0.2490191012620926, | |
| "learning_rate": 1.0908425876598512e-06, | |
| "loss": 0.5963134765625, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.6666666666666665, | |
| "grad_norm": 0.20802119374275208, | |
| "learning_rate": 8.688061284200266e-07, | |
| "loss": 0.5670166015625, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "grad_norm": 0.24264661967754364, | |
| "learning_rate": 6.698729810778065e-07, | |
| "loss": 0.571044921875, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.7619047619047619, | |
| "grad_norm": 0.2163696587085724, | |
| "learning_rate": 4.951556604879049e-07, | |
| "loss": 0.606689453125, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.8095238095238095, | |
| "grad_norm": 0.2215702384710312, | |
| "learning_rate": 3.4563125677897936e-07, | |
| "loss": 0.6102294921875, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.8571428571428572, | |
| "grad_norm": 0.2684735953807831, | |
| "learning_rate": 2.2213597106929608e-07, | |
| "loss": 0.5771484375, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.9047619047619047, | |
| "grad_norm": 0.23904995620250702, | |
| "learning_rate": 1.253604390908819e-07, | |
| "loss": 0.565185546875, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.9523809523809523, | |
| "grad_norm": 0.1847783923149109, | |
| "learning_rate": 5.584586887435739e-08, | |
| "loss": 0.57537841796875, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.2181282937526703, | |
| "learning_rate": 1.3981014094099354e-08, | |
| "loss": 0.5804443359375, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.578125, | |
| "eval_runtime": 10.3842, | |
| "eval_samples_per_second": 0.096, | |
| "eval_steps_per_second": 0.096, | |
| "step": 42 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 42, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 0, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.4450348882132992e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |