Qwen3.5-0.8B-Code-TogetherAI / trainer_state.json
FormlessAI's picture
Upload folder using huggingface_hub
94f5584 verified
Raw
History Blame Contribute Delete
8.47 kB
{
"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
}