Qwen3.5-2B-Math-TogetherAI / trainer_state.json
FormlessAI's picture
Upload folder using huggingface_hub
96dc1e5 verified
Raw
History Blame Contribute Delete
8.46 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": 3.564467668533325,
"learning_rate": 1e-05,
"loss": 1.294921875,
"step": 1
},
{
"epoch": 0.09523809523809523,
"grad_norm": 2.8835957050323486,
"learning_rate": 9.986018985905901e-06,
"loss": 1.15478515625,
"step": 2
},
{
"epoch": 0.14285714285714285,
"grad_norm": 2.4000818729400635,
"learning_rate": 9.944154131125643e-06,
"loss": 1.11669921875,
"step": 3
},
{
"epoch": 0.19047619047619047,
"grad_norm": 1.6106820106506348,
"learning_rate": 9.874639560909118e-06,
"loss": 0.96728515625,
"step": 4
},
{
"epoch": 0.23809523809523808,
"grad_norm": 0.9831730127334595,
"learning_rate": 9.777864028930705e-06,
"loss": 0.7890625,
"step": 5
},
{
"epoch": 0.2857142857142857,
"grad_norm": 0.8111696243286133,
"learning_rate": 9.654368743221022e-06,
"loss": 0.76416015625,
"step": 6
},
{
"epoch": 0.3333333333333333,
"grad_norm": 0.7584248781204224,
"learning_rate": 9.504844339512096e-06,
"loss": 0.753173828125,
"step": 7
},
{
"epoch": 0.38095238095238093,
"grad_norm": 0.6063469648361206,
"learning_rate": 9.330127018922195e-06,
"loss": 0.697265625,
"step": 8
},
{
"epoch": 0.42857142857142855,
"grad_norm": 0.6021122932434082,
"learning_rate": 9.131193871579975e-06,
"loss": 0.692626953125,
"step": 9
},
{
"epoch": 0.47619047619047616,
"grad_norm": 0.45739731192588806,
"learning_rate": 8.90915741234015e-06,
"loss": 0.62939453125,
"step": 10
},
{
"epoch": 0.5238095238095238,
"grad_norm": 0.4716658294200897,
"learning_rate": 8.665259359149132e-06,
"loss": 0.608154296875,
"step": 11
},
{
"epoch": 0.5714285714285714,
"grad_norm": 0.44584110379219055,
"learning_rate": 8.400863688854598e-06,
"loss": 0.612548828125,
"step": 12
},
{
"epoch": 0.6190476190476191,
"grad_norm": 0.4512324631214142,
"learning_rate": 8.117449009293668e-06,
"loss": 0.5791015625,
"step": 13
},
{
"epoch": 0.6666666666666666,
"grad_norm": 0.3347533643245697,
"learning_rate": 7.81660029031811e-06,
"loss": 0.5443115234375,
"step": 14
},
{
"epoch": 0.7142857142857143,
"grad_norm": 0.4175519347190857,
"learning_rate": 7.500000000000001e-06,
"loss": 0.5458984375,
"step": 15
},
{
"epoch": 0.7619047619047619,
"grad_norm": 0.30938720703125,
"learning_rate": 7.169418695587791e-06,
"loss": 0.548095703125,
"step": 16
},
{
"epoch": 0.8095238095238095,
"grad_norm": 0.27624616026878357,
"learning_rate": 6.8267051218319766e-06,
"loss": 0.516357421875,
"step": 17
},
{
"epoch": 0.8571428571428571,
"grad_norm": 0.27667999267578125,
"learning_rate": 6.473775872054522e-06,
"loss": 0.491943359375,
"step": 18
},
{
"epoch": 0.9047619047619048,
"grad_norm": 0.22414721548557281,
"learning_rate": 6.112604669781572e-06,
"loss": 0.48486328125,
"step": 19
},
{
"epoch": 0.9523809523809523,
"grad_norm": 0.17204825580120087,
"learning_rate": 5.745211330880872e-06,
"loss": 0.4989013671875,
"step": 20
},
{
"epoch": 1.0,
"grad_norm": 0.17862312495708466,
"learning_rate": 5.373650467932122e-06,
"loss": 0.4852294921875,
"step": 21
},
{
"epoch": 1.0476190476190477,
"grad_norm": 0.17233222723007202,
"learning_rate": 5e-06,
"loss": 0.4810791015625,
"step": 22
},
{
"epoch": 1.0952380952380953,
"grad_norm": 0.15091440081596375,
"learning_rate": 4.626349532067879e-06,
"loss": 0.4913330078125,
"step": 23
},
{
"epoch": 1.1428571428571428,
"grad_norm": 0.17418180406093597,
"learning_rate": 4.254788669119127e-06,
"loss": 0.4705810546875,
"step": 24
},
{
"epoch": 1.1904761904761905,
"grad_norm": 0.14530283212661743,
"learning_rate": 3.887395330218429e-06,
"loss": 0.48876953125,
"step": 25
},
{
"epoch": 1.2380952380952381,
"grad_norm": 0.11493448913097382,
"learning_rate": 3.526224127945479e-06,
"loss": 0.486083984375,
"step": 26
},
{
"epoch": 1.2857142857142856,
"grad_norm": 0.11849354952573776,
"learning_rate": 3.173294878168025e-06,
"loss": 0.4921875,
"step": 27
},
{
"epoch": 1.3333333333333333,
"grad_norm": 0.12732656300067902,
"learning_rate": 2.83058130441221e-06,
"loss": 0.4814453125,
"step": 28
},
{
"epoch": 1.380952380952381,
"grad_norm": 0.12168189138174057,
"learning_rate": 2.5000000000000015e-06,
"loss": 0.4749755859375,
"step": 29
},
{
"epoch": 1.4285714285714286,
"grad_norm": 0.12903204560279846,
"learning_rate": 2.1833997096818897e-06,
"loss": 0.476318359375,
"step": 30
},
{
"epoch": 1.4761904761904763,
"grad_norm": 0.10554499179124832,
"learning_rate": 1.8825509907063328e-06,
"loss": 0.48193359375,
"step": 31
},
{
"epoch": 1.5238095238095237,
"grad_norm": 0.11661612242460251,
"learning_rate": 1.5991363111454023e-06,
"loss": 0.46728515625,
"step": 32
},
{
"epoch": 1.5714285714285714,
"grad_norm": 0.11701343953609467,
"learning_rate": 1.3347406408508695e-06,
"loss": 0.484375,
"step": 33
},
{
"epoch": 1.619047619047619,
"grad_norm": 0.12012378126382828,
"learning_rate": 1.0908425876598512e-06,
"loss": 0.4693603515625,
"step": 34
},
{
"epoch": 1.6666666666666665,
"grad_norm": 0.10711527615785599,
"learning_rate": 8.688061284200266e-07,
"loss": 0.468017578125,
"step": 35
},
{
"epoch": 1.7142857142857144,
"grad_norm": 0.11778239160776138,
"learning_rate": 6.698729810778065e-07,
"loss": 0.472900390625,
"step": 36
},
{
"epoch": 1.7619047619047619,
"grad_norm": 0.1095920130610466,
"learning_rate": 4.951556604879049e-07,
"loss": 0.4921875,
"step": 37
},
{
"epoch": 1.8095238095238095,
"grad_norm": 0.12085936963558197,
"learning_rate": 3.4563125677897936e-07,
"loss": 0.4647216796875,
"step": 38
},
{
"epoch": 1.8571428571428572,
"grad_norm": 0.12367922812700272,
"learning_rate": 2.2213597106929608e-07,
"loss": 0.44287109375,
"step": 39
},
{
"epoch": 1.9047619047619047,
"grad_norm": 0.11760641634464264,
"learning_rate": 1.253604390908819e-07,
"loss": 0.4493408203125,
"step": 40
},
{
"epoch": 1.9523809523809523,
"grad_norm": 0.10557713359594345,
"learning_rate": 5.584586887435739e-08,
"loss": 0.4727783203125,
"step": 41
},
{
"epoch": 2.0,
"grad_norm": 0.11229511350393295,
"learning_rate": 1.3981014094099354e-08,
"loss": 0.4595947265625,
"step": 42
},
{
"epoch": 2.0,
"eval_loss": 0.46142578125,
"eval_runtime": 11.2858,
"eval_samples_per_second": 0.177,
"eval_steps_per_second": 0.089,
"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": 3.432448487378125e+16,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}