try_multi_gpu / trainer_state.json
bimabk's picture
Upload task output 0fe99f84-0038-4cec-8e61-1eb9fea8dc55
5bdd688 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 210,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.023809523809523808,
"grad_norm": 23.0,
"learning_rate": 4.20004080527265e-07,
"loss": 0.3575,
"step": 5
},
{
"epoch": 0.047619047619047616,
"grad_norm": 17.625,
"learning_rate": 9.450091811863462e-07,
"loss": 0.3096,
"step": 10
},
{
"epoch": 0.07142857142857142,
"grad_norm": 11.9375,
"learning_rate": 1.4700142818454278e-06,
"loss": 0.2658,
"step": 15
},
{
"epoch": 0.09523809523809523,
"grad_norm": 10.625,
"learning_rate": 1.9950193825045087e-06,
"loss": 0.1987,
"step": 20
},
{
"epoch": 0.11904761904761904,
"grad_norm": 13.375,
"learning_rate": 2.52002448316359e-06,
"loss": 0.204,
"step": 25
},
{
"epoch": 0.14285714285714285,
"grad_norm": 12.875,
"learning_rate": 3.0450295838226718e-06,
"loss": 0.1673,
"step": 30
},
{
"epoch": 0.16666666666666666,
"grad_norm": 10.75,
"learning_rate": 3.5700346844817527e-06,
"loss": 0.1856,
"step": 35
},
{
"epoch": 0.19047619047619047,
"grad_norm": 11.5,
"learning_rate": 3.674728355129646e-06,
"loss": 0.1819,
"step": 40
},
{
"epoch": 0.21428571428571427,
"grad_norm": 11.4375,
"learning_rate": 3.673479982799582e-06,
"loss": 0.1577,
"step": 45
},
{
"epoch": 0.23809523809523808,
"grad_norm": 9.0,
"learning_rate": 3.671272247622192e-06,
"loss": 0.1598,
"step": 50
},
{
"epoch": 0.2619047619047619,
"grad_norm": 9.75,
"learning_rate": 3.668106688204025e-06,
"loss": 0.1579,
"step": 55
},
{
"epoch": 0.2857142857142857,
"grad_norm": 9.625,
"learning_rate": 3.6639855106749177e-06,
"loss": 0.1868,
"step": 60
},
{
"epoch": 0.30952380952380953,
"grad_norm": 9.5,
"learning_rate": 3.6589115871505097e-06,
"loss": 0.1898,
"step": 65
},
{
"epoch": 0.3333333333333333,
"grad_norm": 12.6875,
"learning_rate": 3.65288845373062e-06,
"loss": 0.1883,
"step": 70
},
{
"epoch": 0.35714285714285715,
"grad_norm": 9.5625,
"learning_rate": 3.6459203080348775e-06,
"loss": 0.1548,
"step": 75
},
{
"epoch": 0.38095238095238093,
"grad_norm": 8.625,
"learning_rate": 3.6380120062773375e-06,
"loss": 0.148,
"step": 80
},
{
"epoch": 0.40476190476190477,
"grad_norm": 9.375,
"learning_rate": 3.6291690598821e-06,
"loss": 0.1656,
"step": 85
},
{
"epoch": 0.42857142857142855,
"grad_norm": 8.9375,
"learning_rate": 3.6193976316423157e-06,
"loss": 0.1621,
"step": 90
},
{
"epoch": 0.4523809523809524,
"grad_norm": 9.5625,
"learning_rate": 3.6087045314252307e-06,
"loss": 0.1627,
"step": 95
},
{
"epoch": 0.47619047619047616,
"grad_norm": 10.0,
"learning_rate": 3.597097211426281e-06,
"loss": 0.1831,
"step": 100
},
{
"epoch": 0.5,
"grad_norm": 11.5625,
"learning_rate": 3.5845837609755354e-06,
"loss": 0.1655,
"step": 105
},
{
"epoch": 0.5238095238095238,
"grad_norm": 9.9375,
"learning_rate": 3.5711729009001095e-06,
"loss": 0.1668,
"step": 110
},
{
"epoch": 0.5476190476190477,
"grad_norm": 10.125,
"learning_rate": 3.556873977446483e-06,
"loss": 0.1767,
"step": 115
},
{
"epoch": 0.5714285714285714,
"grad_norm": 8.0,
"learning_rate": 3.541696955766943e-06,
"loss": 0.1581,
"step": 120
},
{
"epoch": 0.5952380952380952,
"grad_norm": 10.1875,
"learning_rate": 3.5256524129747123e-06,
"loss": 0.1574,
"step": 125
},
{
"epoch": 0.6190476190476191,
"grad_norm": 11.3125,
"learning_rate": 3.5087515307725825e-06,
"loss": 0.186,
"step": 130
},
{
"epoch": 0.6428571428571429,
"grad_norm": 9.0,
"learning_rate": 3.4910060876602087e-06,
"loss": 0.1665,
"step": 135
},
{
"epoch": 0.6666666666666666,
"grad_norm": 8.875,
"learning_rate": 3.472428450725478e-06,
"loss": 0.1725,
"step": 140
},
{
"epoch": 0.6904761904761905,
"grad_norm": 10.125,
"learning_rate": 3.4530315670256834e-06,
"loss": 0.178,
"step": 145
},
{
"epoch": 0.7142857142857143,
"grad_norm": 9.4375,
"learning_rate": 3.432828954564515e-06,
"loss": 0.1679,
"step": 150
},
{
"epoch": 0.7380952380952381,
"grad_norm": 9.375,
"learning_rate": 3.411834692871138e-06,
"loss": 0.1819,
"step": 155
},
{
"epoch": 0.7619047619047619,
"grad_norm": 9.9375,
"learning_rate": 3.390063413187941e-06,
"loss": 0.1764,
"step": 160
},
{
"epoch": 0.7857142857142857,
"grad_norm": 10.5,
"learning_rate": 3.3675302882737866e-06,
"loss": 0.1655,
"step": 165
},
{
"epoch": 0.8095238095238095,
"grad_norm": 10.0,
"learning_rate": 3.344251021829867e-06,
"loss": 0.1759,
"step": 170
},
{
"epoch": 0.8333333333333334,
"grad_norm": 8.375,
"learning_rate": 3.3202418375555435e-06,
"loss": 0.1502,
"step": 175
},
{
"epoch": 0.8571428571428571,
"grad_norm": 10.6875,
"learning_rate": 3.29551946784178e-06,
"loss": 0.1667,
"step": 180
},
{
"epoch": 0.8809523809523809,
"grad_norm": 9.375,
"learning_rate": 3.2701011421100723e-06,
"loss": 0.1684,
"step": 185
},
{
"epoch": 0.9047619047619048,
"grad_norm": 7.875,
"learning_rate": 3.2440045748049846e-06,
"loss": 0.1475,
"step": 190
},
{
"epoch": 0.9285714285714286,
"grad_norm": 9.4375,
"learning_rate": 3.217247953048661e-06,
"loss": 0.1741,
"step": 195
},
{
"epoch": 0.9523809523809523,
"grad_norm": 9.5625,
"learning_rate": 3.1898499239659283e-06,
"loss": 0.1498,
"step": 200
},
{
"epoch": 0.9761904761904762,
"grad_norm": 9.3125,
"learning_rate": 3.1618295816888093e-06,
"loss": 0.1632,
"step": 205
},
{
"epoch": 1.0,
"grad_norm": 9.0625,
"learning_rate": 3.133206454049512e-06,
"loss": 0.1533,
"step": 210
},
{
"epoch": 1.0,
"eval_loss": 0.1544312834739685,
"eval_runtime": 1.7978,
"eval_samples_per_second": 18.912,
"eval_steps_per_second": 9.456,
"step": 210
}
],
"logging_steps": 5,
"max_steps": 630,
"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": false
},
"attributes": {}
}
},
"total_flos": 1.0275582854792479e+18,
"train_batch_size": 28,
"trial_name": null,
"trial_params": null
}