Ruthvik2835's picture
Initial model upload
6950306 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 100.0,
"global_step": 35,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02857142857142857,
"grad_norm": 0.04918956756591797,
"learning_rate": 0.0,
"loss": 0.5625,
"step": 1
},
{
"epoch": 0.05714285714285714,
"grad_norm": 0.04941160976886749,
"learning_rate": 5e-05,
"loss": 0.5623,
"step": 2
},
{
"epoch": 0.08571428571428572,
"grad_norm": 0.05087224394083023,
"learning_rate": 0.0001,
"loss": 0.5009,
"step": 3
},
{
"epoch": 0.11428571428571428,
"grad_norm": 0.053648702800273895,
"learning_rate": 0.00015000000000000001,
"loss": 0.5467,
"step": 4
},
{
"epoch": 0.14285714285714285,
"grad_norm": 0.056984659284353256,
"learning_rate": 0.0002,
"loss": 0.5003,
"step": 5
},
{
"epoch": 0.17142857142857143,
"grad_norm": 0.06416453421115875,
"learning_rate": 0.00019948693233918952,
"loss": 0.4514,
"step": 6
},
{
"epoch": 0.2,
"grad_norm": 0.07367783039808273,
"learning_rate": 0.00019795299412524945,
"loss": 0.4195,
"step": 7
},
{
"epoch": 0.22857142857142856,
"grad_norm": 0.09809113293886185,
"learning_rate": 0.00019541392564000488,
"loss": 0.3534,
"step": 8
},
{
"epoch": 0.2571428571428571,
"grad_norm": 0.2686680257320404,
"learning_rate": 0.00019189578116202307,
"loss": 0.3339,
"step": 9
},
{
"epoch": 0.2857142857142857,
"grad_norm": 0.12331166863441467,
"learning_rate": 0.00018743466161445823,
"loss": 0.2941,
"step": 10
},
{
"epoch": 0.3142857142857143,
"grad_norm": 0.13653112947940826,
"learning_rate": 0.00018207634412072764,
"loss": 0.2648,
"step": 11
},
{
"epoch": 0.34285714285714286,
"grad_norm": 0.12992143630981445,
"learning_rate": 0.0001758758122692791,
"loss": 0.2015,
"step": 12
},
{
"epoch": 0.37142857142857144,
"grad_norm": 0.13980498909950256,
"learning_rate": 0.00016889669190756868,
"loss": 0.1789,
"step": 13
},
{
"epoch": 0.4,
"grad_norm": 0.1361037641763687,
"learning_rate": 0.0001612105982547663,
"loss": 0.1397,
"step": 14
},
{
"epoch": 0.42857142857142855,
"grad_norm": 0.11609825491905212,
"learning_rate": 0.00015289640103269625,
"loss": 0.1201,
"step": 15
},
{
"epoch": 0.45714285714285713,
"grad_norm": 0.099339060485363,
"learning_rate": 0.00014403941515576344,
"loss": 0.0973,
"step": 16
},
{
"epoch": 0.4857142857142857,
"grad_norm": 0.09612716734409332,
"learning_rate": 0.00013473052528448201,
"loss": 0.0855,
"step": 17
},
{
"epoch": 0.5142857142857142,
"grad_norm": 0.10055588185787201,
"learning_rate": 0.00012506525322587207,
"loss": 0.0849,
"step": 18
},
{
"epoch": 0.5428571428571428,
"grad_norm": 0.08217591792345047,
"learning_rate": 0.00011514277775045768,
"loss": 0.0725,
"step": 19
},
{
"epoch": 0.5714285714285714,
"grad_norm": 0.07315342128276825,
"learning_rate": 0.00010506491688387127,
"loss": 0.0684,
"step": 20
},
{
"epoch": 0.6,
"grad_norm": 0.08092162758111954,
"learning_rate": 9.493508311612874e-05,
"loss": 0.0573,
"step": 21
},
{
"epoch": 0.6285714285714286,
"grad_norm": 0.06385105103254318,
"learning_rate": 8.485722224954237e-05,
"loss": 0.0594,
"step": 22
},
{
"epoch": 0.6571428571428571,
"grad_norm": 0.05351648107171059,
"learning_rate": 7.493474677412794e-05,
"loss": 0.0552,
"step": 23
},
{
"epoch": 0.6857142857142857,
"grad_norm": 0.05012252926826477,
"learning_rate": 6.526947471551798e-05,
"loss": 0.0607,
"step": 24
},
{
"epoch": 0.7142857142857143,
"grad_norm": 0.04566913843154907,
"learning_rate": 5.596058484423656e-05,
"loss": 0.0547,
"step": 25
},
{
"epoch": 0.7428571428571429,
"grad_norm": 0.044832587242126465,
"learning_rate": 4.710359896730379e-05,
"loss": 0.0483,
"step": 26
},
{
"epoch": 0.7714285714285715,
"grad_norm": 0.05177149549126625,
"learning_rate": 3.878940174523371e-05,
"loss": 0.0544,
"step": 27
},
{
"epoch": 0.8,
"grad_norm": 0.04932279884815216,
"learning_rate": 3.110330809243134e-05,
"loss": 0.0483,
"step": 28
},
{
"epoch": 0.8285714285714286,
"grad_norm": 0.05275353044271469,
"learning_rate": 2.4124187730720917e-05,
"loss": 0.0479,
"step": 29
},
{
"epoch": 0.8571428571428571,
"grad_norm": 0.04073500633239746,
"learning_rate": 1.7923655879272393e-05,
"loss": 0.0525,
"step": 30
},
{
"epoch": 0.8857142857142857,
"grad_norm": 0.04079524427652359,
"learning_rate": 1.2565338385541792e-05,
"loss": 0.0469,
"step": 31
},
{
"epoch": 0.9142857142857143,
"grad_norm": 0.06132270023226738,
"learning_rate": 8.10421883797694e-06,
"loss": 0.0421,
"step": 32
},
{
"epoch": 0.9428571428571428,
"grad_norm": 0.04404183104634285,
"learning_rate": 4.586074359995119e-06,
"loss": 0.0467,
"step": 33
},
{
"epoch": 0.9714285714285714,
"grad_norm": 0.03794850781559944,
"learning_rate": 2.0470058747505516e-06,
"loss": 0.0467,
"step": 34
},
{
"epoch": 1.0,
"grad_norm": 0.04732782021164894,
"learning_rate": 5.130676608104845e-07,
"loss": 0.0425,
"step": 35
}
],
"logging_steps": 1.0,
"max_steps": 35,
"num_input_tokens_seen": 0,
"num_train_epochs": 9223372036854775807,
"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": 4.2046170486276096e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}