{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0526315789473684,
"eval_steps": 100,
"global_step": 60,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.017543859649122806,
"grad_norm": 44.84535598754883,
"learning_rate": 1.111111111111111e-06,
"loss": 1.3672,
"step": 1
},
{
"epoch": 0.03508771929824561,
"grad_norm": 46.05864715576172,
"learning_rate": 2.222222222222222e-06,
"loss": 1.3719,
"step": 2
},
{
"epoch": 0.05263157894736842,
"grad_norm": 9.057656288146973,
"learning_rate": 3.3333333333333333e-06,
"loss": 0.7838,
"step": 3
},
{
"epoch": 0.07017543859649122,
"grad_norm": 8.365191459655762,
"learning_rate": 4.444444444444444e-06,
"loss": 0.7781,
"step": 4
},
{
"epoch": 0.08771929824561403,
"grad_norm": 6.402659893035889,
"learning_rate": 5.555555555555557e-06,
"loss": 0.7132,
"step": 5
},
{
"epoch": 0.10526315789473684,
"grad_norm": 5.508246898651123,
"learning_rate": 6.666666666666667e-06,
"loss": 0.6863,
"step": 6
},
{
"epoch": 0.12280701754385964,
"grad_norm": 4.964734077453613,
"learning_rate": 7.77777777777778e-06,
"loss": 0.6237,
"step": 7
},
{
"epoch": 0.14035087719298245,
"grad_norm": 4.011112689971924,
"learning_rate": 8.888888888888888e-06,
"loss": 0.618,
"step": 8
},
{
"epoch": 0.15789473684210525,
"grad_norm": 3.7118031978607178,
"learning_rate": 1e-05,
"loss": 0.5955,
"step": 9
},
{
"epoch": 0.17543859649122806,
"grad_norm": 3.4124467372894287,
"learning_rate": 1.1111111111111113e-05,
"loss": 0.5661,
"step": 10
},
{
"epoch": 0.19298245614035087,
"grad_norm": 2.9919450283050537,
"learning_rate": 1.2222222222222224e-05,
"loss": 0.5436,
"step": 11
},
{
"epoch": 0.21052631578947367,
"grad_norm": 2.6217074394226074,
"learning_rate": 1.3333333333333333e-05,
"loss": 0.4991,
"step": 12
},
{
"epoch": 0.22807017543859648,
"grad_norm": 3.101696014404297,
"learning_rate": 1.4444444444444446e-05,
"loss": 0.4889,
"step": 13
},
{
"epoch": 0.24561403508771928,
"grad_norm": 2.632870674133301,
"learning_rate": 1.555555555555556e-05,
"loss": 0.4727,
"step": 14
},
{
"epoch": 0.2631578947368421,
"grad_norm": 2.158155679702759,
"learning_rate": 1.6666666666666667e-05,
"loss": 0.4647,
"step": 15
},
{
"epoch": 0.2807017543859649,
"grad_norm": 2.006129264831543,
"learning_rate": 1.7777777777777777e-05,
"loss": 0.4476,
"step": 16
},
{
"epoch": 0.2982456140350877,
"grad_norm": 2.096951961517334,
"learning_rate": 1.888888888888889e-05,
"loss": 0.4387,
"step": 17
},
{
"epoch": 0.3157894736842105,
"grad_norm": 1.9885540008544922,
"learning_rate": 2e-05,
"loss": 0.412,
"step": 18
},
{
"epoch": 0.3333333333333333,
"grad_norm": 1.9787037372589111,
"learning_rate": 1.9869281045751635e-05,
"loss": 0.415,
"step": 19
},
{
"epoch": 0.3508771929824561,
"grad_norm": 2.428654193878174,
"learning_rate": 1.973856209150327e-05,
"loss": 0.4068,
"step": 20
},
{
"epoch": 0.3684210526315789,
"grad_norm": 1.8156601190567017,
"learning_rate": 1.9607843137254903e-05,
"loss": 0.3895,
"step": 21
},
{
"epoch": 0.38596491228070173,
"grad_norm": 1.9325244426727295,
"learning_rate": 1.9477124183006536e-05,
"loss": 0.3793,
"step": 22
},
{
"epoch": 0.40350877192982454,
"grad_norm": 1.5293307304382324,
"learning_rate": 1.9346405228758173e-05,
"loss": 0.3753,
"step": 23
},
{
"epoch": 0.42105263157894735,
"grad_norm": 2.211817741394043,
"learning_rate": 1.9215686274509807e-05,
"loss": 0.3858,
"step": 24
},
{
"epoch": 0.43859649122807015,
"grad_norm": 1.7881850004196167,
"learning_rate": 1.908496732026144e-05,
"loss": 0.3735,
"step": 25
},
{
"epoch": 0.45614035087719296,
"grad_norm": 1.7260500192642212,
"learning_rate": 1.8954248366013074e-05,
"loss": 0.3733,
"step": 26
},
{
"epoch": 0.47368421052631576,
"grad_norm": 1.6085237264633179,
"learning_rate": 1.8823529411764708e-05,
"loss": 0.355,
"step": 27
},
{
"epoch": 0.49122807017543857,
"grad_norm": 2.8392181396484375,
"learning_rate": 1.869281045751634e-05,
"loss": 0.3551,
"step": 28
},
{
"epoch": 0.5087719298245614,
"grad_norm": 1.978279948234558,
"learning_rate": 1.8562091503267975e-05,
"loss": 0.3337,
"step": 29
},
{
"epoch": 0.5263157894736842,
"grad_norm": 2.016209125518799,
"learning_rate": 1.843137254901961e-05,
"loss": 0.3408,
"step": 30
},
{
"epoch": 0.543859649122807,
"grad_norm": 1.4631725549697876,
"learning_rate": 1.8300653594771242e-05,
"loss": 0.3434,
"step": 31
},
{
"epoch": 0.5614035087719298,
"grad_norm": 1.4324421882629395,
"learning_rate": 1.8169934640522876e-05,
"loss": 0.3468,
"step": 32
},
{
"epoch": 0.5789473684210527,
"grad_norm": 5.047348976135254,
"learning_rate": 1.8039215686274513e-05,
"loss": 0.3284,
"step": 33
},
{
"epoch": 0.5964912280701754,
"grad_norm": 1.515346884727478,
"learning_rate": 1.7908496732026146e-05,
"loss": 0.3377,
"step": 34
},
{
"epoch": 0.6140350877192983,
"grad_norm": 1.883217692375183,
"learning_rate": 1.7777777777777777e-05,
"loss": 0.333,
"step": 35
},
{
"epoch": 0.631578947368421,
"grad_norm": 1.6431008577346802,
"learning_rate": 1.7647058823529414e-05,
"loss": 0.3319,
"step": 36
},
{
"epoch": 0.6491228070175439,
"grad_norm": 1.630910873413086,
"learning_rate": 1.7516339869281047e-05,
"loss": 0.3214,
"step": 37
},
{
"epoch": 0.6666666666666666,
"grad_norm": 1.4808597564697266,
"learning_rate": 1.738562091503268e-05,
"loss": 0.3258,
"step": 38
},
{
"epoch": 0.6842105263157895,
"grad_norm": 1.6400136947631836,
"learning_rate": 1.7254901960784314e-05,
"loss": 0.3225,
"step": 39
},
{
"epoch": 0.7017543859649122,
"grad_norm": 1.3743259906768799,
"learning_rate": 1.7124183006535948e-05,
"loss": 0.3192,
"step": 40
},
{
"epoch": 0.7192982456140351,
"grad_norm": 1.4262139797210693,
"learning_rate": 1.6993464052287582e-05,
"loss": 0.3121,
"step": 41
},
{
"epoch": 0.7368421052631579,
"grad_norm": 1.4537426233291626,
"learning_rate": 1.686274509803922e-05,
"loss": 0.3164,
"step": 42
},
{
"epoch": 0.7543859649122807,
"grad_norm": 1.2737575769424438,
"learning_rate": 1.6732026143790852e-05,
"loss": 0.3021,
"step": 43
},
{
"epoch": 0.7719298245614035,
"grad_norm": 1.2681057453155518,
"learning_rate": 1.6601307189542486e-05,
"loss": 0.3166,
"step": 44
},
{
"epoch": 0.7894736842105263,
"grad_norm": 5.779806137084961,
"learning_rate": 1.647058823529412e-05,
"loss": 0.3093,
"step": 45
},
{
"epoch": 0.8070175438596491,
"grad_norm": 1.4256994724273682,
"learning_rate": 1.6339869281045753e-05,
"loss": 0.2968,
"step": 46
},
{
"epoch": 0.8245614035087719,
"grad_norm": 1.5250773429870605,
"learning_rate": 1.6209150326797387e-05,
"loss": 0.2972,
"step": 47
},
{
"epoch": 0.8421052631578947,
"grad_norm": 1.2680127620697021,
"learning_rate": 1.607843137254902e-05,
"loss": 0.2914,
"step": 48
},
{
"epoch": 0.8596491228070176,
"grad_norm": 1.6887532472610474,
"learning_rate": 1.5947712418300657e-05,
"loss": 0.2951,
"step": 49
},
{
"epoch": 0.8771929824561403,
"grad_norm": 2.2416443824768066,
"learning_rate": 1.5816993464052288e-05,
"loss": 0.3059,
"step": 50
},
{
"epoch": 0.8947368421052632,
"grad_norm": 1.3144830465316772,
"learning_rate": 1.568627450980392e-05,
"loss": 0.3011,
"step": 51
},
{
"epoch": 0.9122807017543859,
"grad_norm": 2.3271305561065674,
"learning_rate": 1.555555555555556e-05,
"loss": 0.2908,
"step": 52
},
{
"epoch": 0.9298245614035088,
"grad_norm": 1.2403310537338257,
"learning_rate": 1.5424836601307192e-05,
"loss": 0.3001,
"step": 53
},
{
"epoch": 0.9473684210526315,
"grad_norm": 2.7490832805633545,
"learning_rate": 1.5294117647058822e-05,
"loss": 0.2987,
"step": 54
},
{
"epoch": 0.9649122807017544,
"grad_norm": 2.321964979171753,
"learning_rate": 1.5163398692810458e-05,
"loss": 0.287,
"step": 55
},
{
"epoch": 0.9824561403508771,
"grad_norm": 1.1607296466827393,
"learning_rate": 1.5032679738562093e-05,
"loss": 0.2868,
"step": 56
},
{
"epoch": 1.0,
"grad_norm": 1.5422321557998657,
"learning_rate": 1.4901960784313726e-05,
"loss": 0.293,
"step": 57
},
{
"epoch": 1.0175438596491229,
"grad_norm": 1.5632988214492798,
"learning_rate": 1.4771241830065362e-05,
"loss": 0.2768,
"step": 58
},
{
"epoch": 1.0350877192982457,
"grad_norm": 1.620436668395996,
"learning_rate": 1.4640522875816994e-05,
"loss": 0.2727,
"step": 59
},
{
"epoch": 1.0526315789473684,
"grad_norm": 1.2848402261734009,
"learning_rate": 1.4509803921568629e-05,
"loss": 0.2659,
"step": 60
}
],
"logging_steps": 1,
"max_steps": 171,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 12,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 0.0,
"train_batch_size": 4096,
"trial_name": null,
"trial_params": null
}