math-checkpoints / checkpoint-366 /trainer_state.json
Prahaladha's picture
Upload checkpoint-366/trainer_state.json with huggingface_hub
2925064 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 500,
"global_step": 366,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0547945205479452,
"grad_norm": 1.181526780128479,
"learning_rate": 4.736842105263158e-05,
"loss": 1.799,
"step": 10
},
{
"epoch": 0.1095890410958904,
"grad_norm": 0.522590160369873,
"learning_rate": 0.0001,
"loss": 1.2094,
"step": 20
},
{
"epoch": 0.1643835616438356,
"grad_norm": 0.3870140314102173,
"learning_rate": 9.979522160511282e-05,
"loss": 0.8021,
"step": 30
},
{
"epoch": 0.2191780821917808,
"grad_norm": 0.3272338807582855,
"learning_rate": 9.918256378809177e-05,
"loss": 0.7125,
"step": 40
},
{
"epoch": 0.273972602739726,
"grad_norm": 0.39106306433677673,
"learning_rate": 9.816704491231226e-05,
"loss": 0.6694,
"step": 50
},
{
"epoch": 0.3287671232876712,
"grad_norm": 0.5298248529434204,
"learning_rate": 9.675698323078865e-05,
"loss": 0.6647,
"step": 60
},
{
"epoch": 0.3835616438356164,
"grad_norm": 0.33846038579940796,
"learning_rate": 9.496392875023432e-05,
"loss": 0.612,
"step": 70
},
{
"epoch": 0.4383561643835616,
"grad_norm": 0.3002408444881439,
"learning_rate": 9.280256862338821e-05,
"loss": 0.5868,
"step": 80
},
{
"epoch": 0.4931506849315068,
"grad_norm": 0.27812713384628296,
"learning_rate": 9.029060684455229e-05,
"loss": 0.599,
"step": 90
},
{
"epoch": 0.547945205479452,
"grad_norm": 0.3248140513896942,
"learning_rate": 8.744861923377001e-05,
"loss": 0.5933,
"step": 100
},
{
"epoch": 0.6027397260273972,
"grad_norm": 0.36872419714927673,
"learning_rate": 8.429988489749046e-05,
"loss": 0.5952,
"step": 110
},
{
"epoch": 0.6575342465753424,
"grad_norm": 0.3348616659641266,
"learning_rate": 8.087019554624595e-05,
"loss": 0.5813,
"step": 120
},
{
"epoch": 0.7123287671232876,
"grad_norm": 0.33727309107780457,
"learning_rate": 7.718764423124892e-05,
"loss": 0.5511,
"step": 130
},
{
"epoch": 0.7671232876712328,
"grad_norm": 0.35852885246276855,
"learning_rate": 7.32823952303943e-05,
"loss": 0.5837,
"step": 140
},
{
"epoch": 0.821917808219178,
"grad_norm": 0.37122035026550293,
"learning_rate": 6.918643696856333e-05,
"loss": 0.5604,
"step": 150
},
{
"epoch": 0.8767123287671232,
"grad_norm": 0.3272222578525543,
"learning_rate": 6.493331999609131e-05,
"loss": 0.5318,
"step": 160
},
{
"epoch": 0.9315068493150684,
"grad_norm": 0.3521849513053894,
"learning_rate": 6.055788217165383e-05,
"loss": 0.5598,
"step": 170
},
{
"epoch": 0.9863013698630136,
"grad_norm": 0.3393417000770569,
"learning_rate": 5.609596330063558e-05,
"loss": 0.5626,
"step": 180
},
{
"epoch": 1.0383561643835617,
"grad_norm": 0.29794371128082275,
"learning_rate": 5.1584111566417515e-05,
"loss": 0.5401,
"step": 190
},
{
"epoch": 1.093150684931507,
"grad_norm": 0.40294867753982544,
"learning_rate": 4.705928415924373e-05,
"loss": 0.4977,
"step": 200
},
{
"epoch": 1.1479452054794521,
"grad_norm": 0.3701549768447876,
"learning_rate": 4.255854455485753e-05,
"loss": 0.4893,
"step": 210
},
{
"epoch": 1.2027397260273973,
"grad_norm": 0.41681772470474243,
"learning_rate": 3.811875892253853e-05,
"loss": 0.509,
"step": 220
},
{
"epoch": 1.2575342465753425,
"grad_norm": 0.47252005338668823,
"learning_rate": 3.377629414930396e-05,
"loss": 0.4866,
"step": 230
},
{
"epoch": 1.3123287671232877,
"grad_norm": 0.5522735118865967,
"learning_rate": 2.9566719953798473e-05,
"loss": 0.4788,
"step": 240
},
{
"epoch": 1.367123287671233,
"grad_norm": 0.3663751780986786,
"learning_rate": 2.552451752989865e-05,
"loss": 0.5067,
"step": 250
},
{
"epoch": 1.4219178082191781,
"grad_norm": 0.3987874388694763,
"learning_rate": 2.168279710657149e-05,
"loss": 0.4634,
"step": 260
},
{
"epoch": 1.4767123287671233,
"grad_norm": 0.5115519762039185,
"learning_rate": 1.8073026737492782e-05,
"loss": 0.4912,
"step": 270
},
{
"epoch": 1.5315068493150685,
"grad_norm": 0.5251284241676331,
"learning_rate": 1.4724774541946146e-05,
"loss": 0.5087,
"step": 280
},
{
"epoch": 1.5863013698630137,
"grad_norm": 0.5367189049720764,
"learning_rate": 1.1665466508342877e-05,
"loss": 0.462,
"step": 290
},
{
"epoch": 1.641095890410959,
"grad_norm": 0.6373235583305359,
"learning_rate": 8.920161844226415e-06,
"loss": 0.482,
"step": 300
},
{
"epoch": 1.6958904109589041,
"grad_norm": 0.5205274820327759,
"learning_rate": 6.511347712900545e-06,
"loss": 0.4816,
"step": 310
},
{
"epoch": 1.7506849315068493,
"grad_norm": 0.42115122079849243,
"learning_rate": 4.458755038021029e-06,
"loss": 0.4663,
"step": 320
},
{
"epoch": 1.8054794520547945,
"grad_norm": 0.5167638659477234,
"learning_rate": 2.7791968849206428e-06,
"loss": 0.4938,
"step": 330
},
{
"epoch": 1.8602739726027397,
"grad_norm": 0.544147253036499,
"learning_rate": 1.4864307425078327e-06,
"loss": 0.4824,
"step": 340
},
{
"epoch": 1.915068493150685,
"grad_norm": 0.4460655748844147,
"learning_rate": 5.910458338069191e-07,
"loss": 0.4946,
"step": 350
},
{
"epoch": 1.9698630136986301,
"grad_norm": 0.5717807412147522,
"learning_rate": 1.0037637819431123e-07,
"loss": 0.4736,
"step": 360
}
],
"logging_steps": 10,
"max_steps": 366,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 200,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.27377858339115e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}