outputs / rewriting /checkpoint-258 /trainer_state.json
ingeol's picture
Training in progress, epoch 0
161775f verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 500,
"global_step": 258,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.07751937984496124,
"grad_norm": 2.245417356491089,
"learning_rate": 5e-05,
"loss": 2.1087,
"step": 10
},
{
"epoch": 0.15503875968992248,
"grad_norm": 3.3328239917755127,
"learning_rate": 0.0001,
"loss": 1.7547,
"step": 20
},
{
"epoch": 0.23255813953488372,
"grad_norm": 1.6743243932724,
"learning_rate": 9.993684783030088e-05,
"loss": 1.3868,
"step": 30
},
{
"epoch": 0.31007751937984496,
"grad_norm": 1.585747480392456,
"learning_rate": 9.974755084906502e-05,
"loss": 1.1455,
"step": 40
},
{
"epoch": 0.3875968992248062,
"grad_norm": 1.2781128883361816,
"learning_rate": 9.94325872368957e-05,
"loss": 1.1394,
"step": 50
},
{
"epoch": 0.46511627906976744,
"grad_norm": 1.3732120990753174,
"learning_rate": 9.899275261921234e-05,
"loss": 1.0942,
"step": 60
},
{
"epoch": 0.5426356589147286,
"grad_norm": 1.4817951917648315,
"learning_rate": 9.842915805643155e-05,
"loss": 0.9934,
"step": 70
},
{
"epoch": 0.6201550387596899,
"grad_norm": 1.261801838874817,
"learning_rate": 9.774322723733216e-05,
"loss": 1.0093,
"step": 80
},
{
"epoch": 0.6976744186046512,
"grad_norm": 1.801243782043457,
"learning_rate": 9.693669288269372e-05,
"loss": 1.0686,
"step": 90
},
{
"epoch": 0.7751937984496124,
"grad_norm": 1.719342827796936,
"learning_rate": 9.601159236829352e-05,
"loss": 0.9973,
"step": 100
},
{
"epoch": 0.8527131782945736,
"grad_norm": 1.5797449350357056,
"learning_rate": 9.497026257831855e-05,
"loss": 1.0002,
"step": 110
},
{
"epoch": 0.9302325581395349,
"grad_norm": 1.790971279144287,
"learning_rate": 9.381533400219318e-05,
"loss": 0.9484,
"step": 120
},
{
"epoch": 1.0077519379844961,
"grad_norm": 1.6127315759658813,
"learning_rate": 9.254972408973461e-05,
"loss": 0.979,
"step": 130
},
{
"epoch": 1.0852713178294573,
"grad_norm": 1.4869861602783203,
"learning_rate": 9.117662988142138e-05,
"loss": 0.8899,
"step": 140
},
{
"epoch": 1.1627906976744187,
"grad_norm": 2.101341962814331,
"learning_rate": 8.969951993239177e-05,
"loss": 0.9493,
"step": 150
},
{
"epoch": 1.2403100775193798,
"grad_norm": 1.7181503772735596,
"learning_rate": 8.81221255505724e-05,
"loss": 0.8715,
"step": 160
},
{
"epoch": 1.3178294573643412,
"grad_norm": 2.006377696990967,
"learning_rate": 8.644843137107059e-05,
"loss": 0.8846,
"step": 170
},
{
"epoch": 1.3953488372093024,
"grad_norm": 2.0157504081726074,
"learning_rate": 8.468266529064025e-05,
"loss": 0.9292,
"step": 180
},
{
"epoch": 1.4728682170542635,
"grad_norm": 1.704633355140686,
"learning_rate": 8.282928778764783e-05,
"loss": 0.8883,
"step": 190
},
{
"epoch": 1.550387596899225,
"grad_norm": 1.7320111989974976,
"learning_rate": 8.089298065451672e-05,
"loss": 0.874,
"step": 200
},
{
"epoch": 1.627906976744186,
"grad_norm": 2.369300127029419,
"learning_rate": 7.887863517111338e-05,
"loss": 0.8688,
"step": 210
},
{
"epoch": 1.7054263565891472,
"grad_norm": 1.5535732507705688,
"learning_rate": 7.679133974894983e-05,
"loss": 0.8726,
"step": 220
},
{
"epoch": 1.7829457364341086,
"grad_norm": 1.9749231338500977,
"learning_rate": 7.463636707741458e-05,
"loss": 0.8252,
"step": 230
},
{
"epoch": 1.8604651162790697,
"grad_norm": 2.261054277420044,
"learning_rate": 7.241916080450163e-05,
"loss": 0.846,
"step": 240
},
{
"epoch": 1.937984496124031,
"grad_norm": 2.019524097442627,
"learning_rate": 7.014532178568314e-05,
"loss": 0.8104,
"step": 250
}
],
"logging_steps": 10,
"max_steps": 645,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"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": 2.681627524713677e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}