|
{
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 3.1595576619273302,
|
|
"eval_steps": 500,
|
|
"global_step": 500,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 0.1263823064770932,
|
|
"grad_norm": 1.039925456047058,
|
|
"learning_rate": 4e-05,
|
|
"loss": 2.1917,
|
|
"step": 20
|
|
},
|
|
{
|
|
"epoch": 0.2527646129541864,
|
|
"grad_norm": 1.250934362411499,
|
|
"learning_rate": 8e-05,
|
|
"loss": 1.9713,
|
|
"step": 40
|
|
},
|
|
{
|
|
"epoch": 0.3791469194312796,
|
|
"grad_norm": 1.2668324708938599,
|
|
"learning_rate": 0.00012,
|
|
"loss": 1.7553,
|
|
"step": 60
|
|
},
|
|
{
|
|
"epoch": 0.5055292259083728,
|
|
"grad_norm": 1.822996973991394,
|
|
"learning_rate": 0.00016,
|
|
"loss": 1.6959,
|
|
"step": 80
|
|
},
|
|
{
|
|
"epoch": 0.631911532385466,
|
|
"grad_norm": 1.8614917993545532,
|
|
"learning_rate": 0.0002,
|
|
"loss": 1.5757,
|
|
"step": 100
|
|
},
|
|
{
|
|
"epoch": 0.7582938388625592,
|
|
"grad_norm": 2.021389961242676,
|
|
"learning_rate": 0.0001924812030075188,
|
|
"loss": 1.5615,
|
|
"step": 120
|
|
},
|
|
{
|
|
"epoch": 0.8846761453396524,
|
|
"grad_norm": 1.8619110584259033,
|
|
"learning_rate": 0.0001849624060150376,
|
|
"loss": 1.4426,
|
|
"step": 140
|
|
},
|
|
{
|
|
"epoch": 1.0110584518167456,
|
|
"grad_norm": 1.8433139324188232,
|
|
"learning_rate": 0.0001774436090225564,
|
|
"loss": 1.4429,
|
|
"step": 160
|
|
},
|
|
{
|
|
"epoch": 1.1374407582938388,
|
|
"grad_norm": 2.324719190597534,
|
|
"learning_rate": 0.0001699248120300752,
|
|
"loss": 1.2625,
|
|
"step": 180
|
|
},
|
|
{
|
|
"epoch": 1.263823064770932,
|
|
"grad_norm": 1.7142627239227295,
|
|
"learning_rate": 0.00016240601503759398,
|
|
"loss": 1.2677,
|
|
"step": 200
|
|
},
|
|
{
|
|
"epoch": 1.3902053712480253,
|
|
"grad_norm": 2.427729606628418,
|
|
"learning_rate": 0.0001548872180451128,
|
|
"loss": 1.248,
|
|
"step": 220
|
|
},
|
|
{
|
|
"epoch": 1.5165876777251186,
|
|
"grad_norm": 2.2092034816741943,
|
|
"learning_rate": 0.00014736842105263158,
|
|
"loss": 1.1584,
|
|
"step": 240
|
|
},
|
|
{
|
|
"epoch": 1.6429699842022116,
|
|
"grad_norm": 1.9174597263336182,
|
|
"learning_rate": 0.0001398496240601504,
|
|
"loss": 1.1811,
|
|
"step": 260
|
|
},
|
|
{
|
|
"epoch": 1.7693522906793049,
|
|
"grad_norm": 2.3690454959869385,
|
|
"learning_rate": 0.00013233082706766918,
|
|
"loss": 1.1186,
|
|
"step": 280
|
|
},
|
|
{
|
|
"epoch": 1.8957345971563981,
|
|
"grad_norm": 1.9550652503967285,
|
|
"learning_rate": 0.00012481203007518797,
|
|
"loss": 1.1149,
|
|
"step": 300
|
|
},
|
|
{
|
|
"epoch": 2.022116903633491,
|
|
"grad_norm": 2.081315517425537,
|
|
"learning_rate": 0.00011729323308270677,
|
|
"loss": 1.0422,
|
|
"step": 320
|
|
},
|
|
{
|
|
"epoch": 2.1484992101105846,
|
|
"grad_norm": 3.5079455375671387,
|
|
"learning_rate": 0.00010977443609022557,
|
|
"loss": 0.8674,
|
|
"step": 340
|
|
},
|
|
{
|
|
"epoch": 2.2748815165876777,
|
|
"grad_norm": 2.9713032245635986,
|
|
"learning_rate": 0.00010225563909774436,
|
|
"loss": 0.8312,
|
|
"step": 360
|
|
},
|
|
{
|
|
"epoch": 2.401263823064771,
|
|
"grad_norm": 3.1877429485321045,
|
|
"learning_rate": 9.473684210526316e-05,
|
|
"loss": 0.7915,
|
|
"step": 380
|
|
},
|
|
{
|
|
"epoch": 2.527646129541864,
|
|
"grad_norm": 3.9969420433044434,
|
|
"learning_rate": 8.721804511278195e-05,
|
|
"loss": 0.8997,
|
|
"step": 400
|
|
},
|
|
{
|
|
"epoch": 2.654028436018957,
|
|
"grad_norm": 3.038134813308716,
|
|
"learning_rate": 7.969924812030075e-05,
|
|
"loss": 0.7495,
|
|
"step": 420
|
|
},
|
|
{
|
|
"epoch": 2.7804107424960507,
|
|
"grad_norm": 2.5654478073120117,
|
|
"learning_rate": 7.218045112781955e-05,
|
|
"loss": 0.7727,
|
|
"step": 440
|
|
},
|
|
{
|
|
"epoch": 2.9067930489731437,
|
|
"grad_norm": 3.3609306812286377,
|
|
"learning_rate": 6.466165413533834e-05,
|
|
"loss": 0.8009,
|
|
"step": 460
|
|
},
|
|
{
|
|
"epoch": 3.0331753554502368,
|
|
"grad_norm": 3.048936367034912,
|
|
"learning_rate": 5.714285714285714e-05,
|
|
"loss": 0.753,
|
|
"step": 480
|
|
},
|
|
{
|
|
"epoch": 3.1595576619273302,
|
|
"grad_norm": 2.0320680141448975,
|
|
"learning_rate": 4.9624060150375936e-05,
|
|
"loss": 0.5853,
|
|
"step": 500
|
|
}
|
|
],
|
|
"logging_steps": 20,
|
|
"max_steps": 632,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 4,
|
|
"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": 1.8241099229184e+16,
|
|
"train_batch_size": 1,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|
|
|