| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9533678756476682, | |
| "eval_steps": 500, | |
| "global_step": 144, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.20725388601036268, | |
| "grad_norm": 1.8093507425794213, | |
| "learning_rate": 3e-06, | |
| "loss": 0.9129, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.41450777202072536, | |
| "grad_norm": 0.7996825526135815, | |
| "learning_rate": 4.98814758473309e-06, | |
| "loss": 0.7274, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6217616580310881, | |
| "grad_norm": 0.5373843764254267, | |
| "learning_rate": 4.856095207084287e-06, | |
| "loss": 0.6513, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.8290155440414507, | |
| "grad_norm": 0.4621175956467346, | |
| "learning_rate": 4.584994544724695e-06, | |
| "loss": 0.6373, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.0207253886010363, | |
| "grad_norm": 0.47882928868708474, | |
| "learning_rate": 4.190844985952257e-06, | |
| "loss": 0.5683, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.2279792746113989, | |
| "grad_norm": 0.4492344877710059, | |
| "learning_rate": 3.6969078233930235e-06, | |
| "loss": 0.6012, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.4352331606217616, | |
| "grad_norm": 0.4358797089748146, | |
| "learning_rate": 3.132333455979202e-06, | |
| "loss": 0.5866, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.6424870466321244, | |
| "grad_norm": 0.41894841115210807, | |
| "learning_rate": 2.530441037004994e-06, | |
| "loss": 0.5958, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.849740932642487, | |
| "grad_norm": 0.4253754435893472, | |
| "learning_rate": 1.9267520972587754e-06, | |
| "loss": 0.5755, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.0414507772020727, | |
| "grad_norm": 0.40951381645086515, | |
| "learning_rate": 1.3568941917384038e-06, | |
| "loss": 0.5319, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.2487046632124352, | |
| "grad_norm": 0.41726111462999993, | |
| "learning_rate": 8.544982891981304e-07, | |
| "loss": 0.5579, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.4559585492227978, | |
| "grad_norm": 0.4374441335411058, | |
| "learning_rate": 4.4921399305122264e-07, | |
| "loss": 0.5555, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.6632124352331608, | |
| "grad_norm": 0.4146727228301452, | |
| "learning_rate": 1.649597281686302e-07, | |
| "loss": 0.5625, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.8704663212435233, | |
| "grad_norm": 0.4451658295553321, | |
| "learning_rate": 1.851116126993402e-08, | |
| "loss": 0.5588, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.9533678756476682, | |
| "step": 144, | |
| "total_flos": 887572825899008.0, | |
| "train_loss": 0.6164978990952173, | |
| "train_runtime": 16386.6242, | |
| "train_samples_per_second": 1.127, | |
| "train_steps_per_second": 0.009 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 144, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 887572825899008.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |