| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.5131494547787043, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0025657472738935213, | |
| "eval_loss": 1.6426724195480347, | |
| "eval_runtime": 8.0379, | |
| "eval_samples_per_second": 20.528, | |
| "eval_steps_per_second": 10.326, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.025657472738935216, | |
| "grad_norm": 6.0922040939331055, | |
| "learning_rate": 0.0002, | |
| "loss": 5.4096, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05131494547787043, | |
| "grad_norm": 4.473964214324951, | |
| "learning_rate": 0.0002, | |
| "loss": 4.5736, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07697241821680564, | |
| "grad_norm": 5.79656457901001, | |
| "learning_rate": 0.0002, | |
| "loss": 4.236, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10262989095574086, | |
| "grad_norm": 5.566458702087402, | |
| "learning_rate": 0.0002, | |
| "loss": 4.4715, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12828736369467608, | |
| "grad_norm": 3.1581058502197266, | |
| "learning_rate": 0.0002, | |
| "loss": 4.2905, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12828736369467608, | |
| "eval_loss": 0.9886534810066223, | |
| "eval_runtime": 7.9175, | |
| "eval_samples_per_second": 20.84, | |
| "eval_steps_per_second": 10.483, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1539448364336113, | |
| "grad_norm": 5.599130630493164, | |
| "learning_rate": 0.0002, | |
| "loss": 4.1246, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.1796023091725465, | |
| "grad_norm": 6.4759297370910645, | |
| "learning_rate": 0.0002, | |
| "loss": 4.1768, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.20525978191148173, | |
| "grad_norm": 3.1259078979492188, | |
| "learning_rate": 0.0002, | |
| "loss": 3.9254, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.23091725465041693, | |
| "grad_norm": 3.3770580291748047, | |
| "learning_rate": 0.0002, | |
| "loss": 4.1994, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.25657472738935216, | |
| "grad_norm": 3.869525194168091, | |
| "learning_rate": 0.0002, | |
| "loss": 4.144, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.25657472738935216, | |
| "eval_loss": 0.9652090072631836, | |
| "eval_runtime": 7.9298, | |
| "eval_samples_per_second": 20.807, | |
| "eval_steps_per_second": 10.467, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.28223220012828737, | |
| "grad_norm": 5.021260738372803, | |
| "learning_rate": 0.0002, | |
| "loss": 4.0535, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.3078896728672226, | |
| "grad_norm": 3.946540355682373, | |
| "learning_rate": 0.0002, | |
| "loss": 4.2911, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3335471456061578, | |
| "grad_norm": 5.100417137145996, | |
| "learning_rate": 0.0002, | |
| "loss": 4.1604, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.359204618345093, | |
| "grad_norm": 3.0885791778564453, | |
| "learning_rate": 0.0002, | |
| "loss": 3.846, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.38486209108402825, | |
| "grad_norm": 3.596226453781128, | |
| "learning_rate": 0.0002, | |
| "loss": 4.1906, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.38486209108402825, | |
| "eval_loss": 0.9527939558029175, | |
| "eval_runtime": 7.9098, | |
| "eval_samples_per_second": 20.86, | |
| "eval_steps_per_second": 10.493, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.41051956382296345, | |
| "grad_norm": 3.3079276084899902, | |
| "learning_rate": 0.0002, | |
| "loss": 3.9429, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.43617703656189866, | |
| "grad_norm": 2.9778153896331787, | |
| "learning_rate": 0.0002, | |
| "loss": 4.0369, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.46183450930083386, | |
| "grad_norm": 3.6058528423309326, | |
| "learning_rate": 0.0002, | |
| "loss": 4.5255, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.48749198203976907, | |
| "grad_norm": 5.9715447425842285, | |
| "learning_rate": 0.0002, | |
| "loss": 3.9174, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.5131494547787043, | |
| "grad_norm": 4.206804275512695, | |
| "learning_rate": 0.0002, | |
| "loss": 3.9483, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5131494547787043, | |
| "eval_loss": 0.9494011998176575, | |
| "eval_runtime": 7.9027, | |
| "eval_samples_per_second": 20.879, | |
| "eval_steps_per_second": 10.503, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.110150213926912e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |