| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.012251899044351875, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002450379808870375, | |
| "eval_loss": 1.2887710332870483, | |
| "eval_runtime": 202.0425, | |
| "eval_samples_per_second": 8.508, | |
| "eval_steps_per_second": 4.257, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012251899044351876, | |
| "grad_norm": 9.062094688415527, | |
| "learning_rate": 5e-05, | |
| "loss": 5.26, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002450379808870375, | |
| "grad_norm": 7.3053297996521, | |
| "learning_rate": 0.0001, | |
| "loss": 4.7386, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002450379808870375, | |
| "eval_loss": 1.099696159362793, | |
| "eval_runtime": 203.9631, | |
| "eval_samples_per_second": 8.428, | |
| "eval_steps_per_second": 4.216, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0036755697133055622, | |
| "grad_norm": 8.70495891571045, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.2031, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00490075961774075, | |
| "grad_norm": 7.727749347686768, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 4.1983, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00490075961774075, | |
| "eval_loss": 0.9561256170272827, | |
| "eval_runtime": 203.4151, | |
| "eval_samples_per_second": 8.451, | |
| "eval_steps_per_second": 4.228, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006125949522175937, | |
| "grad_norm": 6.156836032867432, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 4.2422, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0073511394266111245, | |
| "grad_norm": 6.922292232513428, | |
| "learning_rate": 5e-05, | |
| "loss": 3.8974, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0073511394266111245, | |
| "eval_loss": 0.9152467250823975, | |
| "eval_runtime": 204.0154, | |
| "eval_samples_per_second": 8.426, | |
| "eval_steps_per_second": 4.215, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008576329331046312, | |
| "grad_norm": 5.732418060302734, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 4.1309, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0098015192354815, | |
| "grad_norm": 4.729028224945068, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.1976, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0098015192354815, | |
| "eval_loss": 0.9041345119476318, | |
| "eval_runtime": 203.9483, | |
| "eval_samples_per_second": 8.429, | |
| "eval_steps_per_second": 4.217, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.011026709139916687, | |
| "grad_norm": 4.707295894622803, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.6423, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.012251899044351875, | |
| "grad_norm": 6.245633125305176, | |
| "learning_rate": 0.0, | |
| "loss": 3.305, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.012251899044351875, | |
| "eval_loss": 0.90166175365448, | |
| "eval_runtime": 203.8285, | |
| "eval_samples_per_second": 8.434, | |
| "eval_steps_per_second": 4.219, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.75267179921408e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |