| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.022629554197782304, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00045259108395564606, | |
| "eval_loss": 0.4409753978252411, | |
| "eval_runtime": 119.5679, | |
| "eval_samples_per_second": 7.786, | |
| "eval_steps_per_second": 3.897, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0022629554197782305, | |
| "grad_norm": 0.2826593220233917, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4614, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004525910839556461, | |
| "grad_norm": 0.3693868815898895, | |
| "learning_rate": 0.0001, | |
| "loss": 0.4523, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004525910839556461, | |
| "eval_loss": 0.4037085175514221, | |
| "eval_runtime": 120.5989, | |
| "eval_samples_per_second": 7.72, | |
| "eval_steps_per_second": 3.864, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006788866259334691, | |
| "grad_norm": 0.38589227199554443, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.3773, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009051821679112922, | |
| "grad_norm": 0.36434707045555115, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.3543, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009051821679112922, | |
| "eval_loss": 0.3476487696170807, | |
| "eval_runtime": 121.2735, | |
| "eval_samples_per_second": 7.677, | |
| "eval_steps_per_second": 3.843, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011314777098891152, | |
| "grad_norm": 0.3032950460910797, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.3064, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.013577732518669382, | |
| "grad_norm": 0.3895096778869629, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3846, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.013577732518669382, | |
| "eval_loss": 0.32912540435791016, | |
| "eval_runtime": 121.1835, | |
| "eval_samples_per_second": 7.683, | |
| "eval_steps_per_second": 3.845, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.015840687938447614, | |
| "grad_norm": 0.3940449059009552, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.3407, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.018103643358225844, | |
| "grad_norm": 0.36751681566238403, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.2876, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.018103643358225844, | |
| "eval_loss": 0.32187148928642273, | |
| "eval_runtime": 121.8496, | |
| "eval_samples_per_second": 7.641, | |
| "eval_steps_per_second": 3.824, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.020366598778004074, | |
| "grad_norm": 0.35453692078590393, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.3371, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.022629554197782304, | |
| "grad_norm": 0.3624661862850189, | |
| "learning_rate": 0.0, | |
| "loss": 0.3531, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.022629554197782304, | |
| "eval_loss": 0.32060080766677856, | |
| "eval_runtime": 121.6604, | |
| "eval_samples_per_second": 7.652, | |
| "eval_steps_per_second": 3.83, | |
| "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": 1.8171978628202496e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |