| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.003770810158562567, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.541620317125135e-05, | |
| "eval_loss": 2.0435900688171387, | |
| "eval_runtime": 652.1431, | |
| "eval_samples_per_second": 8.563, | |
| "eval_steps_per_second": 4.281, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003770810158562567, | |
| "grad_norm": 1.85041081905365, | |
| "learning_rate": 5e-05, | |
| "loss": 2.0936, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0007541620317125134, | |
| "grad_norm": 1.8200923204421997, | |
| "learning_rate": 0.0001, | |
| "loss": 1.82, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007541620317125134, | |
| "eval_loss": 1.3071166276931763, | |
| "eval_runtime": 656.643, | |
| "eval_samples_per_second": 8.504, | |
| "eval_steps_per_second": 4.252, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0011312430475687702, | |
| "grad_norm": 2.0114729404449463, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.9863, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0015083240634250269, | |
| "grad_norm": 1.6664632558822632, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.7031, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0015083240634250269, | |
| "eval_loss": 0.6721987724304199, | |
| "eval_runtime": 656.6676, | |
| "eval_samples_per_second": 8.504, | |
| "eval_steps_per_second": 4.252, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0018854050792812835, | |
| "grad_norm": 1.5729988813400269, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.6764, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0022624860951375404, | |
| "grad_norm": 1.5029770135879517, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5842, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0022624860951375404, | |
| "eval_loss": 0.5466399192810059, | |
| "eval_runtime": 657.5066, | |
| "eval_samples_per_second": 8.493, | |
| "eval_steps_per_second": 4.246, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002639567110993797, | |
| "grad_norm": 1.5323377847671509, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.5669, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0030166481268500537, | |
| "grad_norm": 1.386945128440857, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.53, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0030166481268500537, | |
| "eval_loss": 0.5142520070075989, | |
| "eval_runtime": 657.6286, | |
| "eval_samples_per_second": 8.491, | |
| "eval_steps_per_second": 4.246, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0033937291427063106, | |
| "grad_norm": 2.1587717533111572, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.4441, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.003770810158562567, | |
| "grad_norm": 1.3008843660354614, | |
| "learning_rate": 0.0, | |
| "loss": 0.4892, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.003770810158562567, | |
| "eval_loss": 0.5087710022926331, | |
| "eval_runtime": 658.2197, | |
| "eval_samples_per_second": 8.483, | |
| "eval_steps_per_second": 4.242, | |
| "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": 1.780205588840448e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |