| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.08283288465520812, | |
| "eval_steps": 50, | |
| "global_step": 400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.010354110581901015, | |
| "grad_norm": 7.257113933563232, | |
| "learning_rate": 2.2545090180360722e-05, | |
| "loss": 2.2524, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.010354110581901015, | |
| "eval_loss": 2.0315754413604736, | |
| "eval_runtime": 22593.0877, | |
| "eval_samples_per_second": 0.427, | |
| "eval_steps_per_second": 0.053, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02070822116380203, | |
| "grad_norm": 8.316986083984375, | |
| "learning_rate": 2.0040080160320643e-05, | |
| "loss": 2.015, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02070822116380203, | |
| "eval_loss": 1.9098063707351685, | |
| "eval_runtime": 22720.7806, | |
| "eval_samples_per_second": 0.425, | |
| "eval_steps_per_second": 0.053, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.031062331745703043, | |
| "grad_norm": 9.276594161987305, | |
| "learning_rate": 1.7535070140280564e-05, | |
| "loss": 1.9563, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.031062331745703043, | |
| "eval_loss": 1.8264315128326416, | |
| "eval_runtime": 22682.9888, | |
| "eval_samples_per_second": 0.426, | |
| "eval_steps_per_second": 0.053, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.04141644232760406, | |
| "grad_norm": 17.792049407958984, | |
| "learning_rate": 1.5030060120240483e-05, | |
| "loss": 1.8385, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.04141644232760406, | |
| "eval_loss": 1.7933390140533447, | |
| "eval_runtime": 22674.0168, | |
| "eval_samples_per_second": 0.426, | |
| "eval_steps_per_second": 0.053, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.05177055290950507, | |
| "grad_norm": 12.992188453674316, | |
| "learning_rate": 1.25250501002004e-05, | |
| "loss": 1.8308, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.05177055290950507, | |
| "eval_loss": 1.7789344787597656, | |
| "eval_runtime": 22673.0996, | |
| "eval_samples_per_second": 0.426, | |
| "eval_steps_per_second": 0.053, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.062124663491406086, | |
| "grad_norm": 13.58079719543457, | |
| "learning_rate": 1.0020040080160322e-05, | |
| "loss": 1.8487, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.062124663491406086, | |
| "eval_loss": 1.7638577222824097, | |
| "eval_runtime": 22728.6743, | |
| "eval_samples_per_second": 0.425, | |
| "eval_steps_per_second": 0.053, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.0724787740733071, | |
| "grad_norm": 9.611258506774902, | |
| "learning_rate": 7.515030060120242e-06, | |
| "loss": 1.7439, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.0724787740733071, | |
| "eval_loss": 1.7577449083328247, | |
| "eval_runtime": 22671.3046, | |
| "eval_samples_per_second": 0.426, | |
| "eval_steps_per_second": 0.053, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.08283288465520812, | |
| "grad_norm": 12.747760772705078, | |
| "learning_rate": 5.010020040080161e-06, | |
| "loss": 1.8259, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.08283288465520812, | |
| "eval_loss": 1.7505788803100586, | |
| "eval_runtime": 22670.2702, | |
| "eval_samples_per_second": 0.426, | |
| "eval_steps_per_second": 0.053, | |
| "step": 400 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 500, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6573652967424000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |