| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0751597143930853, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001503194287861706, | |
| "eval_loss": 2.843785524368286, | |
| "eval_runtime": 21.6407, | |
| "eval_samples_per_second": 12.985, | |
| "eval_steps_per_second": 6.516, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00751597143930853, | |
| "grad_norm": 4.628039360046387, | |
| "learning_rate": 5e-05, | |
| "loss": 2.8081, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01503194287861706, | |
| "grad_norm": 3.0285913944244385, | |
| "learning_rate": 0.0001, | |
| "loss": 2.3268, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01503194287861706, | |
| "eval_loss": 1.9367932081222534, | |
| "eval_runtime": 21.9973, | |
| "eval_samples_per_second": 12.774, | |
| "eval_steps_per_second": 6.41, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02254791431792559, | |
| "grad_norm": 1.9986026287078857, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.8442, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03006388575723412, | |
| "grad_norm": 1.3669120073318481, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.6288, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03006388575723412, | |
| "eval_loss": 1.5897588729858398, | |
| "eval_runtime": 22.2023, | |
| "eval_samples_per_second": 12.656, | |
| "eval_steps_per_second": 6.351, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03757985719654265, | |
| "grad_norm": 1.0575623512268066, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.5414, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04509582863585118, | |
| "grad_norm": 1.018785834312439, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4741, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04509582863585118, | |
| "eval_loss": 1.432031273841858, | |
| "eval_runtime": 22.2918, | |
| "eval_samples_per_second": 12.606, | |
| "eval_steps_per_second": 6.325, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05261180007515971, | |
| "grad_norm": 1.1833542585372925, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.4144, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.06012777151446824, | |
| "grad_norm": 1.2001922130584717, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.3596, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06012777151446824, | |
| "eval_loss": 1.3779289722442627, | |
| "eval_runtime": 22.4173, | |
| "eval_samples_per_second": 12.535, | |
| "eval_steps_per_second": 6.29, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06764374295377677, | |
| "grad_norm": 0.9354619383811951, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.375, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0751597143930853, | |
| "grad_norm": 1.0342998504638672, | |
| "learning_rate": 0.0, | |
| "loss": 1.3414, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0751597143930853, | |
| "eval_loss": 1.3660917282104492, | |
| "eval_runtime": 22.4697, | |
| "eval_samples_per_second": 12.506, | |
| "eval_steps_per_second": 6.275, | |
| "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": 4894777933824000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |