| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.012576243476073697, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00025152486952147396, | |
| "eval_loss": 0.7711982727050781, | |
| "eval_runtime": 114.3608, | |
| "eval_samples_per_second": 14.647, | |
| "eval_steps_per_second": 7.328, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012576243476073697, | |
| "grad_norm": 0.17833726108074188, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7628, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0025152486952147394, | |
| "grad_norm": 0.2529178261756897, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7841, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0025152486952147394, | |
| "eval_loss": 0.7362951040267944, | |
| "eval_runtime": 115.5562, | |
| "eval_samples_per_second": 14.495, | |
| "eval_steps_per_second": 7.252, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003772873042822109, | |
| "grad_norm": 0.2876896858215332, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.6817, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005030497390429479, | |
| "grad_norm": 0.35196399688720703, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.6442, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005030497390429479, | |
| "eval_loss": 0.6331722140312195, | |
| "eval_runtime": 115.7734, | |
| "eval_samples_per_second": 14.468, | |
| "eval_steps_per_second": 7.238, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0062881217380368485, | |
| "grad_norm": 0.3112280070781708, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.5533, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007545746085644218, | |
| "grad_norm": 0.3299297094345093, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6657, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.007545746085644218, | |
| "eval_loss": 0.5936422944068909, | |
| "eval_runtime": 115.79, | |
| "eval_samples_per_second": 14.466, | |
| "eval_steps_per_second": 7.237, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008803370433251587, | |
| "grad_norm": 0.2656802833080292, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.6052, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.010060994780858958, | |
| "grad_norm": 0.3224814534187317, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.6067, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.010060994780858958, | |
| "eval_loss": 0.5825388431549072, | |
| "eval_runtime": 115.6224, | |
| "eval_samples_per_second": 14.487, | |
| "eval_steps_per_second": 7.248, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.011318619128466326, | |
| "grad_norm": 0.3185206651687622, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.5621, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.012576243476073697, | |
| "grad_norm": 0.3230144679546356, | |
| "learning_rate": 0.0, | |
| "loss": 0.5723, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.012576243476073697, | |
| "eval_loss": 0.580285370349884, | |
| "eval_runtime": 115.6675, | |
| "eval_samples_per_second": 14.481, | |
| "eval_steps_per_second": 7.245, | |
| "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": 6957230456832000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |