| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0040710810755796205, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.14216215115924e-05, | |
| "eval_loss": 2.5588338375091553, | |
| "eval_runtime": 327.8895, | |
| "eval_samples_per_second": 15.774, | |
| "eval_steps_per_second": 7.887, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00040710810755796204, | |
| "grad_norm": 1.4718071222305298, | |
| "learning_rate": 5e-05, | |
| "loss": 2.4777, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008142162151159241, | |
| "grad_norm": 1.9134249687194824, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5951, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008142162151159241, | |
| "eval_loss": 2.408738851547241, | |
| "eval_runtime": 330.6795, | |
| "eval_samples_per_second": 15.641, | |
| "eval_steps_per_second": 7.82, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001221324322673886, | |
| "grad_norm": 2.1531338691711426, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.3268, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0016284324302318482, | |
| "grad_norm": 2.4186878204345703, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.9394, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0016284324302318482, | |
| "eval_loss": 1.9988257884979248, | |
| "eval_runtime": 330.9251, | |
| "eval_samples_per_second": 15.629, | |
| "eval_steps_per_second": 7.814, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0020355405377898103, | |
| "grad_norm": 2.270822763442993, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.9121, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.002442648645347772, | |
| "grad_norm": 2.1868631839752197, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8007, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002442648645347772, | |
| "eval_loss": 1.936930537223816, | |
| "eval_runtime": 330.7595, | |
| "eval_samples_per_second": 15.637, | |
| "eval_steps_per_second": 7.818, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002849756752905734, | |
| "grad_norm": 1.8994628190994263, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.7277, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0032568648604636963, | |
| "grad_norm": 2.705153465270996, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.9222, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0032568648604636963, | |
| "eval_loss": 1.9053153991699219, | |
| "eval_runtime": 330.6357, | |
| "eval_samples_per_second": 15.643, | |
| "eval_steps_per_second": 7.821, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.003663972968021658, | |
| "grad_norm": 2.419757604598999, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.9121, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0040710810755796205, | |
| "grad_norm": 2.1531717777252197, | |
| "learning_rate": 0.0, | |
| "loss": 1.7793, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0040710810755796205, | |
| "eval_loss": 1.9002810716629028, | |
| "eval_runtime": 330.3711, | |
| "eval_samples_per_second": 15.655, | |
| "eval_steps_per_second": 7.828, | |
| "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": 7769961100738560.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |