| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0009760144450137862, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.9520288900275725e-05, | |
| "eval_loss": 1.9482343196868896, | |
| "eval_runtime": 1582.0989, | |
| "eval_samples_per_second": 13.634, | |
| "eval_steps_per_second": 6.817, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.760144450137862e-05, | |
| "grad_norm": 1.2670663595199585, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8881, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00019520288900275724, | |
| "grad_norm": 1.6480966806411743, | |
| "learning_rate": 0.0001, | |
| "loss": 1.877, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00019520288900275724, | |
| "eval_loss": 1.800879716873169, | |
| "eval_runtime": 1590.9144, | |
| "eval_samples_per_second": 13.558, | |
| "eval_steps_per_second": 6.779, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00029280433350413584, | |
| "grad_norm": 1.7097420692443848, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.7452, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0003904057780055145, | |
| "grad_norm": 1.5260850191116333, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.7393, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0003904057780055145, | |
| "eval_loss": 1.6786584854125977, | |
| "eval_runtime": 1586.6979, | |
| "eval_samples_per_second": 13.594, | |
| "eval_steps_per_second": 6.797, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0004880072225068931, | |
| "grad_norm": 1.5705738067626953, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.6065, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0005856086670082717, | |
| "grad_norm": 1.466151237487793, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6043, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0005856086670082717, | |
| "eval_loss": 1.621889352798462, | |
| "eval_runtime": 1583.6005, | |
| "eval_samples_per_second": 13.621, | |
| "eval_steps_per_second": 6.81, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0006832101115096503, | |
| "grad_norm": 1.3835320472717285, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.5097, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.000780811556011029, | |
| "grad_norm": 1.4106273651123047, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.5349, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.000780811556011029, | |
| "eval_loss": 1.5933020114898682, | |
| "eval_runtime": 1587.888, | |
| "eval_samples_per_second": 13.584, | |
| "eval_steps_per_second": 6.792, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0008784130005124076, | |
| "grad_norm": 1.8581594228744507, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.5793, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0009760144450137862, | |
| "grad_norm": 1.2158750295639038, | |
| "learning_rate": 0.0, | |
| "loss": 1.5234, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0009760144450137862, | |
| "eval_loss": 1.587828516960144, | |
| "eval_runtime": 1585.3929, | |
| "eval_samples_per_second": 13.605, | |
| "eval_steps_per_second": 6.803, | |
| "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": 1.0218842471006208e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |