| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0011810628384483195, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.3621256768966393e-05, | |
| "eval_loss": 2.5973010063171387, | |
| "eval_runtime": 1090.9873, | |
| "eval_samples_per_second": 16.339, | |
| "eval_steps_per_second": 8.17, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00011810628384483197, | |
| "grad_norm": 1.1327033042907715, | |
| "learning_rate": 5e-05, | |
| "loss": 2.5571, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00023621256768966393, | |
| "grad_norm": 1.561854362487793, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5089, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00023621256768966393, | |
| "eval_loss": 2.4637045860290527, | |
| "eval_runtime": 1104.3999, | |
| "eval_samples_per_second": 16.141, | |
| "eval_steps_per_second": 8.07, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0003543188515344959, | |
| "grad_norm": 1.313326358795166, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.451, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00047242513537932787, | |
| "grad_norm": 1.3732658624649048, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.1585, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00047242513537932787, | |
| "eval_loss": 2.032883882522583, | |
| "eval_runtime": 1099.1405, | |
| "eval_samples_per_second": 16.218, | |
| "eval_steps_per_second": 8.109, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0005905314192241598, | |
| "grad_norm": 1.797598958015442, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.0492, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0007086377030689918, | |
| "grad_norm": 1.6009327173233032, | |
| "learning_rate": 5e-05, | |
| "loss": 1.9051, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0007086377030689918, | |
| "eval_loss": 1.93674635887146, | |
| "eval_runtime": 1106.4611, | |
| "eval_samples_per_second": 16.111, | |
| "eval_steps_per_second": 8.055, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0008267439869138238, | |
| "grad_norm": 1.4379733800888062, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.9824, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0009448502707586557, | |
| "grad_norm": 1.50521719455719, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.86, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0009448502707586557, | |
| "eval_loss": 1.9020222425460815, | |
| "eval_runtime": 1103.6246, | |
| "eval_samples_per_second": 16.152, | |
| "eval_steps_per_second": 8.076, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0010629565546034876, | |
| "grad_norm": 1.6052892208099365, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.779, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0011810628384483195, | |
| "grad_norm": 1.7195042371749878, | |
| "learning_rate": 0.0, | |
| "loss": 1.8553, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0011810628384483195, | |
| "eval_loss": 1.8959852457046509, | |
| "eval_runtime": 1102.5425, | |
| "eval_samples_per_second": 16.168, | |
| "eval_steps_per_second": 8.084, | |
| "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": 7810963533987840.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |