| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.012759170653907496, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004253056884635832, | |
| "eval_loss": 0.8287492990493774, | |
| "eval_runtime": 128.7032, | |
| "eval_samples_per_second": 7.692, | |
| "eval_steps_per_second": 3.846, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012759170653907496, | |
| "grad_norm": 0.45128631591796875, | |
| "learning_rate": 6e-05, | |
| "loss": 0.7902, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002551834130781499, | |
| "grad_norm": 0.5250253081321716, | |
| "learning_rate": 0.00012, | |
| "loss": 0.8667, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0034024455077086655, | |
| "eval_loss": 0.7585725784301758, | |
| "eval_runtime": 130.5666, | |
| "eval_samples_per_second": 7.582, | |
| "eval_steps_per_second": 3.791, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003827751196172249, | |
| "grad_norm": 0.5552636981010437, | |
| "learning_rate": 0.00018, | |
| "loss": 0.7197, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005103668261562998, | |
| "grad_norm": 0.5403614044189453, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.6963, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006379585326953748, | |
| "grad_norm": 0.5106764435768127, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.6779, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006804891015417331, | |
| "eval_loss": 0.6631687879562378, | |
| "eval_runtime": 130.792, | |
| "eval_samples_per_second": 7.569, | |
| "eval_steps_per_second": 3.785, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.007655502392344498, | |
| "grad_norm": 0.5691841244697571, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.6017, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.008931419457735247, | |
| "grad_norm": 0.5311877727508545, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.6715, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.010207336523125997, | |
| "grad_norm": 0.4842340648174286, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.6007, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.010207336523125997, | |
| "eval_loss": 0.6371272206306458, | |
| "eval_runtime": 130.8895, | |
| "eval_samples_per_second": 7.564, | |
| "eval_steps_per_second": 3.782, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.011483253588516746, | |
| "grad_norm": 0.46998074650764465, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.6658, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.012759170653907496, | |
| "grad_norm": 0.44314372539520264, | |
| "learning_rate": 0.0, | |
| "loss": 0.6039, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.112830925340672e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |