| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.007494566439331485, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00014989132878662968, | |
| "eval_loss": 10.374155044555664, | |
| "eval_runtime": 12.6184, | |
| "eval_samples_per_second": 222.691, | |
| "eval_steps_per_second": 111.346, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007494566439331485, | |
| "grad_norm": 0.039108939468860626, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3732, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001498913287866297, | |
| "grad_norm": 0.04206083342432976, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3743, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001498913287866297, | |
| "eval_loss": 10.373963356018066, | |
| "eval_runtime": 12.6553, | |
| "eval_samples_per_second": 222.042, | |
| "eval_steps_per_second": 111.021, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0022483699317994454, | |
| "grad_norm": 0.03635816648602486, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.3752, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002997826575732594, | |
| "grad_norm": 0.038423050194978714, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.3757, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002997826575732594, | |
| "eval_loss": 10.373547554016113, | |
| "eval_runtime": 12.9794, | |
| "eval_samples_per_second": 216.497, | |
| "eval_steps_per_second": 108.248, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0037472832196657423, | |
| "grad_norm": 0.03428508713841438, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.3747, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004496739863598891, | |
| "grad_norm": 0.03665791451931, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3744, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004496739863598891, | |
| "eval_loss": 10.373238563537598, | |
| "eval_runtime": 12.852, | |
| "eval_samples_per_second": 218.643, | |
| "eval_steps_per_second": 109.321, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00524619650753204, | |
| "grad_norm": 0.036889541894197464, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 10.3713, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.005995653151465188, | |
| "grad_norm": 0.03897949680685997, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 10.3724, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.005995653151465188, | |
| "eval_loss": 10.37308120727539, | |
| "eval_runtime": 12.7699, | |
| "eval_samples_per_second": 220.049, | |
| "eval_steps_per_second": 110.025, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006745109795398337, | |
| "grad_norm": 0.03459719195961952, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 10.3734, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.007494566439331485, | |
| "grad_norm": 0.03152477368712425, | |
| "learning_rate": 0.0, | |
| "loss": 10.3729, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.007494566439331485, | |
| "eval_loss": 10.373052597045898, | |
| "eval_runtime": 12.5906, | |
| "eval_samples_per_second": 223.182, | |
| "eval_steps_per_second": 111.591, | |
| "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": 646545408000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |