| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.008454872120059184, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001690974424011837, | |
| "eval_loss": 0.30238884687423706, | |
| "eval_runtime": 303.9153, | |
| "eval_samples_per_second": 8.193, | |
| "eval_steps_per_second": 4.097, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008454872120059184, | |
| "grad_norm": 0.06718260049819946, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3094, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0016909744240118367, | |
| "grad_norm": 0.07813317328691483, | |
| "learning_rate": 0.0001, | |
| "loss": 0.284, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0016909744240118367, | |
| "eval_loss": 0.2945749759674072, | |
| "eval_runtime": 303.259, | |
| "eval_samples_per_second": 8.211, | |
| "eval_steps_per_second": 4.105, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0025364616360177552, | |
| "grad_norm": 0.10093750804662704, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.2861, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0033819488480236735, | |
| "grad_norm": 0.17985399067401886, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.2841, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0033819488480236735, | |
| "eval_loss": 0.2696641683578491, | |
| "eval_runtime": 303.3236, | |
| "eval_samples_per_second": 8.209, | |
| "eval_steps_per_second": 4.105, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004227436060029592, | |
| "grad_norm": 0.11035940796136856, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.2481, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0050729232720355105, | |
| "grad_norm": 0.10945611447095871, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2563, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0050729232720355105, | |
| "eval_loss": 0.26252034306526184, | |
| "eval_runtime": 304.3401, | |
| "eval_samples_per_second": 8.182, | |
| "eval_steps_per_second": 4.091, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005918410484041429, | |
| "grad_norm": 0.11487659066915512, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.2584, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.006763897696047347, | |
| "grad_norm": 0.11750715970993042, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.2531, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006763897696047347, | |
| "eval_loss": 0.2599148452281952, | |
| "eval_runtime": 303.6003, | |
| "eval_samples_per_second": 8.202, | |
| "eval_steps_per_second": 4.101, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.007609384908053266, | |
| "grad_norm": 0.11680182069540024, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.2381, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.008454872120059184, | |
| "grad_norm": 0.1036166399717331, | |
| "learning_rate": 0.0, | |
| "loss": 0.2547, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008454872120059184, | |
| "eval_loss": 0.2593758702278137, | |
| "eval_runtime": 304.1021, | |
| "eval_samples_per_second": 8.188, | |
| "eval_steps_per_second": 4.094, | |
| "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": 1.7295662757445632e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |