| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.015278838808250574, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00030557677616501144, | |
| "eval_loss": 11.932645797729492, | |
| "eval_runtime": 12.428, | |
| "eval_samples_per_second": 110.878, | |
| "eval_steps_per_second": 55.439, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015278838808250573, | |
| "grad_norm": 0.010855333879590034, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9327, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0030557677616501145, | |
| "grad_norm": 0.016724513843655586, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9349, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0030557677616501145, | |
| "eval_loss": 11.932631492614746, | |
| "eval_runtime": 12.6411, | |
| "eval_samples_per_second": 109.01, | |
| "eval_steps_per_second": 54.505, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004583651642475172, | |
| "grad_norm": 0.01697218418121338, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.9325, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006111535523300229, | |
| "grad_norm": 0.01060065533965826, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.9331, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006111535523300229, | |
| "eval_loss": 11.932604789733887, | |
| "eval_runtime": 12.5178, | |
| "eval_samples_per_second": 110.083, | |
| "eval_steps_per_second": 55.041, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007639419404125287, | |
| "grad_norm": 0.015284588560461998, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 11.9333, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.009167303284950344, | |
| "grad_norm": 0.014031444676220417, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9326, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.009167303284950344, | |
| "eval_loss": 11.932587623596191, | |
| "eval_runtime": 12.7663, | |
| "eval_samples_per_second": 107.941, | |
| "eval_steps_per_second": 53.97, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0106951871657754, | |
| "grad_norm": 0.026665780693292618, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 11.9352, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.012223071046600458, | |
| "grad_norm": 0.018195880576968193, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 11.9315, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.012223071046600458, | |
| "eval_loss": 11.932579040527344, | |
| "eval_runtime": 12.7987, | |
| "eval_samples_per_second": 107.667, | |
| "eval_steps_per_second": 53.833, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.013750954927425516, | |
| "grad_norm": 0.03546914830803871, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 11.934, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.015278838808250574, | |
| "grad_norm": 0.013694709166884422, | |
| "learning_rate": 0.0, | |
| "loss": 11.9332, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.015278838808250574, | |
| "eval_loss": 11.932577133178711, | |
| "eval_runtime": 12.6629, | |
| "eval_samples_per_second": 108.822, | |
| "eval_steps_per_second": 54.411, | |
| "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": 6026231808.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |