| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00046108447067502766, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.610844706750277e-05, | |
| "grad_norm": 3.4663827419281006, | |
| "learning_rate": 2e-05, | |
| "loss": 13.5415, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.610844706750277e-05, | |
| "eval_loss": 3.3450958728790283, | |
| "eval_runtime": 167.8135, | |
| "eval_samples_per_second": 54.418, | |
| "eval_steps_per_second": 27.209, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.221689413500554e-05, | |
| "grad_norm": 2.5918078422546387, | |
| "learning_rate": 4e-05, | |
| "loss": 12.7993, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0001383253412025083, | |
| "grad_norm": 2.468151092529297, | |
| "learning_rate": 6e-05, | |
| "loss": 14.3332, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0001383253412025083, | |
| "eval_loss": 3.343933343887329, | |
| "eval_runtime": 167.5179, | |
| "eval_samples_per_second": 54.514, | |
| "eval_steps_per_second": 27.257, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00018443378827001107, | |
| "grad_norm": 2.77644944190979, | |
| "learning_rate": 8e-05, | |
| "loss": 11.7637, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00023054223533751383, | |
| "grad_norm": 2.815096139907837, | |
| "learning_rate": 0.0001, | |
| "loss": 14.0333, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0002766506824050166, | |
| "grad_norm": 2.6768336296081543, | |
| "learning_rate": 0.00012, | |
| "loss": 15.6457, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002766506824050166, | |
| "eval_loss": 3.3033151626586914, | |
| "eval_runtime": 167.6598, | |
| "eval_samples_per_second": 54.467, | |
| "eval_steps_per_second": 27.234, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00032275912947251934, | |
| "grad_norm": 2.4870615005493164, | |
| "learning_rate": 0.00014, | |
| "loss": 12.278, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00036886757654002215, | |
| "grad_norm": 4.719938278198242, | |
| "learning_rate": 0.00016, | |
| "loss": 14.5554, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0004149760236075249, | |
| "grad_norm": 4.982387065887451, | |
| "learning_rate": 0.00018, | |
| "loss": 11.9624, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0004149760236075249, | |
| "eval_loss": 3.0232017040252686, | |
| "eval_runtime": 167.912, | |
| "eval_samples_per_second": 54.386, | |
| "eval_steps_per_second": 27.193, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00046108447067502766, | |
| "grad_norm": 3.9339354038238525, | |
| "learning_rate": 0.0002, | |
| "loss": 13.5038, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 321134109130752.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |