| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.26058631921824105, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05211726384364821, | |
| "grad_norm": 0.5809528231620789, | |
| "learning_rate": 1e-05, | |
| "loss": 3.3729, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05211726384364821, | |
| "eval_loss": 3.4135453701019287, | |
| "eval_runtime": 73.5945, | |
| "eval_samples_per_second": 0.448, | |
| "eval_steps_per_second": 0.231, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.10423452768729642, | |
| "grad_norm": 0.5232105255126953, | |
| "learning_rate": 2e-05, | |
| "loss": 3.0151, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.10423452768729642, | |
| "eval_loss": 3.3981997966766357, | |
| "eval_runtime": 0.6761, | |
| "eval_samples_per_second": 48.808, | |
| "eval_steps_per_second": 25.144, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1563517915309446, | |
| "grad_norm": 0.49967160820961, | |
| "learning_rate": 3e-05, | |
| "loss": 3.0695, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.20846905537459284, | |
| "grad_norm": 0.6629552245140076, | |
| "learning_rate": 4e-05, | |
| "loss": 3.3236, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.20846905537459284, | |
| "eval_loss": 3.390848398208618, | |
| "eval_runtime": 0.4689, | |
| "eval_samples_per_second": 70.38, | |
| "eval_steps_per_second": 36.256, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.26058631921824105, | |
| "grad_norm": 0.48219630122184753, | |
| "learning_rate": 5e-05, | |
| "loss": 2.8734, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 511583956500480.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |