| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.05324813631522897, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0010649627263045794, | |
| "eval_loss": 1.6592028141021729, | |
| "eval_runtime": 34.8289, | |
| "eval_samples_per_second": 11.37, | |
| "eval_steps_per_second": 5.685, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005324813631522897, | |
| "grad_norm": 0.9289127588272095, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4958, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010649627263045794, | |
| "grad_norm": 0.9269077181816101, | |
| "learning_rate": 0.0001, | |
| "loss": 1.7006, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010649627263045794, | |
| "eval_loss": 1.5683319568634033, | |
| "eval_runtime": 35.2172, | |
| "eval_samples_per_second": 11.244, | |
| "eval_steps_per_second": 5.622, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01597444089456869, | |
| "grad_norm": 0.9349473714828491, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.4579, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.021299254526091587, | |
| "grad_norm": 1.4881868362426758, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.4518, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.021299254526091587, | |
| "eval_loss": 1.4283188581466675, | |
| "eval_runtime": 35.2186, | |
| "eval_samples_per_second": 11.244, | |
| "eval_steps_per_second": 5.622, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.026624068157614485, | |
| "grad_norm": 0.8776378631591797, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.4113, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03194888178913738, | |
| "grad_norm": 1.4942994117736816, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2995, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03194888178913738, | |
| "eval_loss": 1.3721179962158203, | |
| "eval_runtime": 35.2285, | |
| "eval_samples_per_second": 11.241, | |
| "eval_steps_per_second": 5.62, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03727369542066028, | |
| "grad_norm": 0.8232759237289429, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.2642, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.042598509052183174, | |
| "grad_norm": 0.8788539171218872, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.3297, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.042598509052183174, | |
| "eval_loss": 1.3412672281265259, | |
| "eval_runtime": 35.3203, | |
| "eval_samples_per_second": 11.212, | |
| "eval_steps_per_second": 5.606, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04792332268370607, | |
| "grad_norm": 0.913733959197998, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.3858, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05324813631522897, | |
| "grad_norm": 1.3565720319747925, | |
| "learning_rate": 0.0, | |
| "loss": 1.3473, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05324813631522897, | |
| "eval_loss": 1.336426854133606, | |
| "eval_runtime": 35.4704, | |
| "eval_samples_per_second": 11.164, | |
| "eval_steps_per_second": 5.582, | |
| "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": 1.2577036887392256e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |