| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.08249603384452671, | |
| "eval_steps": 10, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0021152829190904283, | |
| "eval_loss": 0.8276494741439819, | |
| "eval_runtime": 16.2246, | |
| "eval_samples_per_second": 12.265, | |
| "eval_steps_per_second": 6.163, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010576414595452142, | |
| "grad_norm": 63.81797790527344, | |
| "learning_rate": 5e-05, | |
| "loss": 4.1889, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.021152829190904283, | |
| "grad_norm": 21.4931697845459, | |
| "learning_rate": 0.0001, | |
| "loss": 0.841, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.021152829190904283, | |
| "eval_loss": 0.2516094148159027, | |
| "eval_runtime": 16.9953, | |
| "eval_samples_per_second": 11.709, | |
| "eval_steps_per_second": 5.884, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03172924378635643, | |
| "grad_norm": 6.5418853759765625, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.0068, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04230565838180857, | |
| "grad_norm": 1.9580116271972656, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.7493, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04230565838180857, | |
| "eval_loss": 0.2253044992685318, | |
| "eval_runtime": 17.4081, | |
| "eval_samples_per_second": 11.431, | |
| "eval_steps_per_second": 5.744, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05288207297726071, | |
| "grad_norm": 4.782344818115234, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.57, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06345848757271286, | |
| "grad_norm": 1.8820977210998535, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2061, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06345848757271286, | |
| "eval_loss": 0.2232237458229065, | |
| "eval_runtime": 17.669, | |
| "eval_samples_per_second": 11.263, | |
| "eval_steps_per_second": 5.66, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.074034902168165, | |
| "grad_norm": 1.589575171470642, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.7223, | |
| "step": 35 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7189115808251904.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |