| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.07727975270479134, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0015455950540958269, | |
| "eval_loss": 10.375998497009277, | |
| "eval_runtime": 1.5673, | |
| "eval_samples_per_second": 174.182, | |
| "eval_steps_per_second": 87.41, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0077279752704791345, | |
| "grad_norm": 0.04116315767168999, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3764, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015455950540958269, | |
| "grad_norm": 0.03205065801739693, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3734, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.015455950540958269, | |
| "eval_loss": 10.375765800476074, | |
| "eval_runtime": 1.5404, | |
| "eval_samples_per_second": 177.229, | |
| "eval_steps_per_second": 88.939, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.023183925811437404, | |
| "grad_norm": 0.037050023674964905, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.3713, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.030911901081916538, | |
| "grad_norm": 0.037202052772045135, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.3748, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.030911901081916538, | |
| "eval_loss": 10.37524700164795, | |
| "eval_runtime": 1.5713, | |
| "eval_samples_per_second": 173.737, | |
| "eval_steps_per_second": 87.187, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03863987635239567, | |
| "grad_norm": 0.03221876919269562, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.3727, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04636785162287481, | |
| "grad_norm": 0.03972822427749634, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3745, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04636785162287481, | |
| "eval_loss": 10.374836921691895, | |
| "eval_runtime": 1.6013, | |
| "eval_samples_per_second": 170.488, | |
| "eval_steps_per_second": 85.556, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05409582689335394, | |
| "grad_norm": 0.030050573870539665, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 10.3735, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.061823802163833076, | |
| "grad_norm": 0.03952740505337715, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 10.3741, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.061823802163833076, | |
| "eval_loss": 10.3746337890625, | |
| "eval_runtime": 1.5441, | |
| "eval_samples_per_second": 176.804, | |
| "eval_steps_per_second": 88.726, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0695517774343122, | |
| "grad_norm": 0.024366561323404312, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 10.3754, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07727975270479134, | |
| "grad_norm": 0.05005223676562309, | |
| "learning_rate": 0.0, | |
| "loss": 10.3762, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07727975270479134, | |
| "eval_loss": 10.374598503112793, | |
| "eval_runtime": 1.6011, | |
| "eval_samples_per_second": 170.508, | |
| "eval_steps_per_second": 85.566, | |
| "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": 704734494720.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |