| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.017052721330112264, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005684240443370755, | |
| "eval_loss": NaN, | |
| "eval_runtime": 59.2959, | |
| "eval_samples_per_second": 12.497, | |
| "eval_steps_per_second": 6.257, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0017052721330112265, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002842120221685377, | |
| "eval_loss": NaN, | |
| "eval_runtime": 58.4524, | |
| "eval_samples_per_second": 12.677, | |
| "eval_steps_per_second": 6.347, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003410544266022453, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005115816399033679, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005684240443370754, | |
| "eval_loss": NaN, | |
| "eval_runtime": 58.5963, | |
| "eval_samples_per_second": 12.646, | |
| "eval_steps_per_second": 6.331, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006821088532044906, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.008526360665056132, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008526360665056132, | |
| "eval_loss": NaN, | |
| "eval_runtime": 58.6648, | |
| "eval_samples_per_second": 12.631, | |
| "eval_steps_per_second": 6.324, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010231632798067358, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.011368480886741509, | |
| "eval_loss": NaN, | |
| "eval_runtime": 58.6937, | |
| "eval_samples_per_second": 12.625, | |
| "eval_steps_per_second": 6.321, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011936904931078584, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.013642177064089812, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.014210601108426887, | |
| "eval_loss": NaN, | |
| "eval_runtime": 58.7256, | |
| "eval_samples_per_second": 12.618, | |
| "eval_steps_per_second": 6.318, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.015347449197101038, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.017052721330112264, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.017052721330112264, | |
| "eval_loss": NaN, | |
| "eval_runtime": 58.7699, | |
| "eval_samples_per_second": 12.608, | |
| "eval_steps_per_second": 6.313, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 15, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.051602475548672e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |