| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00475963826749167, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00047596382674916705, | |
| "grad_norm": 1.8053474426269531, | |
| "learning_rate": 2e-05, | |
| "loss": 3.712, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00047596382674916705, | |
| "eval_loss": 3.891406536102295, | |
| "eval_runtime": 13.7664, | |
| "eval_samples_per_second": 64.287, | |
| "eval_steps_per_second": 32.18, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009519276534983341, | |
| "grad_norm": 1.8643312454223633, | |
| "learning_rate": 4e-05, | |
| "loss": 3.972, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0014278914802475012, | |
| "grad_norm": 1.9306492805480957, | |
| "learning_rate": 6e-05, | |
| "loss": 3.9292, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0014278914802475012, | |
| "eval_loss": 3.8839597702026367, | |
| "eval_runtime": 12.7111, | |
| "eval_samples_per_second": 69.624, | |
| "eval_steps_per_second": 34.851, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0019038553069966682, | |
| "grad_norm": 1.9931215047836304, | |
| "learning_rate": 8e-05, | |
| "loss": 3.9517, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002379819133745835, | |
| "grad_norm": 2.122426986694336, | |
| "learning_rate": 0.0001, | |
| "loss": 3.8819, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0028557829604950024, | |
| "grad_norm": 1.9000606536865234, | |
| "learning_rate": 0.00012, | |
| "loss": 3.8583, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0028557829604950024, | |
| "eval_loss": 3.78226637840271, | |
| "eval_runtime": 12.7788, | |
| "eval_samples_per_second": 69.255, | |
| "eval_steps_per_second": 34.667, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0033317467872441696, | |
| "grad_norm": 1.9532514810562134, | |
| "learning_rate": 0.00014, | |
| "loss": 3.5203, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0038077106139933364, | |
| "grad_norm": 2.3859152793884277, | |
| "learning_rate": 0.00016, | |
| "loss": 3.7132, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004283674440742504, | |
| "grad_norm": 2.218242883682251, | |
| "learning_rate": 0.00018, | |
| "loss": 3.6354, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004283674440742504, | |
| "eval_loss": 3.4840054512023926, | |
| "eval_runtime": 12.7436, | |
| "eval_samples_per_second": 69.447, | |
| "eval_steps_per_second": 34.763, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00475963826749167, | |
| "grad_norm": 2.1710777282714844, | |
| "learning_rate": 0.0002, | |
| "loss": 3.291, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 240545515438080.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |