| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.000497840616326683, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.97840616326683e-05, | |
| "grad_norm": 8.102911949157715, | |
| "learning_rate": 2e-05, | |
| "loss": 13.1234, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.97840616326683e-05, | |
| "eval_loss": 3.1932132244110107, | |
| "eval_runtime": 103.3636, | |
| "eval_samples_per_second": 81.828, | |
| "eval_steps_per_second": 40.914, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.95681232653366e-05, | |
| "grad_norm": 13.588043212890625, | |
| "learning_rate": 4e-05, | |
| "loss": 13.195, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0001493521848980049, | |
| "grad_norm": 16.6812686920166, | |
| "learning_rate": 6e-05, | |
| "loss": 13.3648, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0001493521848980049, | |
| "eval_loss": 3.1755757331848145, | |
| "eval_runtime": 103.8399, | |
| "eval_samples_per_second": 81.452, | |
| "eval_steps_per_second": 40.726, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0001991362465306732, | |
| "grad_norm": 6.675265789031982, | |
| "learning_rate": 8e-05, | |
| "loss": 11.1413, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0002489203081633415, | |
| "grad_norm": 7.553915500640869, | |
| "learning_rate": 0.0001, | |
| "loss": 11.8859, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0002987043697960098, | |
| "grad_norm": 10.125482559204102, | |
| "learning_rate": 0.00012, | |
| "loss": 13.0801, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002987043697960098, | |
| "eval_loss": 3.055177688598633, | |
| "eval_runtime": 103.9372, | |
| "eval_samples_per_second": 81.376, | |
| "eval_steps_per_second": 40.688, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0003484884314286781, | |
| "grad_norm": 6.967427730560303, | |
| "learning_rate": 0.00014, | |
| "loss": 11.1381, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0003982724930613464, | |
| "grad_norm": 6.143828868865967, | |
| "learning_rate": 0.00016, | |
| "loss": 11.6534, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0004480565546940147, | |
| "grad_norm": 8.886016845703125, | |
| "learning_rate": 0.00018, | |
| "loss": 13.6284, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0004480565546940147, | |
| "eval_loss": 2.9265856742858887, | |
| "eval_runtime": 107.9771, | |
| "eval_samples_per_second": 78.331, | |
| "eval_steps_per_second": 39.166, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.000497840616326683, | |
| "grad_norm": 6.827943801879883, | |
| "learning_rate": 0.0002, | |
| "loss": 11.6631, | |
| "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": 80699876966400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |