| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0013993026808307193, | |
| "eval_steps": 5, | |
| "global_step": 15, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 9.328684538871463e-05, | |
| "eval_loss": 6.389310836791992, | |
| "eval_runtime": 1171.7578, | |
| "eval_samples_per_second": 15.408, | |
| "eval_steps_per_second": 3.852, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00027986053616614387, | |
| "grad_norm": 8.369600296020508, | |
| "learning_rate": 3e-05, | |
| "loss": 6.0336, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00046643422694357315, | |
| "eval_loss": 4.579810619354248, | |
| "eval_runtime": 1127.02, | |
| "eval_samples_per_second": 16.02, | |
| "eval_steps_per_second": 4.005, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005597210723322877, | |
| "grad_norm": 5.414619445800781, | |
| "learning_rate": 6e-05, | |
| "loss": 5.0959, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0008395816084984316, | |
| "grad_norm": 3.53025484085083, | |
| "learning_rate": 9e-05, | |
| "loss": 3.4984, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0009328684538871463, | |
| "eval_loss": 2.2199866771698, | |
| "eval_runtime": 1127.2384, | |
| "eval_samples_per_second": 16.017, | |
| "eval_steps_per_second": 4.004, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0011194421446645755, | |
| "grad_norm": 3.462336540222168, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 2.315, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0013993026808307193, | |
| "grad_norm": 3.0801501274108887, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.5734, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0013993026808307193, | |
| "eval_loss": 1.2294880151748657, | |
| "eval_runtime": 1127.2145, | |
| "eval_samples_per_second": 16.017, | |
| "eval_steps_per_second": 4.005, | |
| "step": 15 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.804021269528576e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |