| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0016086060423264464, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00016086060423264466, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00016086060423264466, | |
| "eval_loss": NaN, | |
| "eval_runtime": 676.2084, | |
| "eval_samples_per_second": 15.483, | |
| "eval_steps_per_second": 7.742, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003217212084652893, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00048258181269793395, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00048258181269793395, | |
| "eval_loss": NaN, | |
| "eval_runtime": 630.5965, | |
| "eval_samples_per_second": 16.603, | |
| "eval_steps_per_second": 8.302, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006434424169305786, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008043030211632232, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0009651636253958679, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0009651636253958679, | |
| "eval_loss": NaN, | |
| "eval_runtime": 631.2792, | |
| "eval_samples_per_second": 16.585, | |
| "eval_steps_per_second": 8.293, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011260242296285126, | |
| "grad_norm": NaN, | |
| "learning_rate": 7e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0012868848338611573, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0014477454380938018, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0014477454380938018, | |
| "eval_loss": NaN, | |
| "eval_runtime": 631.079, | |
| "eval_samples_per_second": 16.591, | |
| "eval_steps_per_second": 8.295, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0016086060423264464, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "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": 1.045015069458432e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |