| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004968326915911067, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004968326915911067, | |
| "grad_norm": 9.666437149047852, | |
| "learning_rate": 2e-05, | |
| "loss": 13.4967, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004968326915911067, | |
| "eval_loss": 4.478808879852295, | |
| "eval_runtime": 9.7106, | |
| "eval_samples_per_second": 87.327, | |
| "eval_steps_per_second": 43.664, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009936653831822133, | |
| "grad_norm": 14.662745475769043, | |
| "learning_rate": 4e-05, | |
| "loss": 18.8801, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0014904980747733202, | |
| "grad_norm": 11.597631454467773, | |
| "learning_rate": 6e-05, | |
| "loss": 16.0001, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0014904980747733202, | |
| "eval_loss": 4.449888229370117, | |
| "eval_runtime": 9.4873, | |
| "eval_samples_per_second": 89.382, | |
| "eval_steps_per_second": 44.691, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0019873307663644266, | |
| "grad_norm": 15.31915283203125, | |
| "learning_rate": 8e-05, | |
| "loss": 19.218, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0024841634579555335, | |
| "grad_norm": 11.866692543029785, | |
| "learning_rate": 0.0001, | |
| "loss": 13.5551, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0029809961495466403, | |
| "grad_norm": 13.42898941040039, | |
| "learning_rate": 0.00012, | |
| "loss": 17.9477, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0029809961495466403, | |
| "eval_loss": 4.24091100692749, | |
| "eval_runtime": 9.8461, | |
| "eval_samples_per_second": 86.125, | |
| "eval_steps_per_second": 43.063, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0034778288411377468, | |
| "grad_norm": 10.920669555664062, | |
| "learning_rate": 0.00014, | |
| "loss": 16.3749, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003974661532728853, | |
| "grad_norm": 18.857372283935547, | |
| "learning_rate": 0.00016, | |
| "loss": 20.6541, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0044714942243199605, | |
| "grad_norm": 18.79514503479004, | |
| "learning_rate": 0.00018, | |
| "loss": 18.1999, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0044714942243199605, | |
| "eval_loss": 3.7939412593841553, | |
| "eval_runtime": 9.6373, | |
| "eval_samples_per_second": 87.992, | |
| "eval_steps_per_second": 43.996, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004968326915911067, | |
| "grad_norm": 13.796027183532715, | |
| "learning_rate": 0.0002, | |
| "loss": 15.6981, | |
| "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": 75069652992000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |