| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0016395458458007132, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00016395458458007132, | |
| "grad_norm": 0.8227975964546204, | |
| "learning_rate": 2e-05, | |
| "loss": 2.0141, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00016395458458007132, | |
| "eval_loss": 2.115278720855713, | |
| "eval_runtime": 34.6101, | |
| "eval_samples_per_second": 74.227, | |
| "eval_steps_per_second": 37.128, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00032790916916014263, | |
| "grad_norm": 0.9019590020179749, | |
| "learning_rate": 4e-05, | |
| "loss": 2.101, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000491863753740214, | |
| "grad_norm": 1.1151551008224487, | |
| "learning_rate": 6e-05, | |
| "loss": 2.3553, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000491863753740214, | |
| "eval_loss": 2.113342523574829, | |
| "eval_runtime": 34.5426, | |
| "eval_samples_per_second": 74.372, | |
| "eval_steps_per_second": 37.2, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006558183383202853, | |
| "grad_norm": 1.9271240234375, | |
| "learning_rate": 8e-05, | |
| "loss": 1.9966, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008197729229003566, | |
| "grad_norm": 0.7142891883850098, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6312, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000983727507480428, | |
| "grad_norm": 1.0902899503707886, | |
| "learning_rate": 0.00012, | |
| "loss": 1.8803, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.000983727507480428, | |
| "eval_loss": 2.0963022708892822, | |
| "eval_runtime": 34.7144, | |
| "eval_samples_per_second": 74.004, | |
| "eval_steps_per_second": 37.016, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011476820920604993, | |
| "grad_norm": 1.0867420434951782, | |
| "learning_rate": 0.00014, | |
| "loss": 1.6876, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0013116366766405705, | |
| "grad_norm": 1.0964165925979614, | |
| "learning_rate": 0.00016, | |
| "loss": 1.9533, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.001475591261220642, | |
| "grad_norm": 1.3594083786010742, | |
| "learning_rate": 0.00018, | |
| "loss": 1.837, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.001475591261220642, | |
| "eval_loss": 2.049168825149536, | |
| "eval_runtime": 34.9221, | |
| "eval_samples_per_second": 73.564, | |
| "eval_steps_per_second": 36.796, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0016395458458007132, | |
| "grad_norm": 1.8565263748168945, | |
| "learning_rate": 0.0002, | |
| "loss": 2.149, | |
| "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": 262186777706496.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |