| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006115272894052897, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006115272894052897, | |
| "grad_norm": 792.2168579101562, | |
| "learning_rate": 2e-05, | |
| "loss": 26.6063, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006115272894052897, | |
| "eval_loss": 6.762737274169922, | |
| "eval_runtime": 21.5337, | |
| "eval_samples_per_second": 31.996, | |
| "eval_steps_per_second": 16.021, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012230545788105794, | |
| "grad_norm": 881.3244018554688, | |
| "learning_rate": 4e-05, | |
| "loss": 25.9391, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001834581868215869, | |
| "grad_norm": 982.9274291992188, | |
| "learning_rate": 6e-05, | |
| "loss": 27.9835, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001834581868215869, | |
| "eval_loss": 6.741152763366699, | |
| "eval_runtime": 20.6089, | |
| "eval_samples_per_second": 33.432, | |
| "eval_steps_per_second": 16.74, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002446109157621159, | |
| "grad_norm": 717.8159790039062, | |
| "learning_rate": 8e-05, | |
| "loss": 27.3533, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0030576364470264487, | |
| "grad_norm": 803.9835815429688, | |
| "learning_rate": 0.0001, | |
| "loss": 25.9769, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003669163736431738, | |
| "grad_norm": 792.4016723632812, | |
| "learning_rate": 0.00012, | |
| "loss": 27.458, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003669163736431738, | |
| "eval_loss": 6.677663326263428, | |
| "eval_runtime": 20.6808, | |
| "eval_samples_per_second": 33.316, | |
| "eval_steps_per_second": 16.682, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004280691025837028, | |
| "grad_norm": 830.0637817382812, | |
| "learning_rate": 0.00014, | |
| "loss": 25.5221, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004892218315242318, | |
| "grad_norm": 1079.168212890625, | |
| "learning_rate": 0.00016, | |
| "loss": 27.009, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005503745604647607, | |
| "grad_norm": 983.8218994140625, | |
| "learning_rate": 0.00018, | |
| "loss": 26.5676, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005503745604647607, | |
| "eval_loss": 6.547703266143799, | |
| "eval_runtime": 20.5746, | |
| "eval_samples_per_second": 33.488, | |
| "eval_steps_per_second": 16.768, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006115272894052897, | |
| "grad_norm": 836.0670776367188, | |
| "learning_rate": 0.0002, | |
| "loss": 25.9466, | |
| "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": 89372900720640.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |