| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0003993158388627485, | |
| "eval_steps": 5, | |
| "global_step": 15, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.6621055924183234e-05, | |
| "eval_loss": 3.000051498413086, | |
| "eval_runtime": 1484.5992, | |
| "eval_samples_per_second": 10.654, | |
| "eval_steps_per_second": 5.327, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.98631677725497e-05, | |
| "grad_norm": 0.2530394494533539, | |
| "learning_rate": 4e-05, | |
| "loss": 2.9135, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00013310527962091616, | |
| "eval_loss": 2.9983794689178467, | |
| "eval_runtime": 1322.4312, | |
| "eval_samples_per_second": 11.961, | |
| "eval_steps_per_second": 5.981, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0001597263355450994, | |
| "grad_norm": 0.28529462218284607, | |
| "learning_rate": 8e-05, | |
| "loss": 3.022, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002395895033176491, | |
| "grad_norm": 0.3292267918586731, | |
| "learning_rate": 0.00012, | |
| "loss": 2.8491, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00026621055924183233, | |
| "eval_loss": 2.9710569381713867, | |
| "eval_runtime": 1223.329, | |
| "eval_samples_per_second": 12.929, | |
| "eval_steps_per_second": 6.465, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0003194526710901988, | |
| "grad_norm": 0.44280529022216797, | |
| "learning_rate": 0.00016, | |
| "loss": 2.7088, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0003993158388627485, | |
| "grad_norm": 0.545186460018158, | |
| "learning_rate": 0.0002, | |
| "loss": 2.95, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0003993158388627485, | |
| "eval_loss": 2.9271042346954346, | |
| "eval_runtime": 1222.8182, | |
| "eval_samples_per_second": 12.935, | |
| "eval_steps_per_second": 6.468, | |
| "step": 15 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 15, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5227908138270720.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |