| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00018709642715985286, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.741928543197057e-05, | |
| "grad_norm": 49.99011993408203, | |
| "learning_rate": 1e-05, | |
| "loss": 53.6858, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.741928543197057e-05, | |
| "eval_loss": 3.4527337551116943, | |
| "eval_runtime": 4414.989, | |
| "eval_samples_per_second": 10.195, | |
| "eval_steps_per_second": 5.097, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.483857086394114e-05, | |
| "grad_norm": 55.361881256103516, | |
| "learning_rate": 2e-05, | |
| "loss": 53.3138, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 7.483857086394114e-05, | |
| "eval_loss": 3.2868571281433105, | |
| "eval_runtime": 2319.8034, | |
| "eval_samples_per_second": 19.403, | |
| "eval_steps_per_second": 9.701, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0001122578562959117, | |
| "grad_norm": 66.64354705810547, | |
| "learning_rate": 3e-05, | |
| "loss": 56.2714, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00014967714172788228, | |
| "grad_norm": 61.32582473754883, | |
| "learning_rate": 4e-05, | |
| "loss": 50.5982, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00014967714172788228, | |
| "eval_loss": 3.1255762577056885, | |
| "eval_runtime": 3048.6019, | |
| "eval_samples_per_second": 14.764, | |
| "eval_steps_per_second": 7.382, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00018709642715985286, | |
| "grad_norm": 69.25088500976562, | |
| "learning_rate": 5e-05, | |
| "loss": 54.756, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3257466271825920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |