| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0003989706557082727, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.9897065570827266e-05, | |
| "grad_norm": 38.08751678466797, | |
| "learning_rate": 2e-05, | |
| "loss": 13.2355, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.9897065570827266e-05, | |
| "eval_loss": 13.641461372375488, | |
| "eval_runtime": 461.4019, | |
| "eval_samples_per_second": 22.874, | |
| "eval_steps_per_second": 11.437, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.979413114165453e-05, | |
| "grad_norm": 32.36470031738281, | |
| "learning_rate": 4e-05, | |
| "loss": 13.3156, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0001196911967124818, | |
| "grad_norm": 35.10114288330078, | |
| "learning_rate": 6e-05, | |
| "loss": 13.899, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0001196911967124818, | |
| "eval_loss": 13.088886260986328, | |
| "eval_runtime": 460.7602, | |
| "eval_samples_per_second": 22.906, | |
| "eval_steps_per_second": 11.453, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00015958826228330906, | |
| "grad_norm": 35.32827377319336, | |
| "learning_rate": 8e-05, | |
| "loss": 12.036, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00019948532785413634, | |
| "grad_norm": 27.98809051513672, | |
| "learning_rate": 0.0001, | |
| "loss": 13.5756, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0002393823934249636, | |
| "grad_norm": 30.70273780822754, | |
| "learning_rate": 0.00012, | |
| "loss": 9.3102, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002393823934249636, | |
| "eval_loss": 6.75634241104126, | |
| "eval_runtime": 460.8268, | |
| "eval_samples_per_second": 22.902, | |
| "eval_steps_per_second": 11.451, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00027927945899579087, | |
| "grad_norm": 42.0061149597168, | |
| "learning_rate": 0.00014, | |
| "loss": 5.6204, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0003191765245666181, | |
| "grad_norm": 15.68433952331543, | |
| "learning_rate": 0.00016, | |
| "loss": 6.5446, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0003590735901374454, | |
| "grad_norm": 8.796845436096191, | |
| "learning_rate": 0.00018, | |
| "loss": 3.0595, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0003590735901374454, | |
| "eval_loss": 3.500016927719116, | |
| "eval_runtime": 460.7356, | |
| "eval_samples_per_second": 22.907, | |
| "eval_steps_per_second": 11.453, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0003989706557082727, | |
| "grad_norm": 12.054160118103027, | |
| "learning_rate": 0.0002, | |
| "loss": 4.0348, | |
| "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": 2774346372218880.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |