| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1276324186343331, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0025526483726866626, | |
| "eval_loss": 2.834757089614868, | |
| "eval_runtime": 9.3708, | |
| "eval_samples_per_second": 17.608, | |
| "eval_steps_per_second": 8.857, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012763241863433313, | |
| "grad_norm": 0.622917652130127, | |
| "learning_rate": 5e-05, | |
| "loss": 2.8162, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.025526483726866625, | |
| "grad_norm": 0.4492838382720947, | |
| "learning_rate": 0.0001, | |
| "loss": 2.7871, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.025526483726866625, | |
| "eval_loss": 2.7915663719177246, | |
| "eval_runtime": 9.2446, | |
| "eval_samples_per_second": 17.848, | |
| "eval_steps_per_second": 8.978, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03828972559029994, | |
| "grad_norm": 0.5710231065750122, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.7649, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05105296745373325, | |
| "grad_norm": 0.5380902886390686, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.7337, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05105296745373325, | |
| "eval_loss": 2.7470574378967285, | |
| "eval_runtime": 9.2673, | |
| "eval_samples_per_second": 17.805, | |
| "eval_steps_per_second": 8.956, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06381620931716656, | |
| "grad_norm": 0.6101768016815186, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.7201, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07657945118059988, | |
| "grad_norm": 0.6069520711898804, | |
| "learning_rate": 5e-05, | |
| "loss": 2.7406, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07657945118059988, | |
| "eval_loss": 2.727977991104126, | |
| "eval_runtime": 9.3209, | |
| "eval_samples_per_second": 17.702, | |
| "eval_steps_per_second": 8.905, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08934269304403318, | |
| "grad_norm": 0.5778947472572327, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.6019, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.1021059349074665, | |
| "grad_norm": 0.6996490359306335, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.7452, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1021059349074665, | |
| "eval_loss": 2.7188756465911865, | |
| "eval_runtime": 9.4298, | |
| "eval_samples_per_second": 17.498, | |
| "eval_steps_per_second": 8.802, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1148691767708998, | |
| "grad_norm": 0.6797233819961548, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.7534, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1276324186343331, | |
| "grad_norm": 0.6642326712608337, | |
| "learning_rate": 0.0, | |
| "loss": 2.6603, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1276324186343331, | |
| "eval_loss": 2.717184543609619, | |
| "eval_runtime": 9.3197, | |
| "eval_samples_per_second": 17.704, | |
| "eval_steps_per_second": 8.906, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4713523634503680.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |