| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00943040362127499, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001886080724254998, | |
| "eval_loss": 1.0262165069580078, | |
| "eval_runtime": 142.6224, | |
| "eval_samples_per_second": 15.657, | |
| "eval_steps_per_second": 7.832, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000943040362127499, | |
| "grad_norm": 21.677078247070312, | |
| "learning_rate": 5e-05, | |
| "loss": 3.7955, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001886080724254998, | |
| "grad_norm": 15.723212242126465, | |
| "learning_rate": 0.0001, | |
| "loss": 3.4928, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001886080724254998, | |
| "eval_loss": 0.7923435568809509, | |
| "eval_runtime": 143.6773, | |
| "eval_samples_per_second": 15.542, | |
| "eval_steps_per_second": 7.774, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002829121086382497, | |
| "grad_norm": 10.258428573608398, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.9175, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003772161448509996, | |
| "grad_norm": 13.949254989624023, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.6865, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003772161448509996, | |
| "eval_loss": 0.6223310232162476, | |
| "eval_runtime": 143.8688, | |
| "eval_samples_per_second": 15.521, | |
| "eval_steps_per_second": 7.764, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004715201810637495, | |
| "grad_norm": 14.729504585266113, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.512, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005658242172764994, | |
| "grad_norm": 10.213173866271973, | |
| "learning_rate": 5e-05, | |
| "loss": 2.3717, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005658242172764994, | |
| "eval_loss": 0.580557644367218, | |
| "eval_runtime": 143.9844, | |
| "eval_samples_per_second": 15.509, | |
| "eval_steps_per_second": 7.758, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006601282534892493, | |
| "grad_norm": 12.30993366241455, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.3534, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.007544322897019992, | |
| "grad_norm": 10.71760082244873, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.1448, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.007544322897019992, | |
| "eval_loss": 0.546802818775177, | |
| "eval_runtime": 143.9082, | |
| "eval_samples_per_second": 15.517, | |
| "eval_steps_per_second": 7.762, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.008487363259147491, | |
| "grad_norm": 12.253548622131348, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.272, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.00943040362127499, | |
| "grad_norm": 9.606593132019043, | |
| "learning_rate": 0.0, | |
| "loss": 2.2752, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.00943040362127499, | |
| "eval_loss": 0.5441392660140991, | |
| "eval_runtime": 143.218, | |
| "eval_samples_per_second": 15.592, | |
| "eval_steps_per_second": 7.799, | |
| "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": 8763358996070400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |