| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.011098779134295227, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003699593044765076, | |
| "eval_loss": 3.463493585586548, | |
| "eval_runtime": 82.8286, | |
| "eval_samples_per_second": 13.751, | |
| "eval_steps_per_second": 6.882, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011098779134295228, | |
| "grad_norm": 3.9652962684631348, | |
| "learning_rate": 6e-05, | |
| "loss": 3.4684, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001849796522382538, | |
| "eval_loss": 3.0570292472839355, | |
| "eval_runtime": 83.4172, | |
| "eval_samples_per_second": 13.654, | |
| "eval_steps_per_second": 6.833, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0022197558268590455, | |
| "grad_norm": 1.842111587524414, | |
| "learning_rate": 0.00012, | |
| "loss": 3.1421, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003329633740288568, | |
| "grad_norm": 1.5706079006195068, | |
| "learning_rate": 0.00018, | |
| "loss": 2.8516, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003699593044765076, | |
| "eval_loss": 2.6839795112609863, | |
| "eval_runtime": 83.5502, | |
| "eval_samples_per_second": 13.633, | |
| "eval_steps_per_second": 6.822, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004439511653718091, | |
| "grad_norm": 1.7584556341171265, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 2.5995, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.005549389567147614, | |
| "grad_norm": 1.462285041809082, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.5446, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005549389567147614, | |
| "eval_loss": 2.5472054481506348, | |
| "eval_runtime": 83.4797, | |
| "eval_samples_per_second": 13.644, | |
| "eval_steps_per_second": 6.828, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006659267480577136, | |
| "grad_norm": 1.4335707426071167, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.5603, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.007399186089530152, | |
| "eval_loss": 2.4723150730133057, | |
| "eval_runtime": 83.5794, | |
| "eval_samples_per_second": 13.628, | |
| "eval_steps_per_second": 6.82, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00776914539400666, | |
| "grad_norm": 1.3720582723617554, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 2.4971, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.008879023307436182, | |
| "grad_norm": 1.0679662227630615, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 2.3067, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00924898261191269, | |
| "eval_loss": 2.4402551651000977, | |
| "eval_runtime": 83.5954, | |
| "eval_samples_per_second": 13.625, | |
| "eval_steps_per_second": 6.819, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.009988901220865706, | |
| "grad_norm": 1.1763719320297241, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 2.4056, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.011098779134295227, | |
| "grad_norm": 1.2664074897766113, | |
| "learning_rate": 0.0, | |
| "loss": 2.4649, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.011098779134295227, | |
| "eval_loss": 2.433227777481079, | |
| "eval_runtime": 83.5169, | |
| "eval_samples_per_second": 13.638, | |
| "eval_steps_per_second": 6.825, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3015894871572480.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |