| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.012759170653907496, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004253056884635832, | |
| "eval_loss": 7.589954376220703, | |
| "eval_runtime": 34.2553, | |
| "eval_samples_per_second": 28.901, | |
| "eval_steps_per_second": 14.45, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012759170653907496, | |
| "grad_norm": 17.56035804748535, | |
| "learning_rate": 6e-05, | |
| "loss": 7.8076, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002551834130781499, | |
| "grad_norm": 13.23971176147461, | |
| "learning_rate": 0.00012, | |
| "loss": 5.9669, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0034024455077086655, | |
| "eval_loss": 3.0875678062438965, | |
| "eval_runtime": 33.8177, | |
| "eval_samples_per_second": 29.275, | |
| "eval_steps_per_second": 14.637, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003827751196172249, | |
| "grad_norm": 20.544353485107422, | |
| "learning_rate": 0.00018, | |
| "loss": 4.246, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005103668261562998, | |
| "grad_norm": 14.120155334472656, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.177, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006379585326953748, | |
| "grad_norm": 4.232186794281006, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.4923, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006804891015417331, | |
| "eval_loss": 0.9170283079147339, | |
| "eval_runtime": 33.8366, | |
| "eval_samples_per_second": 29.258, | |
| "eval_steps_per_second": 14.629, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.007655502392344498, | |
| "grad_norm": 7.722325801849365, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.9044, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.008931419457735247, | |
| "grad_norm": 6.6560845375061035, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.4815, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.010207336523125997, | |
| "grad_norm": 4.8479084968566895, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.3643, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.010207336523125997, | |
| "eval_loss": 0.44391828775405884, | |
| "eval_runtime": 34.1229, | |
| "eval_samples_per_second": 29.013, | |
| "eval_steps_per_second": 14.506, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.011483253588516746, | |
| "grad_norm": 2.4792239665985107, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.3924, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.012759170653907496, | |
| "grad_norm": 5.421734809875488, | |
| "learning_rate": 0.0, | |
| "loss": 0.3814, | |
| "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": 1451583854346240.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |