| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.056555269922879, | |
| "eval_steps": 400, | |
| "global_step": 800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019903980796159233, | |
| "loss": 1.2452, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00019803960792158433, | |
| "loss": 1.2141, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00019703940788157634, | |
| "loss": 1.1351, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00019603920784156832, | |
| "loss": 1.1895, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00019503900780156033, | |
| "loss": 1.1864, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0001940388077615523, | |
| "loss": 1.1171, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00019303860772154432, | |
| "loss": 1.2292, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00019203840768153632, | |
| "loss": 1.1102, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0001910382076415283, | |
| "loss": 1.2064, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0001900380076015203, | |
| "loss": 1.2256, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0001890378075615123, | |
| "loss": 1.1175, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.0001880376075215043, | |
| "loss": 1.098, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.00018703740748149633, | |
| "loss": 1.299, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.0001860372074414883, | |
| "loss": 1.1586, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.00018503700740148032, | |
| "loss": 1.202, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.0001840368073614723, | |
| "loss": 1.0137, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "eval_loss": 0.8309869766235352, | |
| "eval_runtime": 1939.5005, | |
| "eval_samples_per_second": 0.401, | |
| "eval_steps_per_second": 0.051, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.0001830366073214643, | |
| "loss": 0.7305, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.0001820364072814563, | |
| "loss": 0.8463, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.0001810362072414483, | |
| "loss": 0.7727, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.0001800360072014403, | |
| "loss": 0.8441, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.00017903580716143228, | |
| "loss": 0.757, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.00017803560712142429, | |
| "loss": 0.7867, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.0001770354070814163, | |
| "loss": 0.8074, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.0001760352070414083, | |
| "loss": 0.7697, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.0001750350070014003, | |
| "loss": 0.8323, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.0001740348069613923, | |
| "loss": 0.7122, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.0001730346069213843, | |
| "loss": 0.7781, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.00017203440688137627, | |
| "loss": 0.8105, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.00017103420684136828, | |
| "loss": 0.812, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.0001700340068013603, | |
| "loss": 0.7918, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.00016903380676135227, | |
| "loss": 0.7319, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 0.00016803360672134428, | |
| "loss": 0.309, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "eval_loss": 0.2903744876384735, | |
| "eval_runtime": 1946.3315, | |
| "eval_samples_per_second": 0.399, | |
| "eval_steps_per_second": 0.05, | |
| "step": 800 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 5000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 13, | |
| "save_steps": 400, | |
| "total_flos": 1.3574517302954557e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |