| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.802407221664995, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0160481444332999, | |
| "grad_norm": 0.17083685100078583, | |
| "learning_rate": 1e-05, | |
| "loss": 2.3942, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0160481444332999, | |
| "eval_loss": 2.52895188331604, | |
| "eval_runtime": 22.9149, | |
| "eval_samples_per_second": 9.164, | |
| "eval_steps_per_second": 4.582, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0320962888665998, | |
| "grad_norm": 0.14391367137432098, | |
| "learning_rate": 2e-05, | |
| "loss": 2.4064, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.048144433299899696, | |
| "grad_norm": 0.16619427502155304, | |
| "learning_rate": 3e-05, | |
| "loss": 2.418, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0641925777331996, | |
| "grad_norm": 0.143926203250885, | |
| "learning_rate": 4e-05, | |
| "loss": 2.505, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0802407221664995, | |
| "grad_norm": 0.1302526593208313, | |
| "learning_rate": 5e-05, | |
| "loss": 2.4878, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.09628886659979939, | |
| "grad_norm": 0.13934171199798584, | |
| "learning_rate": 6e-05, | |
| "loss": 2.5336, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1123370110330993, | |
| "grad_norm": 0.1536237895488739, | |
| "learning_rate": 7e-05, | |
| "loss": 2.5089, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1283851554663992, | |
| "grad_norm": 0.1386164426803589, | |
| "learning_rate": 8e-05, | |
| "loss": 2.6297, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1444332998996991, | |
| "grad_norm": 0.1524312049150467, | |
| "learning_rate": 9e-05, | |
| "loss": 2.3858, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.160481444332999, | |
| "grad_norm": 0.14153587818145752, | |
| "learning_rate": 0.0001, | |
| "loss": 2.4744, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1765295887662989, | |
| "grad_norm": 0.15249013900756836, | |
| "learning_rate": 9.98458666866564e-05, | |
| "loss": 2.4318, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.19257773319959878, | |
| "grad_norm": 0.14801257848739624, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 2.4946, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2086258776328987, | |
| "grad_norm": 0.1329232156276703, | |
| "learning_rate": 9.861849601988383e-05, | |
| "loss": 2.6347, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2086258776328987, | |
| "eval_loss": 2.5210044384002686, | |
| "eval_runtime": 22.4203, | |
| "eval_samples_per_second": 9.367, | |
| "eval_steps_per_second": 4.683, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2246740220661986, | |
| "grad_norm": 0.14492028951644897, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 2.5018, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.24072216649949849, | |
| "grad_norm": 0.13506127893924713, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.5642, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2567703109327984, | |
| "grad_norm": 0.133815199136734, | |
| "learning_rate": 9.45503262094184e-05, | |
| "loss": 2.484, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2728184553660983, | |
| "grad_norm": 0.1350664347410202, | |
| "learning_rate": 9.263200821770461e-05, | |
| "loss": 2.5023, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.2888665997993982, | |
| "grad_norm": 0.13471205532550812, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 2.5607, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3049147442326981, | |
| "grad_norm": 0.12733304500579834, | |
| "learning_rate": 8.802029828000156e-05, | |
| "loss": 2.3489, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.320962888665998, | |
| "grad_norm": 0.13001815974712372, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.5144, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3370110330992979, | |
| "grad_norm": 0.13591095805168152, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 2.2412, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3530591775325978, | |
| "grad_norm": 0.13400661945343018, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 2.4606, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3691073219658977, | |
| "grad_norm": 0.13440661132335663, | |
| "learning_rate": 7.612492823579745e-05, | |
| "loss": 2.526, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.38515546639919757, | |
| "grad_norm": 0.13519461452960968, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 2.5468, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.4012036108324975, | |
| "grad_norm": 0.14065755903720856, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.4216, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4172517552657974, | |
| "grad_norm": 0.12566477060317993, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 2.3784, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.4172517552657974, | |
| "eval_loss": 2.5140509605407715, | |
| "eval_runtime": 22.4277, | |
| "eval_samples_per_second": 9.363, | |
| "eval_steps_per_second": 4.682, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.43329989969909727, | |
| "grad_norm": 0.12099477648735046, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 2.4904, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.4493480441323972, | |
| "grad_norm": 0.13227578997612, | |
| "learning_rate": 5.782172325201155e-05, | |
| "loss": 2.5992, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.4653961885656971, | |
| "grad_norm": 0.11921201646327972, | |
| "learning_rate": 5.392295478639225e-05, | |
| "loss": 2.4221, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.48144433299899697, | |
| "grad_norm": 0.12202885746955872, | |
| "learning_rate": 5e-05, | |
| "loss": 2.624, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4974924774322969, | |
| "grad_norm": 0.11582452803850174, | |
| "learning_rate": 4.607704521360776e-05, | |
| "loss": 2.4619, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5135406218655968, | |
| "grad_norm": 0.11963976919651031, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 2.4558, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5295887662988967, | |
| "grad_norm": 0.13530096411705017, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 2.3744, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5456369107321966, | |
| "grad_norm": 0.1295008808374405, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 2.3498, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5616850551654965, | |
| "grad_norm": 0.11402874439954758, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.514, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5777331995987964, | |
| "grad_norm": 0.12555132806301117, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 2.3917, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5937813440320963, | |
| "grad_norm": 0.11757726967334747, | |
| "learning_rate": 2.3875071764202563e-05, | |
| "loss": 2.5616, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.6098294884653962, | |
| "grad_norm": 0.12606336176395416, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 2.5237, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.6258776328986961, | |
| "grad_norm": 0.12942460179328918, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 2.4834, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6258776328986961, | |
| "eval_loss": 2.511258840560913, | |
| "eval_runtime": 22.4533, | |
| "eval_samples_per_second": 9.353, | |
| "eval_steps_per_second": 4.676, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.641925777331996, | |
| "grad_norm": 0.1265319287776947, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.4436, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6579739217652959, | |
| "grad_norm": 0.11708834022283554, | |
| "learning_rate": 1.1979701719998453e-05, | |
| "loss": 2.507, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.6740220661985958, | |
| "grad_norm": 0.12580640614032745, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 2.5904, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6900702106318957, | |
| "grad_norm": 0.12004761397838593, | |
| "learning_rate": 7.367991782295391e-06, | |
| "loss": 2.5087, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.7061183550651956, | |
| "grad_norm": 0.11525596678256989, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 2.4277, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.7221664994984955, | |
| "grad_norm": 0.12065120041370392, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.4564, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7382146439317954, | |
| "grad_norm": 0.12320233881473541, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 2.4538, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.7542627883650953, | |
| "grad_norm": 0.11359357833862305, | |
| "learning_rate": 1.3815039801161721e-06, | |
| "loss": 2.5531, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.7703109327983951, | |
| "grad_norm": 0.11881112307310104, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 2.4245, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.7863590772316951, | |
| "grad_norm": 0.12177315354347229, | |
| "learning_rate": 1.5413331334360182e-07, | |
| "loss": 2.601, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.802407221664995, | |
| "grad_norm": 0.11372490227222443, | |
| "learning_rate": 0.0, | |
| "loss": 2.6062, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "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": 2.498903514336461e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |