| { | |
| "best_metric": 1.2639470100402832, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.03617127096803364, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0014468508387213456, | |
| "grad_norm": 51.356468200683594, | |
| "learning_rate": 5e-05, | |
| "loss": 29.8267, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014468508387213456, | |
| "eval_loss": 2.4199445247650146, | |
| "eval_runtime": 3.0943, | |
| "eval_samples_per_second": 16.159, | |
| "eval_steps_per_second": 4.201, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002893701677442691, | |
| "grad_norm": 84.14910125732422, | |
| "learning_rate": 0.0001, | |
| "loss": 35.7566, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004340552516164037, | |
| "grad_norm": 54.97121047973633, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 40.0277, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005787403354885382, | |
| "grad_norm": 41.79493713378906, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 40.736, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.007234254193606728, | |
| "grad_norm": 44.83525848388672, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 39.979, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008681105032328074, | |
| "grad_norm": 57.539268493652344, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 41.4988, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01012795587104942, | |
| "grad_norm": 53.60942840576172, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 40.8046, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.011574806709770765, | |
| "grad_norm": 56.782630920410156, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 43.7478, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01302165754849211, | |
| "grad_norm": 65.85396575927734, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 49.6183, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.014468508387213455, | |
| "grad_norm": 68.12232971191406, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 52.0541, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.015915359225934803, | |
| "grad_norm": 70.19828796386719, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 57.7243, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.017362210064656148, | |
| "grad_norm": 87.33944702148438, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 57.454, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.018809060903377493, | |
| "grad_norm": 93.16725158691406, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 44.6822, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.02025591174209884, | |
| "grad_norm": 31.304059982299805, | |
| "learning_rate": 5.192909139858981e-05, | |
| "loss": 27.7725, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.021702762580820184, | |
| "grad_norm": 34.62314224243164, | |
| "learning_rate": 4.584447941263149e-05, | |
| "loss": 32.3006, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02314961341954153, | |
| "grad_norm": 36.10577392578125, | |
| "learning_rate": 3.9930417452305626e-05, | |
| "loss": 36.5873, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.024596464258262875, | |
| "grad_norm": 35.1816520690918, | |
| "learning_rate": 3.4297073302098156e-05, | |
| "loss": 36.2239, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02604331509698422, | |
| "grad_norm": 34.271888732910156, | |
| "learning_rate": 2.9049385504830985e-05, | |
| "loss": 35.4705, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.027490165935705566, | |
| "grad_norm": 39.33551025390625, | |
| "learning_rate": 2.4285108555160577e-05, | |
| "loss": 42.9444, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02893701677442691, | |
| "grad_norm": 41.35797119140625, | |
| "learning_rate": 2.0092991918301108e-05, | |
| "loss": 41.039, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.030383867613148256, | |
| "grad_norm": 50.83699035644531, | |
| "learning_rate": 1.6551126795408016e-05, | |
| "loss": 43.1771, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.031830718451869605, | |
| "grad_norm": 54.83556365966797, | |
| "learning_rate": 1.3725491432254624e-05, | |
| "loss": 45.7508, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03327756929059095, | |
| "grad_norm": 65.99713134765625, | |
| "learning_rate": 1.1668722069349041e-05, | |
| "loss": 48.7908, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.034724420129312296, | |
| "grad_norm": 86.88928985595703, | |
| "learning_rate": 1.0419132428365116e-05, | |
| "loss": 58.232, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03617127096803364, | |
| "grad_norm": 128.66246032714844, | |
| "learning_rate": 1e-05, | |
| "loss": 68.1281, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03617127096803364, | |
| "eval_loss": 1.2639470100402832, | |
| "eval_runtime": 3.143, | |
| "eval_samples_per_second": 15.908, | |
| "eval_steps_per_second": 4.136, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.8316628651343872e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |