| { | |
| "best_metric": 0.7788119912147522, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-250", | |
| "epoch": 0.29420417769932333, | |
| "eval_steps": 50, | |
| "global_step": 250, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011768167107972932, | |
| "eval_loss": 1.4336028099060059, | |
| "eval_runtime": 63.7044, | |
| "eval_samples_per_second": 22.479, | |
| "eval_steps_per_second": 5.62, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011768167107972934, | |
| "grad_norm": 1.2304390668869019, | |
| "learning_rate": 0.0002, | |
| "loss": 7.4146, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.023536334215945868, | |
| "grad_norm": 0.6472563743591309, | |
| "learning_rate": 0.0001998582695676762, | |
| "loss": 6.0483, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0353045013239188, | |
| "grad_norm": 0.7562745213508606, | |
| "learning_rate": 0.00019943348002101371, | |
| "loss": 3.9027, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.047072668431891736, | |
| "grad_norm": 0.8033158779144287, | |
| "learning_rate": 0.00019872683547213446, | |
| "loss": 1.8585, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05884083553986467, | |
| "grad_norm": 1.7948169708251953, | |
| "learning_rate": 0.00019774033898178667, | |
| "loss": 1.7989, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05884083553986467, | |
| "eval_loss": 0.9343328475952148, | |
| "eval_runtime": 64.9646, | |
| "eval_samples_per_second": 22.043, | |
| "eval_steps_per_second": 5.511, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0706090026478376, | |
| "grad_norm": 0.8677065968513489, | |
| "learning_rate": 0.0001964767868814516, | |
| "loss": 6.2807, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.08237716975581054, | |
| "grad_norm": 0.7287414073944092, | |
| "learning_rate": 0.00019493976084683813, | |
| "loss": 4.9082, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.09414533686378347, | |
| "grad_norm": 1.209147572517395, | |
| "learning_rate": 0.00019313361774523385, | |
| "loss": 3.0766, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.1059135039717564, | |
| "grad_norm": 0.9230589866638184, | |
| "learning_rate": 0.00019106347728549135, | |
| "loss": 1.5117, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.11768167107972934, | |
| "grad_norm": 2.2932982444763184, | |
| "learning_rate": 0.00018873520750565718, | |
| "loss": 1.5895, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.11768167107972934, | |
| "eval_loss": 0.8446639180183411, | |
| "eval_runtime": 64.7346, | |
| "eval_samples_per_second": 22.121, | |
| "eval_steps_per_second": 5.53, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.12944983818770225, | |
| "grad_norm": 0.867832362651825, | |
| "learning_rate": 0.0001861554081393806, | |
| "loss": 6.0238, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.1412180052956752, | |
| "grad_norm": 0.8156207203865051, | |
| "learning_rate": 0.0001833313919082515, | |
| "loss": 4.7902, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.15298617240364812, | |
| "grad_norm": 0.802191436290741, | |
| "learning_rate": 0.00018027116379309638, | |
| "loss": 2.8416, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.16475433951162108, | |
| "grad_norm": 1.274532675743103, | |
| "learning_rate": 0.00017698339834299061, | |
| "loss": 1.3511, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.176522506619594, | |
| "grad_norm": 1.8214877843856812, | |
| "learning_rate": 0.00017347741508630672, | |
| "loss": 1.4454, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.176522506619594, | |
| "eval_loss": 0.8176446557044983, | |
| "eval_runtime": 64.9157, | |
| "eval_samples_per_second": 22.059, | |
| "eval_steps_per_second": 5.515, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.18829067372756694, | |
| "grad_norm": 0.7749770283699036, | |
| "learning_rate": 0.0001697631521134985, | |
| "loss": 5.9457, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.20005884083553988, | |
| "grad_norm": 0.843367338180542, | |
| "learning_rate": 0.00016585113790650388, | |
| "loss": 4.737, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.2118270079435128, | |
| "grad_norm": 0.7175513505935669, | |
| "learning_rate": 0.0001617524614946192, | |
| "loss": 2.8268, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.22359517505148574, | |
| "grad_norm": 0.8358870148658752, | |
| "learning_rate": 0.0001574787410214407, | |
| "loss": 1.3233, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.23536334215945867, | |
| "grad_norm": 2.047827959060669, | |
| "learning_rate": 0.00015304209081197425, | |
| "loss": 1.4239, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.23536334215945867, | |
| "eval_loss": 0.7979318499565125, | |
| "eval_runtime": 64.8822, | |
| "eval_samples_per_second": 22.071, | |
| "eval_steps_per_second": 5.518, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2471315092674316, | |
| "grad_norm": 0.7978292107582092, | |
| "learning_rate": 0.00014845508703326504, | |
| "loss": 5.7924, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.2588996763754045, | |
| "grad_norm": 0.9069154858589172, | |
| "learning_rate": 0.00014373073204588556, | |
| "loss": 4.7768, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.27066784348337747, | |
| "grad_norm": 0.7871260643005371, | |
| "learning_rate": 0.00013888241754733208, | |
| "loss": 2.6733, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.2824360105913504, | |
| "grad_norm": 0.7734578847885132, | |
| "learning_rate": 0.00013392388661180303, | |
| "loss": 1.2857, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.29420417769932333, | |
| "grad_norm": 1.4109017848968506, | |
| "learning_rate": 0.0001288691947339621, | |
| "loss": 1.3427, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.29420417769932333, | |
| "eval_loss": 0.7788119912147522, | |
| "eval_runtime": 65.0714, | |
| "eval_samples_per_second": 22.007, | |
| "eval_steps_per_second": 5.502, | |
| "step": 250 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 600, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.6845926844019507e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |