| { | |
| "best_metric": 3.390733003616333, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.0373831775700935, | |
| "eval_steps": 25, | |
| "global_step": 54, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.037383177570093455, | |
| "grad_norm": 2.831024646759033, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 7.8351, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.037383177570093455, | |
| "eval_loss": 8.958544731140137, | |
| "eval_runtime": 4.6614, | |
| "eval_samples_per_second": 10.727, | |
| "eval_steps_per_second": 1.502, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07476635514018691, | |
| "grad_norm": 3.0343971252441406, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 8.5717, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11214953271028037, | |
| "grad_norm": 3.345459461212158, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 8.8921, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.14953271028037382, | |
| "grad_norm": 3.910405397415161, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 9.2598, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.18691588785046728, | |
| "grad_norm": 5.217698574066162, | |
| "learning_rate": 0.00015, | |
| "loss": 9.0714, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.22429906542056074, | |
| "grad_norm": 10.640775680541992, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 8.8201, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2616822429906542, | |
| "grad_norm": 4.532738208770752, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 6.1276, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.29906542056074764, | |
| "grad_norm": 6.563399791717529, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 6.5805, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3364485981308411, | |
| "grad_norm": 5.796512603759766, | |
| "learning_rate": 0.00027, | |
| "loss": 5.9074, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.37383177570093457, | |
| "grad_norm": 11.563618659973145, | |
| "learning_rate": 0.0003, | |
| "loss": 5.4115, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.411214953271028, | |
| "grad_norm": 9.329169273376465, | |
| "learning_rate": 0.000299617817191538, | |
| "loss": 4.9419, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4485981308411215, | |
| "grad_norm": 8.141528129577637, | |
| "learning_rate": 0.0002984732162821399, | |
| "loss": 4.6769, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.48598130841121495, | |
| "grad_norm": 4.846505641937256, | |
| "learning_rate": 0.00029657202989567393, | |
| "loss": 4.008, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5233644859813084, | |
| "grad_norm": 3.690450429916382, | |
| "learning_rate": 0.0002939239460421746, | |
| "loss": 4.4243, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5607476635514018, | |
| "grad_norm": 3.435105085372925, | |
| "learning_rate": 0.00029054245874996426, | |
| "loss": 3.9618, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5981308411214953, | |
| "grad_norm": 3.6001131534576416, | |
| "learning_rate": 0.00028644479930317775, | |
| "loss": 4.1266, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6355140186915887, | |
| "grad_norm": 3.0784387588500977, | |
| "learning_rate": 0.0002816518484350883, | |
| "loss": 3.7033, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6728971962616822, | |
| "grad_norm": 3.397775173187256, | |
| "learning_rate": 0.0002761880299246772, | |
| "loss": 3.7701, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7102803738317757, | |
| "grad_norm": 3.662536859512329, | |
| "learning_rate": 0.00027008118613865406, | |
| "loss": 3.6325, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7476635514018691, | |
| "grad_norm": 3.3628623485565186, | |
| "learning_rate": 0.00026336243615313873, | |
| "loss": 3.7407, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7850467289719626, | |
| "grad_norm": 2.746609687805176, | |
| "learning_rate": 0.00025606601717798207, | |
| "loss": 3.3609, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.822429906542056, | |
| "grad_norm": 2.6766834259033203, | |
| "learning_rate": 0.00024822911009179276, | |
| "loss": 3.4941, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8598130841121495, | |
| "grad_norm": 3.1183571815490723, | |
| "learning_rate": 0.00023989164997670202, | |
| "loss": 3.4918, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.897196261682243, | |
| "grad_norm": 3.998292922973633, | |
| "learning_rate": 0.00023109612261833963, | |
| "loss": 3.5491, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9345794392523364, | |
| "grad_norm": 2.7714507579803467, | |
| "learning_rate": 0.00022188734800800852, | |
| "loss": 3.1514, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9345794392523364, | |
| "eval_loss": 3.464606285095215, | |
| "eval_runtime": 4.1979, | |
| "eval_samples_per_second": 11.911, | |
| "eval_steps_per_second": 1.668, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9719626168224299, | |
| "grad_norm": 3.2895798683166504, | |
| "learning_rate": 0.00021231225195028297, | |
| "loss": 3.472, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0186915887850467, | |
| "grad_norm": 5.035872936248779, | |
| "learning_rate": 0.00020241962693986476, | |
| "loss": 5.0945, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.0560747663551402, | |
| "grad_norm": 2.4314322471618652, | |
| "learning_rate": 0.00019225988352621445, | |
| "loss": 2.8699, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.0934579439252337, | |
| "grad_norm": 3.1479110717773438, | |
| "learning_rate": 0.00018188479343294648, | |
| "loss": 3.0123, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1308411214953271, | |
| "grad_norm": 3.4593069553375244, | |
| "learning_rate": 0.00017134722574099276, | |
| "loss": 3.2986, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1682242990654206, | |
| "grad_norm": 2.846343517303467, | |
| "learning_rate": 0.00016070087747988482, | |
| "loss": 2.8362, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.205607476635514, | |
| "grad_norm": 3.118037700653076, | |
| "learning_rate": 0.00015, | |
| "loss": 2.8713, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.2429906542056075, | |
| "grad_norm": 2.8634281158447266, | |
| "learning_rate": 0.00013929912252011516, | |
| "loss": 2.7965, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.280373831775701, | |
| "grad_norm": 2.5531721115112305, | |
| "learning_rate": 0.00012865277425900724, | |
| "loss": 2.4958, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.3177570093457944, | |
| "grad_norm": 3.3842477798461914, | |
| "learning_rate": 0.00011811520656705348, | |
| "loss": 2.7512, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.355140186915888, | |
| "grad_norm": 3.1077632904052734, | |
| "learning_rate": 0.00010774011647378553, | |
| "loss": 2.7183, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.3925233644859814, | |
| "grad_norm": 3.4125425815582275, | |
| "learning_rate": 9.758037306013526e-05, | |
| "loss": 2.7866, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.4299065420560748, | |
| "grad_norm": 3.162402629852295, | |
| "learning_rate": 8.768774804971705e-05, | |
| "loss": 2.5485, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.4672897196261683, | |
| "grad_norm": 3.4466617107391357, | |
| "learning_rate": 7.811265199199152e-05, | |
| "loss": 2.8969, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.5046728971962615, | |
| "grad_norm": 3.4401187896728516, | |
| "learning_rate": 6.890387738166041e-05, | |
| "loss": 2.5463, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.542056074766355, | |
| "grad_norm": 3.6022398471832275, | |
| "learning_rate": 6.010835002329795e-05, | |
| "loss": 2.5524, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.5794392523364484, | |
| "grad_norm": 3.837542772293091, | |
| "learning_rate": 5.1770889908207245e-05, | |
| "loss": 2.5875, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.616822429906542, | |
| "grad_norm": 3.5455305576324463, | |
| "learning_rate": 4.3933982822017876e-05, | |
| "loss": 2.8521, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.6542056074766354, | |
| "grad_norm": 3.434196710586548, | |
| "learning_rate": 3.663756384686127e-05, | |
| "loss": 2.5427, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.6915887850467288, | |
| "grad_norm": 3.0461819171905518, | |
| "learning_rate": 2.9918813861345952e-05, | |
| "loss": 2.4531, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.7289719626168223, | |
| "grad_norm": 3.3924200534820557, | |
| "learning_rate": 2.38119700753228e-05, | |
| "loss": 2.4146, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.7663551401869158, | |
| "grad_norm": 3.772728681564331, | |
| "learning_rate": 1.834815156491165e-05, | |
| "loss": 2.5594, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.8037383177570092, | |
| "grad_norm": 3.1197235584259033, | |
| "learning_rate": 1.3555200696822232e-05, | |
| "loss": 2.5783, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.8411214953271027, | |
| "grad_norm": 3.5549519062042236, | |
| "learning_rate": 9.45754125003576e-06, | |
| "loss": 2.6462, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.8785046728971961, | |
| "grad_norm": 4.010706901550293, | |
| "learning_rate": 6.076053957825411e-06, | |
| "loss": 2.9153, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.8785046728971961, | |
| "eval_loss": 3.390733003616333, | |
| "eval_runtime": 4.1949, | |
| "eval_samples_per_second": 11.919, | |
| "eval_steps_per_second": 1.669, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9158878504672896, | |
| "grad_norm": 3.5007739067077637, | |
| "learning_rate": 3.4279701043260886e-06, | |
| "loss": 2.5603, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.953271028037383, | |
| "grad_norm": 3.4901020526885986, | |
| "learning_rate": 1.5267837178600972e-06, | |
| "loss": 2.6862, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.9906542056074765, | |
| "grad_norm": 5.5853047370910645, | |
| "learning_rate": 3.821828084619727e-07, | |
| "loss": 3.6647, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.0373831775700935, | |
| "grad_norm": 2.95920729637146, | |
| "learning_rate": 0.0, | |
| "loss": 2.2325, | |
| "step": 54 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 54, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 50, | |
| "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": 8.51315657885614e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |