| { | |
| "best_metric": 3.401686906814575, | |
| "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": 2.7531967163085938, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 7.8351, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.037383177570093455, | |
| "eval_loss": 8.958544731140137, | |
| "eval_runtime": 4.6786, | |
| "eval_samples_per_second": 10.687, | |
| "eval_steps_per_second": 1.496, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07476635514018691, | |
| "grad_norm": 2.949021100997925, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 8.5717, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11214953271028037, | |
| "grad_norm": 3.286224842071533, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 8.8883, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.14953271028037382, | |
| "grad_norm": 3.830043315887451, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 9.2578, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.18691588785046728, | |
| "grad_norm": 5.241765975952148, | |
| "learning_rate": 0.00015, | |
| "loss": 9.069, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.22429906542056074, | |
| "grad_norm": 10.764116287231445, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 8.8101, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2616822429906542, | |
| "grad_norm": 4.389330863952637, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 6.1341, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.29906542056074764, | |
| "grad_norm": 6.786483287811279, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 6.6059, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3364485981308411, | |
| "grad_norm": 5.6405463218688965, | |
| "learning_rate": 0.00027, | |
| "loss": 5.9216, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.37383177570093457, | |
| "grad_norm": 9.129680633544922, | |
| "learning_rate": 0.0003, | |
| "loss": 5.3773, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.411214953271028, | |
| "grad_norm": 7.611507415771484, | |
| "learning_rate": 0.000299617817191538, | |
| "loss": 4.8489, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4485981308411215, | |
| "grad_norm": 8.8467378616333, | |
| "learning_rate": 0.0002984732162821399, | |
| "loss": 4.6982, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.48598130841121495, | |
| "grad_norm": 5.18742036819458, | |
| "learning_rate": 0.00029657202989567393, | |
| "loss": 4.0034, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5233644859813084, | |
| "grad_norm": 3.5742533206939697, | |
| "learning_rate": 0.0002939239460421746, | |
| "loss": 4.4227, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5607476635514018, | |
| "grad_norm": 3.673884630203247, | |
| "learning_rate": 0.00029054245874996426, | |
| "loss": 3.9501, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5981308411214953, | |
| "grad_norm": 3.613555908203125, | |
| "learning_rate": 0.00028644479930317775, | |
| "loss": 4.1168, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6355140186915887, | |
| "grad_norm": 3.2746894359588623, | |
| "learning_rate": 0.0002816518484350883, | |
| "loss": 3.7159, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6728971962616822, | |
| "grad_norm": 3.354125499725342, | |
| "learning_rate": 0.0002761880299246772, | |
| "loss": 3.7459, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7102803738317757, | |
| "grad_norm": 3.6942992210388184, | |
| "learning_rate": 0.00027008118613865406, | |
| "loss": 3.6319, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7476635514018691, | |
| "grad_norm": 3.4715960025787354, | |
| "learning_rate": 0.00026336243615313873, | |
| "loss": 3.7446, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7850467289719626, | |
| "grad_norm": 2.8266215324401855, | |
| "learning_rate": 0.00025606601717798207, | |
| "loss": 3.3823, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.822429906542056, | |
| "grad_norm": 2.729022979736328, | |
| "learning_rate": 0.00024822911009179276, | |
| "loss": 3.5056, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8598130841121495, | |
| "grad_norm": 3.182410955429077, | |
| "learning_rate": 0.00023989164997670202, | |
| "loss": 3.4934, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.897196261682243, | |
| "grad_norm": 4.04162073135376, | |
| "learning_rate": 0.00023109612261833963, | |
| "loss": 3.5696, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9345794392523364, | |
| "grad_norm": 2.7601511478424072, | |
| "learning_rate": 0.00022188734800800852, | |
| "loss": 3.1508, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9345794392523364, | |
| "eval_loss": 3.467716693878174, | |
| "eval_runtime": 4.2146, | |
| "eval_samples_per_second": 11.864, | |
| "eval_steps_per_second": 1.661, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9719626168224299, | |
| "grad_norm": 3.114112615585327, | |
| "learning_rate": 0.00021231225195028297, | |
| "loss": 3.4493, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0186915887850467, | |
| "grad_norm": 4.9350666999816895, | |
| "learning_rate": 0.00020241962693986476, | |
| "loss": 5.0985, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.0560747663551402, | |
| "grad_norm": 2.5191762447357178, | |
| "learning_rate": 0.00019225988352621445, | |
| "loss": 2.8999, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.0934579439252337, | |
| "grad_norm": 3.0265848636627197, | |
| "learning_rate": 0.00018188479343294648, | |
| "loss": 3.0403, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1308411214953271, | |
| "grad_norm": 3.448732376098633, | |
| "learning_rate": 0.00017134722574099276, | |
| "loss": 3.3247, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1682242990654206, | |
| "grad_norm": 2.8440847396850586, | |
| "learning_rate": 0.00016070087747988482, | |
| "loss": 2.8432, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.205607476635514, | |
| "grad_norm": 3.15624737739563, | |
| "learning_rate": 0.00015, | |
| "loss": 2.8891, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.2429906542056075, | |
| "grad_norm": 2.830214262008667, | |
| "learning_rate": 0.00013929912252011516, | |
| "loss": 2.8265, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.280373831775701, | |
| "grad_norm": 2.4644389152526855, | |
| "learning_rate": 0.00012865277425900724, | |
| "loss": 2.4983, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.3177570093457944, | |
| "grad_norm": 3.523728370666504, | |
| "learning_rate": 0.00011811520656705348, | |
| "loss": 2.8003, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.355140186915888, | |
| "grad_norm": 3.176539897918701, | |
| "learning_rate": 0.00010774011647378553, | |
| "loss": 2.7638, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.3925233644859814, | |
| "grad_norm": 3.2825207710266113, | |
| "learning_rate": 9.758037306013526e-05, | |
| "loss": 2.7658, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.4299065420560748, | |
| "grad_norm": 3.181520938873291, | |
| "learning_rate": 8.768774804971705e-05, | |
| "loss": 2.5484, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.4672897196261683, | |
| "grad_norm": 3.379570960998535, | |
| "learning_rate": 7.811265199199152e-05, | |
| "loss": 2.901, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.5046728971962615, | |
| "grad_norm": 3.2364346981048584, | |
| "learning_rate": 6.890387738166041e-05, | |
| "loss": 2.535, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.542056074766355, | |
| "grad_norm": 3.4163613319396973, | |
| "learning_rate": 6.010835002329795e-05, | |
| "loss": 2.567, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.5794392523364484, | |
| "grad_norm": 3.7154176235198975, | |
| "learning_rate": 5.1770889908207245e-05, | |
| "loss": 2.6049, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.616822429906542, | |
| "grad_norm": 3.4739344120025635, | |
| "learning_rate": 4.3933982822017876e-05, | |
| "loss": 2.8533, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.6542056074766354, | |
| "grad_norm": 3.2199292182922363, | |
| "learning_rate": 3.663756384686127e-05, | |
| "loss": 2.529, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.6915887850467288, | |
| "grad_norm": 3.004704236984253, | |
| "learning_rate": 2.9918813861345952e-05, | |
| "loss": 2.4814, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.7289719626168223, | |
| "grad_norm": 3.350970506668091, | |
| "learning_rate": 2.38119700753228e-05, | |
| "loss": 2.4404, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.7663551401869158, | |
| "grad_norm": 3.503912925720215, | |
| "learning_rate": 1.834815156491165e-05, | |
| "loss": 2.5487, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.8037383177570092, | |
| "grad_norm": 3.0378119945526123, | |
| "learning_rate": 1.3555200696822232e-05, | |
| "loss": 2.5837, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.8411214953271027, | |
| "grad_norm": 3.5352275371551514, | |
| "learning_rate": 9.45754125003576e-06, | |
| "loss": 2.6595, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.8785046728971961, | |
| "grad_norm": 3.9558587074279785, | |
| "learning_rate": 6.076053957825411e-06, | |
| "loss": 2.9114, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.8785046728971961, | |
| "eval_loss": 3.401686906814575, | |
| "eval_runtime": 4.2148, | |
| "eval_samples_per_second": 11.863, | |
| "eval_steps_per_second": 1.661, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9158878504672896, | |
| "grad_norm": 3.5044848918914795, | |
| "learning_rate": 3.4279701043260886e-06, | |
| "loss": 2.5647, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.953271028037383, | |
| "grad_norm": 3.4336962699890137, | |
| "learning_rate": 1.5267837178600972e-06, | |
| "loss": 2.6922, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.9906542056074765, | |
| "grad_norm": 5.213560104370117, | |
| "learning_rate": 3.821828084619727e-07, | |
| "loss": 3.6647, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.0373831775700935, | |
| "grad_norm": 2.9050323963165283, | |
| "learning_rate": 0.0, | |
| "loss": 2.2642, | |
| "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 | |
| } | |