| { | |
| "best_metric": 1.8454655408859253, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.35046728971962615, | |
| "eval_steps": 50, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004672897196261682, | |
| "grad_norm": 66.80829620361328, | |
| "learning_rate": 5e-06, | |
| "loss": 37.307, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004672897196261682, | |
| "eval_loss": 2.270360231399536, | |
| "eval_runtime": 48.2906, | |
| "eval_samples_per_second": 14.93, | |
| "eval_steps_per_second": 3.748, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009345794392523364, | |
| "grad_norm": 43.96245193481445, | |
| "learning_rate": 1e-05, | |
| "loss": 39.3602, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.014018691588785047, | |
| "grad_norm": 36.99504470825195, | |
| "learning_rate": 1.5e-05, | |
| "loss": 35.503, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.018691588785046728, | |
| "grad_norm": 39.434837341308594, | |
| "learning_rate": 2e-05, | |
| "loss": 36.4815, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02336448598130841, | |
| "grad_norm": 33.79097366333008, | |
| "learning_rate": 2.5e-05, | |
| "loss": 37.442, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.028037383177570093, | |
| "grad_norm": 26.76743507385254, | |
| "learning_rate": 3e-05, | |
| "loss": 33.581, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03271028037383177, | |
| "grad_norm": 20.88287353515625, | |
| "learning_rate": 3.5e-05, | |
| "loss": 35.1813, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.037383177570093455, | |
| "grad_norm": 26.102088928222656, | |
| "learning_rate": 4e-05, | |
| "loss": 31.3943, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04205607476635514, | |
| "grad_norm": 21.67459487915039, | |
| "learning_rate": 4.5e-05, | |
| "loss": 32.2694, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04672897196261682, | |
| "grad_norm": 15.997559547424316, | |
| "learning_rate": 5e-05, | |
| "loss": 32.4019, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0514018691588785, | |
| "grad_norm": 17.432832717895508, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 30.7009, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.056074766355140186, | |
| "grad_norm": 17.27799415588379, | |
| "learning_rate": 6e-05, | |
| "loss": 35.4881, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06074766355140187, | |
| "grad_norm": 15.450854301452637, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 30.0011, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06542056074766354, | |
| "grad_norm": 14.18392276763916, | |
| "learning_rate": 7e-05, | |
| "loss": 33.5956, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.07009345794392523, | |
| "grad_norm": 13.806038856506348, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 31.2958, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07476635514018691, | |
| "grad_norm": 14.44079303741455, | |
| "learning_rate": 8e-05, | |
| "loss": 29.5818, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0794392523364486, | |
| "grad_norm": 13.624066352844238, | |
| "learning_rate": 8.5e-05, | |
| "loss": 28.5156, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.08411214953271028, | |
| "grad_norm": 11.987879753112793, | |
| "learning_rate": 9e-05, | |
| "loss": 30.7739, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08878504672897196, | |
| "grad_norm": 11.590877532958984, | |
| "learning_rate": 9.5e-05, | |
| "loss": 33.3138, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.09345794392523364, | |
| "grad_norm": 13.10567569732666, | |
| "learning_rate": 0.0001, | |
| "loss": 30.9867, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09813084112149532, | |
| "grad_norm": 13.021055221557617, | |
| "learning_rate": 9.991845519630678e-05, | |
| "loss": 34.8429, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.102803738317757, | |
| "grad_norm": 10.940986633300781, | |
| "learning_rate": 9.967408676742751e-05, | |
| "loss": 29.6591, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.10747663551401869, | |
| "grad_norm": 13.093828201293945, | |
| "learning_rate": 9.926769179238466e-05, | |
| "loss": 28.1053, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.11214953271028037, | |
| "grad_norm": 14.115128517150879, | |
| "learning_rate": 9.870059584711668e-05, | |
| "loss": 30.8417, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.11682242990654206, | |
| "grad_norm": 11.575407981872559, | |
| "learning_rate": 9.797464868072488e-05, | |
| "loss": 31.5666, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.12149532710280374, | |
| "grad_norm": 13.10224723815918, | |
| "learning_rate": 9.709221818197624e-05, | |
| "loss": 32.2864, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1261682242990654, | |
| "grad_norm": 11.407258033752441, | |
| "learning_rate": 9.60561826557425e-05, | |
| "loss": 25.6238, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1308411214953271, | |
| "grad_norm": 11.045011520385742, | |
| "learning_rate": 9.486992143456792e-05, | |
| "loss": 31.7439, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.13551401869158877, | |
| "grad_norm": 11.990827560424805, | |
| "learning_rate": 9.353730385598887e-05, | |
| "loss": 29.2801, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.14018691588785046, | |
| "grad_norm": 11.327007293701172, | |
| "learning_rate": 9.206267664155907e-05, | |
| "loss": 29.2111, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.14485981308411214, | |
| "grad_norm": 11.330085754394531, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 27.8197, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.14953271028037382, | |
| "grad_norm": 10.81998348236084, | |
| "learning_rate": 8.870708053195413e-05, | |
| "loss": 30.3391, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1542056074766355, | |
| "grad_norm": 12.359819412231445, | |
| "learning_rate": 8.683705689382024e-05, | |
| "loss": 32.7055, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1588785046728972, | |
| "grad_norm": 12.187078475952148, | |
| "learning_rate": 8.484687843276469e-05, | |
| "loss": 28.9465, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.16355140186915887, | |
| "grad_norm": 11.44126033782959, | |
| "learning_rate": 8.274303669726426e-05, | |
| "loss": 23.4919, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.16822429906542055, | |
| "grad_norm": 11.298962593078613, | |
| "learning_rate": 8.053239398177191e-05, | |
| "loss": 27.6871, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.17289719626168223, | |
| "grad_norm": 11.405156135559082, | |
| "learning_rate": 7.822216094333847e-05, | |
| "loss": 28.2709, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.17757009345794392, | |
| "grad_norm": 10.888545036315918, | |
| "learning_rate": 7.58198730819481e-05, | |
| "loss": 28.1322, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.1822429906542056, | |
| "grad_norm": 11.130096435546875, | |
| "learning_rate": 7.333336616128369e-05, | |
| "loss": 28.4985, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.18691588785046728, | |
| "grad_norm": 11.024548530578613, | |
| "learning_rate": 7.077075065009433e-05, | |
| "loss": 28.1634, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.19158878504672897, | |
| "grad_norm": 11.3602294921875, | |
| "learning_rate": 6.814038526753205e-05, | |
| "loss": 35.0791, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.19626168224299065, | |
| "grad_norm": 10.769115447998047, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 34.4084, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.20093457943925233, | |
| "grad_norm": 10.817389488220215, | |
| "learning_rate": 6.271091670967436e-05, | |
| "loss": 32.5228, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.205607476635514, | |
| "grad_norm": 11.504584312438965, | |
| "learning_rate": 5.992952333228728e-05, | |
| "loss": 27.4319, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.2102803738317757, | |
| "grad_norm": 11.034488677978516, | |
| "learning_rate": 5.7115741913664264e-05, | |
| "loss": 31.3554, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.21495327102803738, | |
| "grad_norm": 11.56508731842041, | |
| "learning_rate": 5.427875042394199e-05, | |
| "loss": 28.8597, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.21962616822429906, | |
| "grad_norm": 24.39493751525879, | |
| "learning_rate": 5.142780253968481e-05, | |
| "loss": 27.9015, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.22429906542056074, | |
| "grad_norm": 10.291220664978027, | |
| "learning_rate": 4.85721974603152e-05, | |
| "loss": 31.4947, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.22897196261682243, | |
| "grad_norm": 10.813641548156738, | |
| "learning_rate": 4.5721249576058027e-05, | |
| "loss": 26.6787, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.2336448598130841, | |
| "grad_norm": 12.239684104919434, | |
| "learning_rate": 4.288425808633575e-05, | |
| "loss": 26.2165, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2336448598130841, | |
| "eval_loss": 1.8454655408859253, | |
| "eval_runtime": 48.3592, | |
| "eval_samples_per_second": 14.909, | |
| "eval_steps_per_second": 3.743, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2383177570093458, | |
| "grad_norm": 10.01890754699707, | |
| "learning_rate": 4.007047666771274e-05, | |
| "loss": 28.1479, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.24299065420560748, | |
| "grad_norm": 10.493062973022461, | |
| "learning_rate": 3.728908329032567e-05, | |
| "loss": 26.7191, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.24766355140186916, | |
| "grad_norm": 11.016109466552734, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 29.1286, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.2523364485981308, | |
| "grad_norm": 10.54951000213623, | |
| "learning_rate": 3.1859614732467954e-05, | |
| "loss": 28.8225, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.2570093457943925, | |
| "grad_norm": 10.172712326049805, | |
| "learning_rate": 2.9229249349905684e-05, | |
| "loss": 32.9307, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.2616822429906542, | |
| "grad_norm": 13.219228744506836, | |
| "learning_rate": 2.6666633838716314e-05, | |
| "loss": 28.8002, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.26635514018691586, | |
| "grad_norm": 9.766500473022461, | |
| "learning_rate": 2.418012691805191e-05, | |
| "loss": 27.8569, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.27102803738317754, | |
| "grad_norm": 9.871047973632812, | |
| "learning_rate": 2.1777839056661554e-05, | |
| "loss": 34.0156, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.2757009345794392, | |
| "grad_norm": 11.04659366607666, | |
| "learning_rate": 1.946760601822809e-05, | |
| "loss": 30.437, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.2803738317757009, | |
| "grad_norm": 32.65912628173828, | |
| "learning_rate": 1.725696330273575e-05, | |
| "loss": 28.4228, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2850467289719626, | |
| "grad_norm": 13.58231258392334, | |
| "learning_rate": 1.5153121567235335e-05, | |
| "loss": 32.4821, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.2897196261682243, | |
| "grad_norm": 10.420000076293945, | |
| "learning_rate": 1.3162943106179749e-05, | |
| "loss": 27.4436, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.29439252336448596, | |
| "grad_norm": 10.50948715209961, | |
| "learning_rate": 1.1292919468045877e-05, | |
| "loss": 27.5072, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.29906542056074764, | |
| "grad_norm": 10.826915740966797, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 30.5895, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.3037383177570093, | |
| "grad_norm": 10.006555557250977, | |
| "learning_rate": 7.937323358440935e-06, | |
| "loss": 32.246, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.308411214953271, | |
| "grad_norm": 10.863489151000977, | |
| "learning_rate": 6.462696144011149e-06, | |
| "loss": 27.2672, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.3130841121495327, | |
| "grad_norm": 10.34022331237793, | |
| "learning_rate": 5.13007856543209e-06, | |
| "loss": 29.9912, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.3177570093457944, | |
| "grad_norm": 11.068024635314941, | |
| "learning_rate": 3.9438173442575e-06, | |
| "loss": 34.9261, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.32242990654205606, | |
| "grad_norm": 10.7153902053833, | |
| "learning_rate": 2.9077818180237693e-06, | |
| "loss": 31.9632, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.32710280373831774, | |
| "grad_norm": 11.57532787322998, | |
| "learning_rate": 2.0253513192751373e-06, | |
| "loss": 34.1264, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.3317757009345794, | |
| "grad_norm": 10.075494766235352, | |
| "learning_rate": 1.2994041528833266e-06, | |
| "loss": 31.5173, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.3364485981308411, | |
| "grad_norm": 10.921475410461426, | |
| "learning_rate": 7.323082076153509e-07, | |
| "loss": 29.5536, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.3411214953271028, | |
| "grad_norm": 9.99160099029541, | |
| "learning_rate": 3.2591323257248893e-07, | |
| "loss": 30.6071, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.34579439252336447, | |
| "grad_norm": 9.956338882446289, | |
| "learning_rate": 8.15448036932176e-08, | |
| "loss": 28.1912, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.35046728971962615, | |
| "grad_norm": 10.755599975585938, | |
| "learning_rate": 0.0, | |
| "loss": 28.4376, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.9444284927246336e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |