| { | |
| "best_metric": 0.587303638458252, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-75", | |
| "epoch": 0.6984866123399301, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009313154831199068, | |
| "grad_norm": 4.13957405090332, | |
| "learning_rate": 2e-05, | |
| "loss": 1.6206, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009313154831199068, | |
| "eval_loss": 2.42331862449646, | |
| "eval_runtime": 16.7951, | |
| "eval_samples_per_second": 86.156, | |
| "eval_steps_per_second": 5.418, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.018626309662398137, | |
| "grad_norm": 5.211028575897217, | |
| "learning_rate": 4e-05, | |
| "loss": 1.9336, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.027939464493597205, | |
| "grad_norm": 5.437460899353027, | |
| "learning_rate": 6e-05, | |
| "loss": 1.9453, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.037252619324796274, | |
| "grad_norm": 4.105167865753174, | |
| "learning_rate": 8e-05, | |
| "loss": 1.6002, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.046565774155995346, | |
| "grad_norm": 3.570579767227173, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3408, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05587892898719441, | |
| "grad_norm": 2.802839756011963, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 1.1321, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06519208381839348, | |
| "grad_norm": 2.4726405143737793, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 1.0462, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07450523864959255, | |
| "grad_norm": 1.6714907884597778, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 0.9939, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08381839348079162, | |
| "grad_norm": 1.7399799823760986, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 0.9237, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09313154831199069, | |
| "grad_norm": 1.7758259773254395, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 0.9164, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10244470314318975, | |
| "grad_norm": 1.526700735092163, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 0.8874, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.11175785797438882, | |
| "grad_norm": 1.484175682067871, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 0.8658, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1210710128055879, | |
| "grad_norm": 2.3066554069519043, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 0.8771, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.13038416763678695, | |
| "grad_norm": 1.369391679763794, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 0.7882, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.13969732246798602, | |
| "grad_norm": 2.3046209812164307, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 0.8022, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1490104772991851, | |
| "grad_norm": 1.3936975002288818, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 0.7166, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.15832363213038417, | |
| "grad_norm": 1.3665108680725098, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 0.7556, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.16763678696158324, | |
| "grad_norm": 0.9268532991409302, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 0.7559, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1769499417927823, | |
| "grad_norm": 1.043634057044983, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 0.741, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.18626309662398138, | |
| "grad_norm": 1.2843759059906006, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 0.7239, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.19557625145518046, | |
| "grad_norm": 1.1267271041870117, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 0.7646, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2048894062863795, | |
| "grad_norm": 1.0400360822677612, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 0.7485, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.21420256111757857, | |
| "grad_norm": 1.1732821464538574, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 0.7245, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.22351571594877764, | |
| "grad_norm": 1.28049898147583, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.7087, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.23282887077997672, | |
| "grad_norm": 1.5667166709899902, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 0.734, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.23282887077997672, | |
| "eval_loss": 0.7290714979171753, | |
| "eval_runtime": 16.8674, | |
| "eval_samples_per_second": 85.787, | |
| "eval_steps_per_second": 5.395, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2421420256111758, | |
| "grad_norm": 1.6958057880401611, | |
| "learning_rate": 8.842005554284296e-05, | |
| "loss": 0.7597, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.25145518044237486, | |
| "grad_norm": 1.23319411277771, | |
| "learning_rate": 8.73410738492077e-05, | |
| "loss": 0.6973, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.2607683352735739, | |
| "grad_norm": 0.9983011484146118, | |
| "learning_rate": 8.622126023955446e-05, | |
| "loss": 0.6683, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.270081490104773, | |
| "grad_norm": 0.9224321842193604, | |
| "learning_rate": 8.506183921362443e-05, | |
| "loss": 0.6433, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.27939464493597205, | |
| "grad_norm": 1.100515604019165, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 0.7131, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.28870779976717115, | |
| "grad_norm": 0.9684303402900696, | |
| "learning_rate": 8.262928807620843e-05, | |
| "loss": 0.6402, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.2980209545983702, | |
| "grad_norm": 0.9174941182136536, | |
| "learning_rate": 8.135881792367686e-05, | |
| "loss": 0.6461, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.3073341094295693, | |
| "grad_norm": 0.998300313949585, | |
| "learning_rate": 8.005405736415126e-05, | |
| "loss": 0.6634, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.31664726426076834, | |
| "grad_norm": 1.0989651679992676, | |
| "learning_rate": 7.871643313414718e-05, | |
| "loss": 0.6501, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.3259604190919674, | |
| "grad_norm": 1.152661919593811, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 0.7261, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3352735739231665, | |
| "grad_norm": 1.1657490730285645, | |
| "learning_rate": 7.594847868906076e-05, | |
| "loss": 0.6728, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.3445867287543655, | |
| "grad_norm": 1.2655208110809326, | |
| "learning_rate": 7.452117519152542e-05, | |
| "loss": 0.6361, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3538998835855646, | |
| "grad_norm": 1.10227632522583, | |
| "learning_rate": 7.30670581489344e-05, | |
| "loss": 0.6442, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.36321303841676367, | |
| "grad_norm": 0.8832430243492126, | |
| "learning_rate": 7.158771761692464e-05, | |
| "loss": 0.6495, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.37252619324796277, | |
| "grad_norm": 0.7977732419967651, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 0.6015, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3818393480791618, | |
| "grad_norm": 0.8318562507629395, | |
| "learning_rate": 6.855986244591104e-05, | |
| "loss": 0.6, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3911525029103609, | |
| "grad_norm": 0.8057540655136108, | |
| "learning_rate": 6.701465872208216e-05, | |
| "loss": 0.6115, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.40046565774155995, | |
| "grad_norm": 0.8961812853813171, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.6151, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.409778812572759, | |
| "grad_norm": 0.9129841923713684, | |
| "learning_rate": 6.387014543809223e-05, | |
| "loss": 0.5908, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.4190919674039581, | |
| "grad_norm": 0.970668613910675, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 0.6279, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.42840512223515714, | |
| "grad_norm": 0.9627373814582825, | |
| "learning_rate": 6.066498153718735e-05, | |
| "loss": 0.6181, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.43771827706635624, | |
| "grad_norm": 0.997525691986084, | |
| "learning_rate": 5.90440267166055e-05, | |
| "loss": 0.5777, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.4470314318975553, | |
| "grad_norm": 1.2201300859451294, | |
| "learning_rate": 5.74131823855921e-05, | |
| "loss": 0.6627, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.4563445867287544, | |
| "grad_norm": 1.1989392042160034, | |
| "learning_rate": 5.577423184847932e-05, | |
| "loss": 0.6586, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.46565774155995343, | |
| "grad_norm": 1.3301013708114624, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 0.6635, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.46565774155995343, | |
| "eval_loss": 0.6151813268661499, | |
| "eval_runtime": 16.7916, | |
| "eval_samples_per_second": 86.174, | |
| "eval_steps_per_second": 5.419, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.47497089639115253, | |
| "grad_norm": 2.323246717453003, | |
| "learning_rate": 5.247918773366112e-05, | |
| "loss": 0.6403, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.4842840512223516, | |
| "grad_norm": 1.077490210533142, | |
| "learning_rate": 5.0826697238317935e-05, | |
| "loss": 0.5904, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.4935972060535506, | |
| "grad_norm": 0.8611325621604919, | |
| "learning_rate": 4.917330276168208e-05, | |
| "loss": 0.5742, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.5029103608847497, | |
| "grad_norm": 1.0277608633041382, | |
| "learning_rate": 4.7520812266338885e-05, | |
| "loss": 0.594, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.5122235157159488, | |
| "grad_norm": 1.1187914609909058, | |
| "learning_rate": 4.5871032726383386e-05, | |
| "loss": 0.5995, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.5215366705471478, | |
| "grad_norm": 0.8779079914093018, | |
| "learning_rate": 4.4225768151520694e-05, | |
| "loss": 0.602, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.5308498253783469, | |
| "grad_norm": 0.9306710362434387, | |
| "learning_rate": 4.2586817614407895e-05, | |
| "loss": 0.5815, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.540162980209546, | |
| "grad_norm": 1.022081971168518, | |
| "learning_rate": 4.095597328339452e-05, | |
| "loss": 0.6049, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.5494761350407451, | |
| "grad_norm": 1.087207555770874, | |
| "learning_rate": 3.933501846281267e-05, | |
| "loss": 0.6495, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.5587892898719441, | |
| "grad_norm": 1.0766098499298096, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 0.6144, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5681024447031432, | |
| "grad_norm": 1.2028203010559082, | |
| "learning_rate": 3.612985456190778e-05, | |
| "loss": 0.6065, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.5774155995343423, | |
| "grad_norm": 1.1321920156478882, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.5828, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.5867287543655413, | |
| "grad_norm": 1.5199047327041626, | |
| "learning_rate": 3.298534127791785e-05, | |
| "loss": 0.6298, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.5960419091967404, | |
| "grad_norm": 1.229564905166626, | |
| "learning_rate": 3.144013755408895e-05, | |
| "loss": 0.5927, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.6053550640279395, | |
| "grad_norm": 0.8759309649467468, | |
| "learning_rate": 2.991522876735154e-05, | |
| "loss": 0.5443, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.6146682188591386, | |
| "grad_norm": 0.7552090287208557, | |
| "learning_rate": 2.8412282383075363e-05, | |
| "loss": 0.5487, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.6239813736903376, | |
| "grad_norm": 0.9531745314598083, | |
| "learning_rate": 2.693294185106562e-05, | |
| "loss": 0.5292, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.6332945285215367, | |
| "grad_norm": 1.0337250232696533, | |
| "learning_rate": 2.547882480847461e-05, | |
| "loss": 0.5255, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.6426076833527358, | |
| "grad_norm": 0.9133326411247253, | |
| "learning_rate": 2.405152131093926e-05, | |
| "loss": 0.552, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.6519208381839348, | |
| "grad_norm": 0.99112468957901, | |
| "learning_rate": 2.2652592093878666e-05, | |
| "loss": 0.5296, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6612339930151339, | |
| "grad_norm": 1.1152122020721436, | |
| "learning_rate": 2.128356686585282e-05, | |
| "loss": 0.5799, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.670547147846333, | |
| "grad_norm": 0.9779994487762451, | |
| "learning_rate": 1.9945942635848748e-05, | |
| "loss": 0.5775, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.6798603026775321, | |
| "grad_norm": 0.9947242736816406, | |
| "learning_rate": 1.8641182076323148e-05, | |
| "loss": 0.5926, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.689173457508731, | |
| "grad_norm": 1.2468385696411133, | |
| "learning_rate": 1.7370711923791567e-05, | |
| "loss": 0.5915, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.6984866123399301, | |
| "grad_norm": 1.1480826139450073, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 0.5552, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.6984866123399301, | |
| "eval_loss": 0.587303638458252, | |
| "eval_runtime": 16.8051, | |
| "eval_samples_per_second": 86.105, | |
| "eval_steps_per_second": 5.415, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.768391340490752e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |