{ "best_metric": 0.8000498414039612, "best_model_checkpoint": "miner_id_24/checkpoint-100", "epoch": 0.011100319134175108, "eval_steps": 50, "global_step": 100, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00011100319134175107, "grad_norm": 2.46205735206604, "learning_rate": 1e-05, "loss": 1.2577, "step": 1 }, { "epoch": 0.00011100319134175107, "eval_loss": 2.9744057655334473, "eval_runtime": 1141.4331, "eval_samples_per_second": 13.293, "eval_steps_per_second": 3.324, "step": 1 }, { "epoch": 0.00022200638268350214, "grad_norm": 2.9185256958007812, "learning_rate": 2e-05, "loss": 1.506, "step": 2 }, { "epoch": 0.0003330095740252532, "grad_norm": 2.96941876411438, "learning_rate": 3e-05, "loss": 1.481, "step": 3 }, { "epoch": 0.0004440127653670043, "grad_norm": 2.581153392791748, "learning_rate": 4e-05, "loss": 1.5443, "step": 4 }, { "epoch": 0.0005550159567087554, "grad_norm": 2.7623963356018066, "learning_rate": 5e-05, "loss": 1.5787, "step": 5 }, { "epoch": 0.0006660191480505064, "grad_norm": 2.6426663398742676, "learning_rate": 6e-05, "loss": 1.4454, "step": 6 }, { "epoch": 0.0007770223393922575, "grad_norm": 2.1133389472961426, "learning_rate": 7e-05, "loss": 1.2349, "step": 7 }, { "epoch": 0.0008880255307340086, "grad_norm": 2.273888349533081, "learning_rate": 8e-05, "loss": 1.253, "step": 8 }, { "epoch": 0.0009990287220757598, "grad_norm": 2.109757661819458, "learning_rate": 9e-05, "loss": 1.0575, "step": 9 }, { "epoch": 0.0011100319134175107, "grad_norm": 1.8438607454299927, "learning_rate": 0.0001, "loss": 0.9085, "step": 10 }, { "epoch": 0.001221035104759262, "grad_norm": 1.6636931896209717, "learning_rate": 9.999316524962345e-05, "loss": 0.9911, "step": 11 }, { "epoch": 0.0013320382961010129, "grad_norm": 1.52732515335083, "learning_rate": 9.997266286704631e-05, "loss": 0.9625, "step": 12 }, { "epoch": 0.001443041487442764, "grad_norm": 1.211435079574585, "learning_rate": 9.993849845741524e-05, "loss": 0.7835, "step": 13 }, { "epoch": 0.001554044678784515, "grad_norm": 1.4507479667663574, "learning_rate": 9.989068136093873e-05, "loss": 0.908, "step": 14 }, { "epoch": 0.0016650478701262662, "grad_norm": 1.6412380933761597, "learning_rate": 9.98292246503335e-05, "loss": 0.9051, "step": 15 }, { "epoch": 0.0017760510614680172, "grad_norm": 1.461786150932312, "learning_rate": 9.975414512725057e-05, "loss": 0.9719, "step": 16 }, { "epoch": 0.0018870542528097683, "grad_norm": 1.4119453430175781, "learning_rate": 9.966546331768191e-05, "loss": 0.9492, "step": 17 }, { "epoch": 0.0019980574441515195, "grad_norm": 1.231529712677002, "learning_rate": 9.956320346634876e-05, "loss": 0.858, "step": 18 }, { "epoch": 0.0021090606354932703, "grad_norm": 1.0582536458969116, "learning_rate": 9.944739353007344e-05, "loss": 0.7127, "step": 19 }, { "epoch": 0.0022200638268350214, "grad_norm": 1.2853320837020874, "learning_rate": 9.931806517013612e-05, "loss": 0.8858, "step": 20 }, { "epoch": 0.0023310670181767726, "grad_norm": 1.1679506301879883, "learning_rate": 9.917525374361912e-05, "loss": 0.7529, "step": 21 }, { "epoch": 0.002442070209518524, "grad_norm": 1.2692056894302368, "learning_rate": 9.901899829374047e-05, "loss": 0.8864, "step": 22 }, { "epoch": 0.0025530734008602745, "grad_norm": 1.2956397533416748, "learning_rate": 9.884934153917997e-05, "loss": 0.85, "step": 23 }, { "epoch": 0.0026640765922020257, "grad_norm": 1.4673477411270142, "learning_rate": 9.86663298624003e-05, "loss": 0.9242, "step": 24 }, { "epoch": 0.002775079783543777, "grad_norm": 1.3525632619857788, "learning_rate": 9.847001329696653e-05, "loss": 0.9741, "step": 25 }, { "epoch": 0.002886082974885528, "grad_norm": 1.9216840267181396, "learning_rate": 9.826044551386744e-05, "loss": 1.045, "step": 26 }, { "epoch": 0.002997086166227279, "grad_norm": 1.4240648746490479, "learning_rate": 9.803768380684242e-05, "loss": 0.8114, "step": 27 }, { "epoch": 0.00310808935756903, "grad_norm": 1.5814491510391235, "learning_rate": 9.780178907671789e-05, "loss": 0.7554, "step": 28 }, { "epoch": 0.003219092548910781, "grad_norm": 1.2749347686767578, "learning_rate": 9.755282581475769e-05, "loss": 0.7537, "step": 29 }, { "epoch": 0.0033300957402525324, "grad_norm": 1.3637299537658691, "learning_rate": 9.729086208503174e-05, "loss": 0.7823, "step": 30 }, { "epoch": 0.003441098931594283, "grad_norm": 1.722434401512146, "learning_rate": 9.701596950580806e-05, "loss": 0.9274, "step": 31 }, { "epoch": 0.0035521021229360343, "grad_norm": 1.5786689519882202, "learning_rate": 9.672822322997305e-05, "loss": 0.9189, "step": 32 }, { "epoch": 0.0036631053142777855, "grad_norm": 1.5733418464660645, "learning_rate": 9.642770192448536e-05, "loss": 0.725, "step": 33 }, { "epoch": 0.0037741085056195367, "grad_norm": 1.8876582384109497, "learning_rate": 9.611448774886924e-05, "loss": 0.9021, "step": 34 }, { "epoch": 0.003885111696961288, "grad_norm": 1.4569281339645386, "learning_rate": 9.578866633275288e-05, "loss": 0.8872, "step": 35 }, { "epoch": 0.003996114888303039, "grad_norm": 1.510157823562622, "learning_rate": 9.545032675245813e-05, "loss": 0.8128, "step": 36 }, { "epoch": 0.00410711807964479, "grad_norm": 1.4462164640426636, "learning_rate": 9.509956150664796e-05, "loss": 0.8201, "step": 37 }, { "epoch": 0.0042181212709865405, "grad_norm": 1.422254204750061, "learning_rate": 9.473646649103818e-05, "loss": 0.8283, "step": 38 }, { "epoch": 0.004329124462328292, "grad_norm": 1.3379862308502197, "learning_rate": 9.43611409721806e-05, "loss": 0.5971, "step": 39 }, { "epoch": 0.004440127653670043, "grad_norm": 1.3725043535232544, "learning_rate": 9.397368756032445e-05, "loss": 0.8118, "step": 40 }, { "epoch": 0.0045511308450117945, "grad_norm": 1.5491840839385986, "learning_rate": 9.357421218136386e-05, "loss": 0.7418, "step": 41 }, { "epoch": 0.004662134036353545, "grad_norm": 1.6002413034439087, "learning_rate": 9.316282404787871e-05, "loss": 0.8428, "step": 42 }, { "epoch": 0.004773137227695296, "grad_norm": 1.6917510032653809, "learning_rate": 9.273963562927695e-05, "loss": 0.9056, "step": 43 }, { "epoch": 0.004884140419037048, "grad_norm": 1.7446221113204956, "learning_rate": 9.230476262104677e-05, "loss": 0.8666, "step": 44 }, { "epoch": 0.004995143610378798, "grad_norm": 2.7468857765197754, "learning_rate": 9.185832391312644e-05, "loss": 0.8409, "step": 45 }, { "epoch": 0.005106146801720549, "grad_norm": 2.0201501846313477, "learning_rate": 9.140044155740101e-05, "loss": 0.792, "step": 46 }, { "epoch": 0.005217149993062301, "grad_norm": 1.940047025680542, "learning_rate": 9.093124073433463e-05, "loss": 0.6652, "step": 47 }, { "epoch": 0.0053281531844040515, "grad_norm": 1.9866968393325806, "learning_rate": 9.045084971874738e-05, "loss": 0.6353, "step": 48 }, { "epoch": 0.005439156375745803, "grad_norm": 2.8619282245635986, "learning_rate": 8.995939984474624e-05, "loss": 0.8224, "step": 49 }, { "epoch": 0.005550159567087554, "grad_norm": 2.674960136413574, "learning_rate": 8.945702546981969e-05, "loss": 0.608, "step": 50 }, { "epoch": 0.005550159567087554, "eval_loss": 0.8254091143608093, "eval_runtime": 1145.681, "eval_samples_per_second": 13.244, "eval_steps_per_second": 3.312, "step": 50 }, { "epoch": 0.005661162758429305, "grad_norm": 1.0036686658859253, "learning_rate": 8.894386393810563e-05, "loss": 0.953, "step": 51 }, { "epoch": 0.005772165949771056, "grad_norm": 1.0603018999099731, "learning_rate": 8.842005554284296e-05, "loss": 0.8554, "step": 52 }, { "epoch": 0.005883169141112807, "grad_norm": 0.8736121654510498, "learning_rate": 8.788574348801675e-05, "loss": 0.8861, "step": 53 }, { "epoch": 0.005994172332454558, "grad_norm": 0.9409048557281494, "learning_rate": 8.73410738492077e-05, "loss": 0.8456, "step": 54 }, { "epoch": 0.006105175523796309, "grad_norm": 0.9477500915527344, "learning_rate": 8.678619553365659e-05, "loss": 0.8381, "step": 55 }, { "epoch": 0.00621617871513806, "grad_norm": 1.1850745677947998, "learning_rate": 8.622126023955446e-05, "loss": 0.8929, "step": 56 }, { "epoch": 0.006327181906479812, "grad_norm": 1.0310847759246826, "learning_rate": 8.564642241456986e-05, "loss": 0.8982, "step": 57 }, { "epoch": 0.006438185097821562, "grad_norm": 1.0277560949325562, "learning_rate": 8.506183921362443e-05, "loss": 0.8895, "step": 58 }, { "epoch": 0.006549188289163313, "grad_norm": 0.8867915868759155, "learning_rate": 8.44676704559283e-05, "loss": 0.7826, "step": 59 }, { "epoch": 0.006660191480505065, "grad_norm": 1.078498125076294, "learning_rate": 8.386407858128706e-05, "loss": 0.8777, "step": 60 }, { "epoch": 0.0067711946718468155, "grad_norm": 0.9189152717590332, "learning_rate": 8.32512286056924e-05, "loss": 0.7924, "step": 61 }, { "epoch": 0.006882197863188566, "grad_norm": 1.011573314666748, "learning_rate": 8.262928807620843e-05, "loss": 0.9122, "step": 62 }, { "epoch": 0.006993201054530318, "grad_norm": 1.0407687425613403, "learning_rate": 8.199842702516583e-05, "loss": 0.8104, "step": 63 }, { "epoch": 0.007104204245872069, "grad_norm": 1.0033093690872192, "learning_rate": 8.135881792367686e-05, "loss": 0.9252, "step": 64 }, { "epoch": 0.00721520743721382, "grad_norm": 0.919106662273407, "learning_rate": 8.07106356344834e-05, "loss": 0.7244, "step": 65 }, { "epoch": 0.007326210628555571, "grad_norm": 0.9753147959709167, "learning_rate": 8.005405736415126e-05, "loss": 0.7824, "step": 66 }, { "epoch": 0.007437213819897322, "grad_norm": 0.9869587421417236, "learning_rate": 7.938926261462366e-05, "loss": 0.7801, "step": 67 }, { "epoch": 0.007548217011239073, "grad_norm": 1.0366357564926147, "learning_rate": 7.871643313414718e-05, "loss": 0.821, "step": 68 }, { "epoch": 0.007659220202580824, "grad_norm": 1.1145334243774414, "learning_rate": 7.803575286758364e-05, "loss": 0.8619, "step": 69 }, { "epoch": 0.007770223393922576, "grad_norm": 1.2978206872940063, "learning_rate": 7.734740790612136e-05, "loss": 0.9037, "step": 70 }, { "epoch": 0.007881226585264326, "grad_norm": 1.1509613990783691, "learning_rate": 7.66515864363997e-05, "loss": 0.7544, "step": 71 }, { "epoch": 0.007992229776606078, "grad_norm": 1.0371291637420654, "learning_rate": 7.594847868906076e-05, "loss": 0.7826, "step": 72 }, { "epoch": 0.008103232967947828, "grad_norm": 1.0573813915252686, "learning_rate": 7.52382768867422e-05, "loss": 0.7808, "step": 73 }, { "epoch": 0.00821423615928958, "grad_norm": 1.2486634254455566, "learning_rate": 7.452117519152542e-05, "loss": 0.6838, "step": 74 }, { "epoch": 0.008325239350631331, "grad_norm": 1.2400583028793335, "learning_rate": 7.379736965185368e-05, "loss": 0.8826, "step": 75 }, { "epoch": 0.008436242541973081, "grad_norm": 1.0707412958145142, "learning_rate": 7.30670581489344e-05, "loss": 0.7261, "step": 76 }, { "epoch": 0.008547245733314833, "grad_norm": 1.325318455696106, "learning_rate": 7.233044034264034e-05, "loss": 0.9285, "step": 77 }, { "epoch": 0.008658248924656584, "grad_norm": 1.3431965112686157, "learning_rate": 7.158771761692464e-05, "loss": 0.9954, "step": 78 }, { "epoch": 0.008769252115998334, "grad_norm": 1.395011305809021, "learning_rate": 7.083909302476453e-05, "loss": 0.8256, "step": 79 }, { "epoch": 0.008880255307340086, "grad_norm": 1.2236677408218384, "learning_rate": 7.008477123264848e-05, "loss": 0.8649, "step": 80 }, { "epoch": 0.008991258498681837, "grad_norm": 1.3813550472259521, "learning_rate": 6.932495846462261e-05, "loss": 0.7499, "step": 81 }, { "epoch": 0.009102261690023589, "grad_norm": 1.1952629089355469, "learning_rate": 6.855986244591104e-05, "loss": 0.7567, "step": 82 }, { "epoch": 0.009213264881365339, "grad_norm": 1.1774139404296875, "learning_rate": 6.778969234612584e-05, "loss": 0.5969, "step": 83 }, { "epoch": 0.00932426807270709, "grad_norm": 1.3768928050994873, "learning_rate": 6.701465872208216e-05, "loss": 0.7333, "step": 84 }, { "epoch": 0.009435271264048842, "grad_norm": 1.5121829509735107, "learning_rate": 6.623497346023418e-05, "loss": 0.8053, "step": 85 }, { "epoch": 0.009546274455390592, "grad_norm": 1.3658143281936646, "learning_rate": 6.545084971874738e-05, "loss": 0.8026, "step": 86 }, { "epoch": 0.009657277646732344, "grad_norm": 1.400071620941162, "learning_rate": 6.466250186922325e-05, "loss": 0.6916, "step": 87 }, { "epoch": 0.009768280838074095, "grad_norm": 1.3228888511657715, "learning_rate": 6.387014543809223e-05, "loss": 0.7051, "step": 88 }, { "epoch": 0.009879284029415845, "grad_norm": 1.5070359706878662, "learning_rate": 6.307399704769099e-05, "loss": 0.8033, "step": 89 }, { "epoch": 0.009990287220757597, "grad_norm": 1.335098147392273, "learning_rate": 6.227427435703997e-05, "loss": 0.7683, "step": 90 }, { "epoch": 0.010101290412099348, "grad_norm": 1.4469175338745117, "learning_rate": 6.147119600233758e-05, "loss": 0.5573, "step": 91 }, { "epoch": 0.010212293603441098, "grad_norm": 1.5435446500778198, "learning_rate": 6.066498153718735e-05, "loss": 0.7527, "step": 92 }, { "epoch": 0.01032329679478285, "grad_norm": 1.571133017539978, "learning_rate": 5.985585137257401e-05, "loss": 0.797, "step": 93 }, { "epoch": 0.010434299986124601, "grad_norm": 1.4781806468963623, "learning_rate": 5.90440267166055e-05, "loss": 0.7084, "step": 94 }, { "epoch": 0.010545303177466351, "grad_norm": 1.586531162261963, "learning_rate": 5.8229729514036705e-05, "loss": 0.7317, "step": 95 }, { "epoch": 0.010656306368808103, "grad_norm": 1.778027892112732, "learning_rate": 5.74131823855921e-05, "loss": 0.6611, "step": 96 }, { "epoch": 0.010767309560149855, "grad_norm": 1.9934014081954956, "learning_rate": 5.6594608567103456e-05, "loss": 1.0245, "step": 97 }, { "epoch": 0.010878312751491606, "grad_norm": 2.2396204471588135, "learning_rate": 5.577423184847932e-05, "loss": 0.8315, "step": 98 }, { "epoch": 0.010989315942833356, "grad_norm": 2.139233350753784, "learning_rate": 5.495227651252315e-05, "loss": 0.6726, "step": 99 }, { "epoch": 0.011100319134175108, "grad_norm": 2.108496904373169, "learning_rate": 5.4128967273616625e-05, "loss": 0.6403, "step": 100 }, { "epoch": 0.011100319134175108, "eval_loss": 0.8000498414039612, "eval_runtime": 1145.8791, "eval_samples_per_second": 13.241, "eval_steps_per_second": 3.311, "step": 100 } ], "logging_steps": 1, "max_steps": 200, "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": 1.5122848626927206e+17, "train_batch_size": 8, "trial_name": null, "trial_params": null }