| { | |
| "best_metric": 1.475726842880249, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.01536216299254935, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00030724325985098704, | |
| "grad_norm": 23.011367797851562, | |
| "learning_rate": 5e-06, | |
| "loss": 6.3985, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00030724325985098704, | |
| "eval_loss": 2.409876585006714, | |
| "eval_runtime": 441.0598, | |
| "eval_samples_per_second": 12.429, | |
| "eval_steps_per_second": 6.215, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006144865197019741, | |
| "grad_norm": 32.28715515136719, | |
| "learning_rate": 1e-05, | |
| "loss": 7.734, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0009217297795529611, | |
| "grad_norm": 28.548389434814453, | |
| "learning_rate": 1.5e-05, | |
| "loss": 7.4653, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0012289730394039482, | |
| "grad_norm": 24.919015884399414, | |
| "learning_rate": 2e-05, | |
| "loss": 7.3706, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001536216299254935, | |
| "grad_norm": 22.995384216308594, | |
| "learning_rate": 2.5e-05, | |
| "loss": 6.938, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0018434595591059221, | |
| "grad_norm": 19.593135833740234, | |
| "learning_rate": 3e-05, | |
| "loss": 7.122, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0021507028189569092, | |
| "grad_norm": 18.867374420166016, | |
| "learning_rate": 3.5e-05, | |
| "loss": 5.8915, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0024579460788078963, | |
| "grad_norm": 15.144004821777344, | |
| "learning_rate": 4e-05, | |
| "loss": 5.7937, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002765189338658883, | |
| "grad_norm": 13.516443252563477, | |
| "learning_rate": 4.5e-05, | |
| "loss": 5.6253, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00307243259850987, | |
| "grad_norm": 14.180933952331543, | |
| "learning_rate": 5e-05, | |
| "loss": 5.3894, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003379675858360857, | |
| "grad_norm": 16.558490753173828, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 4.628, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0036869191182118443, | |
| "grad_norm": 14.397795677185059, | |
| "learning_rate": 6e-05, | |
| "loss": 5.3816, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.003994162378062831, | |
| "grad_norm": 15.309121131896973, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 4.9166, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0043014056379138185, | |
| "grad_norm": 15.53266716003418, | |
| "learning_rate": 7e-05, | |
| "loss": 4.5761, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.004608648897764805, | |
| "grad_norm": 13.632649421691895, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 3.6609, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004915892157615793, | |
| "grad_norm": 13.333073616027832, | |
| "learning_rate": 8e-05, | |
| "loss": 4.0839, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.005223135417466779, | |
| "grad_norm": 14.622278213500977, | |
| "learning_rate": 8.5e-05, | |
| "loss": 4.4781, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.005530378677317766, | |
| "grad_norm": 12.793045997619629, | |
| "learning_rate": 9e-05, | |
| "loss": 4.9027, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0058376219371687535, | |
| "grad_norm": 11.85013484954834, | |
| "learning_rate": 9.5e-05, | |
| "loss": 3.8893, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.00614486519701974, | |
| "grad_norm": 13.697391510009766, | |
| "learning_rate": 0.0001, | |
| "loss": 4.6765, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006452108456870728, | |
| "grad_norm": 10.900583267211914, | |
| "learning_rate": 9.999238475781957e-05, | |
| "loss": 3.559, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.006759351716721714, | |
| "grad_norm": 15.428689002990723, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 4.3751, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.007066594976572701, | |
| "grad_norm": 11.113511085510254, | |
| "learning_rate": 9.99314767377287e-05, | |
| "loss": 4.1964, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0073738382364236885, | |
| "grad_norm": 12.102518081665039, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 4.4795, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.007681081496274675, | |
| "grad_norm": 11.722882270812988, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 4.2897, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007988324756125662, | |
| "grad_norm": 11.406682968139648, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 5.0885, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.00829556801597665, | |
| "grad_norm": 11.243815422058105, | |
| "learning_rate": 9.962730758206611e-05, | |
| "loss": 4.4903, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.008602811275827637, | |
| "grad_norm": 11.628358840942383, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 4.4378, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.008910054535678624, | |
| "grad_norm": 10.681234359741211, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 4.691, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.00921729779552961, | |
| "grad_norm": 10.783159255981445, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 4.9312, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.009524541055380597, | |
| "grad_norm": 10.892800331115723, | |
| "learning_rate": 9.908135917238321e-05, | |
| "loss": 5.2761, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.009831784315231585, | |
| "grad_norm": 11.34912109375, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 5.4007, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.010139027575082572, | |
| "grad_norm": 13.050414085388184, | |
| "learning_rate": 9.871850323926177e-05, | |
| "loss": 5.5961, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.010446270834933559, | |
| "grad_norm": 11.140335083007812, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 4.5804, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.010753514094784545, | |
| "grad_norm": 11.838504791259766, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 5.553, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.011060757354635532, | |
| "grad_norm": 12.498956680297852, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 4.8211, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.01136800061448652, | |
| "grad_norm": 12.233826637268066, | |
| "learning_rate": 9.781523779815179e-05, | |
| "loss": 5.3758, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.011675243874337507, | |
| "grad_norm": 12.875245094299316, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 5.2887, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.011982487134188494, | |
| "grad_norm": 14.482268333435059, | |
| "learning_rate": 9.727592877996585e-05, | |
| "loss": 5.3555, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.01228973039403948, | |
| "grad_norm": 12.469817161560059, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 5.1884, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.012596973653890467, | |
| "grad_norm": 14.905447959899902, | |
| "learning_rate": 9.667902132486009e-05, | |
| "loss": 5.7557, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.012904216913741455, | |
| "grad_norm": 12.736101150512695, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 4.3636, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.013211460173592442, | |
| "grad_norm": 13.541585922241211, | |
| "learning_rate": 9.602524267262203e-05, | |
| "loss": 5.2159, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.013518703433443429, | |
| "grad_norm": 14.56790542602539, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 6.1784, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.013825946693294415, | |
| "grad_norm": 14.048850059509277, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 5.7569, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.014133189953145402, | |
| "grad_norm": 14.115535736083984, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 5.7633, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.01444043321299639, | |
| "grad_norm": 13.446468353271484, | |
| "learning_rate": 9.45503262094184e-05, | |
| "loss": 5.7742, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.014747676472847377, | |
| "grad_norm": 15.913680076599121, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 5.6512, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.015054919732698364, | |
| "grad_norm": 13.415315628051758, | |
| "learning_rate": 9.373098535696979e-05, | |
| "loss": 4.9549, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.01536216299254935, | |
| "grad_norm": 22.350265502929688, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 6.6309, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01536216299254935, | |
| "eval_loss": 1.475726842880249, | |
| "eval_runtime": 443.646, | |
| "eval_samples_per_second": 12.357, | |
| "eval_steps_per_second": 6.178, | |
| "step": 50 | |
| } | |
| ], | |
| "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": 7.19077308849193e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |