| { | |
| "best_metric": 1.0213967561721802, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.6855184233076264, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013710368466152529, | |
| "grad_norm": 0.7160943150520325, | |
| "learning_rate": 5e-05, | |
| "loss": 1.077, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013710368466152529, | |
| "eval_loss": 2.041999578475952, | |
| "eval_runtime": 2.2874, | |
| "eval_samples_per_second": 21.859, | |
| "eval_steps_per_second": 5.683, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.027420736932305057, | |
| "grad_norm": 0.8189798593521118, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1494, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04113110539845758, | |
| "grad_norm": 0.7789645791053772, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 1.1257, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.054841473864610114, | |
| "grad_norm": 0.9116306304931641, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.0836, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06855184233076264, | |
| "grad_norm": 0.7163779735565186, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.152, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08226221079691516, | |
| "grad_norm": 1.0974628925323486, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.1058, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0959725792630677, | |
| "grad_norm": 1.01798415184021, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.1899, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.10968294772922023, | |
| "grad_norm": 0.9082322716712952, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.0599, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.12339331619537275, | |
| "grad_norm": 1.6280889511108398, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.1775, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.13710368466152528, | |
| "grad_norm": 1.5951272249221802, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.1523, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15081405312767782, | |
| "grad_norm": 1.9335215091705322, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.266, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.16452442159383032, | |
| "grad_norm": 2.6159534454345703, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.3577, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.17823479005998286, | |
| "grad_norm": 0.7536554932594299, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.9559, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1919451585261354, | |
| "grad_norm": 0.7636892795562744, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.8886, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.20565552699228792, | |
| "grad_norm": 0.5555309057235718, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.9126, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.21936589545844046, | |
| "grad_norm": 0.47230857610702515, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.8897, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.23307626392459296, | |
| "grad_norm": 0.4979608654975891, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.9259, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.2467866323907455, | |
| "grad_norm": 0.6286565065383911, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.9924, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.26049700085689803, | |
| "grad_norm": 0.702115535736084, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.0007, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.27420736932305056, | |
| "grad_norm": 0.6681036353111267, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.9577, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2879177377892031, | |
| "grad_norm": 0.7509329915046692, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.9956, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.30162810625535563, | |
| "grad_norm": 1.0370296239852905, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.0205, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.31533847472150817, | |
| "grad_norm": 1.4013001918792725, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.9855, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.32904884318766064, | |
| "grad_norm": 1.7642357349395752, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.1241, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3427592116538132, | |
| "grad_norm": 2.3584861755371094, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.0618, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3427592116538132, | |
| "eval_loss": 1.0571568012237549, | |
| "eval_runtime": 2.3153, | |
| "eval_samples_per_second": 21.595, | |
| "eval_steps_per_second": 5.615, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3564695801199657, | |
| "grad_norm": 0.3724190294742584, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.8609, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.37017994858611825, | |
| "grad_norm": 0.3975992500782013, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.8236, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3838903170522708, | |
| "grad_norm": 0.4572630226612091, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.8765, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3976006855184233, | |
| "grad_norm": 0.5107871890068054, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.8768, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.41131105398457585, | |
| "grad_norm": 0.6196900606155396, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.9245, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4250214224507284, | |
| "grad_norm": 0.6747974753379822, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.978, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.4387317909168809, | |
| "grad_norm": 0.6937869191169739, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.935, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4524421593830334, | |
| "grad_norm": 0.7304213643074036, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.9434, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.4661525278491859, | |
| "grad_norm": 0.8814483880996704, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.9642, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.47986289631533846, | |
| "grad_norm": 1.1520628929138184, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.9072, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.493573264781491, | |
| "grad_norm": 1.8298850059509277, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.0162, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5072836332476436, | |
| "grad_norm": 1.9809646606445312, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.9673, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5209940017137961, | |
| "grad_norm": 0.39740994572639465, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.9083, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5347043701799485, | |
| "grad_norm": 0.3018646240234375, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.8195, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5484147386461011, | |
| "grad_norm": 0.3188331127166748, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.7938, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5621251071122536, | |
| "grad_norm": 0.35798129439353943, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.849, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5758354755784062, | |
| "grad_norm": 0.4261307716369629, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.8968, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5895458440445587, | |
| "grad_norm": 0.4484318792819977, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.8825, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6032562125107113, | |
| "grad_norm": 0.5180601477622986, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.91, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6169665809768637, | |
| "grad_norm": 0.621738851070404, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.9466, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6306769494430163, | |
| "grad_norm": 0.6436194777488708, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.9237, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6443873179091688, | |
| "grad_norm": 0.837110161781311, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.9483, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6580976863753213, | |
| "grad_norm": 1.1074998378753662, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.0255, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6718080548414739, | |
| "grad_norm": 1.4551877975463867, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.0155, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6855184233076264, | |
| "grad_norm": 1.933646559715271, | |
| "learning_rate": 1e-05, | |
| "loss": 0.8422, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6855184233076264, | |
| "eval_loss": 1.0213967561721802, | |
| "eval_runtime": 2.3124, | |
| "eval_samples_per_second": 21.623, | |
| "eval_steps_per_second": 5.622, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.174479344467968e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |