| { | |
| "best_metric": 0.6914295554161072, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.008128098837681867, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001625619767536373, | |
| "grad_norm": 1.4133057594299316, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8255, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001625619767536373, | |
| "eval_loss": 0.900519073009491, | |
| "eval_runtime": 722.4785, | |
| "eval_samples_per_second": 3.586, | |
| "eval_steps_per_second": 1.794, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003251239535072746, | |
| "grad_norm": 2.0552265644073486, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8089, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000487685930260912, | |
| "grad_norm": 1.21483314037323, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 0.8083, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006502479070145493, | |
| "grad_norm": 1.5333422422409058, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 0.6852, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008128098837681866, | |
| "grad_norm": 1.4478944540023804, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 0.7185, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000975371860521824, | |
| "grad_norm": 1.0845215320587158, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 0.645, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011379338372754612, | |
| "grad_norm": 1.0120457410812378, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 0.7327, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0013004958140290985, | |
| "grad_norm": 0.9877651333808899, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.6438, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.001463057790782736, | |
| "grad_norm": 1.118600606918335, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 0.6499, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0016256197675363732, | |
| "grad_norm": 1.1166441440582275, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 0.6903, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0017881817442900105, | |
| "grad_norm": 1.202609896659851, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 0.6474, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.001950743721043648, | |
| "grad_norm": 0.9753208756446838, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 0.6544, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002113305697797285, | |
| "grad_norm": 0.9574378132820129, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 0.7245, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0022758676745509225, | |
| "grad_norm": 1.0208672285079956, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.6966, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00243842965130456, | |
| "grad_norm": 0.9356812834739685, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 0.6425, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002600991628058197, | |
| "grad_norm": 1.225610613822937, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 0.6601, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0027635536048118345, | |
| "grad_norm": 1.0732367038726807, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 0.682, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.002926115581565472, | |
| "grad_norm": 0.9814640879631042, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.6934, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003088677558319109, | |
| "grad_norm": 0.9613204598426819, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 0.7026, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0032512395350727465, | |
| "grad_norm": 0.9899714589118958, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.7341, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003413801511826384, | |
| "grad_norm": 1.0220943689346313, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 0.7898, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.003576363488580021, | |
| "grad_norm": 1.0292974710464478, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 0.6794, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0037389254653336585, | |
| "grad_norm": 1.0430673360824585, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 0.6881, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.003901487442087296, | |
| "grad_norm": 0.9846102595329285, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 0.6465, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004064049418840933, | |
| "grad_norm": 0.9897501468658447, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 0.6191, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004064049418840933, | |
| "eval_loss": 0.7381670475006104, | |
| "eval_runtime": 726.8538, | |
| "eval_samples_per_second": 3.565, | |
| "eval_steps_per_second": 1.783, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00422661139559457, | |
| "grad_norm": 1.0687131881713867, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6585, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0043891733723482075, | |
| "grad_norm": 1.1945370435714722, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 0.6396, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.004551735349101845, | |
| "grad_norm": 1.2164644002914429, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 0.6072, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0047142973258554825, | |
| "grad_norm": 1.1531621217727661, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 0.6276, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.00487685930260912, | |
| "grad_norm": 1.1373238563537598, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 0.6343, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005039421279362757, | |
| "grad_norm": 1.547668218612671, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 0.6406, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.005201983256116394, | |
| "grad_norm": 1.48245108127594, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 0.6305, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0053645452328700315, | |
| "grad_norm": 1.767665147781372, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 0.621, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.005527107209623669, | |
| "grad_norm": 1.596113681793213, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.6159, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0056896691863773064, | |
| "grad_norm": 1.8545340299606323, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 0.7291, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.005852231163130944, | |
| "grad_norm": 1.7232612371444702, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 0.577, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.006014793139884581, | |
| "grad_norm": 1.8988685607910156, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 0.6809, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.006177355116638218, | |
| "grad_norm": 1.8034489154815674, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.5321, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0063399170933918555, | |
| "grad_norm": 1.6797901391983032, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 0.4751, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.006502479070145493, | |
| "grad_norm": 2.041771173477173, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 0.616, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.00666504104689913, | |
| "grad_norm": 1.8300652503967285, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 0.5089, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.006827603023652768, | |
| "grad_norm": 3.0001614093780518, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 0.6661, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0069901650004064045, | |
| "grad_norm": 2.6504576206207275, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 0.5584, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.007152726977160042, | |
| "grad_norm": 4.451040744781494, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 0.7299, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0073152889539136795, | |
| "grad_norm": 3.389237880706787, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 0.7446, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.007477850930667317, | |
| "grad_norm": 4.1181840896606445, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 0.6918, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.007640412907420954, | |
| "grad_norm": 6.220348358154297, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 0.6454, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.007802974884174592, | |
| "grad_norm": 7.369223117828369, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 0.8291, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.007965536860928229, | |
| "grad_norm": 8.513662338256836, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 0.7855, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.008128098837681867, | |
| "grad_norm": 14.290572166442871, | |
| "learning_rate": 0.0, | |
| "loss": 1.6268, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008128098837681867, | |
| "eval_loss": 0.6914295554161072, | |
| "eval_runtime": 726.8542, | |
| "eval_samples_per_second": 3.565, | |
| "eval_steps_per_second": 1.783, | |
| "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": 7.03129901334528e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |