| { | |
| "best_metric": 10.368429183959961, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.0005295319996187369, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.059063999237474e-05, | |
| "grad_norm": 0.15046997368335724, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3924, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.059063999237474e-05, | |
| "eval_loss": 10.403708457946777, | |
| "eval_runtime": 256.1878, | |
| "eval_samples_per_second": 155.191, | |
| "eval_steps_per_second": 77.595, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.118127998474948e-05, | |
| "grad_norm": 0.1689300686120987, | |
| "learning_rate": 0.0002, | |
| "loss": 10.4028, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 3.1771919977124216e-05, | |
| "grad_norm": 0.13942524790763855, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 10.4085, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 4.236255996949896e-05, | |
| "grad_norm": 0.19832777976989746, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 10.3694, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 5.29531999618737e-05, | |
| "grad_norm": 0.154804065823555, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 10.3817, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 6.354383995424843e-05, | |
| "grad_norm": 0.1635114997625351, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 10.3978, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 7.413447994662318e-05, | |
| "grad_norm": 0.1821622997522354, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 10.3664, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 8.472511993899791e-05, | |
| "grad_norm": 0.17012329399585724, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 10.4036, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 9.531575993137265e-05, | |
| "grad_norm": 0.20254936814308167, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 10.3974, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0001059063999237474, | |
| "grad_norm": 0.17694656550884247, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 10.3638, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00011649703991612213, | |
| "grad_norm": 0.16968543827533722, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 10.3723, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00012708767990849687, | |
| "grad_norm": 0.1666555404663086, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 10.3831, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0001376783199008716, | |
| "grad_norm": 0.191905677318573, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 10.3708, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00014826895989324636, | |
| "grad_norm": 0.19630686938762665, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 10.37, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0001588595998856211, | |
| "grad_norm": 0.2109733670949936, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 10.3807, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00016945023987799583, | |
| "grad_norm": 0.21452225744724274, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 10.3773, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00018004087987037056, | |
| "grad_norm": 0.22486615180969238, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 10.3543, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0001906315198627453, | |
| "grad_norm": 0.21467246115207672, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 10.3444, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00020122215985512003, | |
| "grad_norm": 0.18565407395362854, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 10.418, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0002118127998474948, | |
| "grad_norm": 0.21927490830421448, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 10.406, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00022240343983986953, | |
| "grad_norm": 0.23267850279808044, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 10.3427, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00023299407983224426, | |
| "grad_norm": 0.23452691733837128, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 10.371, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.000243584719824619, | |
| "grad_norm": 0.22493915259838104, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 10.368, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.00025417535981699373, | |
| "grad_norm": 0.2101021260023117, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 10.359, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00026476599980936846, | |
| "grad_norm": 0.2529934048652649, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 10.3683, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00026476599980936846, | |
| "eval_loss": 10.378252029418945, | |
| "eval_runtime": 256.2454, | |
| "eval_samples_per_second": 155.156, | |
| "eval_steps_per_second": 77.578, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0002753566398017432, | |
| "grad_norm": 0.24394074082374573, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3524, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.00028594727979411793, | |
| "grad_norm": 0.21432097256183624, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 10.3553, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0002965379197864927, | |
| "grad_norm": 0.22124646604061127, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 10.3506, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.00030712855977886746, | |
| "grad_norm": 0.21801720559597015, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 10.3924, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0003177191997712422, | |
| "grad_norm": 0.22025315463542938, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 10.3803, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0003283098397636169, | |
| "grad_norm": 0.2573018968105316, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 10.3521, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.00033890047975599166, | |
| "grad_norm": 0.23922796547412872, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 10.3644, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0003494911197483664, | |
| "grad_norm": 0.23983879387378693, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 10.3523, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.00036008175974074113, | |
| "grad_norm": 0.2627752125263214, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 10.3997, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.00037067239973311586, | |
| "grad_norm": 0.26665353775024414, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 10.3918, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0003812630397254906, | |
| "grad_norm": 0.2439327985048294, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 10.3513, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.00039185367971786533, | |
| "grad_norm": 0.2464238703250885, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 10.366, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.00040244431971024006, | |
| "grad_norm": 0.2734537422657013, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 10.3739, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.00041303495970261485, | |
| "grad_norm": 0.27960556745529175, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 10.398, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0004236255996949896, | |
| "grad_norm": 0.25336456298828125, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 10.3466, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0004342162396873643, | |
| "grad_norm": 0.2658770978450775, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 10.3344, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.00044480687967973906, | |
| "grad_norm": 0.28324833512306213, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 10.3558, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0004553975196721138, | |
| "grad_norm": 0.2617306411266327, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 10.3627, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0004659881596644885, | |
| "grad_norm": 0.28455761075019836, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 10.3325, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.00047657879965686326, | |
| "grad_norm": 0.2544795572757721, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 10.3822, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.000487169439649238, | |
| "grad_norm": 0.2631848454475403, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 10.375, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0004977600796416127, | |
| "grad_norm": 0.2916587293148041, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 10.3545, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0005083507196339875, | |
| "grad_norm": 0.3416881263256073, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 10.3671, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0005189413596263622, | |
| "grad_norm": 0.2896738052368164, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 10.3615, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0005295319996187369, | |
| "grad_norm": 0.3720775246620178, | |
| "learning_rate": 0.0, | |
| "loss": 10.3921, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0005295319996187369, | |
| "eval_loss": 10.368429183959961, | |
| "eval_runtime": 256.1367, | |
| "eval_samples_per_second": 155.222, | |
| "eval_steps_per_second": 77.611, | |
| "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": 5230244659200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |