| { | |
| "best_metric": 3.52176570892334, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.2886002886002886, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005772005772005772, | |
| "grad_norm": 9.749709129333496, | |
| "learning_rate": 0.0001, | |
| "loss": 3.7589, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005772005772005772, | |
| "eval_loss": 10.803024291992188, | |
| "eval_runtime": 29.4154, | |
| "eval_samples_per_second": 2.482, | |
| "eval_steps_per_second": 1.258, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011544011544011544, | |
| "grad_norm": 7.1808881759643555, | |
| "learning_rate": 0.0002, | |
| "loss": 5.5834, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.017316017316017316, | |
| "grad_norm": 7.575276851654053, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 5.2038, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.023088023088023088, | |
| "grad_norm": 5.419090747833252, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 5.0399, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02886002886002886, | |
| "grad_norm": 8.910318374633789, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 3.9669, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03463203463203463, | |
| "grad_norm": 45.46010971069336, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 4.2862, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04040404040404041, | |
| "grad_norm": 43.968482971191406, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 4.4392, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.046176046176046176, | |
| "grad_norm": 9.73154354095459, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 3.3899, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05194805194805195, | |
| "grad_norm": 5.469523906707764, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 3.064, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05772005772005772, | |
| "grad_norm": 6.917726516723633, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 3.4218, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06349206349206349, | |
| "grad_norm": 5.250333309173584, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 2.7711, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.06926406926406926, | |
| "grad_norm": 5.692388534545898, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 2.8573, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.07503607503607504, | |
| "grad_norm": 5.600759983062744, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 3.238, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.08080808080808081, | |
| "grad_norm": 8.384806632995605, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.9453, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.08658008658008658, | |
| "grad_norm": 5.953359127044678, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 2.8733, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09235209235209235, | |
| "grad_norm": 5.461154937744141, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 2.4783, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.09812409812409813, | |
| "grad_norm": 5.699024677276611, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 2.7727, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1038961038961039, | |
| "grad_norm": 5.159974098205566, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 2.9109, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.10966810966810966, | |
| "grad_norm": 4.561604022979736, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 3.1012, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.11544011544011544, | |
| "grad_norm": 5.195240497589111, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 2.935, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.12121212121212122, | |
| "grad_norm": 4.813465595245361, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 3.4641, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.12698412698412698, | |
| "grad_norm": 5.874507904052734, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 3.3369, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.13275613275613277, | |
| "grad_norm": 4.917274475097656, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 3.3583, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.13852813852813853, | |
| "grad_norm": 3.70969820022583, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 2.5707, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1443001443001443, | |
| "grad_norm": 6.91110372543335, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 3.474, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1443001443001443, | |
| "eval_loss": 3.883234739303589, | |
| "eval_runtime": 29.8984, | |
| "eval_samples_per_second": 2.442, | |
| "eval_steps_per_second": 1.238, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.15007215007215008, | |
| "grad_norm": 5.483874320983887, | |
| "learning_rate": 0.0001, | |
| "loss": 2.8525, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.15584415584415584, | |
| "grad_norm": 4.851412296295166, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 3.1477, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.16161616161616163, | |
| "grad_norm": 5.818398952484131, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 3.1177, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.1673881673881674, | |
| "grad_norm": 6.832301139831543, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 3.5393, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.17316017316017315, | |
| "grad_norm": 5.470390319824219, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 3.6273, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.17893217893217894, | |
| "grad_norm": 7.099745750427246, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 2.8683, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.1847041847041847, | |
| "grad_norm": 6.852536678314209, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 4.697, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.19047619047619047, | |
| "grad_norm": 7.737475395202637, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 5.2704, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.19624819624819625, | |
| "grad_norm": 8.485671997070312, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 4.3796, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.20202020202020202, | |
| "grad_norm": 5.709878444671631, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 3.9743, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2077922077922078, | |
| "grad_norm": 5.483663082122803, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 3.9421, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.21356421356421357, | |
| "grad_norm": 4.827873706817627, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 4.0746, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.21933621933621933, | |
| "grad_norm": 15.908256530761719, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 7.8459, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.22510822510822512, | |
| "grad_norm": 17.669963836669922, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 7.6677, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.23088023088023088, | |
| "grad_norm": 15.907238006591797, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 6.4001, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.23665223665223664, | |
| "grad_norm": 11.9762601852417, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 7.4365, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.24242424242424243, | |
| "grad_norm": 8.19090461730957, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 6.703, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2481962481962482, | |
| "grad_norm": 8.14680290222168, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 7.3564, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.25396825396825395, | |
| "grad_norm": 7.9732561111450195, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 2.4814, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.2597402597402597, | |
| "grad_norm": 8.285723686218262, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 3.1881, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.26551226551226553, | |
| "grad_norm": 10.690110206604004, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 3.5401, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.2712842712842713, | |
| "grad_norm": 9.28165340423584, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 3.6229, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.27705627705627706, | |
| "grad_norm": 12.119881629943848, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 3.1769, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.2828282828282828, | |
| "grad_norm": 8.861678123474121, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 3.5118, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.2886002886002886, | |
| "grad_norm": 9.257101058959961, | |
| "learning_rate": 0.0, | |
| "loss": 3.6435, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2886002886002886, | |
| "eval_loss": 3.52176570892334, | |
| "eval_runtime": 29.8722, | |
| "eval_samples_per_second": 2.444, | |
| "eval_steps_per_second": 1.239, | |
| "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": 8.23612542025728e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |