| { | |
| "best_metric": 1.1243497133255005, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.013343118286743613, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002668623657348722, | |
| "grad_norm": 3.227802276611328, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6172, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002668623657348722, | |
| "eval_loss": 1.9063847064971924, | |
| "eval_runtime": 321.7231, | |
| "eval_samples_per_second": 4.905, | |
| "eval_steps_per_second": 2.452, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005337247314697444, | |
| "grad_norm": 2.450011968612671, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3715, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008005870972046167, | |
| "grad_norm": 0.9362994432449341, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 1.2027, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0010674494629394889, | |
| "grad_norm": 1.2160959243774414, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 0.9595, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0013343118286743613, | |
| "grad_norm": 1.4689968824386597, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 0.7926, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0016011741944092334, | |
| "grad_norm": 2.0516695976257324, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 0.9129, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0018680365601441056, | |
| "grad_norm": 0.6819640398025513, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 0.8064, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0021348989258789777, | |
| "grad_norm": 0.9235527515411377, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.7465, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0024017612916138503, | |
| "grad_norm": 0.756666898727417, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 0.7217, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0026686236573487225, | |
| "grad_norm": 0.7653118968009949, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 1.0959, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0029354860230835947, | |
| "grad_norm": 0.854770302772522, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 0.5922, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.003202348388818467, | |
| "grad_norm": 0.7380660176277161, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 0.7272, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.003469210754553339, | |
| "grad_norm": 0.6519638895988464, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 0.6851, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.003736073120288211, | |
| "grad_norm": 0.6560354232788086, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.7284, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.004002935486023084, | |
| "grad_norm": 0.5490040183067322, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 0.7328, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0042697978517579555, | |
| "grad_norm": 0.7207716703414917, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 0.5902, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004536660217492828, | |
| "grad_norm": 0.7940784096717834, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 0.7201, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.004803522583227701, | |
| "grad_norm": 0.7808439135551453, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.6098, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.005070384948962572, | |
| "grad_norm": 0.9322609901428223, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 1.0192, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.005337247314697445, | |
| "grad_norm": 0.6111686825752258, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 1.0272, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005604109680432317, | |
| "grad_norm": 0.7473171949386597, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 1.0828, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.005870972046167189, | |
| "grad_norm": 0.6169211268424988, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 0.9449, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.006137834411902062, | |
| "grad_norm": 0.5477904677391052, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 0.8641, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.006404696777636934, | |
| "grad_norm": 0.6941477060317993, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 1.1681, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.006671559143371806, | |
| "grad_norm": 0.649423360824585, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 1.3437, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006671559143371806, | |
| "eval_loss": 1.1469987630844116, | |
| "eval_runtime": 325.4881, | |
| "eval_samples_per_second": 4.848, | |
| "eval_steps_per_second": 2.424, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006938421509106678, | |
| "grad_norm": 0.6408900022506714, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3754, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.007205283874841551, | |
| "grad_norm": 0.9624432921409607, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 1.3455, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.007472146240576422, | |
| "grad_norm": 0.6052916646003723, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 1.3871, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.007739008606311295, | |
| "grad_norm": 0.5944576859474182, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 1.1906, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.008005870972046168, | |
| "grad_norm": 0.66631680727005, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 1.3954, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00827273333778104, | |
| "grad_norm": 0.6512559056282043, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 1.5238, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.008539595703515911, | |
| "grad_norm": 0.6266358494758606, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 1.2382, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.008806458069250784, | |
| "grad_norm": 0.6132543087005615, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 1.053, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.009073320434985656, | |
| "grad_norm": 0.6559033989906311, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.5881, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.009340182800720529, | |
| "grad_norm": 0.6847499012947083, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 1.5597, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.009607045166455401, | |
| "grad_norm": 0.6695072650909424, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 1.464, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.009873907532190272, | |
| "grad_norm": 0.6664255261421204, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 1.4036, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.010140769897925145, | |
| "grad_norm": 0.7430691719055176, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 1.0536, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.010407632263660017, | |
| "grad_norm": 0.7103254795074463, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 1.5054, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.01067449462939489, | |
| "grad_norm": 0.6650035381317139, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 1.6155, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.010941356995129763, | |
| "grad_norm": 0.702969491481781, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 1.3914, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.011208219360864633, | |
| "grad_norm": 0.8632053732872009, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 1.4575, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.011475081726599506, | |
| "grad_norm": 0.757703959941864, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 1.3532, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.011741944092334379, | |
| "grad_norm": 0.7126505970954895, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 1.3034, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.012008806458069251, | |
| "grad_norm": 0.8105053901672363, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 1.6154, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.012275668823804124, | |
| "grad_norm": 0.7980390787124634, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 1.1972, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.012542531189538995, | |
| "grad_norm": 0.8466772437095642, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 1.8855, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.012809393555273867, | |
| "grad_norm": 1.5893186330795288, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 1.6354, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.01307625592100874, | |
| "grad_norm": 1.0377373695373535, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 1.8772, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.013343118286743613, | |
| "grad_norm": 1.9227272272109985, | |
| "learning_rate": 0.0, | |
| "loss": 1.7072, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.013343118286743613, | |
| "eval_loss": 1.1243497133255005, | |
| "eval_runtime": 325.4715, | |
| "eval_samples_per_second": 4.848, | |
| "eval_steps_per_second": 2.424, | |
| "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": 2.75713949171712e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |