| { | |
| "best_metric": 3.1881558895111084, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.12113870381586916, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0024227740763173833, | |
| "grad_norm": 6.354554653167725, | |
| "learning_rate": 0.0001, | |
| "loss": 5.003, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0024227740763173833, | |
| "eval_loss": 4.445741176605225, | |
| "eval_runtime": 48.9332, | |
| "eval_samples_per_second": 3.556, | |
| "eval_steps_per_second": 1.778, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004845548152634767, | |
| "grad_norm": 7.047632217407227, | |
| "learning_rate": 0.0002, | |
| "loss": 5.4559, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0072683222289521504, | |
| "grad_norm": 7.0595598220825195, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 4.8398, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009691096305269533, | |
| "grad_norm": 9.777852058410645, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 4.7029, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.012113870381586917, | |
| "grad_norm": 3.7091481685638428, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 3.8521, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.014536644457904301, | |
| "grad_norm": 3.647103786468506, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 4.2682, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.016959418534221685, | |
| "grad_norm": 4.299393653869629, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 3.9939, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.019382192610539067, | |
| "grad_norm": 3.0232176780700684, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 3.8496, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.021804966686856452, | |
| "grad_norm": 3.2615227699279785, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 3.6195, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.024227740763173834, | |
| "grad_norm": 2.2656781673431396, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 3.746, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.026650514839491216, | |
| "grad_norm": 3.4833717346191406, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 3.1256, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.029073288915808602, | |
| "grad_norm": 5.78814172744751, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 2.9103, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.031496062992125984, | |
| "grad_norm": 3.293673038482666, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 3.0973, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03391883706844337, | |
| "grad_norm": 4.502946376800537, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 3.2474, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03634161114476075, | |
| "grad_norm": 2.1124539375305176, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 2.8826, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03876438522107813, | |
| "grad_norm": 3.9200596809387207, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 3.1527, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04118715929739552, | |
| "grad_norm": 1.7969374656677246, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 2.9535, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.043609933373712904, | |
| "grad_norm": 3.1285815238952637, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 3.2713, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04603270745003028, | |
| "grad_norm": 8.577775955200195, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 3.3961, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04845548152634767, | |
| "grad_norm": 2.5606937408447266, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 3.1592, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.050878255602665054, | |
| "grad_norm": 3.973900318145752, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 2.9197, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05330102967898243, | |
| "grad_norm": 1.974953532218933, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 3.3658, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05572380375529982, | |
| "grad_norm": 3.7481021881103516, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 2.8164, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.058146577831617204, | |
| "grad_norm": 1.198407769203186, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 3.1784, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06056935190793458, | |
| "grad_norm": 2.7096714973449707, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 2.9163, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06056935190793458, | |
| "eval_loss": 3.2418150901794434, | |
| "eval_runtime": 49.5368, | |
| "eval_samples_per_second": 3.513, | |
| "eval_steps_per_second": 1.756, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06299212598425197, | |
| "grad_norm": 1.1748727560043335, | |
| "learning_rate": 0.0001, | |
| "loss": 3.0056, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06541490006056935, | |
| "grad_norm": 3.2900516986846924, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 3.601, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06783767413688674, | |
| "grad_norm": 2.351978063583374, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 2.9973, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07026044821320412, | |
| "grad_norm": 5.829685211181641, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 3.0943, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0726832222895215, | |
| "grad_norm": 6.204741954803467, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 3.156, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07510599636583888, | |
| "grad_norm": 2.1339845657348633, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 3.2766, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.07752877044215627, | |
| "grad_norm": 1.808945655822754, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 2.9227, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.07995154451847365, | |
| "grad_norm": 2.8036043643951416, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 3.0523, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08237431859479104, | |
| "grad_norm": 1.0157161951065063, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 2.8263, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08479709267110842, | |
| "grad_norm": 1.2105307579040527, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 2.7368, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08721986674742581, | |
| "grad_norm": 5.625417709350586, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 3.132, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.08964264082374318, | |
| "grad_norm": 2.4896271228790283, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 2.8508, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.09206541490006057, | |
| "grad_norm": 3.5829272270202637, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 3.223, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.09448818897637795, | |
| "grad_norm": 2.3777010440826416, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 2.8025, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.09691096305269534, | |
| "grad_norm": 2.8074324131011963, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 3.0763, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09933373712901272, | |
| "grad_norm": 2.213160753250122, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 2.7823, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.10175651120533011, | |
| "grad_norm": 3.2287349700927734, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 3.2519, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.10417928528164748, | |
| "grad_norm": 2.1493735313415527, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 2.7395, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.10660205935796487, | |
| "grad_norm": 4.258261680603027, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 2.8477, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.10902483343428225, | |
| "grad_norm": 10.491841316223145, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 3.1237, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11144760751059964, | |
| "grad_norm": 3.0685977935791016, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 2.8701, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.11387038158691702, | |
| "grad_norm": 1.838558316230774, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 2.8348, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.11629315566323441, | |
| "grad_norm": 1.4132007360458374, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 2.6871, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.11871592973955179, | |
| "grad_norm": 1.1663188934326172, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 2.6572, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.12113870381586916, | |
| "grad_norm": 1.921555757522583, | |
| "learning_rate": 0.0, | |
| "loss": 3.009, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12113870381586916, | |
| "eval_loss": 3.1881558895111084, | |
| "eval_runtime": 49.5621, | |
| "eval_samples_per_second": 3.511, | |
| "eval_steps_per_second": 1.755, | |
| "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": 7.41887283560448e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |