| { | |
| "best_metric": 6.920986652374268, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.005646367973800853, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00011292735947601705, | |
| "grad_norm": 0.08981648087501526, | |
| "learning_rate": 0.0001, | |
| "loss": 6.9445, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00011292735947601705, | |
| "eval_loss": 6.9417877197265625, | |
| "eval_runtime": 12.2407, | |
| "eval_samples_per_second": 304.64, | |
| "eval_steps_per_second": 152.361, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002258547189520341, | |
| "grad_norm": 0.14448419213294983, | |
| "learning_rate": 0.0002, | |
| "loss": 6.9432, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00033878207842805115, | |
| "grad_norm": 0.16842809319496155, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 6.9434, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0004517094379040682, | |
| "grad_norm": 0.1534644514322281, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 6.9337, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0005646367973800852, | |
| "grad_norm": 0.18855637311935425, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 6.9489, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0006775641568561023, | |
| "grad_norm": 0.17140968143939972, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 6.9437, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0007904915163321194, | |
| "grad_norm": 0.16273392736911774, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 6.9393, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0009034188758081364, | |
| "grad_norm": 0.18541516363620758, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 6.9405, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0010163462352841535, | |
| "grad_norm": 0.18484199047088623, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 6.9313, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0011292735947601704, | |
| "grad_norm": 0.1925928145647049, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 6.942, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0012422009542361876, | |
| "grad_norm": 0.1826387643814087, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 6.9422, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0013551283137122046, | |
| "grad_norm": 0.17331881821155548, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 6.9411, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0014680556731882218, | |
| "grad_norm": 0.20087401568889618, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 6.9375, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0015809830326642387, | |
| "grad_norm": 0.21413768827915192, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 6.9341, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0016939103921402557, | |
| "grad_norm": 0.18745364248752594, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 6.9353, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0018068377516162728, | |
| "grad_norm": 0.20169200003147125, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 6.9385, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0019197651110922898, | |
| "grad_norm": 0.1928519606590271, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 6.9307, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.002032692470568307, | |
| "grad_norm": 0.2301088273525238, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 6.9311, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.002145619830044324, | |
| "grad_norm": 0.21517930924892426, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 6.9399, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.002258547189520341, | |
| "grad_norm": 0.2270190268754959, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 6.9423, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002371474548996358, | |
| "grad_norm": 0.22742193937301636, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 6.9354, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0024844019084723752, | |
| "grad_norm": 0.20766763389110565, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 6.9354, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.002597329267948392, | |
| "grad_norm": 0.1951204091310501, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 6.9381, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.002710256627424409, | |
| "grad_norm": 0.1879407912492752, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 6.9285, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0028231839869004263, | |
| "grad_norm": 0.2378544956445694, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 6.9262, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0028231839869004263, | |
| "eval_loss": 6.926918983459473, | |
| "eval_runtime": 11.8505, | |
| "eval_samples_per_second": 314.671, | |
| "eval_steps_per_second": 157.378, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0029361113463764435, | |
| "grad_norm": 0.20033280551433563, | |
| "learning_rate": 0.0001, | |
| "loss": 6.9243, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0030490387058524603, | |
| "grad_norm": 0.2356751710176468, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 6.9204, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0031619660653284774, | |
| "grad_norm": 0.2633371949195862, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 6.9216, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0032748934248044946, | |
| "grad_norm": 0.2085108906030655, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 6.9298, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0033878207842805113, | |
| "grad_norm": 0.2274623066186905, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 6.9212, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0035007481437565285, | |
| "grad_norm": 0.22422252595424652, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 6.9258, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0036136755032325457, | |
| "grad_norm": 0.22745665907859802, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 6.9075, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.003726602862708563, | |
| "grad_norm": 0.24554090201854706, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 6.9261, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0038395302221845796, | |
| "grad_norm": 0.21141235530376434, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 6.9256, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.003952457581660597, | |
| "grad_norm": 0.22744667530059814, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 6.9244, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.004065384941136614, | |
| "grad_norm": 0.22644877433776855, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 6.9293, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.004178312300612631, | |
| "grad_norm": 0.2632388472557068, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 6.9136, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.004291239660088648, | |
| "grad_norm": 0.23912282288074493, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 6.92, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.004404167019564665, | |
| "grad_norm": 0.2523389756679535, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 6.9173, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.004517094379040682, | |
| "grad_norm": 0.24466051161289215, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 6.9196, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.004630021738516699, | |
| "grad_norm": 0.24103286862373352, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 6.9223, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.004742949097992716, | |
| "grad_norm": 0.25864821672439575, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 6.914, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.004855876457468733, | |
| "grad_norm": 0.2653087079524994, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 6.922, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0049688038169447505, | |
| "grad_norm": 0.2347327023744583, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 6.9263, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.005081731176420768, | |
| "grad_norm": 0.24755509197711945, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 6.9262, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.005194658535896784, | |
| "grad_norm": 0.23600712418556213, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 6.9333, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.005307585895372801, | |
| "grad_norm": 0.23946261405944824, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 6.9247, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.005420513254848818, | |
| "grad_norm": 0.24361290037631989, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 6.9205, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0055334406143248355, | |
| "grad_norm": 0.26696720719337463, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 6.9275, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.005646367973800853, | |
| "grad_norm": 0.27215808629989624, | |
| "learning_rate": 0.0, | |
| "loss": 6.9104, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.005646367973800853, | |
| "eval_loss": 6.920986652374268, | |
| "eval_runtime": 11.8994, | |
| "eval_samples_per_second": 313.378, | |
| "eval_steps_per_second": 156.731, | |
| "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": 592249503744.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |