| { | |
| "best_metric": 0.8060246706008911, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.034897923573547374, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006979584714709475, | |
| "grad_norm": 72.42657470703125, | |
| "learning_rate": 0.0001, | |
| "loss": 11.898, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006979584714709475, | |
| "eval_loss": 9.104303359985352, | |
| "eval_runtime": 45.1392, | |
| "eval_samples_per_second": 13.381, | |
| "eval_steps_per_second": 6.69, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001395916942941895, | |
| "grad_norm": 70.2101821899414, | |
| "learning_rate": 0.0002, | |
| "loss": 9.8734, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0020938754144128424, | |
| "grad_norm": 43.087833404541016, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 8.1341, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00279183388588379, | |
| "grad_norm": 57.438655853271484, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 6.4755, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003489792357354737, | |
| "grad_norm": 22.67092514038086, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 5.2584, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004187750828825685, | |
| "grad_norm": 26.57111358642578, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 3.7605, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004885709300296632, | |
| "grad_norm": 20.17916488647461, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 2.6688, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00558366777176758, | |
| "grad_norm": 15.502541542053223, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 1.1657, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.006281626243238528, | |
| "grad_norm": 10.5908784866333, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 0.8885, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006979584714709474, | |
| "grad_norm": 20.844127655029297, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 1.8588, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007677543186180422, | |
| "grad_norm": 13.938933372497559, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 1.2396, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00837550165765137, | |
| "grad_norm": 10.462559700012207, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 1.8381, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.009073460129122317, | |
| "grad_norm": 9.832139015197754, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 1.2033, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.009771418600593265, | |
| "grad_norm": 17.391014099121094, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.7832, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.010469377072064212, | |
| "grad_norm": 9.854270935058594, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 1.3104, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01116733554353516, | |
| "grad_norm": 10.468400955200195, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 1.4715, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.011865294015006108, | |
| "grad_norm": 7.751452445983887, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 1.1026, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.012563252486477055, | |
| "grad_norm": 11.4496431350708, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.2344, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.013261210957948003, | |
| "grad_norm": 10.769119262695312, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 1.5078, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.013959169429418949, | |
| "grad_norm": 7.264293193817139, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 1.0419, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.014657127900889896, | |
| "grad_norm": 7.968069553375244, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 0.9254, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.015355086372360844, | |
| "grad_norm": 10.285526275634766, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 1.1889, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01605304484383179, | |
| "grad_norm": 10.647075653076172, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 1.1386, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.01675100331530274, | |
| "grad_norm": 10.445228576660156, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 0.6282, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.017448961786773687, | |
| "grad_norm": 10.61379623413086, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 1.0902, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.017448961786773687, | |
| "eval_loss": 0.9804576635360718, | |
| "eval_runtime": 45.495, | |
| "eval_samples_per_second": 13.276, | |
| "eval_steps_per_second": 6.638, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.018146920258244634, | |
| "grad_norm": 9.390534400939941, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9165, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.018844878729715582, | |
| "grad_norm": 9.242115020751953, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 0.7231, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.01954283720118653, | |
| "grad_norm": 9.97008991241455, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 0.89, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.020240795672657477, | |
| "grad_norm": 7.491469860076904, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 0.842, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.020938754144128425, | |
| "grad_norm": 11.089756965637207, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 1.1112, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.021636712615599372, | |
| "grad_norm": 11.30197811126709, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 0.5563, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.02233467108707032, | |
| "grad_norm": 5.173059463500977, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 0.6147, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.023032629558541268, | |
| "grad_norm": 7.637121200561523, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 0.7262, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.023730588030012215, | |
| "grad_norm": 7.962845802307129, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.7012, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.024428546501483163, | |
| "grad_norm": 9.41506290435791, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 0.7252, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02512650497295411, | |
| "grad_norm": 9.710718154907227, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 0.8126, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.025824463444425058, | |
| "grad_norm": 7.245460033416748, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 0.6849, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.026522421915896006, | |
| "grad_norm": 8.509491920471191, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.6192, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.027220380387366953, | |
| "grad_norm": 6.999649524688721, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 0.5379, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.027918338858837898, | |
| "grad_norm": 4.450455665588379, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 0.5619, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.028616297330308845, | |
| "grad_norm": 7.4137396812438965, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 0.7306, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.029314255801779793, | |
| "grad_norm": 4.460165023803711, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 0.3986, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03001221427325074, | |
| "grad_norm": 5.552957057952881, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 0.8173, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.030710172744721688, | |
| "grad_norm": 4.119052886962891, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 0.7262, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.03140813121619264, | |
| "grad_norm": 6.945855617523193, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 0.5857, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03210608968766358, | |
| "grad_norm": 7.324554443359375, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 0.7503, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.032804048159134534, | |
| "grad_norm": 11.844222068786621, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 0.6069, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.03350200663060548, | |
| "grad_norm": 3.3703107833862305, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 0.5407, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.03419996510207643, | |
| "grad_norm": 10.259138107299805, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 0.9289, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.034897923573547374, | |
| "grad_norm": 11.083820343017578, | |
| "learning_rate": 0.0, | |
| "loss": 0.9481, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.034897923573547374, | |
| "eval_loss": 0.8060246706008911, | |
| "eval_runtime": 44.9024, | |
| "eval_samples_per_second": 13.451, | |
| "eval_steps_per_second": 6.726, | |
| "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": 3106157258342400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |