| { | |
| "best_metric": 7.57550573348999, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.0035377567084711584, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.075513416942317e-05, | |
| "grad_norm": 9.65824031829834, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3012, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.075513416942317e-05, | |
| "eval_loss": 10.297235488891602, | |
| "eval_runtime": 423.7325, | |
| "eval_samples_per_second": 14.044, | |
| "eval_steps_per_second": 7.023, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00014151026833884633, | |
| "grad_norm": 9.520867347717285, | |
| "learning_rate": 0.0002, | |
| "loss": 10.287, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0002122654025082695, | |
| "grad_norm": 8.275415420532227, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 10.6672, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00028302053667769267, | |
| "grad_norm": 11.168041229248047, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 9.8086, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00035377567084711583, | |
| "grad_norm": 10.555876731872559, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 9.4474, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000424530805016539, | |
| "grad_norm": 11.976527214050293, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 8.9594, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0004952859391859622, | |
| "grad_norm": 5.582800388336182, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 10.122, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0005660410733553853, | |
| "grad_norm": 5.889162540435791, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 9.4986, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006367962075248086, | |
| "grad_norm": 5.002773761749268, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 9.6254, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007075513416942317, | |
| "grad_norm": 4.665764808654785, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 8.7045, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007783064758636549, | |
| "grad_norm": 4.601282596588135, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 8.3168, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.000849061610033078, | |
| "grad_norm": 3.299240827560425, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 9.2247, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0009198167442025012, | |
| "grad_norm": 3.7354960441589355, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 7.678, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0009905718783719244, | |
| "grad_norm": 3.463956356048584, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 8.3151, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0010613270125413474, | |
| "grad_norm": 3.156778335571289, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 8.0749, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0011320821467107707, | |
| "grad_norm": 3.7005889415740967, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 7.6126, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0012028372808801939, | |
| "grad_norm": 2.4874415397644043, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 8.5406, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0012735924150496171, | |
| "grad_norm": 2.7680022716522217, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 8.4314, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0013443475492190401, | |
| "grad_norm": 2.0353095531463623, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 9.1595, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0014151026833884633, | |
| "grad_norm": 2.0955147743225098, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 7.6555, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0014858578175578866, | |
| "grad_norm": 2.1922082901000977, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 8.0252, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0015566129517273098, | |
| "grad_norm": 1.7157036066055298, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 6.0305, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0016273680858967328, | |
| "grad_norm": 2.6440823078155518, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 7.3275, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.001698123220066156, | |
| "grad_norm": 2.6981420516967773, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 8.2126, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0017688783542355792, | |
| "grad_norm": 1.8539084196090698, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 8.1024, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0017688783542355792, | |
| "eval_loss": 7.744256496429443, | |
| "eval_runtime": 424.6768, | |
| "eval_samples_per_second": 14.013, | |
| "eval_steps_per_second": 7.008, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0018396334884050024, | |
| "grad_norm": 2.224562883377075, | |
| "learning_rate": 0.0001, | |
| "loss": 7.914, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0019103886225744254, | |
| "grad_norm": 2.1913933753967285, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 6.8205, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.001981143756743849, | |
| "grad_norm": 1.6599905490875244, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 6.0068, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.002051898890913272, | |
| "grad_norm": 2.024454355239868, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 7.8554, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.002122654025082695, | |
| "grad_norm": 1.8849565982818604, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 8.0236, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0021934091592521183, | |
| "grad_norm": 1.9001713991165161, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 7.5121, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0022641642934215413, | |
| "grad_norm": 2.581791400909424, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 8.3276, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0023349194275909648, | |
| "grad_norm": 2.283374786376953, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 8.345, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0024056745617603878, | |
| "grad_norm": 2.3892664909362793, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 7.9309, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.002476429695929811, | |
| "grad_norm": 2.3808767795562744, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 8.4167, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0025471848300992342, | |
| "grad_norm": 2.1643102169036865, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 8.6231, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0026179399642686572, | |
| "grad_norm": 1.6862167119979858, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 7.3128, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0026886950984380802, | |
| "grad_norm": 2.0384624004364014, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 7.4071, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0027594502326075037, | |
| "grad_norm": 2.535562038421631, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 8.768, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0028302053667769267, | |
| "grad_norm": 1.6740695238113403, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 7.8373, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.00290096050094635, | |
| "grad_norm": 2.7595770359039307, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 6.3171, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.002971715635115773, | |
| "grad_norm": 1.7339050769805908, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 8.0472, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.003042470769285196, | |
| "grad_norm": 2.4932544231414795, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 7.427, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0031132259034546196, | |
| "grad_norm": 1.7774704694747925, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 6.9968, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0031839810376240426, | |
| "grad_norm": 2.011033296585083, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 6.9706, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0032547361717934656, | |
| "grad_norm": 1.9285480976104736, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 7.329, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.003325491305962889, | |
| "grad_norm": 1.7312147617340088, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 7.7708, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.003396246440132312, | |
| "grad_norm": 1.7855710983276367, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 7.7837, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0034670015743017354, | |
| "grad_norm": 2.7064085006713867, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 8.5279, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0035377567084711584, | |
| "grad_norm": 2.4912497997283936, | |
| "learning_rate": 0.0, | |
| "loss": 8.6104, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0035377567084711584, | |
| "eval_loss": 7.57550573348999, | |
| "eval_runtime": 425.6988, | |
| "eval_samples_per_second": 13.979, | |
| "eval_steps_per_second": 6.991, | |
| "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": 27149520076800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |