| { | |
| "best_metric": 1.0649921894073486, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.00316641071513386, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.33282143026772e-05, | |
| "grad_norm": 0.22801154851913452, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6629, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.33282143026772e-05, | |
| "eval_loss": 1.2817469835281372, | |
| "eval_runtime": 2330.0946, | |
| "eval_samples_per_second": 2.854, | |
| "eval_steps_per_second": 1.427, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001266564286053544, | |
| "grad_norm": 0.27894729375839233, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9445, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0001899846429080316, | |
| "grad_norm": 0.2692895233631134, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 1.0168, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0002533128572107088, | |
| "grad_norm": 0.2308046519756317, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 0.8271, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.000316641071513386, | |
| "grad_norm": 0.32857978343963623, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 1.1018, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0003799692858160632, | |
| "grad_norm": 0.33558890223503113, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 0.9597, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0004432975001187404, | |
| "grad_norm": 0.27557405829429626, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 0.9525, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0005066257144214176, | |
| "grad_norm": 0.23575201630592346, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.728, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0005699539287240948, | |
| "grad_norm": 0.2544404864311218, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 0.8319, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.000633282143026772, | |
| "grad_norm": 0.29963210225105286, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 0.6908, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0006966103573294492, | |
| "grad_norm": 0.2677765190601349, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 0.7926, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0007599385716321264, | |
| "grad_norm": 0.2788805365562439, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 0.8986, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0008232667859348036, | |
| "grad_norm": 0.2404116690158844, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 0.7741, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0008865950002374808, | |
| "grad_norm": 0.25370389223098755, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.9337, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.000949923214540158, | |
| "grad_norm": 0.26054996252059937, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 0.7543, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0010132514288428351, | |
| "grad_norm": 0.2900119423866272, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 0.9928, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0010765796431455124, | |
| "grad_norm": 0.2647811770439148, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 0.7458, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0011399078574481896, | |
| "grad_norm": 0.29207536578178406, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.1024, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0012032360717508669, | |
| "grad_norm": 0.29020875692367554, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 0.9495, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.001266564286053544, | |
| "grad_norm": 0.3056279122829437, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 1.0244, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0013298925003562211, | |
| "grad_norm": 0.3202858865261078, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 0.9608, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0013932207146588984, | |
| "grad_norm": 0.3170551061630249, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 0.9308, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0014565489289615756, | |
| "grad_norm": 0.3450915813446045, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 1.069, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0015198771432642529, | |
| "grad_norm": 0.32592377066612244, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 0.8749, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00158320535756693, | |
| "grad_norm": 0.37389305233955383, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 1.0783, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00158320535756693, | |
| "eval_loss": 1.0828484296798706, | |
| "eval_runtime": 2341.6611, | |
| "eval_samples_per_second": 2.839, | |
| "eval_steps_per_second": 1.42, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0016465335718696072, | |
| "grad_norm": 0.3657870292663574, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1249, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0017098617861722844, | |
| "grad_norm": 0.3361119031906128, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 0.9925, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0017731900004749617, | |
| "grad_norm": 0.3795837163925171, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 1.1111, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.001836518214777639, | |
| "grad_norm": 0.3373138904571533, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 0.9586, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.001899846429080316, | |
| "grad_norm": 0.38437795639038086, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 1.0469, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0019631746433829934, | |
| "grad_norm": 0.40333160758018494, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 1.473, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0020265028576856702, | |
| "grad_norm": 0.41050985455513, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 1.1563, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0020898310719883475, | |
| "grad_norm": 0.39206528663635254, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 0.922, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0021531592862910247, | |
| "grad_norm": 0.38651344180107117, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.152, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.002216487500593702, | |
| "grad_norm": 0.40726855397224426, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 0.9465, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.002279815714896379, | |
| "grad_norm": 0.40235212445259094, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 0.9281, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0023431439291990565, | |
| "grad_norm": 0.4145893454551697, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 0.998, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0024064721435017337, | |
| "grad_norm": 0.4135442078113556, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 1.0985, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.002469800357804411, | |
| "grad_norm": 0.45291149616241455, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 1.0541, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.002533128572107088, | |
| "grad_norm": 0.5108665823936462, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 1.1154, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.002596456786409765, | |
| "grad_norm": 0.515253484249115, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 1.1978, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0026597850007124423, | |
| "grad_norm": 0.55550616979599, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 1.3102, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0027231132150151195, | |
| "grad_norm": 0.5651044845581055, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 1.2797, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0027864414293177968, | |
| "grad_norm": 0.5689597725868225, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 1.4356, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.002849769643620474, | |
| "grad_norm": 0.5958440899848938, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 1.1597, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0029130978579231513, | |
| "grad_norm": 0.6642472743988037, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 1.3981, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0029764260722258285, | |
| "grad_norm": 0.8447531461715698, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 1.4968, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0030397542865285058, | |
| "grad_norm": 0.7993713021278381, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 1.3666, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.003103082500831183, | |
| "grad_norm": 1.2124278545379639, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 1.9457, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.00316641071513386, | |
| "grad_norm": 1.6007130146026611, | |
| "learning_rate": 0.0, | |
| "loss": 1.9753, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.00316641071513386, | |
| "eval_loss": 1.0649921894073486, | |
| "eval_runtime": 2341.5467, | |
| "eval_samples_per_second": 2.84, | |
| "eval_steps_per_second": 1.42, | |
| "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 | |
| } | |