| { | |
| "best_metric": 2.037623643875122, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-400", | |
| "epoch": 0.028237619568670363, | |
| "eval_steps": 50, | |
| "global_step": 400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.05940489216759e-05, | |
| "eval_loss": 2.8033833503723145, | |
| "eval_runtime": 108.3643, | |
| "eval_samples_per_second": 55.046, | |
| "eval_steps_per_second": 13.768, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007059404892167591, | |
| "grad_norm": 1.7475390434265137, | |
| "learning_rate": 4.1400000000000003e-05, | |
| "loss": 2.648, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0014118809784335181, | |
| "grad_norm": 1.68655526638031, | |
| "learning_rate": 8.280000000000001e-05, | |
| "loss": 2.4858, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002117821467650277, | |
| "grad_norm": 1.582150936126709, | |
| "learning_rate": 0.00012419999999999998, | |
| "loss": 2.4498, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0028237619568670363, | |
| "grad_norm": 1.5243428945541382, | |
| "learning_rate": 0.00016560000000000001, | |
| "loss": 2.4085, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0035297024460837953, | |
| "grad_norm": 1.5775226354599, | |
| "learning_rate": 0.000207, | |
| "loss": 2.3538, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0035297024460837953, | |
| "eval_loss": 2.3329827785491943, | |
| "eval_runtime": 108.5486, | |
| "eval_samples_per_second": 54.952, | |
| "eval_steps_per_second": 13.745, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.004235642935300554, | |
| "grad_norm": 1.0230377912521362, | |
| "learning_rate": 0.00020674787920189178, | |
| "loss": 2.4597, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.004941583424517313, | |
| "grad_norm": 1.1582502126693726, | |
| "learning_rate": 0.00020599274511475253, | |
| "loss": 2.2224, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0056475239137340726, | |
| "grad_norm": 1.2100154161453247, | |
| "learning_rate": 0.00020473827667594888, | |
| "loss": 2.1416, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.006353464402950831, | |
| "grad_norm": 1.165224552154541, | |
| "learning_rate": 0.00020299058552961598, | |
| "loss": 2.2391, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.007059404892167591, | |
| "grad_norm": 1.492423176765442, | |
| "learning_rate": 0.00020075818625134152, | |
| "loss": 2.308, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.007059404892167591, | |
| "eval_loss": 2.240849018096924, | |
| "eval_runtime": 108.306, | |
| "eval_samples_per_second": 55.075, | |
| "eval_steps_per_second": 13.776, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.007765345381384349, | |
| "grad_norm": 0.9571946263313293, | |
| "learning_rate": 0.00019805195486600916, | |
| "loss": 2.3412, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.008471285870601109, | |
| "grad_norm": 1.0861552953720093, | |
| "learning_rate": 0.00019488507586089894, | |
| "loss": 2.1932, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.009177226359817867, | |
| "grad_norm": 1.318565011024475, | |
| "learning_rate": 0.00019127297795219008, | |
| "loss": 2.199, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.009883166849034626, | |
| "grad_norm": 1.283436894416809, | |
| "learning_rate": 0.00018723325891780706, | |
| "loss": 2.2015, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.010589107338251386, | |
| "grad_norm": 1.3785208463668823, | |
| "learning_rate": 0.0001827855998628142, | |
| "loss": 2.1604, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.010589107338251386, | |
| "eval_loss": 2.1907973289489746, | |
| "eval_runtime": 108.2635, | |
| "eval_samples_per_second": 55.097, | |
| "eval_steps_per_second": 13.781, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.011295047827468145, | |
| "grad_norm": 0.9574385285377502, | |
| "learning_rate": 0.0001779516693350504, | |
| "loss": 2.1949, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.012000988316684903, | |
| "grad_norm": 1.022146463394165, | |
| "learning_rate": 0.00017275501775814182, | |
| "loss": 2.0991, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.012706928805901662, | |
| "grad_norm": 1.1318084001541138, | |
| "learning_rate": 0.00016722096269620562, | |
| "loss": 2.1822, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.013412869295118422, | |
| "grad_norm": 1.1545848846435547, | |
| "learning_rate": 0.00016137646550922228, | |
| "loss": 2.1998, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.014118809784335181, | |
| "grad_norm": 1.444872260093689, | |
| "learning_rate": 0.00015525, | |
| "loss": 2.163, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.014118809784335181, | |
| "eval_loss": 2.1361401081085205, | |
| "eval_runtime": 115.7055, | |
| "eval_samples_per_second": 51.553, | |
| "eval_steps_per_second": 12.895, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.01482475027355194, | |
| "grad_norm": 0.986111581325531, | |
| "learning_rate": 0.0001488714136926695, | |
| "loss": 2.2117, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.015530690762768699, | |
| "grad_norm": 1.0047094821929932, | |
| "learning_rate": 0.0001422717824185469, | |
| "loss": 2.1779, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.016236631251985458, | |
| "grad_norm": 1.1812105178833008, | |
| "learning_rate": 0.00013548325891780705, | |
| "loss": 2.1505, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.016942571741202218, | |
| "grad_norm": 1.5376032590866089, | |
| "learning_rate": 0.0001285389161945656, | |
| "loss": 2.0143, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.017648512230418977, | |
| "grad_norm": 1.3409324884414673, | |
| "learning_rate": 0.0001214725863885273, | |
| "loss": 2.1464, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.017648512230418977, | |
| "eval_loss": 2.1107239723205566, | |
| "eval_runtime": 108.6879, | |
| "eval_samples_per_second": 54.882, | |
| "eval_steps_per_second": 13.727, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.018354452719635733, | |
| "grad_norm": 0.8746324777603149, | |
| "learning_rate": 0.00011431869594820213, | |
| "loss": 2.2634, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.019060393208852493, | |
| "grad_norm": 1.0597100257873535, | |
| "learning_rate": 0.00010711209790870886, | |
| "loss": 2.1859, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.019766333698069252, | |
| "grad_norm": 0.9971674084663391, | |
| "learning_rate": 9.988790209129117e-05, | |
| "loss": 2.0446, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.02047227418728601, | |
| "grad_norm": 1.1347280740737915, | |
| "learning_rate": 9.268130405179787e-05, | |
| "loss": 2.0384, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.02117821467650277, | |
| "grad_norm": 1.377494215965271, | |
| "learning_rate": 8.55274136114727e-05, | |
| "loss": 2.0872, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.02117821467650277, | |
| "eval_loss": 2.081465721130371, | |
| "eval_runtime": 115.6558, | |
| "eval_samples_per_second": 51.575, | |
| "eval_steps_per_second": 12.9, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.02188415516571953, | |
| "grad_norm": 0.9409071207046509, | |
| "learning_rate": 7.84610838054344e-05, | |
| "loss": 2.1326, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.02259009565493629, | |
| "grad_norm": 0.9766196608543396, | |
| "learning_rate": 7.151674108219295e-05, | |
| "loss": 2.1009, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.023296036144153046, | |
| "grad_norm": 1.045487880706787, | |
| "learning_rate": 6.472821758145309e-05, | |
| "loss": 1.9352, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.024001976633369806, | |
| "grad_norm": 1.2392162084579468, | |
| "learning_rate": 5.8128586307330475e-05, | |
| "loss": 2.0905, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.024707917122586565, | |
| "grad_norm": 1.3943520784378052, | |
| "learning_rate": 5.175000000000002e-05, | |
| "loss": 2.1226, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.024707917122586565, | |
| "eval_loss": 2.057299852371216, | |
| "eval_runtime": 109.4826, | |
| "eval_samples_per_second": 54.484, | |
| "eval_steps_per_second": 13.628, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.025413857611803325, | |
| "grad_norm": 0.9228034615516663, | |
| "learning_rate": 4.5623534490777714e-05, | |
| "loss": 2.1183, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.026119798101020084, | |
| "grad_norm": 0.9374071955680847, | |
| "learning_rate": 3.9779037303794365e-05, | |
| "loss": 2.0988, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.026825738590236844, | |
| "grad_norm": 1.051098108291626, | |
| "learning_rate": 3.42449822418582e-05, | |
| "loss": 1.9813, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.027531679079453603, | |
| "grad_norm": 1.083287000656128, | |
| "learning_rate": 2.9048330664949622e-05, | |
| "loss": 2.1039, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.028237619568670363, | |
| "grad_norm": 1.2849839925765991, | |
| "learning_rate": 2.4214400137185785e-05, | |
| "loss": 1.9843, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.028237619568670363, | |
| "eval_loss": 2.037623643875122, | |
| "eval_runtime": 107.9784, | |
| "eval_samples_per_second": 55.243, | |
| "eval_steps_per_second": 13.818, | |
| "step": 400 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1105701006934016e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |