| { | |
| "best_metric": 0.6044232249259949, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.443768996960486, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0486322188449848, | |
| "grad_norm": 9.046380996704102, | |
| "learning_rate": 5e-05, | |
| "loss": 3.3931, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0486322188449848, | |
| "eval_loss": 4.781421184539795, | |
| "eval_runtime": 3.3191, | |
| "eval_samples_per_second": 41.879, | |
| "eval_steps_per_second": 5.423, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0972644376899696, | |
| "grad_norm": 7.5731329917907715, | |
| "learning_rate": 0.0001, | |
| "loss": 4.2615, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1458966565349544, | |
| "grad_norm": 7.320644378662109, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 4.4261, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1945288753799392, | |
| "grad_norm": 8.42262077331543, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.7952, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.24316109422492402, | |
| "grad_norm": 9.451285362243652, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.9032, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2917933130699088, | |
| "grad_norm": 8.28438949584961, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.7165, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3404255319148936, | |
| "grad_norm": 5.48672342300415, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.6377, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3890577507598784, | |
| "grad_norm": 3.8141331672668457, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.5142, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.4376899696048632, | |
| "grad_norm": 3.9788246154785156, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.3652, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.48632218844984804, | |
| "grad_norm": 4.899479389190674, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.8154, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5349544072948328, | |
| "grad_norm": 4.353118896484375, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.9319, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.5835866261398176, | |
| "grad_norm": 5.567763328552246, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.1158, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.6322188449848024, | |
| "grad_norm": 4.067556858062744, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.8698, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.6808510638297872, | |
| "grad_norm": 2.3221864700317383, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.777, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.729483282674772, | |
| "grad_norm": 4.185751914978027, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.2234, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.7781155015197568, | |
| "grad_norm": 2.2419371604919434, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.5877, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.8267477203647416, | |
| "grad_norm": 1.3619014024734497, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.5595, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.8753799392097265, | |
| "grad_norm": 2.139798879623413, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.672, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.9240121580547113, | |
| "grad_norm": 2.716907024383545, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.7699, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.9726443768996961, | |
| "grad_norm": 3.265707492828369, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.8743, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.027355623100304, | |
| "grad_norm": 3.6474814414978027, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.7644, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.0759878419452888, | |
| "grad_norm": 2.879976272583008, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.479, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.1246200607902737, | |
| "grad_norm": 3.007579803466797, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.5571, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.1732522796352582, | |
| "grad_norm": 2.000781297683716, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.5527, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.221884498480243, | |
| "grad_norm": 3.722931146621704, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.7381, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.221884498480243, | |
| "eval_loss": 0.6369848251342773, | |
| "eval_runtime": 3.3108, | |
| "eval_samples_per_second": 41.984, | |
| "eval_steps_per_second": 5.437, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.2705167173252279, | |
| "grad_norm": 2.9047136306762695, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7098, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.3191489361702127, | |
| "grad_norm": 1.041992425918579, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.3945, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.3677811550151975, | |
| "grad_norm": 2.0041041374206543, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.5815, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.4164133738601823, | |
| "grad_norm": 2.5717592239379883, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.5842, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.465045592705167, | |
| "grad_norm": 3.187082529067993, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.7317, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.513677811550152, | |
| "grad_norm": 1.6170506477355957, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.5914, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.5623100303951367, | |
| "grad_norm": 1.6614936590194702, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.4377, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.6109422492401215, | |
| "grad_norm": 1.307366132736206, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.5034, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.6595744680851063, | |
| "grad_norm": 1.3304742574691772, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.5726, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.7082066869300911, | |
| "grad_norm": 3.0671167373657227, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.7421, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.756838905775076, | |
| "grad_norm": 2.019221305847168, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.6313, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.8054711246200608, | |
| "grad_norm": 1.5724313259124756, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.429, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.8541033434650456, | |
| "grad_norm": 2.5639946460723877, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.5555, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.9027355623100304, | |
| "grad_norm": 2.508168935775757, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.5811, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.9513677811550152, | |
| "grad_norm": 2.251434087753296, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.6068, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.0060790273556233, | |
| "grad_norm": 1.8268396854400635, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.9764, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.054711246200608, | |
| "grad_norm": 1.0984810590744019, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.3784, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.103343465045593, | |
| "grad_norm": 1.284153699874878, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.5234, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.1519756838905777, | |
| "grad_norm": 1.2855074405670166, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.5177, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.2006079027355625, | |
| "grad_norm": 1.5639398097991943, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.5428, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.2492401215805473, | |
| "grad_norm": 1.7351844310760498, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.6746, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.297872340425532, | |
| "grad_norm": 0.6704594492912292, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.3655, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.3465045592705165, | |
| "grad_norm": 0.8792460560798645, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.446, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.3951367781155017, | |
| "grad_norm": 1.2524126768112183, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.5358, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.443768996960486, | |
| "grad_norm": 1.5105795860290527, | |
| "learning_rate": 0.0, | |
| "loss": 0.5539, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.443768996960486, | |
| "eval_loss": 0.6044232249259949, | |
| "eval_runtime": 3.3157, | |
| "eval_samples_per_second": 41.921, | |
| "eval_steps_per_second": 5.429, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 2.654149397184512e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |