| { | |
| "best_metric": 0.646575927734375, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-1840", | |
| "epoch": 2.798001427551749, | |
| "eval_steps": 40, | |
| "global_step": 1960, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0014275517487508922, | |
| "eval_loss": 2.6241602897644043, | |
| "eval_runtime": 3.454, | |
| "eval_samples_per_second": 33.295, | |
| "eval_steps_per_second": 1.158, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05710206995003569, | |
| "eval_loss": 2.2859995365142822, | |
| "eval_runtime": 3.4369, | |
| "eval_samples_per_second": 33.461, | |
| "eval_steps_per_second": 1.164, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11420413990007137, | |
| "eval_loss": 1.9066081047058105, | |
| "eval_runtime": 3.569, | |
| "eval_samples_per_second": 32.222, | |
| "eval_steps_per_second": 1.121, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.14275517487508924, | |
| "grad_norm": 6.376378536224365, | |
| "learning_rate": 0.00013761467889908255, | |
| "loss": 4.9536, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.17130620985010706, | |
| "eval_loss": 1.7338049411773682, | |
| "eval_runtime": 3.5172, | |
| "eval_samples_per_second": 32.696, | |
| "eval_steps_per_second": 1.137, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.22840827980014275, | |
| "eval_loss": 1.6253185272216797, | |
| "eval_runtime": 3.4638, | |
| "eval_samples_per_second": 33.201, | |
| "eval_steps_per_second": 1.155, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.28551034975017847, | |
| "grad_norm": 3.5151774883270264, | |
| "learning_rate": 0.0002752293577981651, | |
| "loss": 3.6406, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.28551034975017847, | |
| "eval_loss": 1.5643784999847412, | |
| "eval_runtime": 3.5326, | |
| "eval_samples_per_second": 32.554, | |
| "eval_steps_per_second": 1.132, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.3426124197002141, | |
| "eval_loss": 1.4933531284332275, | |
| "eval_runtime": 3.5491, | |
| "eval_samples_per_second": 32.402, | |
| "eval_steps_per_second": 1.127, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.3997144896502498, | |
| "eval_loss": 1.4442161321640015, | |
| "eval_runtime": 3.5073, | |
| "eval_samples_per_second": 32.789, | |
| "eval_steps_per_second": 1.14, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.4282655246252677, | |
| "grad_norm": 3.7754976749420166, | |
| "learning_rate": 0.0002999958858736361, | |
| "loss": 3.1356, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.4568165596002855, | |
| "eval_loss": 1.3713915348052979, | |
| "eval_runtime": 3.4547, | |
| "eval_samples_per_second": 33.288, | |
| "eval_steps_per_second": 1.158, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.5139186295503212, | |
| "eval_loss": 1.3405636548995972, | |
| "eval_runtime": 3.4457, | |
| "eval_samples_per_second": 33.375, | |
| "eval_steps_per_second": 1.161, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.5710206995003569, | |
| "grad_norm": 4.63564920425415, | |
| "learning_rate": 0.00029997973321299517, | |
| "loss": 2.8521, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.5710206995003569, | |
| "eval_loss": 1.3139711618423462, | |
| "eval_runtime": 3.5109, | |
| "eval_samples_per_second": 32.756, | |
| "eval_steps_per_second": 1.139, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.6281227694503926, | |
| "eval_loss": 1.229024052619934, | |
| "eval_runtime": 3.4196, | |
| "eval_samples_per_second": 33.63, | |
| "eval_steps_per_second": 1.17, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.6852248394004282, | |
| "eval_loss": 1.1974313259124756, | |
| "eval_runtime": 3.4703, | |
| "eval_samples_per_second": 33.138, | |
| "eval_steps_per_second": 1.153, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.7137758743754461, | |
| "grad_norm": 3.106452226638794, | |
| "learning_rate": 0.0002999513450932977, | |
| "loss": 2.7573, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.742326909350464, | |
| "eval_loss": 1.1787874698638916, | |
| "eval_runtime": 3.47, | |
| "eval_samples_per_second": 33.141, | |
| "eval_steps_per_second": 1.153, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.7994289793004996, | |
| "eval_loss": 1.1294182538986206, | |
| "eval_runtime": 3.4194, | |
| "eval_samples_per_second": 33.632, | |
| "eval_steps_per_second": 1.17, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.8565310492505354, | |
| "grad_norm": 4.655078411102295, | |
| "learning_rate": 0.00029991072383046797, | |
| "loss": 2.3985, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.8565310492505354, | |
| "eval_loss": 1.1245826482772827, | |
| "eval_runtime": 3.472, | |
| "eval_samples_per_second": 33.122, | |
| "eval_steps_per_second": 1.152, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.913633119200571, | |
| "eval_loss": 1.0636686086654663, | |
| "eval_runtime": 3.4569, | |
| "eval_samples_per_second": 33.267, | |
| "eval_steps_per_second": 1.157, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.9707351891506067, | |
| "eval_loss": 1.0166677236557007, | |
| "eval_runtime": 3.6167, | |
| "eval_samples_per_second": 31.797, | |
| "eval_steps_per_second": 1.106, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.9992862241256245, | |
| "grad_norm": 4.026608467102051, | |
| "learning_rate": 0.0002998578727384189, | |
| "loss": 2.2745, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.0278372591006424, | |
| "eval_loss": 1.0103121995925903, | |
| "eval_runtime": 3.4673, | |
| "eval_samples_per_second": 33.167, | |
| "eval_steps_per_second": 1.154, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.0849393290506781, | |
| "eval_loss": 0.9873223900794983, | |
| "eval_runtime": 3.4608, | |
| "eval_samples_per_second": 33.229, | |
| "eval_steps_per_second": 1.156, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.1420413990007137, | |
| "grad_norm": 6.209025859832764, | |
| "learning_rate": 0.00029979279612878226, | |
| "loss": 1.8141, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.1420413990007137, | |
| "eval_loss": 0.9796751141548157, | |
| "eval_runtime": 3.5186, | |
| "eval_samples_per_second": 32.683, | |
| "eval_steps_per_second": 1.137, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.1991434689507494, | |
| "eval_loss": 0.9596832990646362, | |
| "eval_runtime": 3.4646, | |
| "eval_samples_per_second": 33.193, | |
| "eval_steps_per_second": 1.155, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.2562455389007852, | |
| "eval_loss": 0.945811927318573, | |
| "eval_runtime": 3.4319, | |
| "eval_samples_per_second": 33.509, | |
| "eval_steps_per_second": 1.166, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.284796573875803, | |
| "grad_norm": 4.082645416259766, | |
| "learning_rate": 0.0002997154993105566, | |
| "loss": 1.5585, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.313347608850821, | |
| "eval_loss": 0.9203804135322571, | |
| "eval_runtime": 3.4359, | |
| "eval_samples_per_second": 33.47, | |
| "eval_steps_per_second": 1.164, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.3704496788008567, | |
| "eval_loss": 0.9172277450561523, | |
| "eval_runtime": 3.479, | |
| "eval_samples_per_second": 33.056, | |
| "eval_steps_per_second": 1.15, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.4275517487508922, | |
| "grad_norm": 4.086517333984375, | |
| "learning_rate": 0.0002996259885896743, | |
| "loss": 1.5745, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.4275517487508922, | |
| "eval_loss": 0.9019652009010315, | |
| "eval_runtime": 3.5068, | |
| "eval_samples_per_second": 32.793, | |
| "eval_steps_per_second": 1.141, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.484653818700928, | |
| "eval_loss": 0.8774219751358032, | |
| "eval_runtime": 3.5022, | |
| "eval_samples_per_second": 32.836, | |
| "eval_steps_per_second": 1.142, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 1.5417558886509637, | |
| "eval_loss": 0.8411704897880554, | |
| "eval_runtime": 3.4781, | |
| "eval_samples_per_second": 33.064, | |
| "eval_steps_per_second": 1.15, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 1.5703069236259815, | |
| "grad_norm": 1.3416516780853271, | |
| "learning_rate": 0.0002995242712684871, | |
| "loss": 1.3623, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.5988579586009992, | |
| "eval_loss": 0.8341473340988159, | |
| "eval_runtime": 3.5251, | |
| "eval_samples_per_second": 32.623, | |
| "eval_steps_per_second": 1.135, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 1.655960028551035, | |
| "eval_loss": 0.8323267102241516, | |
| "eval_runtime": 3.4934, | |
| "eval_samples_per_second": 32.919, | |
| "eval_steps_per_second": 1.145, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 1.7130620985010707, | |
| "grad_norm": 5.395486354827881, | |
| "learning_rate": 0.0002994103556451703, | |
| "loss": 1.3262, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.7130620985010707, | |
| "eval_loss": 0.7996125221252441, | |
| "eval_runtime": 3.4858, | |
| "eval_samples_per_second": 32.991, | |
| "eval_steps_per_second": 1.147, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.7701641684511062, | |
| "eval_loss": 0.8066531419754028, | |
| "eval_runtime": 3.4788, | |
| "eval_samples_per_second": 33.057, | |
| "eval_steps_per_second": 1.15, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 1.827266238401142, | |
| "eval_loss": 0.7751766443252563, | |
| "eval_runtime": 3.4563, | |
| "eval_samples_per_second": 33.273, | |
| "eval_steps_per_second": 1.157, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 1.85581727337616, | |
| "grad_norm": 1.97977876663208, | |
| "learning_rate": 0.00029928425101304583, | |
| "loss": 1.2514, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.8843683083511777, | |
| "eval_loss": 0.7176135778427124, | |
| "eval_runtime": 3.4289, | |
| "eval_samples_per_second": 33.539, | |
| "eval_steps_per_second": 1.167, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 1.9414703783012133, | |
| "eval_loss": 0.7170359492301941, | |
| "eval_runtime": 3.4671, | |
| "eval_samples_per_second": 33.168, | |
| "eval_steps_per_second": 1.154, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 1.9985724482512492, | |
| "grad_norm": 3.208996057510376, | |
| "learning_rate": 0.0002991459676598241, | |
| "loss": 1.2277, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.9985724482512492, | |
| "eval_loss": 0.7038947939872742, | |
| "eval_runtime": 3.4967, | |
| "eval_samples_per_second": 32.888, | |
| "eval_steps_per_second": 1.144, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.0556745182012848, | |
| "eval_loss": 0.7032578587532043, | |
| "eval_runtime": 3.4286, | |
| "eval_samples_per_second": 33.542, | |
| "eval_steps_per_second": 1.167, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 2.1127765881513203, | |
| "eval_loss": 0.7024741172790527, | |
| "eval_runtime": 3.4401, | |
| "eval_samples_per_second": 33.429, | |
| "eval_steps_per_second": 1.163, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 2.1413276231263385, | |
| "grad_norm": 5.024557113647461, | |
| "learning_rate": 0.0002989955168667647, | |
| "loss": 0.68, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.1698786581013563, | |
| "eval_loss": 0.7079240083694458, | |
| "eval_runtime": 3.4687, | |
| "eval_samples_per_second": 33.154, | |
| "eval_steps_per_second": 1.153, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 2.226980728051392, | |
| "eval_loss": 0.7214464545249939, | |
| "eval_runtime": 3.4537, | |
| "eval_samples_per_second": 33.297, | |
| "eval_steps_per_second": 1.158, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 2.2840827980014273, | |
| "grad_norm": 2.2797622680664062, | |
| "learning_rate": 0.0002988329109077561, | |
| "loss": 0.809, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.2840827980014273, | |
| "eval_loss": 0.6896761059761047, | |
| "eval_runtime": 3.4437, | |
| "eval_samples_per_second": 33.394, | |
| "eval_steps_per_second": 1.162, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.3411848679514633, | |
| "eval_loss": 0.7046868801116943, | |
| "eval_runtime": 3.4498, | |
| "eval_samples_per_second": 33.335, | |
| "eval_steps_per_second": 1.159, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 2.398286937901499, | |
| "eval_loss": 0.7042288780212402, | |
| "eval_runtime": 3.425, | |
| "eval_samples_per_second": 33.577, | |
| "eval_steps_per_second": 1.168, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 2.4268379728765166, | |
| "grad_norm": 2.373941421508789, | |
| "learning_rate": 0.00029865816304831436, | |
| "loss": 0.7931, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.455389007851535, | |
| "eval_loss": 0.6791558861732483, | |
| "eval_runtime": 3.4601, | |
| "eval_samples_per_second": 33.236, | |
| "eval_steps_per_second": 1.156, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 2.5124910778015703, | |
| "eval_loss": 0.6776650547981262, | |
| "eval_runtime": 3.4939, | |
| "eval_samples_per_second": 32.915, | |
| "eval_steps_per_second": 1.145, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 2.569593147751606, | |
| "grad_norm": 3.9278931617736816, | |
| "learning_rate": 0.0002984712875445008, | |
| "loss": 0.6957, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.569593147751606, | |
| "eval_loss": 0.6809150576591492, | |
| "eval_runtime": 3.4802, | |
| "eval_samples_per_second": 33.044, | |
| "eval_steps_per_second": 1.149, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.626695217701642, | |
| "eval_loss": 0.646575927734375, | |
| "eval_runtime": 3.462, | |
| "eval_samples_per_second": 33.218, | |
| "eval_steps_per_second": 1.155, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 2.6837972876516774, | |
| "eval_loss": 0.6704702377319336, | |
| "eval_runtime": 3.4863, | |
| "eval_samples_per_second": 32.986, | |
| "eval_steps_per_second": 1.147, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 2.712348322626695, | |
| "grad_norm": 3.325489044189453, | |
| "learning_rate": 0.0002982722996417592, | |
| "loss": 0.7611, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.7408993576017133, | |
| "eval_loss": 0.6548537015914917, | |
| "eval_runtime": 3.5385, | |
| "eval_samples_per_second": 32.5, | |
| "eval_steps_per_second": 1.13, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 2.798001427551749, | |
| "eval_loss": 0.6539962887763977, | |
| "eval_runtime": 3.4712, | |
| "eval_samples_per_second": 33.13, | |
| "eval_steps_per_second": 1.152, | |
| "step": 1960 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 35000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "save_steps": 40, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 3 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.3002531516841984e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |