| { | |
| "best_metric": 1.736671805381775, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.6597510373443982, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03319502074688797, | |
| "grad_norm": 1.3888013362884521, | |
| "learning_rate": 5e-05, | |
| "loss": 2.6549, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03319502074688797, | |
| "eval_loss": 3.3357467651367188, | |
| "eval_runtime": 13.4264, | |
| "eval_samples_per_second": 15.119, | |
| "eval_steps_per_second": 1.936, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06639004149377593, | |
| "grad_norm": 1.8296154737472534, | |
| "learning_rate": 0.0001, | |
| "loss": 2.8439, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0995850622406639, | |
| "grad_norm": 2.0284576416015625, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.9364, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.13278008298755187, | |
| "grad_norm": 1.11079740524292, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.9005, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.16597510373443983, | |
| "grad_norm": 1.8842670917510986, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.9907, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1991701244813278, | |
| "grad_norm": 3.5251011848449707, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.4015, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.23236514522821577, | |
| "grad_norm": 7.950530052185059, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 3.4811, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.26556016597510373, | |
| "grad_norm": 1.74943208694458, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.5328, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2987551867219917, | |
| "grad_norm": 1.263008952140808, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.4674, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.33195020746887965, | |
| "grad_norm": 0.8815121054649353, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.3436, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3651452282157676, | |
| "grad_norm": 1.1149423122406006, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.3617, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3983402489626556, | |
| "grad_norm": 1.4619115591049194, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.3046, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.4315352697095436, | |
| "grad_norm": 1.623265027999878, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.3843, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.46473029045643155, | |
| "grad_norm": 2.030881404876709, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.2864, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.4979253112033195, | |
| "grad_norm": 3.0583701133728027, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.234, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5311203319502075, | |
| "grad_norm": 3.715399742126465, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.3731, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5643153526970954, | |
| "grad_norm": 3.8472068309783936, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.3049, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.5975103734439834, | |
| "grad_norm": 3.441741466522217, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.2444, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6307053941908713, | |
| "grad_norm": 3.601855516433716, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.1137, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.6639004149377593, | |
| "grad_norm": 4.1452813148498535, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.2233, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6970954356846473, | |
| "grad_norm": 3.2563297748565674, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.1183, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.7302904564315352, | |
| "grad_norm": 3.6426761150360107, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.9478, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.7634854771784232, | |
| "grad_norm": 1.054520606994629, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 2.057, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.7966804979253111, | |
| "grad_norm": 0.8895332217216492, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.0793, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.8298755186721992, | |
| "grad_norm": 0.7986735105514526, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.0316, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8298755186721992, | |
| "eval_loss": 1.8950231075286865, | |
| "eval_runtime": 13.3773, | |
| "eval_samples_per_second": 15.175, | |
| "eval_steps_per_second": 1.944, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8630705394190872, | |
| "grad_norm": 0.8051521182060242, | |
| "learning_rate": 5e-05, | |
| "loss": 1.949, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.8962655601659751, | |
| "grad_norm": 0.9853439927101135, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.8323, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.9294605809128631, | |
| "grad_norm": 1.0945851802825928, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.7493, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.9626556016597511, | |
| "grad_norm": 1.676234483718872, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.7922, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.995850622406639, | |
| "grad_norm": 3.2048423290252686, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.6883, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0290456431535269, | |
| "grad_norm": 1.70829439163208, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 3.6119, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.062240663900415, | |
| "grad_norm": 1.1503565311431885, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.9121, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.095435684647303, | |
| "grad_norm": 1.1516892910003662, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.8036, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.1286307053941909, | |
| "grad_norm": 1.125571370124817, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.8119, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.161825726141079, | |
| "grad_norm": 1.2525907754898071, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.7454, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.1950207468879668, | |
| "grad_norm": 1.5668110847473145, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.6739, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.2282157676348548, | |
| "grad_norm": 1.3762764930725098, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.6281, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.2614107883817427, | |
| "grad_norm": 0.9111345410346985, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.7097, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.2946058091286308, | |
| "grad_norm": 0.942206084728241, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 2.0938, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.3278008298755186, | |
| "grad_norm": 0.9035945534706116, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.8342, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.3609958506224067, | |
| "grad_norm": 1.1322251558303833, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.7725, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.3941908713692945, | |
| "grad_norm": 1.2130287885665894, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.6429, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.4273858921161826, | |
| "grad_norm": 1.4975661039352417, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.6027, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.4605809128630705, | |
| "grad_norm": 1.4150943756103516, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.5654, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.4937759336099585, | |
| "grad_norm": 2.0287270545959473, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.6134, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.5269709543568464, | |
| "grad_norm": 0.7386268377304077, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.9227, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.5601659751037344, | |
| "grad_norm": 0.951142430305481, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.8699, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.5933609958506225, | |
| "grad_norm": 1.1127924919128418, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.8144, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.6265560165975104, | |
| "grad_norm": 1.1469711065292358, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.7043, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.6597510373443982, | |
| "grad_norm": 1.2899292707443237, | |
| "learning_rate": 0.0, | |
| "loss": 1.6653, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.6597510373443982, | |
| "eval_loss": 1.736671805381775, | |
| "eval_runtime": 13.3627, | |
| "eval_samples_per_second": 15.192, | |
| "eval_steps_per_second": 1.946, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 5.305284264198144e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |