| { |
| "best_metric": 0.8816373944282532, |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", |
| "epoch": 0.8978675645342312, |
| "eval_steps": 25, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.017957351290684626, |
| "grad_norm": 3.9509336948394775, |
| "learning_rate": 5e-05, |
| "loss": 1.7104, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.017957351290684626, |
| "eval_loss": 1.8697540760040283, |
| "eval_runtime": 10.8798, |
| "eval_samples_per_second": 34.468, |
| "eval_steps_per_second": 4.32, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.03591470258136925, |
| "grad_norm": 4.314034461975098, |
| "learning_rate": 0.0001, |
| "loss": 1.7496, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.05387205387205387, |
| "grad_norm": 2.2511677742004395, |
| "learning_rate": 9.989294616193017e-05, |
| "loss": 1.5658, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.0718294051627385, |
| "grad_norm": 1.7218873500823975, |
| "learning_rate": 9.957224306869053e-05, |
| "loss": 1.3851, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.08978675645342311, |
| "grad_norm": 1.3444435596466064, |
| "learning_rate": 9.903926402016153e-05, |
| "loss": 1.2694, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.10774410774410774, |
| "grad_norm": 1.0787757635116577, |
| "learning_rate": 9.829629131445342e-05, |
| "loss": 1.1763, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.12570145903479238, |
| "grad_norm": 0.8413438200950623, |
| "learning_rate": 9.73465064747553e-05, |
| "loss": 1.097, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.143658810325477, |
| "grad_norm": 0.8566951751708984, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 1.088, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.16161616161616163, |
| "grad_norm": 0.7398088574409485, |
| "learning_rate": 9.484363707663442e-05, |
| "loss": 1.0138, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.17957351290684623, |
| "grad_norm": 0.9453352689743042, |
| "learning_rate": 9.330127018922194e-05, |
| "loss": 1.0309, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.19753086419753085, |
| "grad_norm": 0.5798099040985107, |
| "learning_rate": 9.157348061512727e-05, |
| "loss": 0.9848, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.21548821548821548, |
| "grad_norm": 0.8908112049102783, |
| "learning_rate": 8.966766701456177e-05, |
| "loss": 0.9349, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.2334455667789001, |
| "grad_norm": 0.622196614742279, |
| "learning_rate": 8.759199037394887e-05, |
| "loss": 0.975, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.25140291806958476, |
| "grad_norm": 0.776465892791748, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 0.9834, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.26936026936026936, |
| "grad_norm": 0.3768865764141083, |
| "learning_rate": 8.296729075500344e-05, |
| "loss": 0.9695, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.287317620650954, |
| "grad_norm": 0.7923662662506104, |
| "learning_rate": 8.043807145043604e-05, |
| "loss": 0.9734, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.3052749719416386, |
| "grad_norm": 0.661575973033905, |
| "learning_rate": 7.777851165098012e-05, |
| "loss": 0.9709, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.32323232323232326, |
| "grad_norm": 0.7372098565101624, |
| "learning_rate": 7.500000000000001e-05, |
| "loss": 0.9523, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.34118967452300786, |
| "grad_norm": 0.566180944442749, |
| "learning_rate": 7.211443451095007e-05, |
| "loss": 0.934, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.35914702581369246, |
| "grad_norm": 0.8149131536483765, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 0.9457, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.3771043771043771, |
| "grad_norm": 0.4531962275505066, |
| "learning_rate": 6.607197326515808e-05, |
| "loss": 0.931, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "grad_norm": 0.7378969192504883, |
| "learning_rate": 6.294095225512603e-05, |
| "loss": 0.9531, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.41301907968574636, |
| "grad_norm": 0.636336624622345, |
| "learning_rate": 5.9754516100806423e-05, |
| "loss": 0.9221, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.43097643097643096, |
| "grad_norm": 0.49999096989631653, |
| "learning_rate": 5.6526309611002594e-05, |
| "loss": 0.931, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.4489337822671156, |
| "grad_norm": 0.5449424386024475, |
| "learning_rate": 5.327015646150716e-05, |
| "loss": 0.8504, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.4489337822671156, |
| "eval_loss": 0.9176837801933289, |
| "eval_runtime": 10.9226, |
| "eval_samples_per_second": 34.332, |
| "eval_steps_per_second": 4.303, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.4668911335578002, |
| "grad_norm": 0.6586840748786926, |
| "learning_rate": 5e-05, |
| "loss": 0.9306, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.48484848484848486, |
| "grad_norm": 0.6180529594421387, |
| "learning_rate": 4.6729843538492847e-05, |
| "loss": 0.9315, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.5028058361391695, |
| "grad_norm": 0.43769389390945435, |
| "learning_rate": 4.347369038899744e-05, |
| "loss": 0.9108, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.5207631874298541, |
| "grad_norm": 0.5514314770698547, |
| "learning_rate": 4.0245483899193595e-05, |
| "loss": 0.9184, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.5387205387205387, |
| "grad_norm": 0.3724231719970703, |
| "learning_rate": 3.705904774487396e-05, |
| "loss": 0.9071, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.5566778900112234, |
| "grad_norm": 0.4815616309642792, |
| "learning_rate": 3.392802673484193e-05, |
| "loss": 0.9251, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.574635241301908, |
| "grad_norm": 0.6298116445541382, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 0.9048, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.5925925925925926, |
| "grad_norm": 0.43708935379981995, |
| "learning_rate": 2.7885565489049946e-05, |
| "loss": 0.9012, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.6105499438832772, |
| "grad_norm": 0.40635502338409424, |
| "learning_rate": 2.500000000000001e-05, |
| "loss": 0.9315, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.6285072951739619, |
| "grad_norm": 0.3841124176979065, |
| "learning_rate": 2.2221488349019903e-05, |
| "loss": 0.8967, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.6464646464646465, |
| "grad_norm": 0.4346996247768402, |
| "learning_rate": 1.9561928549563968e-05, |
| "loss": 0.878, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.6644219977553311, |
| "grad_norm": 0.4562406539916992, |
| "learning_rate": 1.703270924499656e-05, |
| "loss": 0.8639, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.6823793490460157, |
| "grad_norm": 0.436215877532959, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 0.8593, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.7003367003367004, |
| "grad_norm": 0.4428524374961853, |
| "learning_rate": 1.2408009626051137e-05, |
| "loss": 0.8816, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.7182940516273849, |
| "grad_norm": 0.5406110882759094, |
| "learning_rate": 1.0332332985438248e-05, |
| "loss": 0.8918, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.7362514029180696, |
| "grad_norm": 0.44841742515563965, |
| "learning_rate": 8.426519384872733e-06, |
| "loss": 0.8867, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.7542087542087542, |
| "grad_norm": 0.32828664779663086, |
| "learning_rate": 6.698729810778065e-06, |
| "loss": 0.9081, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.7721661054994389, |
| "grad_norm": 0.600707471370697, |
| "learning_rate": 5.156362923365588e-06, |
| "loss": 0.8924, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "grad_norm": 0.35831689834594727, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 0.8868, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.8080808080808081, |
| "grad_norm": 0.3134266138076782, |
| "learning_rate": 2.653493525244721e-06, |
| "loss": 0.8624, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.8260381593714927, |
| "grad_norm": 0.3953910768032074, |
| "learning_rate": 1.70370868554659e-06, |
| "loss": 0.9129, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.8439955106621774, |
| "grad_norm": 0.346354603767395, |
| "learning_rate": 9.607359798384785e-07, |
| "loss": 0.88, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.8619528619528619, |
| "grad_norm": 0.3914426565170288, |
| "learning_rate": 4.277569313094809e-07, |
| "loss": 0.883, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.8799102132435466, |
| "grad_norm": 0.3426049053668976, |
| "learning_rate": 1.0705383806982606e-07, |
| "loss": 0.8724, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.8978675645342312, |
| "grad_norm": 0.44009047746658325, |
| "learning_rate": 0.0, |
| "loss": 0.8439, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.8978675645342312, |
| "eval_loss": 0.8816373944282532, |
| "eval_runtime": 10.9243, |
| "eval_samples_per_second": 34.327, |
| "eval_steps_per_second": 4.302, |
| "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": 1.589463780163584e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
