| { | |
| "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 | |
| } | |