| { | |
| "best_metric": 1.3830602169036865, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.19422189851905802, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0038844379703811605, | |
| "grad_norm": 0.16940909624099731, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8051, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0038844379703811605, | |
| "eval_loss": 2.214400291442871, | |
| "eval_runtime": 50.4257, | |
| "eval_samples_per_second": 34.407, | |
| "eval_steps_per_second": 4.303, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007768875940762321, | |
| "grad_norm": 0.2265290915966034, | |
| "learning_rate": 0.0001, | |
| "loss": 0.964, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.011653313911143482, | |
| "grad_norm": 0.25076374411582947, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.1359, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.015537751881524642, | |
| "grad_norm": 0.28672662377357483, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.2773, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.019422189851905802, | |
| "grad_norm": 0.34131261706352234, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.4659, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.023306627822286964, | |
| "grad_norm": 0.3849389851093292, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.4853, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.027191065792668122, | |
| "grad_norm": 0.5481998324394226, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.8394, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.031075503763049284, | |
| "grad_norm": 1.2644219398498535, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.0557, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03495994173343044, | |
| "grad_norm": 0.6018820405006409, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.9811, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.038844379703811605, | |
| "grad_norm": 0.16305476427078247, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.1031, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.042728817674192766, | |
| "grad_norm": 0.1696261614561081, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.0489, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04661325564457393, | |
| "grad_norm": 0.28483521938323975, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.2784, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.05049769361495508, | |
| "grad_norm": 0.15984632074832916, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.9149, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.054382131585336245, | |
| "grad_norm": 0.1628602296113968, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.8615, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.05826656955571741, | |
| "grad_norm": 0.18722203373908997, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.9296, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06215100752609857, | |
| "grad_norm": 0.19099275767803192, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.0145, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.06603544549647973, | |
| "grad_norm": 0.19019487500190735, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.132, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.06991988346686089, | |
| "grad_norm": 0.2184630185365677, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.1922, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07380432143724205, | |
| "grad_norm": 0.28920140862464905, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.2977, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.07768875940762321, | |
| "grad_norm": 0.5382729768753052, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.6269, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08157319737800436, | |
| "grad_norm": 2.2659597396850586, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 4.3968, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.08545763534838553, | |
| "grad_norm": 0.1493668556213379, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.0628, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.08934207331876669, | |
| "grad_norm": 0.11811956763267517, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.0409, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.09322651128914786, | |
| "grad_norm": 0.1590295433998108, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.062, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.09711094925952901, | |
| "grad_norm": 0.28556254506111145, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.2848, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09711094925952901, | |
| "eval_loss": 1.5334738492965698, | |
| "eval_runtime": 44.1672, | |
| "eval_samples_per_second": 39.283, | |
| "eval_steps_per_second": 4.913, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10099538722991017, | |
| "grad_norm": 0.1251099556684494, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7044, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.10487982520029134, | |
| "grad_norm": 0.12927348911762238, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.7468, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.10876426317067249, | |
| "grad_norm": 0.15400154888629913, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.9012, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.11264870114105366, | |
| "grad_norm": 0.15517409145832062, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.9867, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.11653313911143481, | |
| "grad_norm": 0.1743563860654831, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.1062, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.12041757708181597, | |
| "grad_norm": 0.22268836200237274, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.2279, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.12430201505219714, | |
| "grad_norm": 0.375324547290802, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.2564, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1281864530225783, | |
| "grad_norm": 1.0053523778915405, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 2.3372, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.13207089099295946, | |
| "grad_norm": 0.38230547308921814, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.3872, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.13595532896334062, | |
| "grad_norm": 0.13769803941249847, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.0393, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.13983976693372177, | |
| "grad_norm": 0.10188828408718109, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.9753, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.14372420490410293, | |
| "grad_norm": 0.1527317613363266, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.1745, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.1476086428744841, | |
| "grad_norm": 0.11825243383646011, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.716, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.15149308084486526, | |
| "grad_norm": 0.11301682144403458, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.7257, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.15537751881524642, | |
| "grad_norm": 0.1494889259338379, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.9107, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.15926195678562757, | |
| "grad_norm": 0.14700599014759064, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.9517, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.16314639475600873, | |
| "grad_norm": 0.17011895775794983, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.0068, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1670308327263899, | |
| "grad_norm": 0.1991521120071411, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.0894, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.17091527069677107, | |
| "grad_norm": 0.2991145849227905, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.2643, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.17479970866715222, | |
| "grad_norm": 0.6368501782417297, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.5727, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.17868414663753338, | |
| "grad_norm": 3.5262486934661865, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 5.0699, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.18256858460791453, | |
| "grad_norm": 0.15134742856025696, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.9543, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.1864530225782957, | |
| "grad_norm": 0.10085561126470566, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.0164, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.19033746054867687, | |
| "grad_norm": 0.1159551590681076, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.0135, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.19422189851905802, | |
| "grad_norm": 0.25713497400283813, | |
| "learning_rate": 0.0, | |
| "loss": 1.2383, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.19422189851905802, | |
| "eval_loss": 1.3830602169036865, | |
| "eval_runtime": 43.9311, | |
| "eval_samples_per_second": 39.494, | |
| "eval_steps_per_second": 4.94, | |
| "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": 2.195711408954409e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |