| { | |
| "best_metric": 0.7657374739646912, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.9673518742442564, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.019347037484885126, | |
| "grad_norm": 0.16485288739204407, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8982, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.019347037484885126, | |
| "eval_loss": 0.9295976161956787, | |
| "eval_runtime": 11.6214, | |
| "eval_samples_per_second": 30.031, | |
| "eval_steps_per_second": 3.786, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03869407496977025, | |
| "grad_norm": 0.19143803417682648, | |
| "learning_rate": 0.0001, | |
| "loss": 0.914, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.05804111245465538, | |
| "grad_norm": 0.1977594941854477, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.9362, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0773881499395405, | |
| "grad_norm": 0.16205620765686035, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.9223, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.09673518742442563, | |
| "grad_norm": 0.11404136568307877, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.9114, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.11608222490931076, | |
| "grad_norm": 0.11512098461389542, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.9179, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1354292623941959, | |
| "grad_norm": 0.10984373837709427, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.9057, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.154776299879081, | |
| "grad_norm": 0.09464925527572632, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.9399, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.17412333736396615, | |
| "grad_norm": 0.08994854986667633, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.868, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.19347037484885127, | |
| "grad_norm": 0.11591281741857529, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.8592, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.21281741233373638, | |
| "grad_norm": 0.17273177206516266, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.7334, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.23216444981862153, | |
| "grad_norm": 0.21951550245285034, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.4669, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.25151148730350664, | |
| "grad_norm": 0.09941945970058441, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.7637, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2708585247883918, | |
| "grad_norm": 0.07142731547355652, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.846, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.29020556227327693, | |
| "grad_norm": 0.07450445741415024, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.8475, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.309552599758162, | |
| "grad_norm": 0.07736336439847946, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.8485, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.32889963724304716, | |
| "grad_norm": 0.07044591009616852, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.821, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3482466747279323, | |
| "grad_norm": 0.07502790540456772, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.8704, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3675937122128174, | |
| "grad_norm": 0.07411929965019226, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.8795, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.38694074969770254, | |
| "grad_norm": 0.0694892555475235, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.854, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4062877871825877, | |
| "grad_norm": 0.06586502492427826, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.8269, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.42563482466747277, | |
| "grad_norm": 0.07531369477510452, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.8258, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.4449818621523579, | |
| "grad_norm": 0.11515411734580994, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.742, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.46432889963724305, | |
| "grad_norm": 0.1324297934770584, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.6325, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.4836759371221282, | |
| "grad_norm": 0.2353169023990631, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.2448, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4836759371221282, | |
| "eval_loss": 0.7837062478065491, | |
| "eval_runtime": 11.3984, | |
| "eval_samples_per_second": 30.618, | |
| "eval_steps_per_second": 3.86, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5030229746070133, | |
| "grad_norm": 0.07031340897083282, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7878, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.5223700120918985, | |
| "grad_norm": 0.07707154750823975, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.786, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.5417170495767836, | |
| "grad_norm": 0.0745035782456398, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.9134, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.5610640870616687, | |
| "grad_norm": 0.06669345498085022, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.8154, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.5804111245465539, | |
| "grad_norm": 0.0690491795539856, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.8274, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.599758162031439, | |
| "grad_norm": 0.07264308631420135, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.8744, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.619105199516324, | |
| "grad_norm": 0.07223401218652725, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.9257, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.6384522370012092, | |
| "grad_norm": 0.0706273689866066, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.9225, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.6577992744860943, | |
| "grad_norm": 0.07520892471075058, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.9234, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.6771463119709794, | |
| "grad_norm": 0.08015627413988113, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.8068, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.6964933494558646, | |
| "grad_norm": 0.09883278608322144, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.6502, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.7158403869407497, | |
| "grad_norm": 0.1318332403898239, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.4271, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.7351874244256348, | |
| "grad_norm": 0.08774442225694656, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.7714, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.75453446191052, | |
| "grad_norm": 0.06477252393960953, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.8214, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.7738814993954051, | |
| "grad_norm": 0.0652678981423378, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.8322, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7932285368802902, | |
| "grad_norm": 0.06607598066329956, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.8466, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.8125755743651754, | |
| "grad_norm": 0.06954794377088547, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.882, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.8319226118500604, | |
| "grad_norm": 0.07791940122842789, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.9292, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.8512696493349455, | |
| "grad_norm": 0.07262781262397766, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.8562, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.8706166868198307, | |
| "grad_norm": 0.070536307990551, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.8477, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.8899637243047158, | |
| "grad_norm": 0.0720757469534874, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.896, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.909310761789601, | |
| "grad_norm": 0.07141188532114029, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.7931, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.9286577992744861, | |
| "grad_norm": 0.08638662099838257, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.7604, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.9480048367593712, | |
| "grad_norm": 0.10718564689159393, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.5603, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.9673518742442564, | |
| "grad_norm": 0.21608486771583557, | |
| "learning_rate": 0.0, | |
| "loss": 0.2008, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.9673518742442564, | |
| "eval_loss": 0.7657374739646912, | |
| "eval_runtime": 11.6416, | |
| "eval_samples_per_second": 29.979, | |
| "eval_steps_per_second": 3.78, | |
| "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": 5.991379090433638e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |