| { | |
| "best_metric": 0.03805486857891083, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.7241379310344827, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.034482758620689655, | |
| "grad_norm": 1.4216771125793457, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0848, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.034482758620689655, | |
| "eval_loss": 2.39210844039917, | |
| "eval_runtime": 3.4427, | |
| "eval_samples_per_second": 56.642, | |
| "eval_steps_per_second": 7.262, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06896551724137931, | |
| "grad_norm": 1.793097734451294, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3579, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.10344827586206896, | |
| "grad_norm": 2.1383931636810303, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.5464, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.13793103448275862, | |
| "grad_norm": 2.577606201171875, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.4512, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.1724137931034483, | |
| "grad_norm": 3.3274736404418945, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.4088, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.20689655172413793, | |
| "grad_norm": 4.567131996154785, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.3443, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2413793103448276, | |
| "grad_norm": 8.802882194519043, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.0981, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.27586206896551724, | |
| "grad_norm": 1.5518375635147095, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.2706, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3103448275862069, | |
| "grad_norm": 1.1802548170089722, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.2011, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3448275862068966, | |
| "grad_norm": 1.9773248434066772, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.1956, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3793103448275862, | |
| "grad_norm": 1.288611650466919, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.1279, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.41379310344827586, | |
| "grad_norm": 1.271929383277893, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.1268, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.4482758620689655, | |
| "grad_norm": 1.3614544868469238, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.1349, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.4827586206896552, | |
| "grad_norm": 2.7347893714904785, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.3473, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5172413793103449, | |
| "grad_norm": 0.2629777491092682, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.0693, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5517241379310345, | |
| "grad_norm": 0.35910603404045105, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.0757, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5862068965517241, | |
| "grad_norm": 0.25192520022392273, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.0367, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6206896551724138, | |
| "grad_norm": 0.3641197085380554, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0517, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6551724137931034, | |
| "grad_norm": 0.5360735058784485, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.0709, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.6896551724137931, | |
| "grad_norm": 0.6334680318832397, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0734, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7241379310344828, | |
| "grad_norm": 3.1821346282958984, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.3172, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.7586206896551724, | |
| "grad_norm": 0.24157719314098358, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.0423, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.7931034482758621, | |
| "grad_norm": 0.15495705604553223, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0303, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.8275862068965517, | |
| "grad_norm": 0.27805107831954956, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.027, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.8620689655172413, | |
| "grad_norm": 0.37765341997146606, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.0363, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8620689655172413, | |
| "eval_loss": 0.05587536096572876, | |
| "eval_runtime": 3.4435, | |
| "eval_samples_per_second": 56.629, | |
| "eval_steps_per_second": 7.26, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.896551724137931, | |
| "grad_norm": 0.3312021791934967, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0124, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.9310344827586207, | |
| "grad_norm": 0.46960943937301636, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.0381, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.9655172413793104, | |
| "grad_norm": 1.4453366994857788, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.1324, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.372202068567276, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0386, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.0344827586206897, | |
| "grad_norm": 0.1700638085603714, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.023, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0689655172413792, | |
| "grad_norm": 0.18088839948177338, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.0189, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.103448275862069, | |
| "grad_norm": 0.1496821790933609, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0136, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.1379310344827587, | |
| "grad_norm": 0.2612413465976715, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.029, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.1724137931034484, | |
| "grad_norm": 0.26097986102104187, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0222, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.206896551724138, | |
| "grad_norm": 0.1584685891866684, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0124, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.2413793103448276, | |
| "grad_norm": 0.7986224889755249, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.113, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.2758620689655173, | |
| "grad_norm": 0.12980884313583374, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.0224, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.3103448275862069, | |
| "grad_norm": 0.08840180188417435, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0153, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.3448275862068966, | |
| "grad_norm": 0.19424304366111755, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.0212, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.3793103448275863, | |
| "grad_norm": 0.1392383873462677, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.011, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.4137931034482758, | |
| "grad_norm": 0.16765029728412628, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0189, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.4482758620689655, | |
| "grad_norm": 0.22004911303520203, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0218, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.4827586206896552, | |
| "grad_norm": 1.6118639707565308, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.0886, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.5172413793103448, | |
| "grad_norm": 0.18371054530143738, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0234, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.5517241379310345, | |
| "grad_norm": 0.18104659020900726, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.0233, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.5862068965517242, | |
| "grad_norm": 0.13094978034496307, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0115, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.6206896551724137, | |
| "grad_norm": 0.12079468369483948, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0153, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.6551724137931034, | |
| "grad_norm": 0.2212318331003189, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0227, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.6896551724137931, | |
| "grad_norm": 0.24219997227191925, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.0172, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.7241379310344827, | |
| "grad_norm": 0.7112542390823364, | |
| "learning_rate": 0.0, | |
| "loss": 0.0526, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.7241379310344827, | |
| "eval_loss": 0.03805486857891083, | |
| "eval_runtime": 3.4427, | |
| "eval_samples_per_second": 56.642, | |
| "eval_steps_per_second": 7.262, | |
| "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": 2.229252309123072e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |