| { | |
| "best_metric": 2.109326124191284, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.47904191616766467, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009580838323353293, | |
| "grad_norm": 7.405320167541504, | |
| "learning_rate": 5e-05, | |
| "loss": 8.6281, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009580838323353293, | |
| "eval_loss": 11.436592102050781, | |
| "eval_runtime": 21.3842, | |
| "eval_samples_per_second": 32.922, | |
| "eval_steps_per_second": 4.115, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.019161676646706587, | |
| "grad_norm": 7.524505138397217, | |
| "learning_rate": 0.0001, | |
| "loss": 9.5475, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02874251497005988, | |
| "grad_norm": 7.415696144104004, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 9.8511, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03832335329341317, | |
| "grad_norm": 7.415373802185059, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 9.1947, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04790419161676647, | |
| "grad_norm": 9.945332527160645, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 8.3233, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05748502994011976, | |
| "grad_norm": 13.68132495880127, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 7.4047, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06706586826347305, | |
| "grad_norm": 11.933572769165039, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 5.9208, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07664670658682635, | |
| "grad_norm": 10.703195571899414, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 5.0541, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08622754491017964, | |
| "grad_norm": 11.239315032958984, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 4.8781, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09580838323353294, | |
| "grad_norm": 11.760834693908691, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 4.2, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10538922155688622, | |
| "grad_norm": 6.869015693664551, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 3.9251, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.11497005988023952, | |
| "grad_norm": 10.173572540283203, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 4.2657, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.12455089820359282, | |
| "grad_norm": 10.54714298248291, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 3.943, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1341317365269461, | |
| "grad_norm": 10.271453857421875, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.1679, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1437125748502994, | |
| "grad_norm": 7.000523567199707, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.7939, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1532934131736527, | |
| "grad_norm": 5.851607322692871, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.5434, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.162874251497006, | |
| "grad_norm": 6.350866794586182, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.7202, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1724550898203593, | |
| "grad_norm": 6.783472061157227, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.7273, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.18203592814371258, | |
| "grad_norm": 7.375641822814941, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.7672, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.19161676646706588, | |
| "grad_norm": 7.740267276763916, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.5563, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.20119760479041915, | |
| "grad_norm": 5.512790679931641, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.4768, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.21077844311377245, | |
| "grad_norm": 6.499993801116943, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.4548, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.22035928143712574, | |
| "grad_norm": 7.227408409118652, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 2.6491, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.22994011976047904, | |
| "grad_norm": 6.21389102935791, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.5929, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.23952095808383234, | |
| "grad_norm": 8.077735900878906, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.9135, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.23952095808383234, | |
| "eval_loss": 2.492065906524658, | |
| "eval_runtime": 21.3669, | |
| "eval_samples_per_second": 32.948, | |
| "eval_steps_per_second": 4.119, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.24910179640718563, | |
| "grad_norm": 6.6661577224731445, | |
| "learning_rate": 5e-05, | |
| "loss": 2.0216, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.25868263473053893, | |
| "grad_norm": 6.830226898193359, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 2.2535, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.2682634730538922, | |
| "grad_norm": 5.6001410484313965, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 2.0359, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.2778443113772455, | |
| "grad_norm": 5.429553985595703, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 2.1816, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2874251497005988, | |
| "grad_norm": 5.00969934463501, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.8676, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2970059880239521, | |
| "grad_norm": 6.511794567108154, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 2.1724, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.3065868263473054, | |
| "grad_norm": 6.313398838043213, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.0962, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.3161676646706587, | |
| "grad_norm": 5.252542018890381, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.9694, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.325748502994012, | |
| "grad_norm": 6.663439750671387, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.3892, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.33532934131736525, | |
| "grad_norm": 6.385496139526367, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 2.2523, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3449101796407186, | |
| "grad_norm": 7.271178722381592, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 2.374, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.35449101796407184, | |
| "grad_norm": 7.476476192474365, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 2.754, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.36407185628742517, | |
| "grad_norm": 5.532874584197998, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.0447, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.37365269461077844, | |
| "grad_norm": 3.851936101913452, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.6564, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.38323353293413176, | |
| "grad_norm": 3.787240743637085, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.9061, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.39281437125748503, | |
| "grad_norm": 4.067002296447754, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.9444, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.4023952095808383, | |
| "grad_norm": 4.330122470855713, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.7166, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.4119760479041916, | |
| "grad_norm": 4.514286518096924, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.8661, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.4215568862275449, | |
| "grad_norm": 4.644809246063232, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.9604, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.4311377245508982, | |
| "grad_norm": 4.697016716003418, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.9133, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.4407185628742515, | |
| "grad_norm": 4.961589336395264, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.8272, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.4502994011976048, | |
| "grad_norm": 4.9489665031433105, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 2.0222, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.4598802395209581, | |
| "grad_norm": 5.845571517944336, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 2.2451, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.4694610778443114, | |
| "grad_norm": 5.190147876739502, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 2.4345, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.47904191616766467, | |
| "grad_norm": 9.36916732788086, | |
| "learning_rate": 0.0, | |
| "loss": 2.7436, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.47904191616766467, | |
| "eval_loss": 2.109326124191284, | |
| "eval_runtime": 21.3715, | |
| "eval_samples_per_second": 32.941, | |
| "eval_steps_per_second": 4.118, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |