| { | |
| "best_metric": 0.986032247543335, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.411946446961895, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008238928939237899, | |
| "grad_norm": 1.3493034839630127, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3213, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008238928939237899, | |
| "eval_loss": 1.754831314086914, | |
| "eval_runtime": 28.9839, | |
| "eval_samples_per_second": 28.223, | |
| "eval_steps_per_second": 3.554, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.016477857878475798, | |
| "grad_norm": 1.0823650360107422, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5151, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.024716786817713696, | |
| "grad_norm": 1.0006831884384155, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.9711, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.032955715756951595, | |
| "grad_norm": 0.5157923102378845, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.1883, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0411946446961895, | |
| "grad_norm": 0.5396899580955505, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.2001, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04943357363542739, | |
| "grad_norm": 0.5691497921943665, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.1429, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.057672502574665295, | |
| "grad_norm": 0.4316560626029968, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.1932, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06591143151390319, | |
| "grad_norm": 0.38552603125572205, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.2687, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07415036045314109, | |
| "grad_norm": 0.3694867491722107, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.4062, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.082389289392379, | |
| "grad_norm": 0.4373791515827179, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.569, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09062821833161688, | |
| "grad_norm": 0.7083751559257507, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.857, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.09886714727085479, | |
| "grad_norm": 3.521287441253662, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.7373, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.10710607621009269, | |
| "grad_norm": 2.4093360900878906, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.9829, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.11534500514933059, | |
| "grad_norm": 1.6218130588531494, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.0176, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.12358393408856849, | |
| "grad_norm": 0.743577778339386, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.4495, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.13182286302780638, | |
| "grad_norm": 0.3841581344604492, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.6022, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1400617919670443, | |
| "grad_norm": 0.40283846855163574, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.036, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.14830072090628219, | |
| "grad_norm": 0.3529587388038635, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.0628, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.15653964984552007, | |
| "grad_norm": 0.3646421432495117, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.0915, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.164778578784758, | |
| "grad_norm": 0.3263953924179077, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.1286, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.17301750772399588, | |
| "grad_norm": 0.296126127243042, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.2489, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.18125643666323377, | |
| "grad_norm": 0.3966723084449768, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.3886, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.18949536560247168, | |
| "grad_norm": 0.4947672486305237, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.5394, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.19773429454170957, | |
| "grad_norm": 1.0129477977752686, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.7833, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2059732234809475, | |
| "grad_norm": 4.30376672744751, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.4598, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2059732234809475, | |
| "eval_loss": 1.0918176174163818, | |
| "eval_runtime": 27.4744, | |
| "eval_samples_per_second": 29.773, | |
| "eval_steps_per_second": 3.749, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.21421215242018538, | |
| "grad_norm": 0.7323720455169678, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5897, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.22245108135942326, | |
| "grad_norm": 1.0876057147979736, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.6764, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.23069001029866118, | |
| "grad_norm": 0.4686364531517029, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.8033, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.23892893923789907, | |
| "grad_norm": 0.22451618313789368, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.7197, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.24716786817713698, | |
| "grad_norm": 0.20337329804897308, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.9707, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2554067971163749, | |
| "grad_norm": 0.22543476521968842, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.0043, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.26364572605561276, | |
| "grad_norm": 0.27064037322998047, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.1156, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.27188465499485065, | |
| "grad_norm": 0.32793888449668884, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.2575, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2801235839340886, | |
| "grad_norm": 0.49145063757896423, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.3977, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.2883625128733265, | |
| "grad_norm": 0.5390352010726929, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.4835, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.29660144181256437, | |
| "grad_norm": 0.8575440049171448, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.6991, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.30484037075180226, | |
| "grad_norm": 1.5018357038497925, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.7517, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.31307929969104015, | |
| "grad_norm": 1.204730749130249, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.0741, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3213182286302781, | |
| "grad_norm": 0.9195225834846497, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.4584, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.329557157569516, | |
| "grad_norm": 0.4034794569015503, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.5015, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.33779608650875387, | |
| "grad_norm": 0.39492160081863403, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.5094, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.34603501544799176, | |
| "grad_norm": 0.17655304074287415, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.9547, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.35427394438722964, | |
| "grad_norm": 0.17320753633975983, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.0494, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.36251287332646753, | |
| "grad_norm": 0.19076572358608246, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.0784, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.3707518022657055, | |
| "grad_norm": 0.17125385999679565, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.0381, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.37899073120494337, | |
| "grad_norm": 0.22827577590942383, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.245, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.38722966014418125, | |
| "grad_norm": 0.2971423268318176, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.3483, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.39546858908341914, | |
| "grad_norm": 0.5259574055671692, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.6239, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.40370751802265703, | |
| "grad_norm": 0.8611096739768982, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.7759, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.411946446961895, | |
| "grad_norm": 3.794422149658203, | |
| "learning_rate": 0.0, | |
| "loss": 1.5341, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.411946446961895, | |
| "eval_loss": 0.986032247543335, | |
| "eval_runtime": 27.9322, | |
| "eval_samples_per_second": 29.285, | |
| "eval_steps_per_second": 3.688, | |
| "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": 6.04008059433386e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |