| { | |
| "best_metric": 0.9942613244056702, | |
| "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": 1.285041093826294, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3212, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008238928939237899, | |
| "eval_loss": 1.754696011543274, | |
| "eval_runtime": 57.0263, | |
| "eval_samples_per_second": 14.344, | |
| "eval_steps_per_second": 1.806, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.016477857878475798, | |
| "grad_norm": 1.0165727138519287, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5153, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.024716786817713696, | |
| "grad_norm": 0.9726688265800476, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.9716, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.032955715756951595, | |
| "grad_norm": 0.4960082769393921, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.1878, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0411946446961895, | |
| "grad_norm": 0.518202006816864, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.2005, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04943357363542739, | |
| "grad_norm": 0.5391622185707092, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.1447, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.057672502574665295, | |
| "grad_norm": 0.43155014514923096, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.1931, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06591143151390319, | |
| "grad_norm": 0.3879729211330414, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.2691, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07415036045314109, | |
| "grad_norm": 0.3610127568244934, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.4065, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.082389289392379, | |
| "grad_norm": 0.4237038791179657, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.5679, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09062821833161688, | |
| "grad_norm": 0.6687376499176025, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.8561, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.09886714727085479, | |
| "grad_norm": 3.46882963180542, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.7443, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.10710607621009269, | |
| "grad_norm": 2.3832569122314453, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.9835, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.11534500514933059, | |
| "grad_norm": 1.5324733257293701, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.0203, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.12358393408856849, | |
| "grad_norm": 0.7405157685279846, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.4499, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.13182286302780638, | |
| "grad_norm": 0.3928067088127136, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.6033, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1400617919670443, | |
| "grad_norm": 0.4208212196826935, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.0389, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.14830072090628219, | |
| "grad_norm": 0.37482503056526184, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.0651, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.15653964984552007, | |
| "grad_norm": 0.39850133657455444, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.0933, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.164778578784758, | |
| "grad_norm": 0.3676826059818268, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.1298, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.17301750772399588, | |
| "grad_norm": 0.29273325204849243, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.2501, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.18125643666323377, | |
| "grad_norm": 0.38638484477996826, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.3895, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.18949536560247168, | |
| "grad_norm": 0.5108461976051331, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.541, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.19773429454170957, | |
| "grad_norm": 1.4381290674209595, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.7898, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2059732234809475, | |
| "grad_norm": 4.901559829711914, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.4978, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2059732234809475, | |
| "eval_loss": 1.097769021987915, | |
| "eval_runtime": 55.7383, | |
| "eval_samples_per_second": 14.676, | |
| "eval_steps_per_second": 1.848, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.21421215242018538, | |
| "grad_norm": 0.7587965130805969, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5869, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.22245108135942326, | |
| "grad_norm": 1.1132606267929077, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.675, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.23069001029866118, | |
| "grad_norm": 0.47598445415496826, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.8052, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.23892893923789907, | |
| "grad_norm": 0.21603046357631683, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.7202, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.24716786817713698, | |
| "grad_norm": 0.20677191019058228, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.9717, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2554067971163749, | |
| "grad_norm": 0.2395070493221283, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.0057, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.26364572605561276, | |
| "grad_norm": 0.29304394125938416, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.1178, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.27188465499485065, | |
| "grad_norm": 0.3763979375362396, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.2607, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2801235839340886, | |
| "grad_norm": 0.559607207775116, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.4018, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.2883625128733265, | |
| "grad_norm": 0.6080499887466431, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.4868, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.29660144181256437, | |
| "grad_norm": 0.8854095339775085, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.7051, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.30484037075180226, | |
| "grad_norm": 1.4029868841171265, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.7953, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.31307929969104015, | |
| "grad_norm": 1.171069860458374, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.0933, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3213182286302781, | |
| "grad_norm": 0.9004032015800476, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.4541, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.329557157569516, | |
| "grad_norm": 0.4076178967952728, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.503, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.33779608650875387, | |
| "grad_norm": 0.3803941011428833, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.5107, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.34603501544799176, | |
| "grad_norm": 0.1711903065443039, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.9551, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.35427394438722964, | |
| "grad_norm": 0.17743289470672607, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.0498, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.36251287332646753, | |
| "grad_norm": 0.19017276167869568, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.0787, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.3707518022657055, | |
| "grad_norm": 0.16853924095630646, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.0387, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.37899073120494337, | |
| "grad_norm": 0.21631433069705963, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.246, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.38722966014418125, | |
| "grad_norm": 0.29879626631736755, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.3496, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.39546858908341914, | |
| "grad_norm": 0.5076752305030823, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.6251, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.40370751802265703, | |
| "grad_norm": 0.8596004247665405, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.7919, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.411946446961895, | |
| "grad_norm": 3.706777572631836, | |
| "learning_rate": 0.0, | |
| "loss": 1.6232, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.411946446961895, | |
| "eval_loss": 0.9942613244056702, | |
| "eval_runtime": 56.5648, | |
| "eval_samples_per_second": 14.461, | |
| "eval_steps_per_second": 1.821, | |
| "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 | |
| } | |