| { | |
| "best_metric": 1.2570868730545044, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.06623064823246957, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013246129646493916, | |
| "grad_norm": 1.6896806955337524, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8853, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013246129646493916, | |
| "eval_loss": 2.9228813648223877, | |
| "eval_runtime": 104.7571, | |
| "eval_samples_per_second": 48.55, | |
| "eval_steps_per_second": 6.071, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002649225929298783, | |
| "grad_norm": 2.716233491897583, | |
| "learning_rate": 0.0001, | |
| "loss": 2.6317, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0039738388939481745, | |
| "grad_norm": 2.624985694885254, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.6739, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005298451858597566, | |
| "grad_norm": 2.169276714324951, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.5246, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006623064823246957, | |
| "grad_norm": 1.8879032135009766, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.3163, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007947677787896349, | |
| "grad_norm": 1.8610759973526, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.1461, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00927229075254574, | |
| "grad_norm": 1.7441582679748535, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.0269, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010596903717195133, | |
| "grad_norm": 1.4809761047363281, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.9799, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.011921516681844524, | |
| "grad_norm": 1.6304855346679688, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.785, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013246129646493915, | |
| "grad_norm": 1.3047534227371216, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.76, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014570742611143307, | |
| "grad_norm": 1.04607093334198, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.8074, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.015895355575792698, | |
| "grad_norm": 0.9902725219726562, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.8008, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01721996854044209, | |
| "grad_norm": 1.4731831550598145, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.3515, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01854458150509148, | |
| "grad_norm": 1.0245866775512695, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.5224, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01986919446974087, | |
| "grad_norm": 0.9316340088844299, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.5249, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.021193807434390265, | |
| "grad_norm": 0.9975677728652954, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.4459, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.022518420399039656, | |
| "grad_norm": 0.8698291182518005, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.4791, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.023843033363689047, | |
| "grad_norm": 0.8500425219535828, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.4864, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.025167646328338438, | |
| "grad_norm": 0.8855979442596436, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.4568, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02649225929298783, | |
| "grad_norm": 0.7662312984466553, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.3977, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02781687225763722, | |
| "grad_norm": 0.8068965673446655, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.4062, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.029141485222286614, | |
| "grad_norm": 0.751783549785614, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.3403, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.030466098186936005, | |
| "grad_norm": 0.7751783132553101, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.3394, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.031790711151585396, | |
| "grad_norm": 0.9629535675048828, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.5133, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03311532411623479, | |
| "grad_norm": 1.074066162109375, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.7629, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03311532411623479, | |
| "eval_loss": 1.3527735471725464, | |
| "eval_runtime": 104.8313, | |
| "eval_samples_per_second": 48.516, | |
| "eval_steps_per_second": 6.067, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03443993708088418, | |
| "grad_norm": 0.928752064704895, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1759, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03576455004553357, | |
| "grad_norm": 1.1340597867965698, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.2971, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03708916301018296, | |
| "grad_norm": 0.986423134803772, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.3528, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03841377597483235, | |
| "grad_norm": 0.8538538813591003, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.2289, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03973838893948174, | |
| "grad_norm": 0.7311115264892578, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.2389, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04106300190413114, | |
| "grad_norm": 0.7120617032051086, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.2412, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.04238761486878053, | |
| "grad_norm": 0.829824686050415, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.1946, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.04371222783342992, | |
| "grad_norm": 0.8339101672172546, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.2097, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.04503684079807931, | |
| "grad_norm": 0.8611684441566467, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.1734, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.046361453762728703, | |
| "grad_norm": 0.807828426361084, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.0594, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.047686066727378094, | |
| "grad_norm": 1.0561130046844482, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.4825, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.049010679692027485, | |
| "grad_norm": 1.1005446910858154, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.5086, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.050335292656676876, | |
| "grad_norm": 0.780189573764801, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.1526, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.05165990562132627, | |
| "grad_norm": 0.6735148429870605, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.3142, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.05298451858597566, | |
| "grad_norm": 0.8071457147598267, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.2842, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05430913155062505, | |
| "grad_norm": 0.7985179424285889, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.209, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.05563374451527444, | |
| "grad_norm": 0.7388365268707275, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.1442, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.05695835747992384, | |
| "grad_norm": 0.8493674993515015, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.2623, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.05828297044457323, | |
| "grad_norm": 0.7348306179046631, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.2582, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.05960758340922262, | |
| "grad_norm": 0.7038648724555969, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.1963, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06093219637387201, | |
| "grad_norm": 0.6773378252983093, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.0985, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0622568093385214, | |
| "grad_norm": 0.7034523487091064, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.1289, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.06358142230317079, | |
| "grad_norm": 0.6909533143043518, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.1907, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06490603526782018, | |
| "grad_norm": 0.6846153140068054, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.3057, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06623064823246957, | |
| "grad_norm": 0.9431920647621155, | |
| "learning_rate": 0.0, | |
| "loss": 1.5908, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06623064823246957, | |
| "eval_loss": 1.2570868730545044, | |
| "eval_runtime": 104.7765, | |
| "eval_samples_per_second": 48.541, | |
| "eval_steps_per_second": 6.07, | |
| "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": 8.33416392081408e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |