| { | |
| "best_metric": 2.433828830718994, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 3.011204481792717, | |
| "eval_steps": 50, | |
| "global_step": 67, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04481792717086835, | |
| "grad_norm": 25.642864227294922, | |
| "learning_rate": 5e-06, | |
| "loss": 10.3377, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04481792717086835, | |
| "eval_loss": 10.295247077941895, | |
| "eval_runtime": 1.1874, | |
| "eval_samples_per_second": 252.661, | |
| "eval_steps_per_second": 16.002, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0896358543417367, | |
| "grad_norm": 25.922531127929688, | |
| "learning_rate": 1e-05, | |
| "loss": 10.223, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.13445378151260504, | |
| "grad_norm": 25.65165138244629, | |
| "learning_rate": 1.5e-05, | |
| "loss": 10.2814, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1792717086834734, | |
| "grad_norm": 25.051061630249023, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3075, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.22408963585434175, | |
| "grad_norm": 27.376066207885742, | |
| "learning_rate": 2.5e-05, | |
| "loss": 10.079, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2689075630252101, | |
| "grad_norm": 28.760995864868164, | |
| "learning_rate": 3e-05, | |
| "loss": 9.866, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3137254901960784, | |
| "grad_norm": 30.537446975708008, | |
| "learning_rate": 3.5e-05, | |
| "loss": 9.6662, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3585434173669468, | |
| "grad_norm": 31.815292358398438, | |
| "learning_rate": 4e-05, | |
| "loss": 9.3129, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.40336134453781514, | |
| "grad_norm": 30.294048309326172, | |
| "learning_rate": 4.5e-05, | |
| "loss": 9.0616, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.4481792717086835, | |
| "grad_norm": 27.685863494873047, | |
| "learning_rate": 5e-05, | |
| "loss": 8.6176, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.49299719887955185, | |
| "grad_norm": 30.450334548950195, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 8.2255, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.5378151260504201, | |
| "grad_norm": 26.99419403076172, | |
| "learning_rate": 6e-05, | |
| "loss": 7.785, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5826330532212886, | |
| "grad_norm": 25.451345443725586, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 7.3677, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.6274509803921569, | |
| "grad_norm": 19.89314079284668, | |
| "learning_rate": 7e-05, | |
| "loss": 7.0903, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.6722689075630253, | |
| "grad_norm": 17.851165771484375, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 6.638, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.7170868347338936, | |
| "grad_norm": 17.867111206054688, | |
| "learning_rate": 8e-05, | |
| "loss": 6.256, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.7619047619047619, | |
| "grad_norm": 15.737651824951172, | |
| "learning_rate": 8.5e-05, | |
| "loss": 5.9234, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.8067226890756303, | |
| "grad_norm": 13.73977279663086, | |
| "learning_rate": 9e-05, | |
| "loss": 5.9018, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.8515406162464986, | |
| "grad_norm": 13.81631088256836, | |
| "learning_rate": 9.5e-05, | |
| "loss": 5.4379, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.896358543417367, | |
| "grad_norm": 13.534049034118652, | |
| "learning_rate": 0.0001, | |
| "loss": 5.0785, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.9411764705882353, | |
| "grad_norm": 13.347393989562988, | |
| "learning_rate": 9.988834393115767e-05, | |
| "loss": 4.7373, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.9859943977591037, | |
| "grad_norm": 13.346118927001953, | |
| "learning_rate": 9.9553874407739e-05, | |
| "loss": 4.534, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.0336134453781514, | |
| "grad_norm": 23.33193588256836, | |
| "learning_rate": 9.899808525182935e-05, | |
| "loss": 7.0157, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.0784313725490196, | |
| "grad_norm": 13.095778465270996, | |
| "learning_rate": 9.822345875271883e-05, | |
| "loss": 4.0933, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.123249299719888, | |
| "grad_norm": 11.095013618469238, | |
| "learning_rate": 9.723345458039594e-05, | |
| "loss": 3.4608, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.1680672268907564, | |
| "grad_norm": 9.79887580871582, | |
| "learning_rate": 9.603249433382144e-05, | |
| "loss": 3.7063, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.2128851540616246, | |
| "grad_norm": 7.285381317138672, | |
| "learning_rate": 9.462594179299406e-05, | |
| "loss": 4.121, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.257703081232493, | |
| "grad_norm": 5.901654243469238, | |
| "learning_rate": 9.302007896300698e-05, | |
| "loss": 2.883, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.3025210084033614, | |
| "grad_norm": 5.953999996185303, | |
| "learning_rate": 9.122207801708802e-05, | |
| "loss": 2.8394, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.3473389355742298, | |
| "grad_norm": 4.182607650756836, | |
| "learning_rate": 8.923996926393305e-05, | |
| "loss": 2.7042, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.392156862745098, | |
| "grad_norm": 3.3463335037231445, | |
| "learning_rate": 8.708260528239788e-05, | |
| "loss": 3.0285, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.4369747899159664, | |
| "grad_norm": 3.1249260902404785, | |
| "learning_rate": 8.475962138373213e-05, | |
| "loss": 2.7339, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.4817927170868348, | |
| "grad_norm": 2.7283530235290527, | |
| "learning_rate": 8.228139257794012e-05, | |
| "loss": 2.7393, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.526610644257703, | |
| "grad_norm": 2.110501527786255, | |
| "learning_rate": 7.965898723646776e-05, | |
| "loss": 2.7651, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.5714285714285714, | |
| "grad_norm": 2.313706874847412, | |
| "learning_rate": 7.690411765816864e-05, | |
| "loss": 2.718, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.6162464985994398, | |
| "grad_norm": 2.0307371616363525, | |
| "learning_rate": 7.402908775933419e-05, | |
| "loss": 2.8055, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.661064425770308, | |
| "grad_norm": 1.9101359844207764, | |
| "learning_rate": 7.104673812141675e-05, | |
| "loss": 2.8809, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.7058823529411766, | |
| "grad_norm": 1.9070402383804321, | |
| "learning_rate": 6.797038864187564e-05, | |
| "loss": 2.8126, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.7507002801120448, | |
| "grad_norm": 1.455893635749817, | |
| "learning_rate": 6.481377904428171e-05, | |
| "loss": 2.4823, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.795518207282913, | |
| "grad_norm": 1.853187918663025, | |
| "learning_rate": 6.159100751337642e-05, | |
| "loss": 2.6832, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.8403361344537816, | |
| "grad_norm": 1.4273921251296997, | |
| "learning_rate": 5.831646772915651e-05, | |
| "loss": 2.5476, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.8851540616246498, | |
| "grad_norm": 1.2385693788528442, | |
| "learning_rate": 5.5004784581204927e-05, | |
| "loss": 2.4887, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.9299719887955182, | |
| "grad_norm": 1.0763683319091797, | |
| "learning_rate": 5.167074885038373e-05, | |
| "loss": 2.5657, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.9747899159663866, | |
| "grad_norm": 1.6198722124099731, | |
| "learning_rate": 4.832925114961629e-05, | |
| "loss": 3.0987, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.022408963585434, | |
| "grad_norm": 2.0531015396118164, | |
| "learning_rate": 4.4995215418795085e-05, | |
| "loss": 4.2895, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.0672268907563027, | |
| "grad_norm": 1.1228376626968384, | |
| "learning_rate": 4.1683532270843504e-05, | |
| "loss": 2.7512, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.112044817927171, | |
| "grad_norm": 2.324376344680786, | |
| "learning_rate": 3.840899248662358e-05, | |
| "loss": 3.5319, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.156862745098039, | |
| "grad_norm": 1.4633479118347168, | |
| "learning_rate": 3.5186220955718306e-05, | |
| "loss": 2.5993, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.2016806722689077, | |
| "grad_norm": 1.424329161643982, | |
| "learning_rate": 3.202961135812437e-05, | |
| "loss": 2.6048, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.246498599439776, | |
| "grad_norm": 1.2687908411026, | |
| "learning_rate": 2.895326187858326e-05, | |
| "loss": 2.4032, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.246498599439776, | |
| "eval_loss": 2.433828830718994, | |
| "eval_runtime": 1.1804, | |
| "eval_samples_per_second": 254.153, | |
| "eval_steps_per_second": 16.096, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.291316526610644, | |
| "grad_norm": 1.2064857482910156, | |
| "learning_rate": 2.5970912240665813e-05, | |
| "loss": 2.4134, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.3361344537815127, | |
| "grad_norm": 1.254510760307312, | |
| "learning_rate": 2.3095882341831372e-05, | |
| "loss": 2.4845, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.380952380952381, | |
| "grad_norm": 1.4852594137191772, | |
| "learning_rate": 2.0341012763532243e-05, | |
| "loss": 2.4392, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.425770308123249, | |
| "grad_norm": 0.9326648116111755, | |
| "learning_rate": 1.771860742205988e-05, | |
| "loss": 2.422, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.4705882352941178, | |
| "grad_norm": 1.0687801837921143, | |
| "learning_rate": 1.5240378616267886e-05, | |
| "loss": 2.3847, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.515406162464986, | |
| "grad_norm": 0.8696810007095337, | |
| "learning_rate": 1.2917394717602121e-05, | |
| "loss": 2.3407, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.560224089635854, | |
| "grad_norm": 1.5607281923294067, | |
| "learning_rate": 1.0760030736066951e-05, | |
| "loss": 2.9372, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.6050420168067228, | |
| "grad_norm": 1.2624620199203491, | |
| "learning_rate": 8.777921982911996e-06, | |
| "loss": 2.5201, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.649859943977591, | |
| "grad_norm": 1.4880586862564087, | |
| "learning_rate": 6.979921036993042e-06, | |
| "loss": 2.9394, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.6946778711484596, | |
| "grad_norm": 0.8246588706970215, | |
| "learning_rate": 5.374058207005944e-06, | |
| "loss": 2.3346, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.7394957983193278, | |
| "grad_norm": 1.5645203590393066, | |
| "learning_rate": 3.967505666178556e-06, | |
| "loss": 2.7406, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.784313725490196, | |
| "grad_norm": 1.2056126594543457, | |
| "learning_rate": 2.7665454196040664e-06, | |
| "loss": 2.396, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.8291316526610646, | |
| "grad_norm": 2.0966439247131348, | |
| "learning_rate": 1.7765412472811771e-06, | |
| "loss": 3.1009, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.8739495798319328, | |
| "grad_norm": 0.9577468633651733, | |
| "learning_rate": 1.0019147481706625e-06, | |
| "loss": 2.4537, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.918767507002801, | |
| "grad_norm": 1.0243852138519287, | |
| "learning_rate": 4.461255922609986e-07, | |
| "loss": 2.4703, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.9635854341736696, | |
| "grad_norm": 1.1177788972854614, | |
| "learning_rate": 1.1165606884234181e-07, | |
| "loss": 2.6208, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 3.011204481792717, | |
| "grad_norm": 3.6235415935516357, | |
| "learning_rate": 0.0, | |
| "loss": 4.9354, | |
| "step": 67 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 67, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": 701219513303040.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |