| { | |
| "best_metric": 0.7424139976501465, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.07923930269413629, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001584786053882726, | |
| "grad_norm": 2.344426393508911, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 3.1155, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001584786053882726, | |
| "eval_loss": 4.5734944343566895, | |
| "eval_runtime": 3.2337, | |
| "eval_samples_per_second": 15.462, | |
| "eval_steps_per_second": 4.02, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003169572107765452, | |
| "grad_norm": 1.989837884902954, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 3.0433, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004754358161648178, | |
| "grad_norm": 2.0686755180358887, | |
| "learning_rate": 0.0001, | |
| "loss": 3.0158, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006339144215530904, | |
| "grad_norm": 2.5443685054779053, | |
| "learning_rate": 9.997376600647783e-05, | |
| "loss": 2.9057, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00792393026941363, | |
| "grad_norm": 2.039285659790039, | |
| "learning_rate": 9.989509461357426e-05, | |
| "loss": 2.3574, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009508716323296355, | |
| "grad_norm": 2.248792886734009, | |
| "learning_rate": 9.976407754861426e-05, | |
| "loss": 2.1331, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011093502377179081, | |
| "grad_norm": 1.847161889076233, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 1.762, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.012678288431061807, | |
| "grad_norm": 2.0366954803466797, | |
| "learning_rate": 9.934567829727386e-05, | |
| "loss": 1.6532, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.014263074484944533, | |
| "grad_norm": 2.5140931606292725, | |
| "learning_rate": 9.905878394570453e-05, | |
| "loss": 1.4923, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01584786053882726, | |
| "grad_norm": 2.7745964527130127, | |
| "learning_rate": 9.872051902290737e-05, | |
| "loss": 1.0749, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.017432646592709985, | |
| "grad_norm": 2.2155520915985107, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 0.9472, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01901743264659271, | |
| "grad_norm": 3.2750940322875977, | |
| "learning_rate": 9.789151450663723e-05, | |
| "loss": 1.2059, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.020602218700475437, | |
| "grad_norm": 7.851731777191162, | |
| "learning_rate": 9.740174149534693e-05, | |
| "loss": 1.2002, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.022187004754358162, | |
| "grad_norm": 2.0609889030456543, | |
| "learning_rate": 9.686252995020249e-05, | |
| "loss": 1.0557, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.02377179080824089, | |
| "grad_norm": 1.621334433555603, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 0.8744, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.025356576862123614, | |
| "grad_norm": 1.06352961063385, | |
| "learning_rate": 9.563836295460398e-05, | |
| "loss": 0.9567, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.02694136291600634, | |
| "grad_norm": 1.0080907344818115, | |
| "learning_rate": 9.495483482810688e-05, | |
| "loss": 0.9841, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.028526148969889066, | |
| "grad_norm": 1.0307260751724243, | |
| "learning_rate": 9.422472115147382e-05, | |
| "loss": 0.8911, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.030110935023771792, | |
| "grad_norm": 0.9563176035881042, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 0.8358, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03169572107765452, | |
| "grad_norm": 0.9397155046463013, | |
| "learning_rate": 9.2628195591462e-05, | |
| "loss": 0.6939, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03328050713153724, | |
| "grad_norm": 0.9912440180778503, | |
| "learning_rate": 9.176364518546989e-05, | |
| "loss": 0.6091, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03486529318541997, | |
| "grad_norm": 0.9592384099960327, | |
| "learning_rate": 9.08562300137157e-05, | |
| "loss": 0.7451, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03645007923930269, | |
| "grad_norm": 1.3581793308258057, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 0.6801, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03803486529318542, | |
| "grad_norm": 1.7192140817642212, | |
| "learning_rate": 8.891708613973126e-05, | |
| "loss": 0.7422, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.039619651347068144, | |
| "grad_norm": 1.995835304260254, | |
| "learning_rate": 8.788761839251559e-05, | |
| "loss": 0.8001, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.039619651347068144, | |
| "eval_loss": 0.8743540048599243, | |
| "eval_runtime": 3.2909, | |
| "eval_samples_per_second": 15.193, | |
| "eval_steps_per_second": 3.95, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04120443740095087, | |
| "grad_norm": 0.7731386423110962, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.8463, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.042789223454833596, | |
| "grad_norm": 0.6917439103126526, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 0.8448, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.044374009508716325, | |
| "grad_norm": 0.6431922316551208, | |
| "learning_rate": 8.457416554680877e-05, | |
| "loss": 0.7683, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.04595879556259905, | |
| "grad_norm": 0.7308835387229919, | |
| "learning_rate": 8.339895749467238e-05, | |
| "loss": 0.9075, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.04754358161648178, | |
| "grad_norm": 1.5559896230697632, | |
| "learning_rate": 8.219063752844926e-05, | |
| "loss": 0.7099, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0491283676703645, | |
| "grad_norm": 0.7101494669914246, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 0.7386, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.05071315372424723, | |
| "grad_norm": 0.7161931991577148, | |
| "learning_rate": 7.968033420621935e-05, | |
| "loss": 0.6076, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.05229793977812995, | |
| "grad_norm": 0.7691206336021423, | |
| "learning_rate": 7.838127775159452e-05, | |
| "loss": 0.6235, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.05388272583201268, | |
| "grad_norm": 0.9122820496559143, | |
| "learning_rate": 7.705495977301078e-05, | |
| "loss": 0.7181, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0554675118858954, | |
| "grad_norm": 1.6549066305160522, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 0.7327, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.05705229793977813, | |
| "grad_norm": 2.5280091762542725, | |
| "learning_rate": 7.43267549363537e-05, | |
| "loss": 0.5369, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.058637083993660855, | |
| "grad_norm": 1.9925541877746582, | |
| "learning_rate": 7.292804904308087e-05, | |
| "loss": 0.5835, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.060221870047543584, | |
| "grad_norm": 1.2063634395599365, | |
| "learning_rate": 7.150843984658754e-05, | |
| "loss": 0.8154, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.061806656101426306, | |
| "grad_norm": 0.6842193603515625, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 0.8401, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.06339144215530904, | |
| "grad_norm": 0.6004986763000488, | |
| "learning_rate": 6.861315478964841e-05, | |
| "loss": 0.6677, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06497622820919176, | |
| "grad_norm": 0.5825014710426331, | |
| "learning_rate": 6.714085470206609e-05, | |
| "loss": 0.7524, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.06656101426307448, | |
| "grad_norm": 0.966681182384491, | |
| "learning_rate": 6.56543989209901e-05, | |
| "loss": 0.8021, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.06814580031695722, | |
| "grad_norm": 0.6058341860771179, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 0.6558, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.06973058637083994, | |
| "grad_norm": 0.730965256690979, | |
| "learning_rate": 6.264596732629e-05, | |
| "loss": 0.5955, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.07131537242472266, | |
| "grad_norm": 0.8394338488578796, | |
| "learning_rate": 6.112749920933111e-05, | |
| "loss": 0.6537, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07290015847860538, | |
| "grad_norm": 0.7698927521705627, | |
| "learning_rate": 5.960188670239154e-05, | |
| "loss": 0.7215, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.07448494453248812, | |
| "grad_norm": 1.0021368265151978, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 0.5779, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.07606973058637084, | |
| "grad_norm": 0.9064629077911377, | |
| "learning_rate": 5.653634995836856e-05, | |
| "loss": 0.4996, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.07765451664025357, | |
| "grad_norm": 1.479453682899475, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.5706, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.07923930269413629, | |
| "grad_norm": 1.81675124168396, | |
| "learning_rate": 5.346365004163145e-05, | |
| "loss": 0.6822, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07923930269413629, | |
| "eval_loss": 0.7424139976501465, | |
| "eval_runtime": 3.2822, | |
| "eval_samples_per_second": 15.234, | |
| "eval_steps_per_second": 3.961, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 95, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.32019209568256e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |