| { | |
| "best_metric": 0.9881898164749146, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.10989010989010989, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002197802197802198, | |
| "grad_norm": 0.21487364172935486, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9811, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002197802197802198, | |
| "eval_loss": 1.3610094785690308, | |
| "eval_runtime": 78.8611, | |
| "eval_samples_per_second": 38.866, | |
| "eval_steps_per_second": 4.869, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004395604395604396, | |
| "grad_norm": 0.2571617364883423, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1019, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006593406593406593, | |
| "grad_norm": 0.2487349510192871, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.0345, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008791208791208791, | |
| "grad_norm": 0.20780736207962036, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.117, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01098901098901099, | |
| "grad_norm": 0.19582928717136383, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.0173, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.013186813186813187, | |
| "grad_norm": 0.2051258385181427, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.0673, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.015384615384615385, | |
| "grad_norm": 0.23487438261508942, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.1065, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.017582417582417582, | |
| "grad_norm": 0.31598445773124695, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.0685, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01978021978021978, | |
| "grad_norm": 0.3017100393772125, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.0804, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02197802197802198, | |
| "grad_norm": 0.32337093353271484, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.1059, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.024175824175824177, | |
| "grad_norm": 0.37783730030059814, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.188, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.026373626373626374, | |
| "grad_norm": 0.6735274791717529, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.2564, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02857142857142857, | |
| "grad_norm": 0.2667316198348999, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.9144, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03076923076923077, | |
| "grad_norm": 0.26433002948760986, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.9781, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03296703296703297, | |
| "grad_norm": 0.2589879035949707, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.0107, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.035164835164835165, | |
| "grad_norm": 0.2522350251674652, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.0064, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03736263736263736, | |
| "grad_norm": 0.21559680998325348, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.0199, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03956043956043956, | |
| "grad_norm": 0.16048331558704376, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.0393, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.041758241758241756, | |
| "grad_norm": 0.18694011867046356, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.0253, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04395604395604396, | |
| "grad_norm": 0.2267119288444519, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.0112, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.046153846153846156, | |
| "grad_norm": 0.2845146358013153, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.0199, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04835164835164835, | |
| "grad_norm": 0.2891934812068939, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.042, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05054945054945055, | |
| "grad_norm": 0.2993755042552948, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.0591, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05274725274725275, | |
| "grad_norm": 0.43687695264816284, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.0165, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.054945054945054944, | |
| "grad_norm": 0.9223211407661438, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.1642, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.054945054945054944, | |
| "eval_loss": 1.0042818784713745, | |
| "eval_runtime": 78.6025, | |
| "eval_samples_per_second": 38.994, | |
| "eval_steps_per_second": 4.885, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05714285714285714, | |
| "grad_norm": 0.09768153727054596, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8227, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.05934065934065934, | |
| "grad_norm": 0.1193651407957077, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.9298, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06153846153846154, | |
| "grad_norm": 0.12479138374328613, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.9275, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.06373626373626373, | |
| "grad_norm": 0.1730612963438034, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.9792, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.06593406593406594, | |
| "grad_norm": 0.19377125799655914, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.9948, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06813186813186813, | |
| "grad_norm": 0.23251435160636902, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.0133, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.07032967032967033, | |
| "grad_norm": 0.27232635021209717, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.0032, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.07252747252747253, | |
| "grad_norm": 0.2883213460445404, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.0006, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.07472527472527472, | |
| "grad_norm": 0.32518672943115234, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.9873, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.07692307692307693, | |
| "grad_norm": 0.39549028873443604, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.0333, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.07912087912087912, | |
| "grad_norm": 0.4742918312549591, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.0452, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.08131868131868132, | |
| "grad_norm": 0.48459553718566895, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.0917, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.08351648351648351, | |
| "grad_norm": 0.12874945998191833, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.7476, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.08571428571428572, | |
| "grad_norm": 0.10771364718675613, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.92, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.08791208791208792, | |
| "grad_norm": 0.1112380102276802, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.9362, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09010989010989011, | |
| "grad_norm": 0.1193305179476738, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.9528, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.09230769230769231, | |
| "grad_norm": 0.12227167934179306, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.0025, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0945054945054945, | |
| "grad_norm": 0.1358231008052826, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.0041, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0967032967032967, | |
| "grad_norm": 0.15751737356185913, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.035, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0989010989010989, | |
| "grad_norm": 0.16361792385578156, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.9849, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1010989010989011, | |
| "grad_norm": 0.19641879200935364, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.0449, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.10329670329670329, | |
| "grad_norm": 0.22158043086528778, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.092, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.1054945054945055, | |
| "grad_norm": 0.2766644358634949, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.9987, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1076923076923077, | |
| "grad_norm": 0.3460257053375244, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.0618, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.10989010989010989, | |
| "grad_norm": 0.6922152638435364, | |
| "learning_rate": 0.0, | |
| "loss": 1.0693, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.10989010989010989, | |
| "eval_loss": 0.9881898164749146, | |
| "eval_runtime": 78.5894, | |
| "eval_samples_per_second": 39.0, | |
| "eval_steps_per_second": 4.886, | |
| "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": 5.634602943203246e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |