| { | |
| "best_metric": 0.8535917401313782, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.09740655059052722, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0019481310118105442, | |
| "grad_norm": 23.000314712524414, | |
| "learning_rate": 5e-05, | |
| "loss": 2.7164, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0019481310118105442, | |
| "eval_loss": 3.9044392108917236, | |
| "eval_runtime": 29.8355, | |
| "eval_samples_per_second": 115.902, | |
| "eval_steps_per_second": 14.513, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0038962620236210883, | |
| "grad_norm": 23.18843650817871, | |
| "learning_rate": 0.0001, | |
| "loss": 2.7355, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005844393035431633, | |
| "grad_norm": 17.209299087524414, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.6214, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007792524047242177, | |
| "grad_norm": 9.175566673278809, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.3306, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.009740655059052722, | |
| "grad_norm": 7.254579544067383, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.2872, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.011688786070863266, | |
| "grad_norm": 6.648281574249268, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.7377, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01363691708267381, | |
| "grad_norm": 3.4053423404693604, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.6466, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.015585048094484353, | |
| "grad_norm": 2.829256772994995, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.5147, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0175331791062949, | |
| "grad_norm": 4.3303608894348145, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.629, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.019481310118105444, | |
| "grad_norm": 4.374320030212402, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.602, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.021429441129915988, | |
| "grad_norm": 3.482375144958496, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.6133, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.023377572141726533, | |
| "grad_norm": 3.8871004581451416, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.3356, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.025325703153537077, | |
| "grad_norm": 2.3258163928985596, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.7787, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.02727383416534762, | |
| "grad_norm": 1.4656181335449219, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.8414, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.029221965177158162, | |
| "grad_norm": 1.4904340505599976, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.9771, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.031170096188968707, | |
| "grad_norm": 1.236912727355957, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.0273, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.033118227200779254, | |
| "grad_norm": 1.1031506061553955, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.9108, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0350663582125898, | |
| "grad_norm": 1.278933048248291, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.0385, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03701448922440034, | |
| "grad_norm": 1.6012283563613892, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.0603, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03896262023621089, | |
| "grad_norm": 1.4366340637207031, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.1865, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04091075124802143, | |
| "grad_norm": 1.5510519742965698, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.1492, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.042858882259831976, | |
| "grad_norm": 1.4250149726867676, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.2327, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.04480701327164252, | |
| "grad_norm": 2.2062790393829346, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.4777, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.046755144283453065, | |
| "grad_norm": 2.0388667583465576, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.1637, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.04870327529526361, | |
| "grad_norm": 3.433821201324463, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.7372, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04870327529526361, | |
| "eval_loss": 0.9098588824272156, | |
| "eval_runtime": 29.8515, | |
| "eval_samples_per_second": 115.84, | |
| "eval_steps_per_second": 14.505, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.050651406307074154, | |
| "grad_norm": 1.0087053775787354, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6443, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0525995373188847, | |
| "grad_norm": 0.9601799249649048, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.6904, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.05454766833069524, | |
| "grad_norm": 0.9024684429168701, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.8345, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.05649579934250579, | |
| "grad_norm": 1.067520260810852, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.7891, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.058443930354316324, | |
| "grad_norm": 1.0981365442276, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.8215, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06039206136612687, | |
| "grad_norm": 1.0717315673828125, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.8982, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.06234019237793741, | |
| "grad_norm": 1.1622248888015747, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.0009, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.06428832338974796, | |
| "grad_norm": 1.4013619422912598, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.0698, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.06623645440155851, | |
| "grad_norm": 1.499001383781433, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.2458, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.06818458541336905, | |
| "grad_norm": 1.7074172496795654, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.0946, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0701327164251796, | |
| "grad_norm": 1.734402060508728, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.1359, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.07208084743699014, | |
| "grad_norm": 2.261868715286255, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.7585, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.07402897844880069, | |
| "grad_norm": 0.9555121660232544, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.5668, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.07597710946061123, | |
| "grad_norm": 0.8737242221832275, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.6213, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.07792524047242178, | |
| "grad_norm": 0.9610376954078674, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.6776, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07987337148423232, | |
| "grad_norm": 1.0207109451293945, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.8021, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.08182150249604286, | |
| "grad_norm": 1.0356788635253906, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.8581, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.08376963350785341, | |
| "grad_norm": 1.0629724264144897, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.8796, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.08571776451966395, | |
| "grad_norm": 1.2652376890182495, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.028, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0876658955314745, | |
| "grad_norm": 1.1882436275482178, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.9639, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.08961402654328504, | |
| "grad_norm": 1.58311128616333, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.1072, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.09156215755509559, | |
| "grad_norm": 1.32377290725708, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.0653, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.09351028856690613, | |
| "grad_norm": 1.4533188343048096, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.1439, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.09545841957871667, | |
| "grad_norm": 1.530142903327942, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.9235, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.09740655059052722, | |
| "grad_norm": 2.5200765132904053, | |
| "learning_rate": 0.0, | |
| "loss": 0.6299, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09740655059052722, | |
| "eval_loss": 0.8535917401313782, | |
| "eval_runtime": 29.845, | |
| "eval_samples_per_second": 115.865, | |
| "eval_steps_per_second": 14.508, | |
| "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 | |
| } | |