| { | |
| "best_metric": 2.5222702026367188, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.348280365694384, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006965607313887679, | |
| "grad_norm": 15.229019165039062, | |
| "learning_rate": 5e-05, | |
| "loss": 2.9946, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006965607313887679, | |
| "eval_loss": 3.8551180362701416, | |
| "eval_runtime": 39.7943, | |
| "eval_samples_per_second": 24.3, | |
| "eval_steps_per_second": 3.041, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013931214627775359, | |
| "grad_norm": 13.67873764038086, | |
| "learning_rate": 0.0001, | |
| "loss": 3.1224, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02089682194166304, | |
| "grad_norm": 14.9080171585083, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 3.22, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.027862429255550717, | |
| "grad_norm": 20.993005752563477, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.1743, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0348280365694384, | |
| "grad_norm": 29.366485595703125, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.1078, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04179364388332608, | |
| "grad_norm": 27.484878540039062, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.9921, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.048759251197213756, | |
| "grad_norm": 32.65122985839844, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.9243, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.055724858511101434, | |
| "grad_norm": 38.21415328979492, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.8423, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06269046582498912, | |
| "grad_norm": 39.87234878540039, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.8132, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0696560731388768, | |
| "grad_norm": 33.98863983154297, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 3.3895, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07662168045276448, | |
| "grad_norm": 36.042884826660156, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 3.5155, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.08358728776665215, | |
| "grad_norm": 35.477813720703125, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 3.7259, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.09055289508053983, | |
| "grad_norm": 26.74056625366211, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 3.4778, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.09751850239442751, | |
| "grad_norm": 21.886476516723633, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.7733, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.10448410970831519, | |
| "grad_norm": 25.439306259155273, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.6163, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.11144971702220287, | |
| "grad_norm": 19.48577117919922, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.5545, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.11841532433609055, | |
| "grad_norm": 79.62557220458984, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.5872, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.12538093164997824, | |
| "grad_norm": 14.575848579406738, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.3927, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.13234653896386592, | |
| "grad_norm": 15.852194786071777, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.3631, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.1393121462777536, | |
| "grad_norm": 22.415136337280273, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.3999, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14627775359164127, | |
| "grad_norm": 15.4609956741333, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.3585, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.15324336090552895, | |
| "grad_norm": 38.18202590942383, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.7733, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.16020896821941663, | |
| "grad_norm": 53.641685485839844, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 3.1575, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1671745755333043, | |
| "grad_norm": 48.16782760620117, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 3.0562, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.174140182847192, | |
| "grad_norm": 43.047733306884766, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 3.7527, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.174140182847192, | |
| "eval_loss": 2.6552484035491943, | |
| "eval_runtime": 39.811, | |
| "eval_samples_per_second": 24.29, | |
| "eval_steps_per_second": 3.039, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.18110579016107967, | |
| "grad_norm": 10.78183650970459, | |
| "learning_rate": 5e-05, | |
| "loss": 2.7925, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.18807139747496734, | |
| "grad_norm": 10.190346717834473, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 2.4493, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.19503700478885502, | |
| "grad_norm": 11.52568244934082, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 2.3815, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.2020026121027427, | |
| "grad_norm": 7.325039863586426, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 2.3123, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.20896821941663038, | |
| "grad_norm": 6.588929176330566, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 2.3014, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.21593382673051806, | |
| "grad_norm": 7.719417572021484, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 2.2622, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.22289943404440574, | |
| "grad_norm": 9.654048919677734, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.2692, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.22986504135829341, | |
| "grad_norm": 9.051423072814941, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 2.3102, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2368306486721811, | |
| "grad_norm": 8.692105293273926, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.3599, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.24379625598606877, | |
| "grad_norm": 19.115230560302734, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 2.9567, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2507618632999565, | |
| "grad_norm": 26.625967025756836, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 2.6196, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.25772747061384416, | |
| "grad_norm": 24.278709411621094, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 3.0971, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.26469307792773183, | |
| "grad_norm": 18.138113021850586, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.3459, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.2716586852416195, | |
| "grad_norm": 7.01446008682251, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 2.5923, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.2786242925555072, | |
| "grad_norm": 5.951314926147461, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 2.3039, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.28558989986939487, | |
| "grad_norm": 5.891165256500244, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 2.2985, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.29255550718328255, | |
| "grad_norm": 6.349960803985596, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.3085, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2995211144971702, | |
| "grad_norm": 7.006208896636963, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 2.2457, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.3064867218110579, | |
| "grad_norm": 6.453885555267334, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.1739, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.3134523291249456, | |
| "grad_norm": 7.156106948852539, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 2.2258, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.32041793643883326, | |
| "grad_norm": 9.0035982131958, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 2.2745, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.32738354375272094, | |
| "grad_norm": 15.360855102539062, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 2.721, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3343491510666086, | |
| "grad_norm": 18.129810333251953, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 2.7609, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3413147583804963, | |
| "grad_norm": 22.803747177124023, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 2.5381, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.348280365694384, | |
| "grad_norm": 27.541250228881836, | |
| "learning_rate": 0.0, | |
| "loss": 3.4004, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.348280365694384, | |
| "eval_loss": 2.5222702026367188, | |
| "eval_runtime": 39.798, | |
| "eval_samples_per_second": 24.298, | |
| "eval_steps_per_second": 3.04, | |
| "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": 5.259156315439104e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |