| { | |
| "best_metric": 10.373128890991211, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.06038191561627292, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012076383123254585, | |
| "grad_norm": 0.02054658718407154, | |
| "learning_rate": 5e-05, | |
| "loss": 10.377, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012076383123254585, | |
| "eval_loss": 10.376673698425293, | |
| "eval_runtime": 16.7762, | |
| "eval_samples_per_second": 332.555, | |
| "eval_steps_per_second": 41.607, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002415276624650917, | |
| "grad_norm": 0.021067120134830475, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3772, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0036229149369763755, | |
| "grad_norm": 0.021995069459080696, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 10.3769, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004830553249301834, | |
| "grad_norm": 0.022329607978463173, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 10.3762, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0060381915616272925, | |
| "grad_norm": 0.023136308416724205, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 10.3757, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007245829873952751, | |
| "grad_norm": 0.022182868793606758, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 10.3759, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00845346818627821, | |
| "grad_norm": 0.022928915917873383, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 10.3752, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.009661106498603668, | |
| "grad_norm": 0.02278953790664673, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.3767, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.010868744810929127, | |
| "grad_norm": 0.025178467854857445, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 10.3753, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012076383123254585, | |
| "grad_norm": 0.024889159947633743, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.3766, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013284021435580044, | |
| "grad_norm": 0.025027789175510406, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 10.3749, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.014491659747905502, | |
| "grad_norm": 0.02514810487627983, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 10.3752, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01569929806023096, | |
| "grad_norm": 0.020523950457572937, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 10.3763, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01690693637255642, | |
| "grad_norm": 0.02050662226974964, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.3763, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.018114574684881878, | |
| "grad_norm": 0.024075357243418694, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 10.3751, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.019322212997207336, | |
| "grad_norm": 0.02626577951014042, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 10.3744, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.020529851309532793, | |
| "grad_norm": 0.024741550907492638, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 10.3755, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.021737489621858255, | |
| "grad_norm": 0.024174431338906288, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 10.3744, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.022945127934183712, | |
| "grad_norm": 0.026602614670991898, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 10.3756, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02415276624650917, | |
| "grad_norm": 0.027851395308971405, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.3744, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.025360404558834627, | |
| "grad_norm": 0.029516013339161873, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 10.374, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02656804287116009, | |
| "grad_norm": 0.026961779221892357, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 10.3747, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.027775681183485546, | |
| "grad_norm": 0.029911626130342484, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 10.3738, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.028983319495811004, | |
| "grad_norm": 0.02945856936275959, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 10.3736, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03019095780813646, | |
| "grad_norm": 0.033795420080423355, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 10.3733, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03019095780813646, | |
| "eval_loss": 10.374112129211426, | |
| "eval_runtime": 17.0544, | |
| "eval_samples_per_second": 327.129, | |
| "eval_steps_per_second": 40.928, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03139859612046192, | |
| "grad_norm": 0.024625129997730255, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3753, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03260623443278738, | |
| "grad_norm": 0.026763916015625, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 10.3739, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03381387274511284, | |
| "grad_norm": 0.030746644362807274, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 10.374, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.035021511057438295, | |
| "grad_norm": 0.03364461660385132, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 10.3744, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.036229149369763756, | |
| "grad_norm": 0.033119410276412964, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 10.3735, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03743678768208922, | |
| "grad_norm": 0.03178080543875694, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 10.3737, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03864442599441467, | |
| "grad_norm": 0.036192599684000015, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 10.3739, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.03985206430674013, | |
| "grad_norm": 0.03531722351908684, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 10.3734, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.04105970261906559, | |
| "grad_norm": 0.03745344281196594, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 10.3732, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.04226734093139105, | |
| "grad_norm": 0.03681091219186783, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 10.3728, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04347497924371651, | |
| "grad_norm": 0.03902368247509003, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 10.3737, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04468261755604196, | |
| "grad_norm": 0.03727221488952637, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 10.3722, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.045890255868367424, | |
| "grad_norm": 0.03553437814116478, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 10.3739, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.047097894180692886, | |
| "grad_norm": 0.03101722151041031, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 10.3747, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.04830553249301834, | |
| "grad_norm": 0.034259457141160965, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 10.374, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0495131708053438, | |
| "grad_norm": 0.036786723881959915, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 10.3732, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.050720809117669255, | |
| "grad_norm": 0.03839438781142235, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 10.3741, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.051928447429994716, | |
| "grad_norm": 0.037743955850601196, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 10.3733, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.05313608574232018, | |
| "grad_norm": 0.0409163199365139, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 10.3725, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.05434372405464563, | |
| "grad_norm": 0.03863488510251045, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 10.3723, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05555136236697109, | |
| "grad_norm": 0.03931540250778198, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 10.3729, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.05675900067929655, | |
| "grad_norm": 0.04146362096071243, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 10.3724, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.05796663899162201, | |
| "grad_norm": 0.04202931001782417, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 10.3723, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.05917427730394747, | |
| "grad_norm": 0.041146498173475266, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 10.3726, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06038191561627292, | |
| "grad_norm": 0.04683046415448189, | |
| "learning_rate": 0.0, | |
| "loss": 10.3726, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06038191561627292, | |
| "eval_loss": 10.373128890991211, | |
| "eval_runtime": 17.1121, | |
| "eval_samples_per_second": 326.027, | |
| "eval_steps_per_second": 40.79, | |
| "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": 42781424615424.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |