| { | |
| "best_metric": 1.746710181236267, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.359882005899705, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0471976401179941, | |
| "grad_norm": 2.267878293991089, | |
| "learning_rate": 5e-05, | |
| "loss": 3.837, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0471976401179941, | |
| "eval_loss": 4.282490253448486, | |
| "eval_runtime": 3.6257, | |
| "eval_samples_per_second": 39.441, | |
| "eval_steps_per_second": 4.965, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0943952802359882, | |
| "grad_norm": 2.31219482421875, | |
| "learning_rate": 0.0001, | |
| "loss": 4.1517, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1415929203539823, | |
| "grad_norm": 2.6523308753967285, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 4.161, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1887905604719764, | |
| "grad_norm": 4.234918117523193, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.9273, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.2359882005899705, | |
| "grad_norm": 6.553568363189697, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.8426, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2831858407079646, | |
| "grad_norm": 3.9042091369628906, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.943, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3303834808259587, | |
| "grad_norm": 3.4163200855255127, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.7462, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3775811209439528, | |
| "grad_norm": 3.7535297870635986, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.5355, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.4247787610619469, | |
| "grad_norm": 4.458499908447266, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.5068, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.471976401179941, | |
| "grad_norm": 4.730748176574707, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.3886, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5191740412979351, | |
| "grad_norm": 3.80424165725708, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.2423, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.5663716814159292, | |
| "grad_norm": 2.9450316429138184, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.9936, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.6135693215339233, | |
| "grad_norm": 2.1466267108917236, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.9452, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.6607669616519174, | |
| "grad_norm": 1.2779139280319214, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.8148, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.7079646017699115, | |
| "grad_norm": 0.9844837188720703, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.9177, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.7551622418879056, | |
| "grad_norm": 1.0039042234420776, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.927, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.8023598820058997, | |
| "grad_norm": 0.7406976819038391, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.7682, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.8495575221238938, | |
| "grad_norm": 0.7292348146438599, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.7606, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.8967551622418879, | |
| "grad_norm": 0.7878444194793701, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.743, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.943952802359882, | |
| "grad_norm": 0.9409651160240173, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.9168, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.9911504424778761, | |
| "grad_norm": 1.0702290534973145, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.8446, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.0383480825958702, | |
| "grad_norm": 2.130236864089966, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 3.2193, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.0855457227138643, | |
| "grad_norm": 1.185346007347107, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.7793, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.1327433628318584, | |
| "grad_norm": 1.003104329109192, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.5872, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.1799410029498525, | |
| "grad_norm": 1.0049196481704712, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.7389, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.1799410029498525, | |
| "eval_loss": 1.7648794651031494, | |
| "eval_runtime": 3.6517, | |
| "eval_samples_per_second": 39.159, | |
| "eval_steps_per_second": 4.929, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.2271386430678466, | |
| "grad_norm": 1.1068404912948608, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7302, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.2743362831858407, | |
| "grad_norm": 1.2672423124313354, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.7341, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.3215339233038348, | |
| "grad_norm": 1.0532811880111694, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.6848, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.368731563421829, | |
| "grad_norm": 1.037347674369812, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.6998, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.415929203539823, | |
| "grad_norm": 1.1231845617294312, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.6996, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.463126843657817, | |
| "grad_norm": 1.1563193798065186, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.655, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.5103244837758112, | |
| "grad_norm": 1.0125848054885864, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.5737, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.5575221238938053, | |
| "grad_norm": 1.0071817636489868, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.8132, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.6047197640117994, | |
| "grad_norm": 0.9246135354042053, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.6492, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.6519174041297935, | |
| "grad_norm": 1.0794720649719238, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.6322, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.6991150442477876, | |
| "grad_norm": 1.4046562910079956, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.6497, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.7463126843657817, | |
| "grad_norm": 1.0453946590423584, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.5673, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.7935103244837758, | |
| "grad_norm": 1.0008294582366943, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.8059, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.8407079646017699, | |
| "grad_norm": 0.9396019577980042, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.5804, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.887905604719764, | |
| "grad_norm": 1.0129765272140503, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.6912, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.935103244837758, | |
| "grad_norm": 1.0260602235794067, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.6417, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.9823008849557522, | |
| "grad_norm": 1.5143276453018188, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.7454, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.0294985250737465, | |
| "grad_norm": 1.6464427709579468, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 2.9107, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.0766961651917404, | |
| "grad_norm": 0.8135335445404053, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.6117, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.1238938053097347, | |
| "grad_norm": 0.8873955011367798, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.6066, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.1710914454277286, | |
| "grad_norm": 1.112796664237976, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.7035, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.218289085545723, | |
| "grad_norm": 1.3752461671829224, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.7328, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.265486725663717, | |
| "grad_norm": 0.9514968395233154, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.5891, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.312684365781711, | |
| "grad_norm": 0.9039832353591919, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.6777, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.359882005899705, | |
| "grad_norm": 0.9195019006729126, | |
| "learning_rate": 0.0, | |
| "loss": 1.6891, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.359882005899705, | |
| "eval_loss": 1.746710181236267, | |
| "eval_runtime": 3.624, | |
| "eval_samples_per_second": 39.459, | |
| "eval_steps_per_second": 4.967, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 1.059536353886208e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |