| { | |
| "best_metric": 1.0577250719070435, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.2903225806451613, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.025806451612903226, | |
| "grad_norm": 0.8220058083534241, | |
| "learning_rate": 5e-05, | |
| "loss": 2.036, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.025806451612903226, | |
| "eval_loss": 1.9736554622650146, | |
| "eval_runtime": 2.9976, | |
| "eval_samples_per_second": 87.403, | |
| "eval_steps_per_second": 11.009, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05161290322580645, | |
| "grad_norm": 0.9786584377288818, | |
| "learning_rate": 0.0001, | |
| "loss": 1.953, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.07741935483870968, | |
| "grad_norm": 1.0898869037628174, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.8547, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1032258064516129, | |
| "grad_norm": 0.9177775979042053, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.6855, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.12903225806451613, | |
| "grad_norm": 1.0047584772109985, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.4721, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.15483870967741936, | |
| "grad_norm": 1.099215030670166, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.4536, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.18064516129032257, | |
| "grad_norm": 1.1849559545516968, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.3585, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2064516129032258, | |
| "grad_norm": 1.0470384359359741, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.2279, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.23225806451612904, | |
| "grad_norm": 0.8208673000335693, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.9951, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.25806451612903225, | |
| "grad_norm": 1.2860324382781982, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.659, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2838709677419355, | |
| "grad_norm": 1.092450499534607, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.56, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3096774193548387, | |
| "grad_norm": 0.6195999383926392, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.4472, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.33548387096774196, | |
| "grad_norm": 0.7615762948989868, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.3041, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.36129032258064514, | |
| "grad_norm": 0.8887320160865784, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.0784, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3870967741935484, | |
| "grad_norm": 0.7487991452217102, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.0261, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.4129032258064516, | |
| "grad_norm": 0.6079425811767578, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.0409, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.43870967741935485, | |
| "grad_norm": 0.5330397486686707, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.002, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.4645161290322581, | |
| "grad_norm": 0.6109048128128052, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.9235, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.49032258064516127, | |
| "grad_norm": 0.6474350690841675, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.7902, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.5161290322580645, | |
| "grad_norm": 0.8159425854682922, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.6519, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5419354838709678, | |
| "grad_norm": 0.7559259533882141, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.4361, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.567741935483871, | |
| "grad_norm": 0.6141023635864258, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.2908, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5935483870967742, | |
| "grad_norm": 0.523212730884552, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.1428, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.6193548387096774, | |
| "grad_norm": 0.46284154057502747, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.0109, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.6451612903225806, | |
| "grad_norm": 0.5253970623016357, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.0057, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6451612903225806, | |
| "eval_loss": 1.1055667400360107, | |
| "eval_runtime": 2.9956, | |
| "eval_samples_per_second": 87.462, | |
| "eval_steps_per_second": 11.016, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6709677419354839, | |
| "grad_norm": 0.595125138759613, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9649, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.6967741935483871, | |
| "grad_norm": 0.8294361233711243, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.0171, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.7225806451612903, | |
| "grad_norm": 0.9938029050827026, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.8827, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.7483870967741936, | |
| "grad_norm": 0.5188781023025513, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.4422, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.7741935483870968, | |
| "grad_norm": 0.4888777732849121, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.4637, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.5658689141273499, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.4176, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.8258064516129032, | |
| "grad_norm": 0.5756728053092957, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.1852, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.8516129032258064, | |
| "grad_norm": 0.6184505820274353, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.0945, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.8774193548387097, | |
| "grad_norm": 0.592873215675354, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.9161, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.9032258064516129, | |
| "grad_norm": 0.5111616253852844, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.0042, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.9290322580645162, | |
| "grad_norm": 0.47419649362564087, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.0056, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.9548387096774194, | |
| "grad_norm": 0.5003200173377991, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.8988, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.9806451612903225, | |
| "grad_norm": 0.9362741112709045, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.7959, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.0064516129032257, | |
| "grad_norm": 0.4995446801185608, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.4934, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.032258064516129, | |
| "grad_norm": 0.4925078749656677, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.4401, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.0580645161290323, | |
| "grad_norm": 0.45888611674308777, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.2628, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.0838709677419356, | |
| "grad_norm": 0.512951135635376, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.0872, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.1096774193548387, | |
| "grad_norm": 0.47870081663131714, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.0501, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.135483870967742, | |
| "grad_norm": 0.4896996021270752, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.9109, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.1612903225806452, | |
| "grad_norm": 0.48330628871917725, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.8797, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.1870967741935483, | |
| "grad_norm": 0.5584717392921448, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.8834, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.2129032258064516, | |
| "grad_norm": 0.5270745158195496, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.9089, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.238709677419355, | |
| "grad_norm": 0.5363309979438782, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.6341, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.2645161290322582, | |
| "grad_norm": 0.5114651918411255, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.8123, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.2903225806451613, | |
| "grad_norm": 0.49089324474334717, | |
| "learning_rate": 0.0, | |
| "loss": 1.4389, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.2903225806451613, | |
| "eval_loss": 1.0577250719070435, | |
| "eval_runtime": 2.9964, | |
| "eval_samples_per_second": 87.439, | |
| "eval_steps_per_second": 11.013, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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 | |
| } | |