| { | |
| "best_metric": 0.7876038551330566, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.150537634408602, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.043010752688172046, | |
| "grad_norm": 9.35327434539795, | |
| "learning_rate": 5e-05, | |
| "loss": 13.6544, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.043010752688172046, | |
| "eval_loss": 13.57972526550293, | |
| "eval_runtime": 7.9714, | |
| "eval_samples_per_second": 19.695, | |
| "eval_steps_per_second": 2.509, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08602150537634409, | |
| "grad_norm": 8.438759803771973, | |
| "learning_rate": 0.0001, | |
| "loss": 13.6314, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.12903225806451613, | |
| "grad_norm": 6.360323905944824, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 13.4301, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.17204301075268819, | |
| "grad_norm": 8.016193389892578, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 12.3516, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.21505376344086022, | |
| "grad_norm": 7.792659282684326, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 9.8482, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.25806451612903225, | |
| "grad_norm": 7.131053447723389, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 9.283, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3010752688172043, | |
| "grad_norm": 11.247384071350098, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 6.194, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.34408602150537637, | |
| "grad_norm": 7.143100261688232, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.8235, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3870967741935484, | |
| "grad_norm": 6.129095077514648, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 5.4014, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.43010752688172044, | |
| "grad_norm": 14.87994384765625, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 5.0606, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4731182795698925, | |
| "grad_norm": 11.771108627319336, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 4.6802, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.5161290322580645, | |
| "grad_norm": 5.785019874572754, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 4.1953, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5591397849462365, | |
| "grad_norm": 4.753819942474365, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.6155, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.6021505376344086, | |
| "grad_norm": 4.773311614990234, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.2332, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.6451612903225806, | |
| "grad_norm": 5.8297810554504395, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.3767, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6881720430107527, | |
| "grad_norm": 6.003252983093262, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.3936, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.7311827956989247, | |
| "grad_norm": 4.296295166015625, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.2567, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.7741935483870968, | |
| "grad_norm": 2.917107343673706, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.0352, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.8172043010752689, | |
| "grad_norm": 3.7247848510742188, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.577, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.8602150537634409, | |
| "grad_norm": 3.8060548305511475, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.8322, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.9032258064516129, | |
| "grad_norm": 2.8651576042175293, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.4222, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.946236559139785, | |
| "grad_norm": 2.706366777420044, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.3017, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.989247311827957, | |
| "grad_norm": 2.2514758110046387, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.3554, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.032258064516129, | |
| "grad_norm": 8.478227615356445, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.731, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.075268817204301, | |
| "grad_norm": 5.380260467529297, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.7884, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.075268817204301, | |
| "eval_loss": 1.0795084238052368, | |
| "eval_runtime": 7.9611, | |
| "eval_samples_per_second": 19.721, | |
| "eval_steps_per_second": 2.512, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.118279569892473, | |
| "grad_norm": 4.564328670501709, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2343, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.1612903225806452, | |
| "grad_norm": 3.6037137508392334, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.0317, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.2043010752688172, | |
| "grad_norm": 3.2914304733276367, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.9329, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.2473118279569892, | |
| "grad_norm": 5.4039154052734375, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.3014, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.2903225806451613, | |
| "grad_norm": 3.8691208362579346, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.9831, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 4.34861946105957, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.0507, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.3763440860215055, | |
| "grad_norm": 2.965681314468384, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.1723, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.4193548387096775, | |
| "grad_norm": 3.439244508743286, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.9571, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.4623655913978495, | |
| "grad_norm": 2.797593593597412, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.8522, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.5053763440860215, | |
| "grad_norm": 2.8328845500946045, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.0963, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.5483870967741935, | |
| "grad_norm": 2.290050506591797, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.701, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.5913978494623655, | |
| "grad_norm": 3.077988386154175, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.8191, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.6344086021505375, | |
| "grad_norm": 2.5467429161071777, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.9073, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.6774193548387095, | |
| "grad_norm": 2.68570876121521, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.8795, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.7204301075268817, | |
| "grad_norm": 2.404557466506958, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.7958, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.7634408602150538, | |
| "grad_norm": 2.3604447841644287, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.8523, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.8064516129032258, | |
| "grad_norm": 1.8468281030654907, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.6095, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.849462365591398, | |
| "grad_norm": 3.724862813949585, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.7875, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.89247311827957, | |
| "grad_norm": 3.9843430519104004, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.906, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.935483870967742, | |
| "grad_norm": 1.6732141971588135, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.7148, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.978494623655914, | |
| "grad_norm": 2.5346105098724365, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.8121, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.021505376344086, | |
| "grad_norm": 5.31929349899292, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.3606, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.064516129032258, | |
| "grad_norm": 1.4526803493499756, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.6546, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.10752688172043, | |
| "grad_norm": 2.4552512168884277, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.819, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.150537634408602, | |
| "grad_norm": 1.7610336542129517, | |
| "learning_rate": 0.0, | |
| "loss": 0.816, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.150537634408602, | |
| "eval_loss": 0.7876038551330566, | |
| "eval_runtime": 7.9591, | |
| "eval_samples_per_second": 19.726, | |
| "eval_steps_per_second": 2.513, | |
| "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": 1.0627374735425536e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |