| { | |
| "best_metric": 0.9366380572319031, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.2598870056497176, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04519774011299435, | |
| "grad_norm": 0.12051593512296677, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9371, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04519774011299435, | |
| "eval_loss": 1.2566331624984741, | |
| "eval_runtime": 7.1186, | |
| "eval_samples_per_second": 20.931, | |
| "eval_steps_per_second": 2.669, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0903954802259887, | |
| "grad_norm": 0.26028257608413696, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0567, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.13559322033898305, | |
| "grad_norm": 0.2643623948097229, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.1577, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1807909604519774, | |
| "grad_norm": 0.3180350065231323, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.282, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.22598870056497175, | |
| "grad_norm": 0.6172782182693481, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.4226, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2711864406779661, | |
| "grad_norm": 0.11615486443042755, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.8679, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3163841807909605, | |
| "grad_norm": 0.14377813041210175, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.8714, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3615819209039548, | |
| "grad_norm": 0.14928121864795685, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.9545, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.4067796610169492, | |
| "grad_norm": 0.1883212774991989, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.0538, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.4519774011299435, | |
| "grad_norm": 0.1983480006456375, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.0588, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4971751412429379, | |
| "grad_norm": 0.3440364897251129, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.335, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.5423728813559322, | |
| "grad_norm": 0.07611960172653198, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.8769, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5875706214689266, | |
| "grad_norm": 0.10882534831762314, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.9328, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.632768361581921, | |
| "grad_norm": 0.1283181756734848, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.9265, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.6779661016949152, | |
| "grad_norm": 0.13232509791851044, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.0183, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.7231638418079096, | |
| "grad_norm": 0.17690761387348175, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.1061, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.768361581920904, | |
| "grad_norm": 0.07591235637664795, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.8341, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.8135593220338984, | |
| "grad_norm": 0.08945614844560623, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.8708, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.8587570621468926, | |
| "grad_norm": 0.12213297933340073, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.9412, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.903954802259887, | |
| "grad_norm": 0.12393030524253845, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.9791, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.9491525423728814, | |
| "grad_norm": 0.14773356914520264, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.0005, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.9943502824858758, | |
| "grad_norm": 0.31622564792633057, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.2379, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.03954802259887, | |
| "grad_norm": 0.21881358325481415, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.6934, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.0847457627118644, | |
| "grad_norm": 0.08667930215597153, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.8353, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.1299435028248588, | |
| "grad_norm": 0.1069195568561554, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.9082, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.1299435028248588, | |
| "eval_loss": 0.9493563771247864, | |
| "eval_runtime": 7.0741, | |
| "eval_samples_per_second": 21.063, | |
| "eval_steps_per_second": 2.686, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.1751412429378532, | |
| "grad_norm": 0.13968133926391602, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9774, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.2203389830508475, | |
| "grad_norm": 0.20083756744861603, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.0867, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.2655367231638417, | |
| "grad_norm": 0.0883803591132164, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.7986, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.310734463276836, | |
| "grad_norm": 0.0967683270573616, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.9001, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.3559322033898304, | |
| "grad_norm": 0.10467801243066788, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.8887, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.4011299435028248, | |
| "grad_norm": 0.12629304826259613, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.9147, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.4463276836158192, | |
| "grad_norm": 0.15558573603630066, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.9604, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.4915254237288136, | |
| "grad_norm": 0.30503368377685547, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.2131, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.536723163841808, | |
| "grad_norm": 0.08666601777076721, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.8113, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.5819209039548023, | |
| "grad_norm": 0.10060662031173706, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.8429, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.6271186440677967, | |
| "grad_norm": 0.1265161782503128, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.8955, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.672316384180791, | |
| "grad_norm": 0.14413928985595703, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.9875, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.7175141242937855, | |
| "grad_norm": 0.19615449011325836, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.0382, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.7627118644067796, | |
| "grad_norm": 0.09353553503751755, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.7597, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.807909604519774, | |
| "grad_norm": 0.1021425724029541, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.8842, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.8531073446327684, | |
| "grad_norm": 0.11777127534151077, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.8963, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.8983050847457628, | |
| "grad_norm": 0.13572406768798828, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.9136, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.943502824858757, | |
| "grad_norm": 0.180810809135437, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.9424, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.9887005649717513, | |
| "grad_norm": 0.32613012194633484, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.2046, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.0338983050847457, | |
| "grad_norm": 0.22946643829345703, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.5967, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.07909604519774, | |
| "grad_norm": 0.10317717492580414, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.7804, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.1242937853107344, | |
| "grad_norm": 0.1184142455458641, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.8891, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.169491525423729, | |
| "grad_norm": 0.13897018134593964, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.9444, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.214689265536723, | |
| "grad_norm": 0.20523014664649963, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.0576, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.2598870056497176, | |
| "grad_norm": 0.10931195318698883, | |
| "learning_rate": 0.0, | |
| "loss": 0.7252, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.2598870056497176, | |
| "eval_loss": 0.9366380572319031, | |
| "eval_runtime": 7.1084, | |
| "eval_samples_per_second": 20.961, | |
| "eval_steps_per_second": 2.673, | |
| "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": 1.1215740952389878e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |