| { | |
| "best_metric": 1.3308466672897339, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.013775646379157448, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00027551292758314896, | |
| "grad_norm": 4.985652446746826, | |
| "learning_rate": 5e-05, | |
| "loss": 3.345, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00027551292758314896, | |
| "eval_loss": 3.855706214904785, | |
| "eval_runtime": 2.3104, | |
| "eval_samples_per_second": 21.641, | |
| "eval_steps_per_second": 5.627, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005510258551662979, | |
| "grad_norm": 6.339283466339111, | |
| "learning_rate": 0.0001, | |
| "loss": 3.6077, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008265387827494468, | |
| "grad_norm": 5.504337310791016, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 3.3122, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011020517103325959, | |
| "grad_norm": 2.902787685394287, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.654, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0013775646379157447, | |
| "grad_norm": 2.803334951400757, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.2916, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0016530775654988936, | |
| "grad_norm": 2.3478095531463623, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.2673, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0019285904930820426, | |
| "grad_norm": 1.7243198156356812, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.1345, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0022041034206651917, | |
| "grad_norm": 1.657291293144226, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.1614, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0024796163482483403, | |
| "grad_norm": 1.478399395942688, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.9236, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0027551292758314894, | |
| "grad_norm": 1.503095030784607, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.9579, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0030306422034146385, | |
| "grad_norm": 1.3471025228500366, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.9872, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.003306155130997787, | |
| "grad_norm": 1.953307867050171, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.7656, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.003581668058580936, | |
| "grad_norm": 1.4133480787277222, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 2.2645, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0038571809861640853, | |
| "grad_norm": 1.2810511589050293, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.3035, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.004132693913747234, | |
| "grad_norm": 1.3834335803985596, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 2.0962, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004408206841330383, | |
| "grad_norm": 1.2161914110183716, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 2.0253, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004683719768913532, | |
| "grad_norm": 1.2627516984939575, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.8418, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.004959232696496681, | |
| "grad_norm": 1.310968041419983, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.8342, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00523474562407983, | |
| "grad_norm": 1.149875283241272, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.8164, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.005510258551662979, | |
| "grad_norm": 1.3373379707336426, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.798, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0057857714792461275, | |
| "grad_norm": 1.3559110164642334, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.7143, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.006061284406829277, | |
| "grad_norm": 1.158542275428772, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.7487, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.006336797334412426, | |
| "grad_norm": 1.2300978899002075, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.6934, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.006612310261995574, | |
| "grad_norm": 1.8234623670578003, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.6099, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.006887823189578724, | |
| "grad_norm": 1.70737886428833, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.7116, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006887823189578724, | |
| "eval_loss": 1.4621353149414062, | |
| "eval_runtime": 2.2624, | |
| "eval_samples_per_second": 22.1, | |
| "eval_steps_per_second": 5.746, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007163336117161872, | |
| "grad_norm": 1.08351731300354, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 2.1669, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.007438849044745021, | |
| "grad_norm": 1.1508958339691162, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 1.796, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0077143619723281705, | |
| "grad_norm": 1.2080681324005127, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.879, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.00798987489991132, | |
| "grad_norm": 1.3611031770706177, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.7371, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.008265387827494468, | |
| "grad_norm": 1.3392175436019897, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.6612, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008540900755077617, | |
| "grad_norm": 1.2826539278030396, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.68, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.008816413682660767, | |
| "grad_norm": 1.4184712171554565, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.6392, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.009091926610243915, | |
| "grad_norm": 1.42243230342865, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.5867, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.009367439537827064, | |
| "grad_norm": 1.5949103832244873, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.4738, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.009642952465410214, | |
| "grad_norm": 1.6676265001296997, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.596, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.009918465392993361, | |
| "grad_norm": 1.4162265062332153, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.5618, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.010193978320576511, | |
| "grad_norm": 1.7664705514907837, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.3765, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.01046949124815966, | |
| "grad_norm": 1.2374845743179321, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 2.0416, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.010745004175742808, | |
| "grad_norm": 1.4492584466934204, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 1.9999, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.011020517103325958, | |
| "grad_norm": 1.5911473035812378, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.8249, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.011296030030909107, | |
| "grad_norm": 1.7549965381622314, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.7741, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.011571542958492255, | |
| "grad_norm": 1.734220027923584, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.5942, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.011847055886075404, | |
| "grad_norm": 1.8675172328948975, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.5419, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.012122568813658554, | |
| "grad_norm": 1.4374147653579712, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.5869, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.012398081741241702, | |
| "grad_norm": 1.2492765188217163, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.5914, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.012673594668824851, | |
| "grad_norm": 1.2149417400360107, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.535, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.012949107596408, | |
| "grad_norm": 1.3839102983474731, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.4046, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.013224620523991149, | |
| "grad_norm": 1.3655040264129639, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.5681, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.013500133451574298, | |
| "grad_norm": 1.9632959365844727, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.3139, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.013775646379157448, | |
| "grad_norm": 2.0195958614349365, | |
| "learning_rate": 1e-05, | |
| "loss": 1.4892, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.013775646379157448, | |
| "eval_loss": 1.3308466672897339, | |
| "eval_runtime": 2.2559, | |
| "eval_samples_per_second": 22.164, | |
| "eval_steps_per_second": 5.763, | |
| "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": 1.601881470140416e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |