| { | |
| "best_metric": 1.9585036039352417, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.0767160161507403, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.021534320323014805, | |
| "grad_norm": 7.428799152374268, | |
| "learning_rate": 5e-05, | |
| "loss": 71.0635, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.021534320323014805, | |
| "eval_loss": 2.1911211013793945, | |
| "eval_runtime": 2.3061, | |
| "eval_samples_per_second": 21.681, | |
| "eval_steps_per_second": 5.637, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04306864064602961, | |
| "grad_norm": 7.895357608795166, | |
| "learning_rate": 0.0001, | |
| "loss": 70.0483, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06460296096904442, | |
| "grad_norm": 7.492817401885986, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 72.7399, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.08613728129205922, | |
| "grad_norm": 4.754925727844238, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 71.1941, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.10767160161507403, | |
| "grad_norm": 10.112983703613281, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 69.2045, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.12920592193808883, | |
| "grad_norm": 8.431731224060059, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 68.3191, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.15074024226110364, | |
| "grad_norm": 5.205851078033447, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 67.9009, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.17227456258411844, | |
| "grad_norm": 4.076101303100586, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 65.1974, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.19380888290713325, | |
| "grad_norm": 4.14735221862793, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 64.3393, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.21534320323014805, | |
| "grad_norm": 4.449265003204346, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 64.4913, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.23687752355316286, | |
| "grad_norm": 3.8274850845336914, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 61.2182, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.25841184387617766, | |
| "grad_norm": 6.239875316619873, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 61.4221, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.27994616419919244, | |
| "grad_norm": 7.284544467926025, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 66.3373, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.30148048452220727, | |
| "grad_norm": 4.4093499183654785, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 66.7453, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.32301480484522205, | |
| "grad_norm": 5.580052375793457, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 67.3063, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3445491251682369, | |
| "grad_norm": 5.168661117553711, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 65.9563, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.36608344549125166, | |
| "grad_norm": 4.806717395782471, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 65.3724, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3876177658142665, | |
| "grad_norm": 4.3158087730407715, | |
| "learning_rate": 7.75e-05, | |
| "loss": 63.5243, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.40915208613728127, | |
| "grad_norm": 4.206009387969971, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 63.5102, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.4306864064602961, | |
| "grad_norm": 3.7067387104034424, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 60.9615, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4522207267833109, | |
| "grad_norm": 3.939070224761963, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 59.907, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.4737550471063257, | |
| "grad_norm": 3.8720157146453857, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 58.2856, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.4952893674293405, | |
| "grad_norm": 4.3019585609436035, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 53.3796, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5168236877523553, | |
| "grad_norm": 9.856036186218262, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 67.6518, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5383580080753702, | |
| "grad_norm": 6.734169960021973, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 65.4684, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5383580080753702, | |
| "eval_loss": 1.9989453554153442, | |
| "eval_runtime": 2.3064, | |
| "eval_samples_per_second": 21.679, | |
| "eval_steps_per_second": 5.636, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5598923283983849, | |
| "grad_norm": 4.498115539550781, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 65.8819, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.5814266487213997, | |
| "grad_norm": 4.602976322174072, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 65.7282, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.6029609690444145, | |
| "grad_norm": 5.164878845214844, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 64.1922, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.6244952893674294, | |
| "grad_norm": 5.493595600128174, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 63.0684, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.6460296096904441, | |
| "grad_norm": 5.563244342803955, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 62.7678, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6675639300134589, | |
| "grad_norm": 4.930936813354492, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 61.9361, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.6890982503364738, | |
| "grad_norm": 4.097081661224365, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 58.2433, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.7106325706594886, | |
| "grad_norm": 3.6659867763519287, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 59.146, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.7321668909825033, | |
| "grad_norm": 3.9649877548217773, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 55.3594, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.7537012113055181, | |
| "grad_norm": 5.052422523498535, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 58.547, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.775235531628533, | |
| "grad_norm": 7.707125186920166, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 65.0094, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.7967698519515478, | |
| "grad_norm": 6.823256015777588, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 64.2297, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.8183041722745625, | |
| "grad_norm": 5.60520076751709, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 63.7831, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.8398384925975774, | |
| "grad_norm": 4.831979751586914, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 63.5944, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.8613728129205922, | |
| "grad_norm": 4.534188747406006, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 64.0645, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.882907133243607, | |
| "grad_norm": 5.040567398071289, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 64.2196, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.9044414535666218, | |
| "grad_norm": 3.988529920578003, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 61.5929, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.9259757738896366, | |
| "grad_norm": 3.7538902759552, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 58.979, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.9475100942126514, | |
| "grad_norm": 4.008431911468506, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 59.3505, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.9690444145356663, | |
| "grad_norm": 4.040865898132324, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 56.4883, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.990578734858681, | |
| "grad_norm": 4.638698101043701, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 55.8449, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.012113055181696, | |
| "grad_norm": 5.850164413452148, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 63.1024, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.0336473755047106, | |
| "grad_norm": 6.791426658630371, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 64.9107, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.0551816958277254, | |
| "grad_norm": 5.96373987197876, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 65.2047, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.0767160161507403, | |
| "grad_norm": 5.147349834442139, | |
| "learning_rate": 1e-05, | |
| "loss": 62.8758, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.0767160161507403, | |
| "eval_loss": 1.9585036039352417, | |
| "eval_runtime": 2.3042, | |
| "eval_samples_per_second": 21.699, | |
| "eval_steps_per_second": 5.642, | |
| "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": 5.2665520021621965e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |