| { | |
| "best_metric": 0.1284322291612625, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.14875418371141688, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0029750836742283376, | |
| "grad_norm": 94.49833679199219, | |
| "learning_rate": 5e-05, | |
| "loss": 110.0389, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0029750836742283376, | |
| "eval_loss": 6.522195339202881, | |
| "eval_runtime": 2.9036, | |
| "eval_samples_per_second": 17.22, | |
| "eval_steps_per_second": 4.477, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005950167348456675, | |
| "grad_norm": 94.23184204101562, | |
| "learning_rate": 0.0001, | |
| "loss": 107.5397, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.008925251022685012, | |
| "grad_norm": 85.81897735595703, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 104.0706, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01190033469691335, | |
| "grad_norm": 93.9833984375, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 83.8273, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.014875418371141688, | |
| "grad_norm": 75.50196838378906, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 62.3496, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.017850502045370024, | |
| "grad_norm": 73.75382995605469, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 47.1918, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.020825585719598364, | |
| "grad_norm": 58.85063934326172, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 36.059, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0238006693938267, | |
| "grad_norm": 46.654170989990234, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 29.4482, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02677575306805504, | |
| "grad_norm": 42.541351318359375, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 23.1892, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.029750836742283376, | |
| "grad_norm": 42.09115219116211, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 17.4144, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03272592041651171, | |
| "grad_norm": 38.61639404296875, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 13.7265, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03570100409074005, | |
| "grad_norm": 39.79591369628906, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 11.5362, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03867608776496839, | |
| "grad_norm": 41.74700164794922, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 10.3744, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04165117143919673, | |
| "grad_norm": 28.49478530883789, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 7.2114, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.044626255113425065, | |
| "grad_norm": 67.33341217041016, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 10.6912, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0476013387876534, | |
| "grad_norm": 67.70757293701172, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 7.0669, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05057642246188174, | |
| "grad_norm": 58.75659942626953, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 4.9047, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05355150613611008, | |
| "grad_norm": 32.62245559692383, | |
| "learning_rate": 7.75e-05, | |
| "loss": 4.4634, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.056526589810338417, | |
| "grad_norm": 26.23690414428711, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 4.2252, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05950167348456675, | |
| "grad_norm": 23.85607147216797, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 4.3725, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06247675715879509, | |
| "grad_norm": 21.009428024291992, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 3.7226, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06545184083302343, | |
| "grad_norm": 13.951952934265137, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 3.2343, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.06842692450725177, | |
| "grad_norm": 9.990436553955078, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 3.0301, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0714020081814801, | |
| "grad_norm": 25.964582443237305, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 3.2149, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.07437709185570844, | |
| "grad_norm": 26.048837661743164, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 3.1906, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07437709185570844, | |
| "eval_loss": 0.2122662216424942, | |
| "eval_runtime": 2.9074, | |
| "eval_samples_per_second": 17.198, | |
| "eval_steps_per_second": 4.471, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07735217552993678, | |
| "grad_norm": 39.105255126953125, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 3.2978, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08032725920416511, | |
| "grad_norm": 29.777935028076172, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 4.3169, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.08330234287839346, | |
| "grad_norm": 34.50019454956055, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 3.5684, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.08627742655262179, | |
| "grad_norm": 16.251876831054688, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 2.9726, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.08925251022685013, | |
| "grad_norm": 35.28190994262695, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 3.0923, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09222759390107847, | |
| "grad_norm": 33.3674430847168, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 2.8551, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0952026775753068, | |
| "grad_norm": 23.594511032104492, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 2.7141, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.09817776124953514, | |
| "grad_norm": 22.697614669799805, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 2.7784, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.10115284492376347, | |
| "grad_norm": 16.394115447998047, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 2.4427, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.10412792859799182, | |
| "grad_norm": 14.120108604431152, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 2.3841, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.10710301227222016, | |
| "grad_norm": 6.709747791290283, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 2.0642, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.11007809594644849, | |
| "grad_norm": 19.074462890625, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 2.2314, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.11305317962067683, | |
| "grad_norm": 18.0113525390625, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 2.2726, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.11602826329490516, | |
| "grad_norm": 14.895197868347168, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 2.2632, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1190033469691335, | |
| "grad_norm": 32.464725494384766, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 3.7555, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12197843064336185, | |
| "grad_norm": 38.17766189575195, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 4.1778, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.12495351431759018, | |
| "grad_norm": 29.950498580932617, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 3.3807, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.12792859799181852, | |
| "grad_norm": 27.437570571899414, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 3.1036, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.13090368166604685, | |
| "grad_norm": 18.265331268310547, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 2.4419, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1338787653402752, | |
| "grad_norm": 11.058792114257812, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 2.1983, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.13685384901450354, | |
| "grad_norm": 12.375876426696777, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 2.0319, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.13982893268873187, | |
| "grad_norm": 10.287103652954102, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 2.2049, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.1428040163629602, | |
| "grad_norm": 8.568561553955078, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.8594, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.14577910003718855, | |
| "grad_norm": 10.927348136901855, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.6348, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.14875418371141688, | |
| "grad_norm": 16.63982582092285, | |
| "learning_rate": 1e-05, | |
| "loss": 1.8796, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14875418371141688, | |
| "eval_loss": 0.1284322291612625, | |
| "eval_runtime": 2.9278, | |
| "eval_samples_per_second": 17.078, | |
| "eval_steps_per_second": 4.44, | |
| "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": 5.259104775831552e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |