| { | |
| "best_metric": 0.9813548922538757, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.045004500450045004, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009000900090009, | |
| "grad_norm": 5.405413627624512, | |
| "learning_rate": 1e-06, | |
| "loss": 2.6833, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009000900090009, | |
| "eval_loss": 1.522924780845642, | |
| "eval_runtime": 106.2023, | |
| "eval_samples_per_second": 4.407, | |
| "eval_steps_per_second": 1.102, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018001800180018, | |
| "grad_norm": 6.125265121459961, | |
| "learning_rate": 2e-06, | |
| "loss": 2.7378, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0027002700270027003, | |
| "grad_norm": 5.993320465087891, | |
| "learning_rate": 3e-06, | |
| "loss": 2.9158, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0036003600360036, | |
| "grad_norm": 6.266770362854004, | |
| "learning_rate": 4e-06, | |
| "loss": 2.7044, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004500450045004501, | |
| "grad_norm": 6.800923824310303, | |
| "learning_rate": 4.9999999999999996e-06, | |
| "loss": 2.8806, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0054005400540054005, | |
| "grad_norm": 6.074341297149658, | |
| "learning_rate": 6e-06, | |
| "loss": 2.7618, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0063006300630063005, | |
| "grad_norm": 5.479096412658691, | |
| "learning_rate": 7e-06, | |
| "loss": 2.5574, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0072007200720072, | |
| "grad_norm": 3.8990819454193115, | |
| "learning_rate": 8e-06, | |
| "loss": 2.425, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.008100810081008101, | |
| "grad_norm": 3.068220376968384, | |
| "learning_rate": 9e-06, | |
| "loss": 2.6252, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.009000900090009001, | |
| "grad_norm": 3.1901001930236816, | |
| "learning_rate": 9.999999999999999e-06, | |
| "loss": 2.4851, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009900990099009901, | |
| "grad_norm": 3.36604380607605, | |
| "learning_rate": 1.1e-05, | |
| "loss": 2.4045, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.010801080108010801, | |
| "grad_norm": 2.9655489921569824, | |
| "learning_rate": 1.2e-05, | |
| "loss": 2.5242, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.011701170117011701, | |
| "grad_norm": 2.827815532684326, | |
| "learning_rate": 1.3000000000000001e-05, | |
| "loss": 2.6771, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.012601260126012601, | |
| "grad_norm": 2.3643851280212402, | |
| "learning_rate": 1.4e-05, | |
| "loss": 2.5468, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.013501350135013501, | |
| "grad_norm": 2.146620273590088, | |
| "learning_rate": 1.5e-05, | |
| "loss": 2.2051, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0144014401440144, | |
| "grad_norm": 2.0729222297668457, | |
| "learning_rate": 1.6e-05, | |
| "loss": 2.5173, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0153015301530153, | |
| "grad_norm": 1.7945488691329956, | |
| "learning_rate": 1.7e-05, | |
| "loss": 2.0158, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.016201620162016202, | |
| "grad_norm": 1.7809333801269531, | |
| "learning_rate": 1.8e-05, | |
| "loss": 2.3056, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.017101710171017102, | |
| "grad_norm": 1.6572290658950806, | |
| "learning_rate": 1.9e-05, | |
| "loss": 2.4406, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.018001800180018002, | |
| "grad_norm": 1.8199654817581177, | |
| "learning_rate": 1.9999999999999998e-05, | |
| "loss": 2.3008, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.018901890189018902, | |
| "grad_norm": 1.445672869682312, | |
| "learning_rate": 2.1e-05, | |
| "loss": 2.4013, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.019801980198019802, | |
| "grad_norm": 1.3299720287322998, | |
| "learning_rate": 2.2e-05, | |
| "loss": 2.5153, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.020702070207020702, | |
| "grad_norm": 1.3345452547073364, | |
| "learning_rate": 2.3000000000000003e-05, | |
| "loss": 1.9483, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.021602160216021602, | |
| "grad_norm": 1.339888334274292, | |
| "learning_rate": 2.4e-05, | |
| "loss": 2.2493, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.022502250225022502, | |
| "grad_norm": 1.1863774061203003, | |
| "learning_rate": 2.5e-05, | |
| "loss": 2.0514, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.023402340234023402, | |
| "grad_norm": 1.347615361213684, | |
| "learning_rate": 2.6000000000000002e-05, | |
| "loss": 2.1209, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.024302430243024302, | |
| "grad_norm": 1.3726738691329956, | |
| "learning_rate": 2.7000000000000002e-05, | |
| "loss": 2.08, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.025202520252025202, | |
| "grad_norm": 1.4481537342071533, | |
| "learning_rate": 2.8e-05, | |
| "loss": 2.1589, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.026102610261026102, | |
| "grad_norm": 1.3069828748703003, | |
| "learning_rate": 2.9e-05, | |
| "loss": 2.0717, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.027002700270027002, | |
| "grad_norm": 1.3439555168151855, | |
| "learning_rate": 3e-05, | |
| "loss": 2.3236, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0279027902790279, | |
| "grad_norm": 1.3758991956710815, | |
| "learning_rate": 2.9984895998119723e-05, | |
| "loss": 2.3634, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0288028802880288, | |
| "grad_norm": 1.342500925064087, | |
| "learning_rate": 2.993961440992859e-05, | |
| "loss": 2.4211, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0297029702970297, | |
| "grad_norm": 1.2951146364212036, | |
| "learning_rate": 2.9864246426519023e-05, | |
| "loss": 2.0738, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0306030603060306, | |
| "grad_norm": 1.210880994796753, | |
| "learning_rate": 2.9758943828979444e-05, | |
| "loss": 2.3646, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0315031503150315, | |
| "grad_norm": 1.453122854232788, | |
| "learning_rate": 2.9623918682727355e-05, | |
| "loss": 2.1522, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.032403240324032405, | |
| "grad_norm": 1.259437084197998, | |
| "learning_rate": 2.9459442910437798e-05, | |
| "loss": 2.5665, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0333033303330333, | |
| "grad_norm": 1.358750581741333, | |
| "learning_rate": 2.9265847744427305e-05, | |
| "loss": 2.101, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.034203420342034205, | |
| "grad_norm": 1.1546375751495361, | |
| "learning_rate": 2.904352305959606e-05, | |
| "loss": 2.0149, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0351035103510351, | |
| "grad_norm": 1.28835928440094, | |
| "learning_rate": 2.8792916588271762e-05, | |
| "loss": 2.9375, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.036003600360036005, | |
| "grad_norm": 1.1649773120880127, | |
| "learning_rate": 2.8514533018536286e-05, | |
| "loss": 2.2544, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0369036903690369, | |
| "grad_norm": 1.1442354917526245, | |
| "learning_rate": 2.820893297785107e-05, | |
| "loss": 2.6504, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.037803780378037805, | |
| "grad_norm": 1.11664617061615, | |
| "learning_rate": 2.7876731904027994e-05, | |
| "loss": 2.8791, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0387038703870387, | |
| "grad_norm": 1.0840619802474976, | |
| "learning_rate": 2.7518598805819542e-05, | |
| "loss": 2.6283, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.039603960396039604, | |
| "grad_norm": 1.1481599807739258, | |
| "learning_rate": 2.7135254915624213e-05, | |
| "loss": 2.7925, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0405040504050405, | |
| "grad_norm": 1.1215124130249023, | |
| "learning_rate": 2.672747223702045e-05, | |
| "loss": 3.1867, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.041404140414041404, | |
| "grad_norm": 1.1518648862838745, | |
| "learning_rate": 2.6296071990054167e-05, | |
| "loss": 2.9494, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0423042304230423, | |
| "grad_norm": 1.0652910470962524, | |
| "learning_rate": 2.5841922957410875e-05, | |
| "loss": 3.5141, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.043204320432043204, | |
| "grad_norm": 1.111494541168213, | |
| "learning_rate": 2.5365939734802973e-05, | |
| "loss": 3.3104, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.04410441044104411, | |
| "grad_norm": 1.044433832168579, | |
| "learning_rate": 2.4869080889095693e-05, | |
| "loss": 2.6152, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.045004500450045004, | |
| "grad_norm": 0.9503619074821472, | |
| "learning_rate": 2.4352347027881003e-05, | |
| "loss": 2.9733, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.045004500450045004, | |
| "eval_loss": 0.9813548922538757, | |
| "eval_runtime": 107.9014, | |
| "eval_samples_per_second": 4.337, | |
| "eval_steps_per_second": 1.084, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.3211020214272e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |