| { | |
| "best_metric": 1.0798553228378296, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.0007506662162669369, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.0026648650677475e-05, | |
| "grad_norm": 2.322167158126831, | |
| "learning_rate": 2e-05, | |
| "loss": 3.318, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.0026648650677475e-05, | |
| "eval_loss": 4.371880054473877, | |
| "eval_runtime": 2915.1959, | |
| "eval_samples_per_second": 4.81, | |
| "eval_steps_per_second": 2.405, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.005329730135495e-05, | |
| "grad_norm": 2.5270724296569824, | |
| "learning_rate": 4e-05, | |
| "loss": 4.8858, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 9.007994595203243e-05, | |
| "grad_norm": 2.7269139289855957, | |
| "learning_rate": 6e-05, | |
| "loss": 4.5174, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0001201065946027099, | |
| "grad_norm": 2.931736707687378, | |
| "learning_rate": 8e-05, | |
| "loss": 4.0881, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00015013324325338737, | |
| "grad_norm": 3.4653429985046387, | |
| "learning_rate": 0.0001, | |
| "loss": 4.9989, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00015013324325338737, | |
| "eval_loss": 4.284289360046387, | |
| "eval_runtime": 2900.7521, | |
| "eval_samples_per_second": 4.834, | |
| "eval_steps_per_second": 2.417, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00018015989190406487, | |
| "grad_norm": 3.635000467300415, | |
| "learning_rate": 0.00012, | |
| "loss": 4.6812, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00021018654055474234, | |
| "grad_norm": 5.219367504119873, | |
| "learning_rate": 0.00014, | |
| "loss": 3.52, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0002402131892054198, | |
| "grad_norm": 4.964032173156738, | |
| "learning_rate": 0.00016, | |
| "loss": 3.7769, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0002702398378560973, | |
| "grad_norm": 6.0093464851379395, | |
| "learning_rate": 0.00018, | |
| "loss": 3.8621, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00030026648650677474, | |
| "grad_norm": 4.796992778778076, | |
| "learning_rate": 0.0002, | |
| "loss": 2.576, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00030026648650677474, | |
| "eval_loss": 2.4847874641418457, | |
| "eval_runtime": 2885.8394, | |
| "eval_samples_per_second": 4.859, | |
| "eval_steps_per_second": 2.43, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00033029313515745224, | |
| "grad_norm": 3.3358001708984375, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 2.242, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00036031978380812973, | |
| "grad_norm": 3.195758104324341, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 1.496, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0003903464324588072, | |
| "grad_norm": 4.277500152587891, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 2.4095, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00042037308110948467, | |
| "grad_norm": 2.7910850048065186, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 1.4658, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00045039972976016217, | |
| "grad_norm": 2.787341356277466, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.063, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00045039972976016217, | |
| "eval_loss": 1.3606845140457153, | |
| "eval_runtime": 2900.5049, | |
| "eval_samples_per_second": 4.835, | |
| "eval_steps_per_second": 2.418, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0004804263784108396, | |
| "grad_norm": 3.5803050994873047, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.6737, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0005104530270615171, | |
| "grad_norm": 4.97550106048584, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 1.6215, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0005404796757121946, | |
| "grad_norm": 3.135634183883667, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 1.2527, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0005705063243628721, | |
| "grad_norm": 2.8997962474823, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.9732, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0006005329730135495, | |
| "grad_norm": 2.7014966011047363, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.9837, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0006005329730135495, | |
| "eval_loss": 1.111261010169983, | |
| "eval_runtime": 2898.5893, | |
| "eval_samples_per_second": 4.838, | |
| "eval_steps_per_second": 2.419, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.000630559621664227, | |
| "grad_norm": 2.9081523418426514, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 0.9943, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0006605862703149045, | |
| "grad_norm": 2.5095632076263428, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.9972, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.000690612918965582, | |
| "grad_norm": 2.449805974960327, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 0.8407, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0007206395676162595, | |
| "grad_norm": 3.1592514514923096, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 1.09, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0007506662162669369, | |
| "grad_norm": 2.864450693130493, | |
| "learning_rate": 0.0, | |
| "loss": 1.0781, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0007506662162669369, | |
| "eval_loss": 1.0798553228378296, | |
| "eval_runtime": 2878.3341, | |
| "eval_samples_per_second": 4.872, | |
| "eval_steps_per_second": 2.436, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": 1.044847376990208e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |