| { | |
| "best_metric": 0.8249684572219849, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.0344827586206895, | |
| "eval_steps": 25, | |
| "global_step": 33, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09195402298850575, | |
| "grad_norm": 36.40338134765625, | |
| "learning_rate": 5e-05, | |
| "loss": 7.3875, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.09195402298850575, | |
| "eval_loss": 7.518415927886963, | |
| "eval_runtime": 2.3602, | |
| "eval_samples_per_second": 31.353, | |
| "eval_steps_per_second": 4.237, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1839080459770115, | |
| "grad_norm": 36.9449462890625, | |
| "learning_rate": 0.0001, | |
| "loss": 7.4548, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.27586206896551724, | |
| "grad_norm": 50.2653694152832, | |
| "learning_rate": 9.974346616959476e-05, | |
| "loss": 4.7082, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.367816091954023, | |
| "grad_norm": 18.120019912719727, | |
| "learning_rate": 9.897649706262473e-05, | |
| "loss": 1.6205, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.45977011494252873, | |
| "grad_norm": 11.145186424255371, | |
| "learning_rate": 9.770696282000244e-05, | |
| "loss": 1.1133, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5517241379310345, | |
| "grad_norm": 11.67027473449707, | |
| "learning_rate": 9.594789058101153e-05, | |
| "loss": 0.9955, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.6436781609195402, | |
| "grad_norm": 2.167078971862793, | |
| "learning_rate": 9.371733080722911e-05, | |
| "loss": 0.8398, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.735632183908046, | |
| "grad_norm": 7.674814224243164, | |
| "learning_rate": 9.103817206036382e-05, | |
| "loss": 1.0311, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.8275862068965517, | |
| "grad_norm": 1.134879469871521, | |
| "learning_rate": 8.793790613463955e-05, | |
| "loss": 0.8035, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.9195402298850575, | |
| "grad_norm": 4.637085437774658, | |
| "learning_rate": 8.444834595378434e-05, | |
| "loss": 0.8538, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0114942528735633, | |
| "grad_norm": 22.309356689453125, | |
| "learning_rate": 8.060529912738315e-05, | |
| "loss": 1.2659, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.103448275862069, | |
| "grad_norm": 17.529563903808594, | |
| "learning_rate": 7.644820051634812e-05, | |
| "loss": 1.0434, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.1954022988505748, | |
| "grad_norm": 2.4869232177734375, | |
| "learning_rate": 7.201970757788172e-05, | |
| "loss": 0.7968, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.2873563218390804, | |
| "grad_norm": 6.888029098510742, | |
| "learning_rate": 6.736526264224101e-05, | |
| "loss": 0.9996, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.3793103448275863, | |
| "grad_norm": 1.6961114406585693, | |
| "learning_rate": 6.253262661293604e-05, | |
| "loss": 0.8331, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.471264367816092, | |
| "grad_norm": 5.048608779907227, | |
| "learning_rate": 5.757138887522884e-05, | |
| "loss": 1.0152, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.5632183908045976, | |
| "grad_norm": 0.6340063810348511, | |
| "learning_rate": 5.2532458441935636e-05, | |
| "loss": 0.7896, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.6551724137931034, | |
| "grad_norm": 0.6864052414894104, | |
| "learning_rate": 4.746754155806437e-05, | |
| "loss": 0.7839, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.7471264367816093, | |
| "grad_norm": 5.3248724937438965, | |
| "learning_rate": 4.2428611124771184e-05, | |
| "loss": 0.8882, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.839080459770115, | |
| "grad_norm": 1.964074969291687, | |
| "learning_rate": 3.746737338706397e-05, | |
| "loss": 0.8144, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.9310344827586206, | |
| "grad_norm": 2.0052649974823, | |
| "learning_rate": 3.263473735775899e-05, | |
| "loss": 0.8666, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.0229885057471266, | |
| "grad_norm": 2.9962081909179688, | |
| "learning_rate": 2.798029242211828e-05, | |
| "loss": 0.9786, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.1149425287356323, | |
| "grad_norm": 3.63395094871521, | |
| "learning_rate": 2.3551799483651894e-05, | |
| "loss": 0.8251, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.206896551724138, | |
| "grad_norm": 2.464134931564331, | |
| "learning_rate": 1.9394700872616855e-05, | |
| "loss": 0.8161, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.2988505747126435, | |
| "grad_norm": 3.2755239009857178, | |
| "learning_rate": 1.555165404621567e-05, | |
| "loss": 0.8579, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.2988505747126435, | |
| "eval_loss": 0.8249684572219849, | |
| "eval_runtime": 2.3682, | |
| "eval_samples_per_second": 31.248, | |
| "eval_steps_per_second": 4.223, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.3908045977011496, | |
| "grad_norm": 1.2132009267807007, | |
| "learning_rate": 1.2062093865360458e-05, | |
| "loss": 0.7836, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.4827586206896552, | |
| "grad_norm": 5.591070652008057, | |
| "learning_rate": 8.961827939636196e-06, | |
| "loss": 0.8673, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.574712643678161, | |
| "grad_norm": 1.2173008918762207, | |
| "learning_rate": 6.282669192770896e-06, | |
| "loss": 0.7963, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 0.9013738036155701, | |
| "learning_rate": 4.05210941898847e-06, | |
| "loss": 0.7776, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.7586206896551726, | |
| "grad_norm": 4.316105365753174, | |
| "learning_rate": 2.2930371799975594e-06, | |
| "loss": 0.8378, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.8505747126436782, | |
| "grad_norm": 0.7817060351371765, | |
| "learning_rate": 1.0235029373752758e-06, | |
| "loss": 0.7891, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.942528735632184, | |
| "grad_norm": 5.667788505554199, | |
| "learning_rate": 2.5653383040524227e-07, | |
| "loss": 0.8836, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 3.0344827586206895, | |
| "grad_norm": 0.7555753588676453, | |
| "learning_rate": 0.0, | |
| "loss": 0.8817, | |
| "step": 33 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 33, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 4.075156367348859e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |