{ "best_metric": 2.598724126815796, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.13824088474166235, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.002764817694833247, "grad_norm": 1.1742911338806152, "learning_rate": 5e-05, "loss": 2.6986, "step": 1 }, { "epoch": 0.002764817694833247, "eval_loss": 2.875308036804199, "eval_runtime": 16.7408, "eval_samples_per_second": 145.572, "eval_steps_per_second": 18.219, "step": 1 }, { "epoch": 0.005529635389666494, "grad_norm": 1.2949481010437012, "learning_rate": 0.0001, "loss": 2.7546, "step": 2 }, { "epoch": 0.00829445308449974, "grad_norm": 1.0101735591888428, "learning_rate": 9.989294616193017e-05, "loss": 2.6672, "step": 3 }, { "epoch": 0.011059270779332988, "grad_norm": 0.9494262337684631, "learning_rate": 9.957224306869053e-05, "loss": 2.6501, "step": 4 }, { "epoch": 0.013824088474166234, "grad_norm": 0.944379985332489, "learning_rate": 9.903926402016153e-05, "loss": 2.6389, "step": 5 }, { "epoch": 0.01658890616899948, "grad_norm": 0.9478722810745239, "learning_rate": 9.829629131445342e-05, "loss": 2.6936, "step": 6 }, { "epoch": 0.019353723863832727, "grad_norm": 0.9653313755989075, "learning_rate": 9.73465064747553e-05, "loss": 2.6917, "step": 7 }, { "epoch": 0.022118541558665977, "grad_norm": 0.9041957855224609, "learning_rate": 9.619397662556435e-05, "loss": 2.6873, "step": 8 }, { "epoch": 0.024883359253499222, "grad_norm": 0.8747812509536743, "learning_rate": 9.484363707663442e-05, "loss": 2.7184, "step": 9 }, { "epoch": 0.027648176948332468, "grad_norm": 0.9741718173027039, "learning_rate": 9.330127018922194e-05, "loss": 2.6142, "step": 10 }, { "epoch": 0.030412994643165717, "grad_norm": 1.4103081226348877, "learning_rate": 9.157348061512727e-05, "loss": 2.6527, "step": 11 }, { "epoch": 0.03317781233799896, "grad_norm": 1.8044036626815796, "learning_rate": 8.966766701456177e-05, "loss": 2.685, "step": 12 }, { "epoch": 0.03594263003283221, "grad_norm": 1.9407167434692383, "learning_rate": 8.759199037394887e-05, "loss": 2.6937, "step": 13 }, { "epoch": 0.038707447727665455, "grad_norm": 2.277519941329956, "learning_rate": 8.535533905932738e-05, "loss": 2.7815, "step": 14 }, { "epoch": 0.041472265422498704, "grad_norm": 2.2202413082122803, "learning_rate": 8.296729075500344e-05, "loss": 2.7259, "step": 15 }, { "epoch": 0.04423708311733195, "grad_norm": 1.8662134408950806, "learning_rate": 8.043807145043604e-05, "loss": 2.7203, "step": 16 }, { "epoch": 0.047001900812165195, "grad_norm": 1.5702985525131226, "learning_rate": 7.777851165098012e-05, "loss": 2.6468, "step": 17 }, { "epoch": 0.049766718506998445, "grad_norm": 1.2403249740600586, "learning_rate": 7.500000000000001e-05, "loss": 2.6034, "step": 18 }, { "epoch": 0.052531536201831694, "grad_norm": 0.9190433621406555, "learning_rate": 7.211443451095007e-05, "loss": 2.5819, "step": 19 }, { "epoch": 0.055296353896664936, "grad_norm": 0.7897427082061768, "learning_rate": 6.91341716182545e-05, "loss": 2.6424, "step": 20 }, { "epoch": 0.058061171591498185, "grad_norm": 0.911276638507843, "learning_rate": 6.607197326515808e-05, "loss": 2.5984, "step": 21 }, { "epoch": 0.060825989286331435, "grad_norm": 1.3512458801269531, "learning_rate": 6.294095225512603e-05, "loss": 2.6273, "step": 22 }, { "epoch": 0.06359080698116468, "grad_norm": 1.441872000694275, "learning_rate": 5.9754516100806423e-05, "loss": 2.6648, "step": 23 }, { "epoch": 0.06635562467599793, "grad_norm": 1.8847798109054565, "learning_rate": 5.6526309611002594e-05, "loss": 2.6991, "step": 24 }, { "epoch": 0.06912044237083118, "grad_norm": 3.8344838619232178, "learning_rate": 5.327015646150716e-05, "loss": 2.8208, "step": 25 }, { "epoch": 0.06912044237083118, "eval_loss": 2.641629695892334, "eval_runtime": 16.7537, "eval_samples_per_second": 145.46, "eval_steps_per_second": 18.205, "step": 25 }, { "epoch": 0.07188526006566442, "grad_norm": 0.5620300769805908, "learning_rate": 5e-05, "loss": 2.5575, "step": 26 }, { "epoch": 0.07465007776049767, "grad_norm": 0.6803304553031921, "learning_rate": 4.6729843538492847e-05, "loss": 2.6463, "step": 27 }, { "epoch": 0.07741489545533091, "grad_norm": 0.8547685146331787, "learning_rate": 4.347369038899744e-05, "loss": 2.6041, "step": 28 }, { "epoch": 0.08017971315016416, "grad_norm": 0.718602180480957, "learning_rate": 4.0245483899193595e-05, "loss": 2.5597, "step": 29 }, { "epoch": 0.08294453084499741, "grad_norm": 0.6359795331954956, "learning_rate": 3.705904774487396e-05, "loss": 2.5481, "step": 30 }, { "epoch": 0.08570934853983066, "grad_norm": 0.7042436599731445, "learning_rate": 3.392802673484193e-05, "loss": 2.5978, "step": 31 }, { "epoch": 0.0884741662346639, "grad_norm": 0.6024742722511292, "learning_rate": 3.086582838174551e-05, "loss": 2.5476, "step": 32 }, { "epoch": 0.09123898392949716, "grad_norm": 0.7030935883522034, "learning_rate": 2.7885565489049946e-05, "loss": 2.5704, "step": 33 }, { "epoch": 0.09400380162433039, "grad_norm": 0.7609543800354004, "learning_rate": 2.500000000000001e-05, "loss": 2.6509, "step": 34 }, { "epoch": 0.09676861931916364, "grad_norm": 1.006309151649475, "learning_rate": 2.2221488349019903e-05, "loss": 2.5651, "step": 35 }, { "epoch": 0.09953343701399689, "grad_norm": 1.313661813735962, "learning_rate": 1.9561928549563968e-05, "loss": 2.6464, "step": 36 }, { "epoch": 0.10229825470883014, "grad_norm": 2.0305123329162598, "learning_rate": 1.703270924499656e-05, "loss": 2.6647, "step": 37 }, { "epoch": 0.10506307240366339, "grad_norm": 0.48308926820755005, "learning_rate": 1.4644660940672627e-05, "loss": 2.4811, "step": 38 }, { "epoch": 0.10782789009849664, "grad_norm": 0.47622811794281006, "learning_rate": 1.2408009626051137e-05, "loss": 2.6301, "step": 39 }, { "epoch": 0.11059270779332987, "grad_norm": 0.5079199075698853, "learning_rate": 1.0332332985438248e-05, "loss": 2.6056, "step": 40 }, { "epoch": 0.11335752548816312, "grad_norm": 0.5400040149688721, "learning_rate": 8.426519384872733e-06, "loss": 2.561, "step": 41 }, { "epoch": 0.11612234318299637, "grad_norm": 0.5759101510047913, "learning_rate": 6.698729810778065e-06, "loss": 2.5636, "step": 42 }, { "epoch": 0.11888716087782962, "grad_norm": 0.5764763951301575, "learning_rate": 5.156362923365588e-06, "loss": 2.5641, "step": 43 }, { "epoch": 0.12165197857266287, "grad_norm": 0.6086241006851196, "learning_rate": 3.8060233744356633e-06, "loss": 2.5616, "step": 44 }, { "epoch": 0.12441679626749612, "grad_norm": 0.6851764917373657, "learning_rate": 2.653493525244721e-06, "loss": 2.5202, "step": 45 }, { "epoch": 0.12718161396232935, "grad_norm": 0.7342571020126343, "learning_rate": 1.70370868554659e-06, "loss": 2.6312, "step": 46 }, { "epoch": 0.1299464316571626, "grad_norm": 0.8653113842010498, "learning_rate": 9.607359798384785e-07, "loss": 2.6744, "step": 47 }, { "epoch": 0.13271124935199585, "grad_norm": 1.0654218196868896, "learning_rate": 4.277569313094809e-07, "loss": 2.5864, "step": 48 }, { "epoch": 0.1354760670468291, "grad_norm": 1.6293843984603882, "learning_rate": 1.0705383806982606e-07, "loss": 2.5471, "step": 49 }, { "epoch": 0.13824088474166235, "grad_norm": 3.1217777729034424, "learning_rate": 0.0, "loss": 2.6951, "step": 50 }, { "epoch": 0.13824088474166235, "eval_loss": 2.598724126815796, "eval_runtime": 16.7383, "eval_samples_per_second": 145.594, "eval_steps_per_second": 18.222, "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": 2.95300912644096e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }