| { | |
| "best_metric": 0.5393621325492859, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.6843455945252352, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013686911890504704, | |
| "grad_norm": 1.831357479095459, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2229, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013686911890504704, | |
| "eval_loss": 1.6845617294311523, | |
| "eval_runtime": 3.3685, | |
| "eval_samples_per_second": 146.358, | |
| "eval_steps_per_second": 18.406, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02737382378100941, | |
| "grad_norm": 2.4423232078552246, | |
| "learning_rate": 0.0001, | |
| "loss": 1.4341, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.041060735671514116, | |
| "grad_norm": 2.57499098777771, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.4394, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05474764756201882, | |
| "grad_norm": 1.744922161102295, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.2074, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06843455945252352, | |
| "grad_norm": 1.8592020273208618, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.296, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08212147134302823, | |
| "grad_norm": 2.41068172454834, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.2023, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09580838323353294, | |
| "grad_norm": 2.1957151889801025, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.0849, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.10949529512403763, | |
| "grad_norm": 1.7045655250549316, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.5065, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.12318220701454234, | |
| "grad_norm": 3.0237951278686523, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.153, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.13686911890504705, | |
| "grad_norm": 2.2770192623138428, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.2246, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15055603079555174, | |
| "grad_norm": 2.465864658355713, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.3054, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.16424294268605646, | |
| "grad_norm": 3.907484292984009, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.734, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.17792985457656116, | |
| "grad_norm": 1.580411434173584, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.9187, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.19161676646706588, | |
| "grad_norm": 1.1672953367233276, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.9169, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.20530367835757057, | |
| "grad_norm": 2.307849884033203, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.7971, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.21899059024807527, | |
| "grad_norm": 1.4963828325271606, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.7534, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.23267750213858, | |
| "grad_norm": 1.3901129961013794, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.7156, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.24636441402908468, | |
| "grad_norm": 1.3330930471420288, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.7648, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2600513259195894, | |
| "grad_norm": 3.1775882244110107, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.534, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2737382378100941, | |
| "grad_norm": 1.4021908044815063, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.0418, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2874251497005988, | |
| "grad_norm": 1.9394640922546387, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.1208, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3011120615911035, | |
| "grad_norm": 2.5855765342712402, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.9451, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.31479897348160824, | |
| "grad_norm": 2.3143441677093506, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.9487, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.32848588537211293, | |
| "grad_norm": 2.0257346630096436, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.0948, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3421727972626176, | |
| "grad_norm": 4.116374492645264, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.6779, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3421727972626176, | |
| "eval_loss": 0.6941483616828918, | |
| "eval_runtime": 3.3658, | |
| "eval_samples_per_second": 146.473, | |
| "eval_steps_per_second": 18.421, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3558597091531223, | |
| "grad_norm": 1.6155089139938354, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6285, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.369546621043627, | |
| "grad_norm": 1.031862497329712, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.5529, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.38323353293413176, | |
| "grad_norm": 1.5417953729629517, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.388, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.39692044482463645, | |
| "grad_norm": 1.5241392850875854, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.444, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.41060735671514115, | |
| "grad_norm": 1.4948774576187134, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.4667, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.42429426860564584, | |
| "grad_norm": 2.6010279655456543, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.5152, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.43798118049615054, | |
| "grad_norm": 3.134805202484131, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.4711, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4516680923866553, | |
| "grad_norm": 2.2566981315612793, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.9955, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.46535500427716, | |
| "grad_norm": 1.405287265777588, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.7662, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.47904191616766467, | |
| "grad_norm": 1.2101404666900635, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.6766, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.49272882805816937, | |
| "grad_norm": 1.462323546409607, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.7952, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5064157399486741, | |
| "grad_norm": 1.990311861038208, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.0486, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5201026518391788, | |
| "grad_norm": 1.2818390130996704, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.5182, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5337895637296834, | |
| "grad_norm": 0.8473722338676453, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.5777, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5474764756201882, | |
| "grad_norm": 1.3635905981063843, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.4073, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.561163387510693, | |
| "grad_norm": 1.370269536972046, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.3791, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5748502994011976, | |
| "grad_norm": 1.566010594367981, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.4403, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5885372112917023, | |
| "grad_norm": 1.6927084922790527, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.4468, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.602224123182207, | |
| "grad_norm": 1.8676680326461792, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.3234, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6159110350727117, | |
| "grad_norm": 1.352358102798462, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.6321, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6295979469632165, | |
| "grad_norm": 1.2584972381591797, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.907, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6432848588537211, | |
| "grad_norm": 1.0651510953903198, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.6019, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6569717707442259, | |
| "grad_norm": 1.1571849584579468, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.605, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6706586826347305, | |
| "grad_norm": 1.4067716598510742, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.7436, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6843455945252352, | |
| "grad_norm": 2.812145709991455, | |
| "learning_rate": 0.0, | |
| "loss": 1.1729, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6843455945252352, | |
| "eval_loss": 0.5393621325492859, | |
| "eval_runtime": 3.3647, | |
| "eval_samples_per_second": 146.522, | |
| "eval_steps_per_second": 18.427, | |
| "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 | |
| } | |