| { | |
| "best_metric": 2.0215489864349365, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.11555683952043912, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0023111367904087824, | |
| "grad_norm": 4.867423057556152, | |
| "learning_rate": 5e-05, | |
| "loss": 8.8266, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0023111367904087824, | |
| "eval_loss": 10.756378173828125, | |
| "eval_runtime": 88.5333, | |
| "eval_samples_per_second": 32.925, | |
| "eval_steps_per_second": 4.123, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004622273580817565, | |
| "grad_norm": 4.943393230438232, | |
| "learning_rate": 0.0001, | |
| "loss": 8.5569, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006933410371226347, | |
| "grad_norm": 5.516867160797119, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 8.935, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00924454716163513, | |
| "grad_norm": 12.486185073852539, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 8.4587, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011555683952043911, | |
| "grad_norm": 8.330039024353027, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 7.6042, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.013866820742452693, | |
| "grad_norm": 7.818983554840088, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 5.6482, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.016177957532861477, | |
| "grad_norm": 6.784229278564453, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 5.0793, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01848909432327026, | |
| "grad_norm": 6.701813697814941, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.2245, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02080023111367904, | |
| "grad_norm": 7.068186283111572, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 3.9385, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.023111367904087823, | |
| "grad_norm": 4.6960554122924805, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 3.1494, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.025422504694496605, | |
| "grad_norm": 7.6565937995910645, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 3.0822, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.027733641484905387, | |
| "grad_norm": 8.551094055175781, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 3.2583, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03004477827531417, | |
| "grad_norm": 10.7207612991333, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.85, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.032355915065722954, | |
| "grad_norm": 6.115133285522461, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.4146, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03466705185613173, | |
| "grad_norm": 3.4856739044189453, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.2936, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03697818864654052, | |
| "grad_norm": 7.104086875915527, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.4697, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.039289325436949296, | |
| "grad_norm": 6.850383281707764, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.5218, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04160046222735808, | |
| "grad_norm": 2.007159948348999, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.0478, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04391159901776687, | |
| "grad_norm": 4.289352893829346, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.1116, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.046222735808175645, | |
| "grad_norm": 3.054633855819702, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.9732, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04853387259858443, | |
| "grad_norm": 2.677506685256958, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.0099, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05084500938899321, | |
| "grad_norm": 1.43423593044281, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.0625, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.053156146179401995, | |
| "grad_norm": 1.656862497329712, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 2.2018, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05546728296981077, | |
| "grad_norm": 1.8817427158355713, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.3284, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05777841976021956, | |
| "grad_norm": 2.1708879470825195, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.6079, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05777841976021956, | |
| "eval_loss": 2.129227638244629, | |
| "eval_runtime": 88.5454, | |
| "eval_samples_per_second": 32.921, | |
| "eval_steps_per_second": 4.122, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06008955655062834, | |
| "grad_norm": 2.029036521911621, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7592, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06240069334103712, | |
| "grad_norm": 1.2845566272735596, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.7265, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06471183013144591, | |
| "grad_norm": 1.540757417678833, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.8619, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0670229669218547, | |
| "grad_norm": 1.925443410873413, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 2.0363, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.06933410371226346, | |
| "grad_norm": 1.3662012815475464, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.963, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07164524050267225, | |
| "grad_norm": 1.4941176176071167, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.7522, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.07395637729308104, | |
| "grad_norm": 1.380921483039856, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.8181, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.07626751408348982, | |
| "grad_norm": 0.9916651844978333, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.7789, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.07857865087389859, | |
| "grad_norm": 1.4869825839996338, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.8595, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08088978766430738, | |
| "grad_norm": 1.5238620042800903, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 2.0914, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08320092445471616, | |
| "grad_norm": 0.9279425144195557, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 2.1554, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.08551206124512495, | |
| "grad_norm": 1.8256399631500244, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 2.2334, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.08782319803553373, | |
| "grad_norm": 1.595869779586792, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.9371, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0901343348259425, | |
| "grad_norm": 2.3368899822235107, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.729, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.09244547161635129, | |
| "grad_norm": 1.7104312181472778, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.7021, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09475660840676008, | |
| "grad_norm": 1.2494852542877197, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.8049, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.09706774519716886, | |
| "grad_norm": 0.9061923623085022, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.956, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.09937888198757763, | |
| "grad_norm": 0.9129108190536499, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.7123, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.10169001877798642, | |
| "grad_norm": 1.039075255393982, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.7464, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1040011555683952, | |
| "grad_norm": 1.1822948455810547, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.8953, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.10631229235880399, | |
| "grad_norm": 1.2711695432662964, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.8632, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.10862342914921277, | |
| "grad_norm": 1.3928056955337524, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.9191, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.11093456593962155, | |
| "grad_norm": 1.9826236963272095, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 2.1083, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.11324570273003033, | |
| "grad_norm": 1.459694504737854, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 2.0827, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.11555683952043912, | |
| "grad_norm": 1.7293628454208374, | |
| "learning_rate": 0.0, | |
| "loss": 2.5267, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11555683952043912, | |
| "eval_loss": 2.0215489864349365, | |
| "eval_runtime": 88.588, | |
| "eval_samples_per_second": 32.905, | |
| "eval_steps_per_second": 4.12, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |