| { | |
| "best_metric": 0.8821292519569397, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.073827980804725, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0014765596160944998, | |
| "grad_norm": 0.1818460375070572, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1539, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014765596160944998, | |
| "eval_loss": 1.1631402969360352, | |
| "eval_runtime": 129.8622, | |
| "eval_samples_per_second": 35.137, | |
| "eval_steps_per_second": 4.397, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0029531192321889995, | |
| "grad_norm": 0.16521954536437988, | |
| "learning_rate": 0.0001, | |
| "loss": 1.004, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004429678848283499, | |
| "grad_norm": 0.1754024773836136, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.9722, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005906238464377999, | |
| "grad_norm": 0.15705806016921997, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.8649, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.007382798080472499, | |
| "grad_norm": 0.16214314103126526, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.8635, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008859357696566999, | |
| "grad_norm": 0.2013317346572876, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.7941, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0103359173126615, | |
| "grad_norm": 0.2235545665025711, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.7279, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.011812476928755998, | |
| "grad_norm": 0.21569271385669708, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.7931, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.013289036544850499, | |
| "grad_norm": 0.2180687040090561, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.6813, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.014765596160944998, | |
| "grad_norm": 0.25018155574798584, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.878, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.016242155777039496, | |
| "grad_norm": 0.2837720215320587, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.923, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.017718715393133997, | |
| "grad_norm": 0.44269615411758423, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.2738, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.019195275009228498, | |
| "grad_norm": 0.21942086517810822, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.0935, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.020671834625323, | |
| "grad_norm": 0.18628297746181488, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.0398, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0221483942414175, | |
| "grad_norm": 0.1614045947790146, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.8923, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.023624953857511996, | |
| "grad_norm": 0.15972940623760223, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.8274, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.025101513473606497, | |
| "grad_norm": 0.14789007604122162, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.7568, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.026578073089700997, | |
| "grad_norm": 0.15202145278453827, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.7883, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.028054632705795498, | |
| "grad_norm": 0.15781249105930328, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.6665, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.029531192321889995, | |
| "grad_norm": 0.16561953723430634, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.6958, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.031007751937984496, | |
| "grad_norm": 0.18272924423217773, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.6805, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03248431155407899, | |
| "grad_norm": 0.19771401584148407, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.653, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0339608711701735, | |
| "grad_norm": 0.2506113350391388, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.7537, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.035437430786267994, | |
| "grad_norm": 0.32823091745376587, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.9407, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0369139904023625, | |
| "grad_norm": 1.0504305362701416, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.7177, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0369139904023625, | |
| "eval_loss": 0.9141214489936829, | |
| "eval_runtime": 131.0966, | |
| "eval_samples_per_second": 34.806, | |
| "eval_steps_per_second": 4.356, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.038390550018456995, | |
| "grad_norm": 0.15258188545703888, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0821, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03986710963455149, | |
| "grad_norm": 0.16078627109527588, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.9651, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.041343669250646, | |
| "grad_norm": 0.16188524663448334, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.821, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.042820228866740494, | |
| "grad_norm": 0.17332187294960022, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.9002, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.044296788482835, | |
| "grad_norm": 0.18269848823547363, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.7494, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.045773348098929495, | |
| "grad_norm": 0.17247238755226135, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.6904, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.04724990771502399, | |
| "grad_norm": 0.18827833235263824, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.6211, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.048726467331118496, | |
| "grad_norm": 0.2117096185684204, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.6906, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.05020302694721299, | |
| "grad_norm": 0.23306560516357422, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.678, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.05167958656330749, | |
| "grad_norm": 0.267149418592453, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.7681, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.053156146179401995, | |
| "grad_norm": 0.34443435072898865, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.8942, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.05463270579549649, | |
| "grad_norm": 0.545831561088562, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.2254, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.056109265411590996, | |
| "grad_norm": 0.193207785487175, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.1269, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.05758582502768549, | |
| "grad_norm": 0.16855843365192413, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.0996, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.05906238464377999, | |
| "grad_norm": 0.14967533946037292, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.9894, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.060538944259874494, | |
| "grad_norm": 0.1433860808610916, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.8061, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.06201550387596899, | |
| "grad_norm": 0.14255517721176147, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.8361, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.06349206349206349, | |
| "grad_norm": 0.14755815267562866, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.6904, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.06496862310815799, | |
| "grad_norm": 0.16876764595508575, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.6982, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0664451827242525, | |
| "grad_norm": 0.1740587055683136, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.7029, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.067921742340347, | |
| "grad_norm": 0.19714155793190002, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.6876, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.06939830195644149, | |
| "grad_norm": 0.21021583676338196, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.6576, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.07087486157253599, | |
| "grad_norm": 0.2548488974571228, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.7183, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.07235142118863049, | |
| "grad_norm": 0.34631800651550293, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.8755, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.073827980804725, | |
| "grad_norm": 0.8000274896621704, | |
| "learning_rate": 0.0, | |
| "loss": 1.6595, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.073827980804725, | |
| "eval_loss": 0.8821292519569397, | |
| "eval_runtime": 130.0288, | |
| "eval_samples_per_second": 35.092, | |
| "eval_steps_per_second": 4.391, | |
| "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": 5.6328454211108864e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |