| { | |
| "best_metric": 2.7374379634857178, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.6872852233676976, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013745704467353952, | |
| "grad_norm": 0.633126974105835, | |
| "learning_rate": 5e-05, | |
| "loss": 3.7941, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013745704467353952, | |
| "eval_loss": 3.7618861198425293, | |
| "eval_runtime": 30.5394, | |
| "eval_samples_per_second": 16.045, | |
| "eval_steps_per_second": 2.03, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.027491408934707903, | |
| "grad_norm": 0.654931902885437, | |
| "learning_rate": 0.0001, | |
| "loss": 3.7007, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.041237113402061855, | |
| "grad_norm": 0.6610121726989746, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 3.8049, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.054982817869415807, | |
| "grad_norm": 0.6573833227157593, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.6173, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06872852233676977, | |
| "grad_norm": 0.6862820982933044, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.5289, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08247422680412371, | |
| "grad_norm": 0.6219794750213623, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.4455, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09621993127147767, | |
| "grad_norm": 0.6177584528923035, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 3.3436, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.10996563573883161, | |
| "grad_norm": 0.5731457471847534, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.2447, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.12371134020618557, | |
| "grad_norm": 0.6419684290885925, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 3.2408, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.13745704467353953, | |
| "grad_norm": 0.6953072547912598, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 3.0887, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15120274914089346, | |
| "grad_norm": 0.8918637037277222, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 3.1175, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.16494845360824742, | |
| "grad_norm": 1.198569655418396, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 3.2409, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.17869415807560138, | |
| "grad_norm": 0.6394647359848022, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 3.2072, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.19243986254295534, | |
| "grad_norm": 0.7178822755813599, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.1186, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.20618556701030927, | |
| "grad_norm": 0.7316906452178955, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 3.1448, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.21993127147766323, | |
| "grad_norm": 0.7377943992614746, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.9385, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.23367697594501718, | |
| "grad_norm": 0.646327793598175, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 3.0327, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.24742268041237114, | |
| "grad_norm": 0.5574729442596436, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 3.0255, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2611683848797251, | |
| "grad_norm": 0.5094675421714783, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.9431, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.27491408934707906, | |
| "grad_norm": 0.4401124119758606, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.8594, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.28865979381443296, | |
| "grad_norm": 0.4236370325088501, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.8503, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3024054982817869, | |
| "grad_norm": 0.48745620250701904, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.9523, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3161512027491409, | |
| "grad_norm": 0.5854716300964355, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 2.8143, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.32989690721649484, | |
| "grad_norm": 0.7844096422195435, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.6956, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3436426116838488, | |
| "grad_norm": 1.3506336212158203, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.992, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3436426116838488, | |
| "eval_loss": 2.8326058387756348, | |
| "eval_runtime": 30.509, | |
| "eval_samples_per_second": 16.061, | |
| "eval_steps_per_second": 2.032, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.35738831615120276, | |
| "grad_norm": 0.5904625654220581, | |
| "learning_rate": 5e-05, | |
| "loss": 3.0126, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3711340206185567, | |
| "grad_norm": 0.6415864825248718, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 2.9682, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3848797250859107, | |
| "grad_norm": 0.5782291889190674, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 2.9303, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.39862542955326463, | |
| "grad_norm": 0.5609015822410583, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 2.9249, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.41237113402061853, | |
| "grad_norm": 0.48684611916542053, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 2.8978, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4261168384879725, | |
| "grad_norm": 0.45882076025009155, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 2.8614, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.43986254295532645, | |
| "grad_norm": 0.40644049644470215, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.7954, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4536082474226804, | |
| "grad_norm": 0.4016781449317932, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 2.7111, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.46735395189003437, | |
| "grad_norm": 0.45421966910362244, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.7871, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.48109965635738833, | |
| "grad_norm": 0.48663410544395447, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 2.7124, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4948453608247423, | |
| "grad_norm": 0.6618165373802185, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 2.921, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5085910652920962, | |
| "grad_norm": 0.9185125231742859, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 2.6715, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5223367697594502, | |
| "grad_norm": 0.3857472538948059, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.971, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5360824742268041, | |
| "grad_norm": 0.3716031312942505, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 2.9631, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5498281786941581, | |
| "grad_norm": 0.4130760133266449, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 2.9389, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.563573883161512, | |
| "grad_norm": 0.37855178117752075, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 2.8596, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5773195876288659, | |
| "grad_norm": 0.3730044364929199, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.8893, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5910652920962199, | |
| "grad_norm": 0.399122953414917, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 2.7885, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6048109965635738, | |
| "grad_norm": 0.38850271701812744, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.8442, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6185567010309279, | |
| "grad_norm": 0.41439515352249146, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 2.652, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6323024054982818, | |
| "grad_norm": 0.41602662205696106, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 2.6787, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6460481099656358, | |
| "grad_norm": 0.4596008360385895, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 2.7676, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6597938144329897, | |
| "grad_norm": 0.4760560691356659, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 2.6652, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6735395189003437, | |
| "grad_norm": 0.6931067109107971, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 2.59, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6872852233676976, | |
| "grad_norm": 1.223355770111084, | |
| "learning_rate": 0.0, | |
| "loss": 2.7209, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6872852233676976, | |
| "eval_loss": 2.7374379634857178, | |
| "eval_runtime": 30.5331, | |
| "eval_samples_per_second": 16.048, | |
| "eval_steps_per_second": 2.031, | |
| "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": 5.624057810649088e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |