| { | |
| "best_metric": 2.2921998500823975, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.05148667782211353, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0010297335564422706, | |
| "grad_norm": 0.8929134607315063, | |
| "learning_rate": 5e-05, | |
| "loss": 2.4557, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010297335564422706, | |
| "eval_loss": 2.7570552825927734, | |
| "eval_runtime": 175.7225, | |
| "eval_samples_per_second": 37.235, | |
| "eval_steps_per_second": 4.655, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0020594671128845413, | |
| "grad_norm": 0.9756417274475098, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5202, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0030892006693268117, | |
| "grad_norm": 0.92064368724823, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.5701, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0041189342257690826, | |
| "grad_norm": 0.6526315808296204, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.5096, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005148667782211353, | |
| "grad_norm": 0.5155959129333496, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.4502, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006178401338653623, | |
| "grad_norm": 0.8588674664497375, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.5344, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007208134895095894, | |
| "grad_norm": 0.7088305950164795, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.5974, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.008237868451538165, | |
| "grad_norm": 0.49732106924057007, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.4481, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.009267602007980436, | |
| "grad_norm": 0.4471207559108734, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.3997, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010297335564422706, | |
| "grad_norm": 0.46612808108329773, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.3746, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.011327069120864976, | |
| "grad_norm": 0.5947970151901245, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.3757, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.012356802677307247, | |
| "grad_norm": 0.8185470104217529, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.3324, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.013386536233749517, | |
| "grad_norm": 0.5207706093788147, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.2878, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.014416269790191788, | |
| "grad_norm": 0.5401433110237122, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.3362, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.015446003346634058, | |
| "grad_norm": 0.42743393778800964, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.3843, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01647573690307633, | |
| "grad_norm": 0.3370291292667389, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.3383, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0175054704595186, | |
| "grad_norm": 0.303751140832901, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.3253, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01853520401596087, | |
| "grad_norm": 0.3212032914161682, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.349, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01956493757240314, | |
| "grad_norm": 0.3480638265609741, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.3595, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.020594671128845412, | |
| "grad_norm": 0.3701308071613312, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.3459, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02162440468528768, | |
| "grad_norm": 0.3703393042087555, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.3096, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.022654138241729953, | |
| "grad_norm": 0.3946841359138489, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.3381, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.02368387179817222, | |
| "grad_norm": 0.4017675817012787, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 2.3173, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.024713605354614494, | |
| "grad_norm": 0.45406264066696167, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.3222, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.025743338911056766, | |
| "grad_norm": 0.506672739982605, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.3418, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.025743338911056766, | |
| "eval_loss": 2.3048317432403564, | |
| "eval_runtime": 395.8459, | |
| "eval_samples_per_second": 16.529, | |
| "eval_steps_per_second": 2.066, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.026773072467499034, | |
| "grad_norm": 0.19370198249816895, | |
| "learning_rate": 5e-05, | |
| "loss": 2.1976, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.027802806023941307, | |
| "grad_norm": 0.24108867347240448, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 2.3017, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.028832539580383575, | |
| "grad_norm": 0.27671366930007935, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 2.2344, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.029862273136825847, | |
| "grad_norm": 0.31665876507759094, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 2.3259, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.030892006693268116, | |
| "grad_norm": 0.31963345408439636, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 2.2986, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03192174024971039, | |
| "grad_norm": 0.3043651580810547, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 2.3242, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03295147380615266, | |
| "grad_norm": 0.31157439947128296, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.3512, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.033981207362594926, | |
| "grad_norm": 0.3314283490180969, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 2.2847, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0350109409190372, | |
| "grad_norm": 0.32019686698913574, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.3864, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.03604067447547947, | |
| "grad_norm": 0.36727410554885864, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 2.3033, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03707040803192174, | |
| "grad_norm": 0.37023940682411194, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 2.3378, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.03810014158836401, | |
| "grad_norm": 0.41137710213661194, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 2.2779, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.03912987514480628, | |
| "grad_norm": 0.21810898184776306, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.2157, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.04015960870124855, | |
| "grad_norm": 0.1864442676305771, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 2.2263, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.041189342257690824, | |
| "grad_norm": 0.22965551912784576, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 2.2934, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.042219075814133096, | |
| "grad_norm": 0.21589107811450958, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 2.3018, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.04324880937057536, | |
| "grad_norm": 0.23642565310001373, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.2772, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.04427854292701763, | |
| "grad_norm": 0.25743380188941956, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 2.2781, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.045308276483459906, | |
| "grad_norm": 0.26554742455482483, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.344, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.04633801003990218, | |
| "grad_norm": 0.2861109673976898, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 2.3187, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04736774359634444, | |
| "grad_norm": 0.3041130304336548, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 2.3098, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.048397477152786715, | |
| "grad_norm": 0.3207823634147644, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 2.2769, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.04942721070922899, | |
| "grad_norm": 0.38269367814064026, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 2.4022, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.05045694426567126, | |
| "grad_norm": 0.39273184537887573, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 2.3109, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.05148667782211353, | |
| "grad_norm": 0.5086196660995483, | |
| "learning_rate": 0.0, | |
| "loss": 2.3821, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05148667782211353, | |
| "eval_loss": 2.2921998500823975, | |
| "eval_runtime": 284.4612, | |
| "eval_samples_per_second": 23.001, | |
| "eval_steps_per_second": 2.876, | |
| "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": 5.971813667564421e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |