| { | |
| "best_metric": 3.5846145153045654, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.013916189747247204, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002783237949449441, | |
| "grad_norm": 0.8763601779937744, | |
| "learning_rate": 5e-05, | |
| "loss": 4.2308, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002783237949449441, | |
| "eval_loss": 4.522602081298828, | |
| "eval_runtime": 277.9908, | |
| "eval_samples_per_second": 87.071, | |
| "eval_steps_per_second": 10.885, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005566475898898882, | |
| "grad_norm": 0.9096955060958862, | |
| "learning_rate": 0.0001, | |
| "loss": 4.3967, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008349713848348322, | |
| "grad_norm": 0.9401690363883972, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 4.6497, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011132951797797764, | |
| "grad_norm": 0.933310329914093, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 4.3687, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0013916189747247203, | |
| "grad_norm": 0.8714249134063721, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 4.5192, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0016699427696696644, | |
| "grad_norm": 0.8110895752906799, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 4.1845, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0019482665646146085, | |
| "grad_norm": 0.7333737015724182, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 4.0796, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002226590359559553, | |
| "grad_norm": 0.7350586652755737, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.1837, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002504914154504497, | |
| "grad_norm": 0.80406254529953, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 3.9974, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0027832379494494405, | |
| "grad_norm": 0.8980859518051147, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 4.0257, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0030615617443943846, | |
| "grad_norm": 0.8786382079124451, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 4.0053, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0033398855393393287, | |
| "grad_norm": 0.8526495099067688, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 3.8001, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.003618209334284273, | |
| "grad_norm": 0.877073347568512, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 3.948, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.003896533129229217, | |
| "grad_norm": 0.8117573261260986, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.7985, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.004174856924174161, | |
| "grad_norm": 0.774189293384552, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 3.6935, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004453180719119106, | |
| "grad_norm": 0.7428269982337952, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 3.7893, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004731504514064049, | |
| "grad_norm": 0.6813673973083496, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 3.7173, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.005009828309008994, | |
| "grad_norm": 0.7335220575332642, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 3.803, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.005288152103953937, | |
| "grad_norm": 0.6577491164207458, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 3.7833, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.005566475898898881, | |
| "grad_norm": 0.6891123056411743, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.6431, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005844799693843826, | |
| "grad_norm": 0.6233853697776794, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 3.6553, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.006123123488788769, | |
| "grad_norm": 0.7227319478988647, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 3.7862, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.006401447283733714, | |
| "grad_norm": 0.6844795942306519, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 3.5573, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0066797710786786575, | |
| "grad_norm": 0.6574005484580994, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 3.4255, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.006958094873623602, | |
| "grad_norm": 0.800177276134491, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 3.8353, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006958094873623602, | |
| "eval_loss": 3.6570544242858887, | |
| "eval_runtime": 278.6942, | |
| "eval_samples_per_second": 86.851, | |
| "eval_steps_per_second": 10.858, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007236418668568546, | |
| "grad_norm": 0.6127904057502747, | |
| "learning_rate": 5e-05, | |
| "loss": 3.5487, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.00751474246351349, | |
| "grad_norm": 0.5885407328605652, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 3.5667, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.007793066258458434, | |
| "grad_norm": 0.5534403920173645, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 3.6743, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.008071390053403378, | |
| "grad_norm": 0.5488076210021973, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 3.5629, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.008349713848348322, | |
| "grad_norm": 0.5961767435073853, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 3.7467, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008628037643293266, | |
| "grad_norm": 0.6138086318969727, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 3.6084, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.008906361438238211, | |
| "grad_norm": 0.5839231014251709, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.565, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.009184685233183155, | |
| "grad_norm": 0.5631768703460693, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 3.5084, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.009463009028128098, | |
| "grad_norm": 0.5296745300292969, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 3.522, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.009741332823073042, | |
| "grad_norm": 0.5764396786689758, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 3.5396, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.010019656618017988, | |
| "grad_norm": 0.5587449073791504, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 3.4536, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.010297980412962931, | |
| "grad_norm": 0.5895846486091614, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 3.4087, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.010576304207907875, | |
| "grad_norm": 0.5716074109077454, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.5968, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.010854628002852819, | |
| "grad_norm": 0.567530632019043, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 3.5489, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.011132951797797762, | |
| "grad_norm": 0.5670365691184998, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 3.7333, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.011411275592742708, | |
| "grad_norm": 0.5206403136253357, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 3.5818, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.011689599387687651, | |
| "grad_norm": 0.5400410890579224, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 3.5827, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.011967923182632595, | |
| "grad_norm": 0.5015483498573303, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 3.4444, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.012246246977577539, | |
| "grad_norm": 0.5309357643127441, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.6769, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.012524570772522484, | |
| "grad_norm": 0.5056427121162415, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 3.6734, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.012802894567467428, | |
| "grad_norm": 0.5647780895233154, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 3.5375, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.013081218362412371, | |
| "grad_norm": 0.5235017538070679, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 3.4555, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.013359542157357315, | |
| "grad_norm": 0.5554877519607544, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 3.5906, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.01363786595230226, | |
| "grad_norm": 0.6095041036605835, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 3.4301, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.013916189747247204, | |
| "grad_norm": 0.6034445762634277, | |
| "learning_rate": 0.0, | |
| "loss": 3.636, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.013916189747247204, | |
| "eval_loss": 3.5846145153045654, | |
| "eval_runtime": 278.0802, | |
| "eval_samples_per_second": 87.043, | |
| "eval_steps_per_second": 10.882, | |
| "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": 1.059536353886208e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |