| { | |
| "best_metric": 0.22447234392166138, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.49443757725587145, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009888751545117428, | |
| "grad_norm": 0.9498234987258911, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0219, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009888751545117428, | |
| "eval_loss": 1.3110345602035522, | |
| "eval_runtime": 7.7849, | |
| "eval_samples_per_second": 87.477, | |
| "eval_steps_per_second": 11.047, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.019777503090234856, | |
| "grad_norm": 1.00467050075531, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1021, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.029666254635352288, | |
| "grad_norm": 0.9182856678962708, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.0862, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03955500618046971, | |
| "grad_norm": 0.7954713106155396, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.9706, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.049443757725587144, | |
| "grad_norm": 0.7194277048110962, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.9129, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.059332509270704575, | |
| "grad_norm": 0.7397326231002808, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.8595, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.069221260815822, | |
| "grad_norm": 0.8078145980834961, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.7941, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07911001236093942, | |
| "grad_norm": 0.8605826497077942, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.7831, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08899876390605686, | |
| "grad_norm": 1.0141797065734863, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.705, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09888751545117429, | |
| "grad_norm": 0.9999209642410278, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.5849, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10877626699629171, | |
| "grad_norm": 1.2414041757583618, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.5656, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.11866501854140915, | |
| "grad_norm": 2.1830151081085205, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.7165, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.12855377008652658, | |
| "grad_norm": 1.1881226301193237, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.6026, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.138442521631644, | |
| "grad_norm": 0.7219433784484863, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.3601, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.14833127317676142, | |
| "grad_norm": 0.6777482628822327, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.3757, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.15822002472187885, | |
| "grad_norm": 0.8717928528785706, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.3428, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1681087762669963, | |
| "grad_norm": 0.6932504773139954, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.3448, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.17799752781211373, | |
| "grad_norm": 0.42397570610046387, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.3069, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.18788627935723115, | |
| "grad_norm": 0.39525195956230164, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.3032, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.19777503090234858, | |
| "grad_norm": 0.47349047660827637, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.3345, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.207663782447466, | |
| "grad_norm": 0.4722050428390503, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.3035, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.21755253399258342, | |
| "grad_norm": 0.399589478969574, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.305, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.22744128553770088, | |
| "grad_norm": 0.39039430022239685, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.2853, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2373300370828183, | |
| "grad_norm": 0.39863502979278564, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.2797, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.24721878862793573, | |
| "grad_norm": 0.6198586225509644, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.4673, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.24721878862793573, | |
| "eval_loss": 0.2853955626487732, | |
| "eval_runtime": 7.8138, | |
| "eval_samples_per_second": 87.154, | |
| "eval_steps_per_second": 11.006, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.25710754017305315, | |
| "grad_norm": 0.2861676812171936, | |
| "learning_rate": 5e-05, | |
| "loss": 0.197, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.2669962917181706, | |
| "grad_norm": 0.33408257365226746, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.2081, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.276885043263288, | |
| "grad_norm": 0.35981813073158264, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.2318, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.2867737948084054, | |
| "grad_norm": 0.3032781779766083, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.2176, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.29666254635352285, | |
| "grad_norm": 0.3172026574611664, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.2132, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3065512978986403, | |
| "grad_norm": 0.4827124774456024, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.2184, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.3164400494437577, | |
| "grad_norm": 0.3745855689048767, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.2186, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.3263288009888752, | |
| "grad_norm": 0.2829774022102356, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.2105, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.3362175525339926, | |
| "grad_norm": 0.39190301299095154, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.2478, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.34610630407911, | |
| "grad_norm": 0.35959282517433167, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.2367, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.35599505562422745, | |
| "grad_norm": 0.411085307598114, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.2345, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.3658838071693449, | |
| "grad_norm": 0.40547600388526917, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.2819, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3757725587144623, | |
| "grad_norm": 0.4824545979499817, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.2983, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3856613102595797, | |
| "grad_norm": 0.329110711812973, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.1677, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.39555006180469715, | |
| "grad_norm": 0.356700599193573, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.1869, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4054388133498146, | |
| "grad_norm": 0.2657184302806854, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.1838, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.415327564894932, | |
| "grad_norm": 0.2612319886684418, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.1941, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.4252163164400494, | |
| "grad_norm": 0.24629908800125122, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.1719, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.43510506798516685, | |
| "grad_norm": 0.3054180145263672, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.1964, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.44499381953028433, | |
| "grad_norm": 0.3393312096595764, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.1916, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.45488257107540175, | |
| "grad_norm": 0.460034042596817, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.2208, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.4647713226205192, | |
| "grad_norm": 0.3530525863170624, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.202, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.4746600741656366, | |
| "grad_norm": 0.32375937700271606, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.2218, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.484548825710754, | |
| "grad_norm": 0.3782595694065094, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.2258, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.49443757725587145, | |
| "grad_norm": 0.9745090007781982, | |
| "learning_rate": 0.0, | |
| "loss": 0.4591, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.49443757725587145, | |
| "eval_loss": 0.22447234392166138, | |
| "eval_runtime": 7.8034, | |
| "eval_samples_per_second": 87.27, | |
| "eval_steps_per_second": 11.021, | |
| "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 | |
| } | |