{ "best_metric": 1.2696001529693604, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.11802891708468574, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.002360578341693715, "grad_norm": 1.6582841873168945, "learning_rate": 5e-05, "loss": 2.5389, "step": 1 }, { "epoch": 0.002360578341693715, "eval_loss": 2.5085434913635254, "eval_runtime": 190.7916, "eval_samples_per_second": 14.959, "eval_steps_per_second": 1.871, "step": 1 }, { "epoch": 0.00472115668338743, "grad_norm": 1.9195595979690552, "learning_rate": 0.0001, "loss": 2.4467, "step": 2 }, { "epoch": 0.007081735025081145, "grad_norm": 1.9389009475708008, "learning_rate": 9.989294616193017e-05, "loss": 2.3606, "step": 3 }, { "epoch": 0.00944231336677486, "grad_norm": 2.7598226070404053, "learning_rate": 9.957224306869053e-05, "loss": 2.0687, "step": 4 }, { "epoch": 0.011802891708468575, "grad_norm": 1.9392552375793457, "learning_rate": 9.903926402016153e-05, "loss": 1.7583, "step": 5 }, { "epoch": 0.01416347005016229, "grad_norm": 1.4081734418869019, "learning_rate": 9.829629131445342e-05, "loss": 1.6312, "step": 6 }, { "epoch": 0.016524048391856005, "grad_norm": 1.4279638528823853, "learning_rate": 9.73465064747553e-05, "loss": 1.5276, "step": 7 }, { "epoch": 0.01888462673354972, "grad_norm": 1.8191046714782715, "learning_rate": 9.619397662556435e-05, "loss": 1.3788, "step": 8 }, { "epoch": 0.021245205075243436, "grad_norm": 1.9649258852005005, "learning_rate": 9.484363707663442e-05, "loss": 1.3271, "step": 9 }, { "epoch": 0.02360578341693715, "grad_norm": 1.860330581665039, "learning_rate": 9.330127018922194e-05, "loss": 1.2583, "step": 10 }, { "epoch": 0.025966361758630863, "grad_norm": 0.7525962591171265, "learning_rate": 9.157348061512727e-05, "loss": 1.1484, "step": 11 }, { "epoch": 0.02832694010032458, "grad_norm": 0.653978705406189, "learning_rate": 8.966766701456177e-05, "loss": 1.067, "step": 12 }, { "epoch": 0.030687518442018294, "grad_norm": 1.2077994346618652, "learning_rate": 8.759199037394887e-05, "loss": 1.717, "step": 13 }, { "epoch": 0.03304809678371201, "grad_norm": 1.0091378688812256, "learning_rate": 8.535533905932738e-05, "loss": 1.6345, "step": 14 }, { "epoch": 0.03540867512540572, "grad_norm": 0.6111875176429749, "learning_rate": 8.296729075500344e-05, "loss": 1.5061, "step": 15 }, { "epoch": 0.03776925346709944, "grad_norm": 0.6062878966331482, "learning_rate": 8.043807145043604e-05, "loss": 1.4739, "step": 16 }, { "epoch": 0.040129831808793155, "grad_norm": 0.5858495831489563, "learning_rate": 7.777851165098012e-05, "loss": 1.4096, "step": 17 }, { "epoch": 0.04249041015048687, "grad_norm": 0.537530243396759, "learning_rate": 7.500000000000001e-05, "loss": 1.3064, "step": 18 }, { "epoch": 0.04485098849218058, "grad_norm": 0.4932622015476227, "learning_rate": 7.211443451095007e-05, "loss": 1.3131, "step": 19 }, { "epoch": 0.0472115668338743, "grad_norm": 0.4686102867126465, "learning_rate": 6.91341716182545e-05, "loss": 1.2661, "step": 20 }, { "epoch": 0.049572145175568016, "grad_norm": 0.4631757140159607, "learning_rate": 6.607197326515808e-05, "loss": 1.153, "step": 21 }, { "epoch": 0.05193272351726173, "grad_norm": 0.4108315110206604, "learning_rate": 6.294095225512603e-05, "loss": 1.1622, "step": 22 }, { "epoch": 0.054293301858955444, "grad_norm": 0.39236700534820557, "learning_rate": 5.9754516100806423e-05, "loss": 1.055, "step": 23 }, { "epoch": 0.05665388020064916, "grad_norm": 0.39308735728263855, "learning_rate": 5.6526309611002594e-05, "loss": 0.9717, "step": 24 }, { "epoch": 0.05901445854234287, "grad_norm": 0.5479398965835571, "learning_rate": 5.327015646150716e-05, "loss": 0.9173, "step": 25 }, { "epoch": 0.05901445854234287, "eval_loss": 1.3017019033432007, "eval_runtime": 190.4112, "eval_samples_per_second": 14.989, "eval_steps_per_second": 1.875, "step": 25 }, { "epoch": 0.06137503688403659, "grad_norm": 0.6911665797233582, "learning_rate": 5e-05, "loss": 1.7851, "step": 26 }, { "epoch": 0.0637356152257303, "grad_norm": 0.6142681241035461, "learning_rate": 4.6729843538492847e-05, "loss": 1.5944, "step": 27 }, { "epoch": 0.06609619356742402, "grad_norm": 0.5505021810531616, "learning_rate": 4.347369038899744e-05, "loss": 1.4149, "step": 28 }, { "epoch": 0.06845677190911774, "grad_norm": 0.4889450669288635, "learning_rate": 4.0245483899193595e-05, "loss": 1.4167, "step": 29 }, { "epoch": 0.07081735025081144, "grad_norm": 0.41566815972328186, "learning_rate": 3.705904774487396e-05, "loss": 1.3479, "step": 30 }, { "epoch": 0.07317792859250516, "grad_norm": 0.43414074182510376, "learning_rate": 3.392802673484193e-05, "loss": 1.2498, "step": 31 }, { "epoch": 0.07553850693419888, "grad_norm": 0.3600168824195862, "learning_rate": 3.086582838174551e-05, "loss": 1.2066, "step": 32 }, { "epoch": 0.0778990852758926, "grad_norm": 0.4459245204925537, "learning_rate": 2.7885565489049946e-05, "loss": 1.1753, "step": 33 }, { "epoch": 0.08025966361758631, "grad_norm": 0.4490649998188019, "learning_rate": 2.500000000000001e-05, "loss": 1.1367, "step": 34 }, { "epoch": 0.08262024195928003, "grad_norm": 0.44567686319351196, "learning_rate": 2.2221488349019903e-05, "loss": 1.0871, "step": 35 }, { "epoch": 0.08498082030097374, "grad_norm": 0.47326353192329407, "learning_rate": 1.9561928549563968e-05, "loss": 1.0577, "step": 36 }, { "epoch": 0.08734139864266745, "grad_norm": 0.5644652247428894, "learning_rate": 1.703270924499656e-05, "loss": 0.9545, "step": 37 }, { "epoch": 0.08970197698436116, "grad_norm": 0.35153478384017944, "learning_rate": 1.4644660940672627e-05, "loss": 1.5445, "step": 38 }, { "epoch": 0.09206255532605488, "grad_norm": 0.36541318893432617, "learning_rate": 1.2408009626051137e-05, "loss": 1.5593, "step": 39 }, { "epoch": 0.0944231336677486, "grad_norm": 0.387804239988327, "learning_rate": 1.0332332985438248e-05, "loss": 1.4624, "step": 40 }, { "epoch": 0.09678371200944232, "grad_norm": 0.35317885875701904, "learning_rate": 8.426519384872733e-06, "loss": 1.4352, "step": 41 }, { "epoch": 0.09914429035113603, "grad_norm": 0.33535659313201904, "learning_rate": 6.698729810778065e-06, "loss": 1.3673, "step": 42 }, { "epoch": 0.10150486869282975, "grad_norm": 0.31882593035697937, "learning_rate": 5.156362923365588e-06, "loss": 1.316, "step": 43 }, { "epoch": 0.10386544703452345, "grad_norm": 0.32166722416877747, "learning_rate": 3.8060233744356633e-06, "loss": 1.2454, "step": 44 }, { "epoch": 0.10622602537621717, "grad_norm": 0.36580532789230347, "learning_rate": 2.653493525244721e-06, "loss": 1.1923, "step": 45 }, { "epoch": 0.10858660371791089, "grad_norm": 0.369552880525589, "learning_rate": 1.70370868554659e-06, "loss": 1.1445, "step": 46 }, { "epoch": 0.1109471820596046, "grad_norm": 0.3656086325645447, "learning_rate": 9.607359798384785e-07, "loss": 1.0958, "step": 47 }, { "epoch": 0.11330776040129832, "grad_norm": 0.39978259801864624, "learning_rate": 4.277569313094809e-07, "loss": 1.0955, "step": 48 }, { "epoch": 0.11566833874299204, "grad_norm": 0.4766823947429657, "learning_rate": 1.0705383806982606e-07, "loss": 0.9948, "step": 49 }, { "epoch": 0.11802891708468574, "grad_norm": 0.6909182667732239, "learning_rate": 0.0, "loss": 0.909, "step": 50 }, { "epoch": 0.11802891708468574, "eval_loss": 1.2696001529693604, "eval_runtime": 191.0143, "eval_samples_per_second": 14.941, "eval_steps_per_second": 1.869, "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": 5.968083617316864e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }