| { | |
| "best_metric": 1.3559179306030273, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.01113368775572689, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00044534751022907564, | |
| "grad_norm": 47.07219696044922, | |
| "learning_rate": 5e-05, | |
| "loss": 5.2543, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00044534751022907564, | |
| "eval_loss": 6.243781089782715, | |
| "eval_runtime": 744.7627, | |
| "eval_samples_per_second": 20.313, | |
| "eval_steps_per_second": 2.539, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008906950204581513, | |
| "grad_norm": 45.64754867553711, | |
| "learning_rate": 0.0001, | |
| "loss": 5.2971, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001336042530687227, | |
| "grad_norm": 47.91440200805664, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 5.4586, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0017813900409163026, | |
| "grad_norm": 70.59400939941406, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 5.7296, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002226737551145378, | |
| "grad_norm": 76.9289779663086, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 4.7535, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002672085061374454, | |
| "grad_norm": 85.37005615234375, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 4.4255, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0031174325716035295, | |
| "grad_norm": 78.97339630126953, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 3.985, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003562780081832605, | |
| "grad_norm": 72.35723876953125, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.5995, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00400812759206168, | |
| "grad_norm": 47.47407150268555, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 3.2972, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004453475102290756, | |
| "grad_norm": 50.4141731262207, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.7779, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0048988226125198315, | |
| "grad_norm": 49.30196762084961, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.5713, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005344170122748908, | |
| "grad_norm": 48.11530303955078, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.6868, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0057895176329779835, | |
| "grad_norm": 44.87623596191406, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.4733, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006234865143207059, | |
| "grad_norm": 37.1474494934082, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.1475, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.006680212653436135, | |
| "grad_norm": 39.766693115234375, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.8127, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00712556016366521, | |
| "grad_norm": 44.069801330566406, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.7889, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.007570907673894286, | |
| "grad_norm": 41.7119255065918, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.8528, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.00801625518412336, | |
| "grad_norm": 44.02607345581055, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.6579, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.008461602694352437, | |
| "grad_norm": 44.727508544921875, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.592, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.008906950204581512, | |
| "grad_norm": 30.102256774902344, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.3037, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009352297714810588, | |
| "grad_norm": 35.799583435058594, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.3378, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.009797645225039663, | |
| "grad_norm": 38.51300811767578, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.5105, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01024299273526874, | |
| "grad_norm": 37.920658111572266, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.4866, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.010688340245497816, | |
| "grad_norm": 36.737457275390625, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.3023, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01113368775572689, | |
| "grad_norm": 34.89516830444336, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.4595, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01113368775572689, | |
| "eval_loss": 1.3559179306030273, | |
| "eval_runtime": 747.1899, | |
| "eval_samples_per_second": 20.247, | |
| "eval_steps_per_second": 2.531, | |
| "step": 25 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.476375360176128e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |