| { | |
| "best_metric": 1.6445624828338623, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.05919786887672044, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011839573775344087, | |
| "grad_norm": 27.89992332458496, | |
| "learning_rate": 5e-05, | |
| "loss": 6.5386, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011839573775344087, | |
| "eval_loss": 8.78251838684082, | |
| "eval_runtime": 51.8303, | |
| "eval_samples_per_second": 109.781, | |
| "eval_steps_per_second": 13.737, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0023679147550688174, | |
| "grad_norm": 30.31666374206543, | |
| "learning_rate": 0.0001, | |
| "loss": 7.0524, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0035518721326032263, | |
| "grad_norm": 31.726072311401367, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 6.8072, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004735829510137635, | |
| "grad_norm": 25.1890811920166, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 5.9375, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005919786887672044, | |
| "grad_norm": 17.413185119628906, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 4.9296, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007103744265206453, | |
| "grad_norm": 10.779654502868652, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 4.2199, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008287701642740862, | |
| "grad_norm": 10.736058235168457, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 3.6875, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00947165902027527, | |
| "grad_norm": 11.277963638305664, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.0933, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.010655616397809679, | |
| "grad_norm": 5.682778358459473, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.7098, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011839573775344088, | |
| "grad_norm": 7.735358238220215, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.8232, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013023531152878496, | |
| "grad_norm": 6.408288478851318, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.6756, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.014207488530412905, | |
| "grad_norm": 17.372358322143555, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.7677, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.015391445907947315, | |
| "grad_norm": 6.794909954071045, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.0829, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.016575403285481724, | |
| "grad_norm": 7.218286514282227, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.8899, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01775936066301613, | |
| "grad_norm": 10.104575157165527, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.8154, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01894331804055054, | |
| "grad_norm": 9.391705513000488, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.9853, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.02012727541808495, | |
| "grad_norm": 4.443215370178223, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.0018, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.021311232795619358, | |
| "grad_norm": 2.794290542602539, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.9346, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.022495190173153767, | |
| "grad_norm": 2.372328281402588, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.7992, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.023679147550688177, | |
| "grad_norm": 2.640687942504883, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.8727, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.024863104928222583, | |
| "grad_norm": 2.7497122287750244, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.8563, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.026047062305756992, | |
| "grad_norm": 2.6223559379577637, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.9953, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0272310196832914, | |
| "grad_norm": 3.1684682369232178, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 2.0066, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.02841497706082581, | |
| "grad_norm": 3.5079777240753174, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.0631, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02959893443836022, | |
| "grad_norm": 5.562316417694092, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.2727, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02959893443836022, | |
| "eval_loss": 1.830102801322937, | |
| "eval_runtime": 52.6393, | |
| "eval_samples_per_second": 108.094, | |
| "eval_steps_per_second": 13.526, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03078289181589463, | |
| "grad_norm": 6.333754539489746, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4631, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.031966849193429035, | |
| "grad_norm": 5.988046646118164, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.5457, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03315080657096345, | |
| "grad_norm": 4.666529178619385, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.6051, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.034334763948497854, | |
| "grad_norm": 3.764298915863037, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.5352, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03551872132603226, | |
| "grad_norm": 2.0698702335357666, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.62, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03670267870356667, | |
| "grad_norm": 2.650376796722412, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.6256, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03788663608110108, | |
| "grad_norm": 2.5088350772857666, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.6179, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.03907059345863549, | |
| "grad_norm": 3.2323107719421387, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.7883, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0402545508361699, | |
| "grad_norm": 3.3702969551086426, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.7842, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.04143850821370431, | |
| "grad_norm": 4.248794078826904, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.9471, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.042622465591238716, | |
| "grad_norm": 3.2208549976348877, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.8535, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04380642296877312, | |
| "grad_norm": 5.214898109436035, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 2.0621, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.044990380346307535, | |
| "grad_norm": 3.3143386840820312, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.4488, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.04617433772384194, | |
| "grad_norm": 2.913778066635132, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.2645, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.04735829510137635, | |
| "grad_norm": 2.4461803436279297, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.3157, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04854225247891076, | |
| "grad_norm": 2.449554681777954, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.3519, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.049726209856445165, | |
| "grad_norm": 2.1570582389831543, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.4461, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.05091016723397958, | |
| "grad_norm": 2.617800235748291, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.501, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.052094124611513984, | |
| "grad_norm": 2.0715324878692627, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.5023, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0532780819890484, | |
| "grad_norm": 2.4961233139038086, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.6375, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0544620393665828, | |
| "grad_norm": 2.1479310989379883, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.6086, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.05564599674411721, | |
| "grad_norm": 2.451838970184326, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.7377, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.05682995412165162, | |
| "grad_norm": 3.4158780574798584, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.9478, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.05801391149918603, | |
| "grad_norm": 3.3791892528533936, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.9543, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.05919786887672044, | |
| "grad_norm": 4.547910213470459, | |
| "learning_rate": 0.0, | |
| "loss": 2.1126, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05919786887672044, | |
| "eval_loss": 1.6445624828338623, | |
| "eval_runtime": 51.8608, | |
| "eval_samples_per_second": 109.717, | |
| "eval_steps_per_second": 13.729, | |
| "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": 8.33416392081408e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |