| { | |
| "best_metric": 1.6362560987472534, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.6514657980456026, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013029315960912053, | |
| "grad_norm": 3.9804611206054688, | |
| "learning_rate": 5e-05, | |
| "loss": 4.4207, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013029315960912053, | |
| "eval_loss": 6.510675430297852, | |
| "eval_runtime": 15.7425, | |
| "eval_samples_per_second": 32.841, | |
| "eval_steps_per_second": 4.129, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.026058631921824105, | |
| "grad_norm": 4.506410121917725, | |
| "learning_rate": 0.0001, | |
| "loss": 4.8966, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03908794788273615, | |
| "grad_norm": 5.26943302154541, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 4.8095, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05211726384364821, | |
| "grad_norm": 4.4826979637146, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 4.1138, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06514657980456026, | |
| "grad_norm": 4.836989402770996, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.2671, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0781758957654723, | |
| "grad_norm": 3.6174402236938477, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.7413, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09120521172638436, | |
| "grad_norm": 3.1943180561065674, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.733, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.10423452768729642, | |
| "grad_norm": 3.414454936981201, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.4486, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.11726384364820847, | |
| "grad_norm": 3.725461959838867, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.2302, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.13029315960912052, | |
| "grad_norm": 2.78312087059021, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.1825, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14332247557003258, | |
| "grad_norm": 3.028385877609253, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.8801, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1563517915309446, | |
| "grad_norm": 7.067371845245361, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.61, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.16938110749185667, | |
| "grad_norm": 9.130725860595703, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.9379, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.18241042345276873, | |
| "grad_norm": 7.21467399597168, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.6888, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.19543973941368079, | |
| "grad_norm": 3.8242032527923584, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.3183, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.20846905537459284, | |
| "grad_norm": 2.006392478942871, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.3413, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.22149837133550487, | |
| "grad_norm": 1.9493643045425415, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.1485, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.23452768729641693, | |
| "grad_norm": 2.1967434883117676, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.0753, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.247557003257329, | |
| "grad_norm": 2.3730552196502686, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.1074, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.26058631921824105, | |
| "grad_norm": 2.259002685546875, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.0209, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2736156351791531, | |
| "grad_norm": 1.7629563808441162, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.8868, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.28664495114006516, | |
| "grad_norm": 1.8788514137268066, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.8753, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2996742671009772, | |
| "grad_norm": 1.9790754318237305, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.4624, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3127035830618892, | |
| "grad_norm": 1.9001291990280151, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.2073, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3257328990228013, | |
| "grad_norm": 7.722370624542236, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.5946, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3257328990228013, | |
| "eval_loss": 1.85377836227417, | |
| "eval_runtime": 15.7082, | |
| "eval_samples_per_second": 32.913, | |
| "eval_steps_per_second": 4.138, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.33876221498371334, | |
| "grad_norm": 3.0881364345550537, | |
| "learning_rate": 5e-05, | |
| "loss": 2.3289, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3517915309446254, | |
| "grad_norm": 2.868217706680298, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 2.2265, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.36482084690553745, | |
| "grad_norm": 2.419745445251465, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.9786, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3778501628664495, | |
| "grad_norm": 2.326369047164917, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 2.0915, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.39087947882736157, | |
| "grad_norm": 1.7050875425338745, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.7147, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.40390879478827363, | |
| "grad_norm": 1.4443508386611938, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.8553, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.4169381107491857, | |
| "grad_norm": 1.584908366203308, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.8206, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.42996742671009774, | |
| "grad_norm": 1.7143025398254395, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.8255, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.44299674267100975, | |
| "grad_norm": 1.6111055612564087, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.6737, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.4560260586319218, | |
| "grad_norm": 1.8511838912963867, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.5223, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.46905537459283386, | |
| "grad_norm": 2.0485684871673584, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.4314, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.4820846905537459, | |
| "grad_norm": 2.691328525543213, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.1187, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.495114006514658, | |
| "grad_norm": 1.681522011756897, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.8898, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.50814332247557, | |
| "grad_norm": 1.448625087738037, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.9981, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5211726384364821, | |
| "grad_norm": 1.5197402238845825, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.9404, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5342019543973942, | |
| "grad_norm": 1.4934030771255493, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.8512, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5472312703583062, | |
| "grad_norm": 1.3975049257278442, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.8375, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5602605863192183, | |
| "grad_norm": 1.4014006853103638, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.8908, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5732899022801303, | |
| "grad_norm": 1.4836615324020386, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.7045, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5863192182410424, | |
| "grad_norm": 1.3463841676712036, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.5498, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5993485342019544, | |
| "grad_norm": 1.5299338102340698, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.615, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6123778501628665, | |
| "grad_norm": 1.717320442199707, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.7706, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6254071661237784, | |
| "grad_norm": 1.6710180044174194, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.3533, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6384364820846905, | |
| "grad_norm": 1.7277498245239258, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.1741, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6514657980456026, | |
| "grad_norm": 2.389922618865967, | |
| "learning_rate": 0.0, | |
| "loss": 0.5103, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6514657980456026, | |
| "eval_loss": 1.6362560987472534, | |
| "eval_runtime": 15.7084, | |
| "eval_samples_per_second": 32.912, | |
| "eval_steps_per_second": 4.138, | |
| "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 | |
| } | |