| { | |
| "best_metric": 0.3012233078479767, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.2466091245376079, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004932182490752158, | |
| "grad_norm": 1.8650400638580322, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1438, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004932182490752158, | |
| "eval_loss": 1.414349913597107, | |
| "eval_runtime": 20.2671, | |
| "eval_samples_per_second": 67.4, | |
| "eval_steps_per_second": 8.437, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009864364981504316, | |
| "grad_norm": 1.849665880203247, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1763, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.014796547472256474, | |
| "grad_norm": 1.5722370147705078, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.1466, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01972872996300863, | |
| "grad_norm": 1.2196251153945923, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.9743, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02466091245376079, | |
| "grad_norm": 1.2063157558441162, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.8742, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.029593094944512947, | |
| "grad_norm": 1.196218729019165, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.7981, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0345252774352651, | |
| "grad_norm": 1.059170126914978, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.7206, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03945745992601726, | |
| "grad_norm": 1.107353925704956, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.6495, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04438964241676942, | |
| "grad_norm": 1.1146334409713745, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.6043, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04932182490752158, | |
| "grad_norm": 1.1989785432815552, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.5555, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05425400739827373, | |
| "grad_norm": 1.366790533065796, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.5734, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.059186189889025895, | |
| "grad_norm": 1.1458686590194702, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.5739, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06411837237977805, | |
| "grad_norm": 1.9404748678207397, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.3946, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0690505548705302, | |
| "grad_norm": 1.2511030435562134, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.3832, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.07398273736128237, | |
| "grad_norm": 0.8801244497299194, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.3734, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07891491985203453, | |
| "grad_norm": 0.7699196934700012, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.381, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.08384710234278668, | |
| "grad_norm": 0.6188871264457703, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.3598, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.08877928483353884, | |
| "grad_norm": 0.5674222707748413, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.3389, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.093711467324291, | |
| "grad_norm": 0.6306641101837158, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.3669, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.09864364981504316, | |
| "grad_norm": 0.4506845474243164, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.3072, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.10357583230579531, | |
| "grad_norm": 0.4561832547187805, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.3402, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.10850801479654747, | |
| "grad_norm": 0.5709429979324341, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.3453, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.11344019728729964, | |
| "grad_norm": 0.5596646666526794, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.3298, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.11837237977805179, | |
| "grad_norm": 0.6210820078849792, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.4192, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.12330456226880394, | |
| "grad_norm": 1.0289266109466553, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.3351, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.12330456226880394, | |
| "eval_loss": 0.32884421944618225, | |
| "eval_runtime": 20.2458, | |
| "eval_samples_per_second": 67.471, | |
| "eval_steps_per_second": 8.446, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1282367447595561, | |
| "grad_norm": 0.9765304327011108, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3001, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.13316892725030827, | |
| "grad_norm": 0.5973970890045166, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.3099, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1381011097410604, | |
| "grad_norm": 0.4834292531013489, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.3176, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.14303329223181258, | |
| "grad_norm": 0.42007580399513245, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.3156, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.14796547472256474, | |
| "grad_norm": 0.5430471301078796, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.2989, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.15289765721331688, | |
| "grad_norm": 0.5922935605049133, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.3115, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.15782983970406905, | |
| "grad_norm": 0.5440362691879272, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.3028, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.16276202219482122, | |
| "grad_norm": 0.536367654800415, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.3017, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.16769420468557336, | |
| "grad_norm": 0.5181109309196472, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.2986, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.17262638717632553, | |
| "grad_norm": 0.6546456813812256, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.3319, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.17755856966707767, | |
| "grad_norm": 0.6339057087898254, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.3259, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.18249075215782984, | |
| "grad_norm": 1.3519337177276611, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.3915, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.187422934648582, | |
| "grad_norm": 0.47506600618362427, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.2711, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.19235511713933415, | |
| "grad_norm": 0.6212289333343506, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.2839, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.19728729963008632, | |
| "grad_norm": 0.6477142572402954, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.2859, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.20221948212083848, | |
| "grad_norm": 0.8822614550590515, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.3087, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.20715166461159062, | |
| "grad_norm": 0.7327987551689148, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.2934, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2120838471023428, | |
| "grad_norm": 0.5722291469573975, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.2892, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.21701602959309493, | |
| "grad_norm": 0.6610158085823059, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.3084, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.2219482120838471, | |
| "grad_norm": 0.583101212978363, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.2954, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.22688039457459927, | |
| "grad_norm": 0.5043917298316956, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.2806, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.2318125770653514, | |
| "grad_norm": 0.624017059803009, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.3121, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.23674475955610358, | |
| "grad_norm": 0.4712766110897064, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.2941, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.24167694204685575, | |
| "grad_norm": 0.6848615407943726, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.3745, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.2466091245376079, | |
| "grad_norm": 0.3380556106567383, | |
| "learning_rate": 0.0, | |
| "loss": 0.2895, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2466091245376079, | |
| "eval_loss": 0.3012233078479767, | |
| "eval_runtime": 20.2561, | |
| "eval_samples_per_second": 67.437, | |
| "eval_steps_per_second": 8.442, | |
| "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": 5.80081729709015e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |