| { | |
| "best_metric": 9.840042114257812, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.8967971530249113, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05693950177935943, | |
| "grad_norm": 45.28810119628906, | |
| "learning_rate": 5e-05, | |
| "loss": 11.0032, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05693950177935943, | |
| "eval_loss": 10.988347053527832, | |
| "eval_runtime": 0.3716, | |
| "eval_samples_per_second": 317.542, | |
| "eval_steps_per_second": 40.366, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11387900355871886, | |
| "grad_norm": 47.311309814453125, | |
| "learning_rate": 0.0001, | |
| "loss": 10.9773, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1708185053380783, | |
| "grad_norm": 47.365325927734375, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 10.95, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.2277580071174377, | |
| "grad_norm": 47.05634689331055, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 10.9143, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.2846975088967972, | |
| "grad_norm": 46.96867370605469, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 10.8904, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3416370106761566, | |
| "grad_norm": 46.250003814697266, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 10.8301, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.398576512455516, | |
| "grad_norm": 46.047027587890625, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 10.7888, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.4555160142348754, | |
| "grad_norm": 47.10445022583008, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.7385, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5124555160142349, | |
| "grad_norm": 46.2197265625, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 10.7051, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5693950177935944, | |
| "grad_norm": 47.324302673339844, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.6487, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6263345195729537, | |
| "grad_norm": 45.841121673583984, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 10.6003, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.6832740213523132, | |
| "grad_norm": 47.93464660644531, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 10.5461, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.7402135231316725, | |
| "grad_norm": 45.14745330810547, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 10.5117, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.797153024911032, | |
| "grad_norm": 44.894248962402344, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.4819, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.8540925266903915, | |
| "grad_norm": 44.00173568725586, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 10.4341, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.9110320284697508, | |
| "grad_norm": 43.787349700927734, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 10.3848, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.9679715302491103, | |
| "grad_norm": 43.00312805175781, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 10.3401, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.0498220640569396, | |
| "grad_norm": 44.83312225341797, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 10.2764, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.106761565836299, | |
| "grad_norm": 42.4040641784668, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 10.2664, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.1637010676156583, | |
| "grad_norm": 42.81514358520508, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.2043, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2206405693950177, | |
| "grad_norm": 42.0441780090332, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 10.1707, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.2775800711743772, | |
| "grad_norm": 41.85948181152344, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 10.1716, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.3345195729537367, | |
| "grad_norm": 41.912811279296875, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 10.1462, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.3914590747330962, | |
| "grad_norm": 45.35523986816406, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 10.1057, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.4483985765124556, | |
| "grad_norm": 40.60725402832031, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 10.0679, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.4483985765124556, | |
| "eval_loss": 10.045815467834473, | |
| "eval_runtime": 0.3677, | |
| "eval_samples_per_second": 320.954, | |
| "eval_steps_per_second": 40.799, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.5053380782918149, | |
| "grad_norm": 38.11540222167969, | |
| "learning_rate": 5e-05, | |
| "loss": 10.072, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.5622775800711743, | |
| "grad_norm": 39.571685791015625, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 10.0232, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.6192170818505338, | |
| "grad_norm": 41.4750862121582, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 10.0354, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.6761565836298933, | |
| "grad_norm": 37.119781494140625, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 9.9949, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.7330960854092528, | |
| "grad_norm": 42.86286163330078, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 9.9595, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.790035587188612, | |
| "grad_norm": 38.61808395385742, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 9.9456, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.8469750889679717, | |
| "grad_norm": 36.03926086425781, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 9.936, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.903914590747331, | |
| "grad_norm": 40.077388763427734, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 9.9351, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.9608540925266904, | |
| "grad_norm": 40.48755645751953, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 9.9229, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.0427046263345194, | |
| "grad_norm": 35.62944412231445, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 9.8735, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.099644128113879, | |
| "grad_norm": 36.916019439697266, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 9.9023, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.1565836298932384, | |
| "grad_norm": 36.197017669677734, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 9.8721, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.213523131672598, | |
| "grad_norm": 35.923587799072266, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 9.8582, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.2704626334519573, | |
| "grad_norm": 36.493167877197266, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 9.8835, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.3274021352313166, | |
| "grad_norm": 35.68815994262695, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 9.8633, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.3843416370106763, | |
| "grad_norm": 33.767513275146484, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 9.8711, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.4412811387900355, | |
| "grad_norm": 33.899662017822266, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 9.8601, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.498220640569395, | |
| "grad_norm": 33.72667694091797, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 9.8633, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.5551601423487544, | |
| "grad_norm": 33.61977005004883, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 9.8389, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.612099644128114, | |
| "grad_norm": 36.16455841064453, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 9.8418, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.6690391459074734, | |
| "grad_norm": 36.392059326171875, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 9.8425, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.7259786476868326, | |
| "grad_norm": 32.6194953918457, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 9.8186, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.7829181494661923, | |
| "grad_norm": 33.61957931518555, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 9.8596, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.8398576512455516, | |
| "grad_norm": 35.53854751586914, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 9.8435, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.8967971530249113, | |
| "grad_norm": 32.84313201904297, | |
| "learning_rate": 0.0, | |
| "loss": 9.8328, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.8967971530249113, | |
| "eval_loss": 9.840042114257812, | |
| "eval_runtime": 0.363, | |
| "eval_samples_per_second": 325.09, | |
| "eval_steps_per_second": 41.325, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 38111123865600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |