| { | |
| "best_metric": 9.844544410705566, | |
| "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": 47.327762603759766, | |
| "learning_rate": 5e-05, | |
| "loss": 11.0032, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05693950177935943, | |
| "eval_loss": 10.988347053527832, | |
| "eval_runtime": 0.1267, | |
| "eval_samples_per_second": 931.273, | |
| "eval_steps_per_second": 118.382, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11387900355871886, | |
| "grad_norm": 48.20378494262695, | |
| "learning_rate": 0.0001, | |
| "loss": 10.9773, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1708185053380783, | |
| "grad_norm": 48.77847671508789, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 10.9514, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.2277580071174377, | |
| "grad_norm": 47.74806213378906, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 10.9131, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.2846975088967972, | |
| "grad_norm": 48.20513916015625, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 10.8906, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3416370106761566, | |
| "grad_norm": 47.07430648803711, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 10.8293, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.398576512455516, | |
| "grad_norm": 47.30954360961914, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 10.7832, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.4555160142348754, | |
| "grad_norm": 48.195648193359375, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.7327, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5124555160142349, | |
| "grad_norm": 47.463016510009766, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 10.7017, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5693950177935944, | |
| "grad_norm": 47.86130142211914, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.6458, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6263345195729537, | |
| "grad_norm": 46.269691467285156, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 10.6008, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.6832740213523132, | |
| "grad_norm": 48.29341125488281, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 10.5371, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.7402135231316725, | |
| "grad_norm": 45.96389389038086, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 10.5044, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.797153024911032, | |
| "grad_norm": 45.680782318115234, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.4729, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.8540925266903915, | |
| "grad_norm": 44.67899703979492, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 10.4297, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.9110320284697508, | |
| "grad_norm": 44.54277420043945, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 10.3801, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.9679715302491103, | |
| "grad_norm": 43.47139358520508, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 10.3376, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.0498220640569396, | |
| "grad_norm": 45.576438903808594, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 10.283, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.106761565836299, | |
| "grad_norm": 43.14785385131836, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 10.27, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.1637010676156583, | |
| "grad_norm": 42.904544830322266, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.2073, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2206405693950177, | |
| "grad_norm": 42.01190185546875, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 10.1704, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.2775800711743772, | |
| "grad_norm": 41.79740524291992, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 10.1731, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.3345195729537367, | |
| "grad_norm": 41.79007339477539, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 10.1479, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.3914590747330962, | |
| "grad_norm": 45.14829635620117, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 10.106, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.4483985765124556, | |
| "grad_norm": 40.45480728149414, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 10.0693, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.4483985765124556, | |
| "eval_loss": 10.047934532165527, | |
| "eval_runtime": 0.1219, | |
| "eval_samples_per_second": 967.694, | |
| "eval_steps_per_second": 123.012, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.5053380782918149, | |
| "grad_norm": 38.16707229614258, | |
| "learning_rate": 5e-05, | |
| "loss": 10.0674, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.5622775800711743, | |
| "grad_norm": 39.47360610961914, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 10.0273, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.6192170818505338, | |
| "grad_norm": 41.1451530456543, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 10.0354, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.6761565836298933, | |
| "grad_norm": 37.08360290527344, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 9.9929, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.7330960854092528, | |
| "grad_norm": 42.404457092285156, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 9.9641, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.790035587188612, | |
| "grad_norm": 38.849552154541016, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 9.9485, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.8469750889679717, | |
| "grad_norm": 35.90088653564453, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 9.9368, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.903914590747331, | |
| "grad_norm": 39.651119232177734, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 9.9373, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.9608540925266904, | |
| "grad_norm": 39.915504455566406, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 9.9233, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.0427046263345194, | |
| "grad_norm": 35.5047492980957, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 9.8757, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.099644128113879, | |
| "grad_norm": 36.85204315185547, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 9.9016, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.1565836298932384, | |
| "grad_norm": 36.31344985961914, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 9.8718, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.213523131672598, | |
| "grad_norm": 36.17488098144531, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 9.8591, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.2704626334519573, | |
| "grad_norm": 36.54132080078125, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 9.884, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.3274021352313166, | |
| "grad_norm": 36.260841369628906, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 9.8633, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.3843416370106763, | |
| "grad_norm": 33.74192428588867, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 9.8713, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.4412811387900355, | |
| "grad_norm": 34.44586944580078, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 9.864, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.498220640569395, | |
| "grad_norm": 33.68125915527344, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 9.8672, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.5551601423487544, | |
| "grad_norm": 34.21220397949219, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 9.8374, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.612099644128114, | |
| "grad_norm": 36.1893424987793, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 9.8433, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.6690391459074734, | |
| "grad_norm": 36.4090690612793, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 9.8464, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.7259786476868326, | |
| "grad_norm": 32.83701705932617, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 9.8167, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.7829181494661923, | |
| "grad_norm": 33.877655029296875, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 9.8623, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.8398576512455516, | |
| "grad_norm": 36.13532257080078, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 9.8472, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.8967971530249113, | |
| "grad_norm": 33.10332489013672, | |
| "learning_rate": 0.0, | |
| "loss": 9.8337, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.8967971530249113, | |
| "eval_loss": 9.844544410705566, | |
| "eval_runtime": 0.1222, | |
| "eval_samples_per_second": 965.317, | |
| "eval_steps_per_second": 122.71, | |
| "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 | |
| } | |