| { | |
| "best_metric": 0.6561319231987, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.823045267489712, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01646090534979424, | |
| "grad_norm": 2.0745296478271484, | |
| "learning_rate": 5e-05, | |
| "loss": 2.8513, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01646090534979424, | |
| "eval_loss": 3.8586878776550293, | |
| "eval_runtime": 9.15, | |
| "eval_samples_per_second": 44.809, | |
| "eval_steps_per_second": 5.683, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03292181069958848, | |
| "grad_norm": 4.245978832244873, | |
| "learning_rate": 0.0001, | |
| "loss": 3.7586, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04938271604938271, | |
| "grad_norm": 3.185753345489502, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.3779, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06584362139917696, | |
| "grad_norm": 1.9672001600265503, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.0297, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0823045267489712, | |
| "grad_norm": 1.712628960609436, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.8397, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.09876543209876543, | |
| "grad_norm": 1.813711166381836, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.8286, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.11522633744855967, | |
| "grad_norm": 1.2593228816986084, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.4568, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.13168724279835392, | |
| "grad_norm": 1.2200363874435425, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.3131, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.14814814814814814, | |
| "grad_norm": 1.1022920608520508, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.2503, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1646090534979424, | |
| "grad_norm": 1.273776650428772, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.1055, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.18106995884773663, | |
| "grad_norm": 1.3083699941635132, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.0066, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.19753086419753085, | |
| "grad_norm": 1.1210218667984009, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.8673, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2139917695473251, | |
| "grad_norm": 0.7338252663612366, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.9367, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.23045267489711935, | |
| "grad_norm": 2.1798887252807617, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.6209, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.24691358024691357, | |
| "grad_norm": 1.767669677734375, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.7957, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.26337448559670784, | |
| "grad_norm": 1.1363743543624878, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.7195, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.27983539094650206, | |
| "grad_norm": 0.9281293749809265, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.7021, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.2962962962962963, | |
| "grad_norm": 0.8513988852500916, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.6473, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.31275720164609055, | |
| "grad_norm": 0.8034453988075256, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.6974, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.3292181069958848, | |
| "grad_norm": 0.7160072922706604, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.5821, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.345679012345679, | |
| "grad_norm": 0.5699191093444824, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.7074, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.36213991769547327, | |
| "grad_norm": 0.5850489735603333, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.7256, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3786008230452675, | |
| "grad_norm": 0.5858528017997742, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.6395, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "grad_norm": 0.5442656874656677, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.7342, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.411522633744856, | |
| "grad_norm": 0.49498945474624634, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.5981, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.411522633744856, | |
| "eval_loss": 0.7050751447677612, | |
| "eval_runtime": 9.1683, | |
| "eval_samples_per_second": 44.719, | |
| "eval_steps_per_second": 5.672, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4279835390946502, | |
| "grad_norm": 1.625022053718567, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3808, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 0.6726037263870239, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.6507, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.4609053497942387, | |
| "grad_norm": 0.6659382581710815, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.5273, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.4773662551440329, | |
| "grad_norm": 0.698225736618042, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.5542, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.49382716049382713, | |
| "grad_norm": 0.6371154189109802, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.6459, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5102880658436214, | |
| "grad_norm": 0.5590847730636597, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.685, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5267489711934157, | |
| "grad_norm": 0.4336808919906616, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.5531, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5432098765432098, | |
| "grad_norm": 0.5399011969566345, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.6532, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5596707818930041, | |
| "grad_norm": 0.4386877417564392, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.6143, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5761316872427984, | |
| "grad_norm": 0.5017386078834534, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.6102, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 0.6162391304969788, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.6991, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6090534979423868, | |
| "grad_norm": 0.6711835265159607, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.693, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.6255144032921811, | |
| "grad_norm": 0.5756227970123291, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.8572, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.6419753086419753, | |
| "grad_norm": 2.781473398208618, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.7294, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6584362139917695, | |
| "grad_norm": 0.6352210640907288, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.5651, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6748971193415638, | |
| "grad_norm": 0.47287803888320923, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.5217, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.691358024691358, | |
| "grad_norm": 0.5060291886329651, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.5924, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.7078189300411523, | |
| "grad_norm": 0.434349000453949, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.529, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.7242798353909465, | |
| "grad_norm": 0.5044702291488647, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.5424, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.7407407407407407, | |
| "grad_norm": 0.42993804812431335, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.6676, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.757201646090535, | |
| "grad_norm": 0.4085606634616852, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.5848, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.7736625514403292, | |
| "grad_norm": 0.4246390163898468, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.6776, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "grad_norm": 0.35061928629875183, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.5528, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.8065843621399177, | |
| "grad_norm": 0.4323487877845764, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.6973, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.823045267489712, | |
| "grad_norm": 0.4282306730747223, | |
| "learning_rate": 0.0, | |
| "loss": 0.5867, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.823045267489712, | |
| "eval_loss": 0.6561319231987, | |
| "eval_runtime": 9.1655, | |
| "eval_samples_per_second": 44.733, | |
| "eval_steps_per_second": 5.673, | |
| "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": 2.450087619686564e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |