| { | |
| "best_metric": 3.9628827571868896, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.129680661371373, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00259361322742746, | |
| "grad_norm": 1.6940388679504395, | |
| "learning_rate": 5e-05, | |
| "loss": 4.6743, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00259361322742746, | |
| "eval_loss": 6.233916759490967, | |
| "eval_runtime": 2.9407, | |
| "eval_samples_per_second": 17.003, | |
| "eval_steps_per_second": 4.421, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00518722645485492, | |
| "grad_norm": 1.856988787651062, | |
| "learning_rate": 0.0001, | |
| "loss": 4.9163, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007780839682282379, | |
| "grad_norm": 2.035275936126709, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 5.0268, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01037445290970984, | |
| "grad_norm": 2.503596544265747, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 4.9019, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0129680661371373, | |
| "grad_norm": 2.6175785064697266, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 4.6751, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015561679364564759, | |
| "grad_norm": 2.6087710857391357, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 4.5516, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01815529259199222, | |
| "grad_norm": 2.979328155517578, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 4.3765, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02074890581941968, | |
| "grad_norm": 3.121478796005249, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 4.3714, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02334251904684714, | |
| "grad_norm": 2.653797149658203, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 4.2804, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0259361322742746, | |
| "grad_norm": 2.0227596759796143, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 4.1567, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.028529745501702057, | |
| "grad_norm": 3.0764029026031494, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 4.1404, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.031123358729129517, | |
| "grad_norm": 3.810685634613037, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 4.0954, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03371697195655698, | |
| "grad_norm": 3.860100030899048, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 4.1878, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03631058518398444, | |
| "grad_norm": 4.56925106048584, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 4.1403, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0389041984114119, | |
| "grad_norm": 3.53771710395813, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 3.9998, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04149781163883936, | |
| "grad_norm": 3.482703685760498, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 3.9196, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04409142486626682, | |
| "grad_norm": 3.159472703933716, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 3.9289, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04668503809369428, | |
| "grad_norm": 2.7094318866729736, | |
| "learning_rate": 7.75e-05, | |
| "loss": 4.0382, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04927865132112174, | |
| "grad_norm": 2.210520029067993, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 3.9136, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0518722645485492, | |
| "grad_norm": 1.6063358783721924, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 4.0866, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05446587777597666, | |
| "grad_norm": 1.8930221796035767, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 3.9762, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.057059491003404114, | |
| "grad_norm": 2.1200878620147705, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 3.9973, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.059653104230831575, | |
| "grad_norm": 2.3754780292510986, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 4.09, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.062246717458259035, | |
| "grad_norm": 2.797358751296997, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 4.0797, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0648403306856865, | |
| "grad_norm": 5.929616451263428, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 4.0793, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0648403306856865, | |
| "eval_loss": 4.085999011993408, | |
| "eval_runtime": 2.3279, | |
| "eval_samples_per_second": 21.478, | |
| "eval_steps_per_second": 5.584, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06743394391311396, | |
| "grad_norm": 2.760413408279419, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 3.963, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.07002755714054142, | |
| "grad_norm": 3.3028481006622314, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 4.0512, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07262117036796888, | |
| "grad_norm": 3.695802927017212, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 3.9918, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07521478359539634, | |
| "grad_norm": 3.3420543670654297, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 4.0709, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0778083968228238, | |
| "grad_norm": 2.8132102489471436, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 3.936, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08040201005025126, | |
| "grad_norm": 2.410557270050049, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 3.8944, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.08299562327767872, | |
| "grad_norm": 1.9881235361099243, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 3.9089, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08558923650510618, | |
| "grad_norm": 1.8629140853881836, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 3.8896, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08818284973253364, | |
| "grad_norm": 1.81000554561615, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 3.9437, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0907764629599611, | |
| "grad_norm": 1.6936609745025635, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 3.9741, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09337007618738856, | |
| "grad_norm": 2.0665626525878906, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 4.1504, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09596368941481602, | |
| "grad_norm": 2.5222113132476807, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 4.0006, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.09855730264224348, | |
| "grad_norm": 1.097839593887329, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 3.7587, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.10115091586967094, | |
| "grad_norm": 0.9856619238853455, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 3.7098, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1037445290970984, | |
| "grad_norm": 0.9252366423606873, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 3.7605, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10633814232452586, | |
| "grad_norm": 0.8420267105102539, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 3.6713, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.10893175555195332, | |
| "grad_norm": 0.8332710862159729, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 3.7245, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.11152536877938077, | |
| "grad_norm": 0.8014082312583923, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 3.8029, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.11411898200680823, | |
| "grad_norm": 0.8639490008354187, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 3.9165, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.11671259523423569, | |
| "grad_norm": 0.9951760172843933, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 3.8803, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11930620846166315, | |
| "grad_norm": 1.2074276208877563, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 3.8738, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.12189982168909061, | |
| "grad_norm": 1.2788665294647217, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 4.0534, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.12449343491651807, | |
| "grad_norm": 1.6001139879226685, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 3.9496, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.12708704814394553, | |
| "grad_norm": 2.474669933319092, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 4.0053, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.129680661371373, | |
| "grad_norm": 5.6437201499938965, | |
| "learning_rate": 1e-05, | |
| "loss": 4.2376, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.129680661371373, | |
| "eval_loss": 3.9628827571868896, | |
| "eval_runtime": 2.3228, | |
| "eval_samples_per_second": 21.526, | |
| "eval_steps_per_second": 5.597, | |
| "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": 5.968086838542336e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |