| { | |
| "best_metric": 2.9394378662109375, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.021088704362725714, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004217740872545143, | |
| "grad_norm": 0.8807809948921204, | |
| "learning_rate": 5e-05, | |
| "loss": 3.2017, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004217740872545143, | |
| "eval_loss": 3.472999334335327, | |
| "eval_runtime": 16.69, | |
| "eval_samples_per_second": 957.041, | |
| "eval_steps_per_second": 119.653, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008435481745090286, | |
| "grad_norm": 0.9277527928352356, | |
| "learning_rate": 0.0001, | |
| "loss": 3.1734, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0012653222617635428, | |
| "grad_norm": 0.9124799966812134, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 3.158, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0016870963490180572, | |
| "grad_norm": 0.8708792328834534, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.1617, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0021088704362725716, | |
| "grad_norm": 0.821029782295227, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.1465, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0025306445235270857, | |
| "grad_norm": 0.8018046617507935, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.1731, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0029524186107816003, | |
| "grad_norm": 0.7562153339385986, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 3.1514, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0033741926980361144, | |
| "grad_norm": 0.7681687474250793, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.2082, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0037959667852906285, | |
| "grad_norm": 0.8212509155273438, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 3.2567, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004217740872545143, | |
| "grad_norm": 0.9729005098342896, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 3.3004, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004639514959799657, | |
| "grad_norm": 1.1585873365402222, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 3.5116, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005061289047054171, | |
| "grad_norm": 1.5668766498565674, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 3.7301, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0054830631343086855, | |
| "grad_norm": 0.8633925318717957, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 3.1699, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0059048372215632005, | |
| "grad_norm": 0.6210086941719055, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.0269, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.006326611308817715, | |
| "grad_norm": 0.5729047060012817, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.9796, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006748385396072229, | |
| "grad_norm": 0.6185963749885559, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.9874, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.007170159483326743, | |
| "grad_norm": 0.5972022414207458, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 3.0223, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.007591933570581257, | |
| "grad_norm": 0.6167501211166382, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.9491, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.008013707657835772, | |
| "grad_norm": 0.6453245282173157, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.9323, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.008435481745090286, | |
| "grad_norm": 0.7007386684417725, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.8964, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0088572558323448, | |
| "grad_norm": 0.7275696396827698, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.9685, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.009279029919599315, | |
| "grad_norm": 0.828760027885437, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 3.0577, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.009700804006853829, | |
| "grad_norm": 1.030902624130249, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 3.1201, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.010122578094108343, | |
| "grad_norm": 1.4113749265670776, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 3.2093, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.010544352181362857, | |
| "grad_norm": 2.300382614135742, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 3.6416, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.010544352181362857, | |
| "eval_loss": 3.041290760040283, | |
| "eval_runtime": 16.6699, | |
| "eval_samples_per_second": 958.195, | |
| "eval_steps_per_second": 119.797, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.010966126268617371, | |
| "grad_norm": 0.711467981338501, | |
| "learning_rate": 5e-05, | |
| "loss": 3.0241, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.011387900355871887, | |
| "grad_norm": 0.515529215335846, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 2.919, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.011809674443126401, | |
| "grad_norm": 0.5799137949943542, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 2.9172, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.012231448530380915, | |
| "grad_norm": 0.5831902027130127, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 2.8513, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.01265322261763543, | |
| "grad_norm": 0.6149861216545105, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 2.8322, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.013074996704889943, | |
| "grad_norm": 0.6361252665519714, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 2.9744, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.013496770792144458, | |
| "grad_norm": 0.6748908758163452, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.8639, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.013918544879398972, | |
| "grad_norm": 0.7482442855834961, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 2.8446, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.014340318966653486, | |
| "grad_norm": 0.8180491924285889, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.8883, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.014762093053908, | |
| "grad_norm": 0.9697517156600952, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 2.9138, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.015183867141162514, | |
| "grad_norm": 1.127631425857544, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 3.0415, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.015605641228417028, | |
| "grad_norm": 1.7890645265579224, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 3.1437, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.016027415315671544, | |
| "grad_norm": 0.8554721474647522, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.1099, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.016449189402926057, | |
| "grad_norm": 0.7087699174880981, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 2.9339, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.016870963490180572, | |
| "grad_norm": 0.6325855255126953, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 2.9197, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.017292737577435085, | |
| "grad_norm": 0.6757078766822815, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 2.9094, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0177145116646896, | |
| "grad_norm": 0.6649094223976135, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.8939, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.018136285751944117, | |
| "grad_norm": 0.6372946500778198, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 2.8133, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.01855805983919863, | |
| "grad_norm": 0.6511436700820923, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.8358, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.018979833926453145, | |
| "grad_norm": 0.6909969449043274, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 2.8616, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.019401608013707657, | |
| "grad_norm": 0.7018306851387024, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 2.8483, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.019823382100962173, | |
| "grad_norm": 0.816609263420105, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 2.8795, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.020245156188216686, | |
| "grad_norm": 1.0902043581008911, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 2.9522, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0206669302754712, | |
| "grad_norm": 1.5287140607833862, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 3.0308, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.021088704362725714, | |
| "grad_norm": 2.4891648292541504, | |
| "learning_rate": 0.0, | |
| "loss": 3.3932, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.021088704362725714, | |
| "eval_loss": 2.9394378662109375, | |
| "eval_runtime": 16.6471, | |
| "eval_samples_per_second": 959.509, | |
| "eval_steps_per_second": 119.961, | |
| "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": 3506283793612800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |