| { | |
| "best_metric": 5.487072944641113, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.01525320317266626, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006101281269066504, | |
| "grad_norm": 3.2737698554992676, | |
| "learning_rate": 2e-05, | |
| "loss": 6.8164, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006101281269066504, | |
| "eval_loss": 6.713930606842041, | |
| "eval_runtime": 102.4095, | |
| "eval_samples_per_second": 6.747, | |
| "eval_steps_per_second": 3.379, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012202562538133007, | |
| "grad_norm": 2.322046995162964, | |
| "learning_rate": 4e-05, | |
| "loss": 6.6216, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0018303843807199512, | |
| "grad_norm": 2.4447498321533203, | |
| "learning_rate": 6e-05, | |
| "loss": 6.1817, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0024405125076266015, | |
| "grad_norm": 4.9170451164245605, | |
| "learning_rate": 8e-05, | |
| "loss": 6.615, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003050640634533252, | |
| "grad_norm": 2.392526388168335, | |
| "learning_rate": 0.0001, | |
| "loss": 6.4283, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003050640634533252, | |
| "eval_loss": 6.601726531982422, | |
| "eval_runtime": 100.8001, | |
| "eval_samples_per_second": 6.855, | |
| "eval_steps_per_second": 3.433, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0036607687614399025, | |
| "grad_norm": 2.418440341949463, | |
| "learning_rate": 0.00012, | |
| "loss": 6.6246, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004270896888346553, | |
| "grad_norm": 2.0582504272460938, | |
| "learning_rate": 0.00014, | |
| "loss": 6.1862, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004881025015253203, | |
| "grad_norm": 1.9576926231384277, | |
| "learning_rate": 0.00016, | |
| "loss": 5.9144, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005491153142159854, | |
| "grad_norm": 1.743924617767334, | |
| "learning_rate": 0.00018, | |
| "loss": 5.9392, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006101281269066504, | |
| "grad_norm": 2.0612897872924805, | |
| "learning_rate": 0.0002, | |
| "loss": 6.0787, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006101281269066504, | |
| "eval_loss": 6.148561954498291, | |
| "eval_runtime": 100.8382, | |
| "eval_samples_per_second": 6.853, | |
| "eval_steps_per_second": 3.431, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006711409395973154, | |
| "grad_norm": 1.978797435760498, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 6.0012, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.007321537522879805, | |
| "grad_norm": 3.436152458190918, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 6.7344, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.007931665649786455, | |
| "grad_norm": 1.6734408140182495, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 5.6312, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.008541793776693106, | |
| "grad_norm": 2.174579620361328, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 5.7046, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.009151921903599756, | |
| "grad_norm": 2.0292463302612305, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 5.7352, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009151921903599756, | |
| "eval_loss": 5.779726028442383, | |
| "eval_runtime": 101.1831, | |
| "eval_samples_per_second": 6.829, | |
| "eval_steps_per_second": 3.42, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009762050030506406, | |
| "grad_norm": 2.211259603500366, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 5.5493, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.010372178157413058, | |
| "grad_norm": 2.099989652633667, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 5.8209, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.010982306284319707, | |
| "grad_norm": 2.493408679962158, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 5.1595, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.011592434411226357, | |
| "grad_norm": 1.6317073106765747, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 5.3294, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.012202562538133009, | |
| "grad_norm": 1.6446095705032349, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 5.276, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.012202562538133009, | |
| "eval_loss": 5.523056507110596, | |
| "eval_runtime": 101.0601, | |
| "eval_samples_per_second": 6.838, | |
| "eval_steps_per_second": 3.424, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.012812690665039659, | |
| "grad_norm": 1.8376624584197998, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 5.4096, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.013422818791946308, | |
| "grad_norm": 1.71583890914917, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 5.3737, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.014032946918852958, | |
| "grad_norm": 1.852288842201233, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 5.3239, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.01464307504575961, | |
| "grad_norm": 1.8837882280349731, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 5.3845, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01525320317266626, | |
| "grad_norm": 1.9514257907867432, | |
| "learning_rate": 0.0, | |
| "loss": 5.4464, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01525320317266626, | |
| "eval_loss": 5.487072944641113, | |
| "eval_runtime": 100.9583, | |
| "eval_samples_per_second": 6.844, | |
| "eval_steps_per_second": 3.427, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": 191809506508800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |