| { | |
| "best_metric": 1.4622470140457153, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.03757985719654265, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001503194287861706, | |
| "grad_norm": 4.442657470703125, | |
| "learning_rate": 2e-05, | |
| "loss": 2.8355, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001503194287861706, | |
| "eval_loss": 2.8466711044311523, | |
| "eval_runtime": 42.2168, | |
| "eval_samples_per_second": 6.656, | |
| "eval_steps_per_second": 3.34, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003006388575723412, | |
| "grad_norm": 4.723255634307861, | |
| "learning_rate": 4e-05, | |
| "loss": 3.0172, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004509582863585118, | |
| "grad_norm": 4.133962631225586, | |
| "learning_rate": 6e-05, | |
| "loss": 2.6374, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006012777151446824, | |
| "grad_norm": 4.12436580657959, | |
| "learning_rate": 8e-05, | |
| "loss": 2.7077, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00751597143930853, | |
| "grad_norm": 3.8988733291625977, | |
| "learning_rate": 0.0001, | |
| "loss": 2.6041, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00751597143930853, | |
| "eval_loss": 2.3214762210845947, | |
| "eval_runtime": 41.99, | |
| "eval_samples_per_second": 6.692, | |
| "eval_steps_per_second": 3.358, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009019165727170236, | |
| "grad_norm": 3.2591164112091064, | |
| "learning_rate": 0.00012, | |
| "loss": 2.4381, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.010522360015031942, | |
| "grad_norm": 2.177001714706421, | |
| "learning_rate": 0.00014, | |
| "loss": 2.0728, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.012025554302893648, | |
| "grad_norm": 3.5476269721984863, | |
| "learning_rate": 0.00016, | |
| "loss": 2.044, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.013528748590755355, | |
| "grad_norm": 3.3373279571533203, | |
| "learning_rate": 0.00018, | |
| "loss": 1.8168, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01503194287861706, | |
| "grad_norm": 3.0763943195343018, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9386, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01503194287861706, | |
| "eval_loss": 1.8197484016418457, | |
| "eval_runtime": 41.0918, | |
| "eval_samples_per_second": 6.838, | |
| "eval_steps_per_second": 3.431, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.016535137166478767, | |
| "grad_norm": 1.9952398538589478, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 1.8169, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.018038331454340473, | |
| "grad_norm": 2.826005697250366, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 1.7178, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01954152574220218, | |
| "grad_norm": 2.133068799972534, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.7541, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.021044720030063885, | |
| "grad_norm": 1.2888638973236084, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 1.614, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.02254791431792559, | |
| "grad_norm": 1.4778361320495605, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.6948, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02254791431792559, | |
| "eval_loss": 1.599828839302063, | |
| "eval_runtime": 41.0285, | |
| "eval_samples_per_second": 6.849, | |
| "eval_steps_per_second": 3.437, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.024051108605787297, | |
| "grad_norm": 1.1350922584533691, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.4866, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.025554302893649003, | |
| "grad_norm": 1.1794151067733765, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 1.5395, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02705749718151071, | |
| "grad_norm": 1.146877408027649, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 1.5711, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.028560691469372415, | |
| "grad_norm": 0.8555176854133606, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.4243, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03006388575723412, | |
| "grad_norm": 1.237547516822815, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.4742, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03006388575723412, | |
| "eval_loss": 1.4909831285476685, | |
| "eval_runtime": 41.4345, | |
| "eval_samples_per_second": 6.782, | |
| "eval_steps_per_second": 3.403, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03156708004509583, | |
| "grad_norm": 1.7778785228729248, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 1.5468, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03307027433295753, | |
| "grad_norm": 1.183743953704834, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 1.4544, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03457346862081924, | |
| "grad_norm": 1.3352869749069214, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 1.4477, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.036076662908680945, | |
| "grad_norm": 1.0573396682739258, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 1.4292, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03757985719654265, | |
| "grad_norm": 1.080513834953308, | |
| "learning_rate": 0.0, | |
| "loss": 1.4703, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03757985719654265, | |
| "eval_loss": 1.4622470140457153, | |
| "eval_runtime": 41.6533, | |
| "eval_samples_per_second": 6.746, | |
| "eval_steps_per_second": 3.385, | |
| "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": 2447388966912000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |