| { | |
| "best_metric": 1.1210252046585083, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.0316055625790139, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012642225031605564, | |
| "grad_norm": 1.9378573894500732, | |
| "learning_rate": 2e-05, | |
| "loss": 8.6874, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012642225031605564, | |
| "eval_loss": 2.1115481853485107, | |
| "eval_runtime": 49.5266, | |
| "eval_samples_per_second": 6.744, | |
| "eval_steps_per_second": 3.372, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0025284450063211127, | |
| "grad_norm": 2.0282223224639893, | |
| "learning_rate": 4e-05, | |
| "loss": 8.3938, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0037926675094816687, | |
| "grad_norm": 1.9364533424377441, | |
| "learning_rate": 6e-05, | |
| "loss": 9.1156, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0050568900126422255, | |
| "grad_norm": 2.017167329788208, | |
| "learning_rate": 8e-05, | |
| "loss": 8.4278, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006321112515802781, | |
| "grad_norm": 2.3764736652374268, | |
| "learning_rate": 0.0001, | |
| "loss": 7.7881, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006321112515802781, | |
| "eval_loss": 2.0647788047790527, | |
| "eval_runtime": 49.568, | |
| "eval_samples_per_second": 6.738, | |
| "eval_steps_per_second": 3.369, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007585335018963337, | |
| "grad_norm": 2.7689037322998047, | |
| "learning_rate": 0.00012, | |
| "loss": 7.601, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008849557522123894, | |
| "grad_norm": 3.710773468017578, | |
| "learning_rate": 0.00014, | |
| "loss": 7.6337, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010113780025284451, | |
| "grad_norm": 4.302574157714844, | |
| "learning_rate": 0.00016, | |
| "loss": 7.6958, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.011378002528445006, | |
| "grad_norm": 5.66724967956543, | |
| "learning_rate": 0.00018, | |
| "loss": 8.0003, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012642225031605562, | |
| "grad_norm": 4.579207897186279, | |
| "learning_rate": 0.0002, | |
| "loss": 6.8932, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012642225031605562, | |
| "eval_loss": 1.5803078413009644, | |
| "eval_runtime": 49.5724, | |
| "eval_samples_per_second": 6.738, | |
| "eval_steps_per_second": 3.369, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01390644753476612, | |
| "grad_norm": 6.442827224731445, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 6.7037, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.015170670037926675, | |
| "grad_norm": 3.3107621669769287, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 6.0347, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01643489254108723, | |
| "grad_norm": 1.9668668508529663, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 5.1631, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.017699115044247787, | |
| "grad_norm": 2.2284107208251953, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 5.5038, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.018963337547408345, | |
| "grad_norm": 2.1553852558135986, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 5.3603, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.018963337547408345, | |
| "eval_loss": 1.167852759361267, | |
| "eval_runtime": 49.5281, | |
| "eval_samples_per_second": 6.744, | |
| "eval_steps_per_second": 3.372, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.020227560050568902, | |
| "grad_norm": 1.3784503936767578, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 4.7254, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.021491782553729456, | |
| "grad_norm": 1.227391004562378, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 4.822, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.022756005056890013, | |
| "grad_norm": 1.6564104557037354, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 4.9, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02402022756005057, | |
| "grad_norm": 1.3059868812561035, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 4.7932, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.025284450063211124, | |
| "grad_norm": 1.5731518268585205, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 4.0506, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.025284450063211124, | |
| "eval_loss": 1.1268237829208374, | |
| "eval_runtime": 49.5323, | |
| "eval_samples_per_second": 6.743, | |
| "eval_steps_per_second": 3.372, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02654867256637168, | |
| "grad_norm": 1.2747409343719482, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 3.6453, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02781289506953224, | |
| "grad_norm": 1.8635807037353516, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 3.4369, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.029077117572692796, | |
| "grad_norm": 1.1131011247634888, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 4.6832, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03034134007585335, | |
| "grad_norm": 1.1229186058044434, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 4.6339, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0316055625790139, | |
| "grad_norm": 1.836712121963501, | |
| "learning_rate": 0.0, | |
| "loss": 4.6557, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0316055625790139, | |
| "eval_loss": 1.1210252046585083, | |
| "eval_runtime": 49.5, | |
| "eval_samples_per_second": 6.747, | |
| "eval_steps_per_second": 3.374, | |
| "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": 8578352598220800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |