| { | |
| "best_metric": 1.0434695482254028, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.0021246308453906136, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.498523381562454e-05, | |
| "grad_norm": 0.2922225594520569, | |
| "learning_rate": 2e-05, | |
| "loss": 1.2053, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.498523381562454e-05, | |
| "eval_loss": 1.3844845294952393, | |
| "eval_runtime": 3381.9851, | |
| "eval_samples_per_second": 1.465, | |
| "eval_steps_per_second": 0.733, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00016997046763124907, | |
| "grad_norm": 0.3761480450630188, | |
| "learning_rate": 4e-05, | |
| "loss": 1.3331, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0002549557014468736, | |
| "grad_norm": 0.39635875821113586, | |
| "learning_rate": 6e-05, | |
| "loss": 1.7427, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00033994093526249815, | |
| "grad_norm": 0.3360555171966553, | |
| "learning_rate": 8e-05, | |
| "loss": 1.22, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00042492616907812265, | |
| "grad_norm": 0.3878980875015259, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1324, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00042492616907812265, | |
| "eval_loss": 1.3745969533920288, | |
| "eval_runtime": 1321.6033, | |
| "eval_samples_per_second": 3.749, | |
| "eval_steps_per_second": 1.875, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005099114028937472, | |
| "grad_norm": 0.40587636828422546, | |
| "learning_rate": 0.00012, | |
| "loss": 1.2451, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005948966367093718, | |
| "grad_norm": 0.4392871558666229, | |
| "learning_rate": 0.00014, | |
| "loss": 1.2641, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0006798818705249963, | |
| "grad_norm": 0.5529392957687378, | |
| "learning_rate": 0.00016, | |
| "loss": 1.04, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0007648671043406208, | |
| "grad_norm": 0.4955708086490631, | |
| "learning_rate": 0.00018, | |
| "loss": 1.1158, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0008498523381562453, | |
| "grad_norm": 0.47972533106803894, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2657, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008498523381562453, | |
| "eval_loss": 1.182800531387329, | |
| "eval_runtime": 1329.7539, | |
| "eval_samples_per_second": 3.726, | |
| "eval_steps_per_second": 1.864, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0009348375719718699, | |
| "grad_norm": 0.5133495330810547, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 1.4981, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0010198228057874943, | |
| "grad_norm": 0.4741702377796173, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 1.0614, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.001104808039603119, | |
| "grad_norm": 0.48592695593833923, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.3289, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0011897932734187436, | |
| "grad_norm": 0.5056785941123962, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 1.0073, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.001274778507234368, | |
| "grad_norm": 0.3255745768547058, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.3241, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.001274778507234368, | |
| "eval_loss": 1.0932385921478271, | |
| "eval_runtime": 1319.1764, | |
| "eval_samples_per_second": 3.756, | |
| "eval_steps_per_second": 1.878, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0013597637410499926, | |
| "grad_norm": 0.3560282289981842, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.8673, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.001444748974865617, | |
| "grad_norm": 0.3492855131626129, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 0.9656, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0015297342086812416, | |
| "grad_norm": 0.33957651257514954, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 1.0601, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0016147194424968661, | |
| "grad_norm": 0.3338528871536255, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.025, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0016997046763124906, | |
| "grad_norm": 0.3303922116756439, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.2887, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0016997046763124906, | |
| "eval_loss": 1.0485574007034302, | |
| "eval_runtime": 2250.8, | |
| "eval_samples_per_second": 2.201, | |
| "eval_steps_per_second": 1.101, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0017846899101281153, | |
| "grad_norm": 0.2990271747112274, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 0.8543, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0018696751439437399, | |
| "grad_norm": 0.27824667096138, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.9073, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.001954660377759364, | |
| "grad_norm": 0.39718323945999146, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 1.2813, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0020396456115749887, | |
| "grad_norm": 0.3636144995689392, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 0.831, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0021246308453906136, | |
| "grad_norm": 0.3469758629798889, | |
| "learning_rate": 0.0, | |
| "loss": 0.9989, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0021246308453906136, | |
| "eval_loss": 1.0434695482254028, | |
| "eval_runtime": 2449.2051, | |
| "eval_samples_per_second": 2.023, | |
| "eval_steps_per_second": 1.012, | |
| "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": 1.511863093297152e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |