| { | |
| "best_metric": 2.0168991088867188, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.1653575857792476, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006614303431169905, | |
| "grad_norm": 17.736679077148438, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 11.468, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006614303431169905, | |
| "eval_loss": 11.592829704284668, | |
| "eval_runtime": 4.0134, | |
| "eval_samples_per_second": 12.458, | |
| "eval_steps_per_second": 3.239, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01322860686233981, | |
| "grad_norm": 20.307588577270508, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 11.3596, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.019842910293509715, | |
| "grad_norm": 15.574076652526855, | |
| "learning_rate": 0.0001, | |
| "loss": 10.8161, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02645721372467962, | |
| "grad_norm": 12.424201011657715, | |
| "learning_rate": 9.997376600647783e-05, | |
| "loss": 9.4755, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03307151715584952, | |
| "grad_norm": 9.448874473571777, | |
| "learning_rate": 9.989509461357426e-05, | |
| "loss": 8.0971, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03968582058701943, | |
| "grad_norm": 10.42374038696289, | |
| "learning_rate": 9.976407754861426e-05, | |
| "loss": 7.2079, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04630012401818934, | |
| "grad_norm": 12.758567810058594, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 5.7105, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05291442744935924, | |
| "grad_norm": 13.52912712097168, | |
| "learning_rate": 9.934567829727386e-05, | |
| "loss": 3.8279, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.059528730880529145, | |
| "grad_norm": 15.979461669921875, | |
| "learning_rate": 9.905878394570453e-05, | |
| "loss": 3.0876, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06614303431169904, | |
| "grad_norm": 7.501053333282471, | |
| "learning_rate": 9.872051902290737e-05, | |
| "loss": 2.8203, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07275733774286895, | |
| "grad_norm": 7.698332786560059, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 3.329, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.07937164117403886, | |
| "grad_norm": 7.099416732788086, | |
| "learning_rate": 9.789151450663723e-05, | |
| "loss": 2.6664, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08598594460520877, | |
| "grad_norm": 15.326375961303711, | |
| "learning_rate": 9.740174149534693e-05, | |
| "loss": 2.7908, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.09260024803637867, | |
| "grad_norm": 10.195456504821777, | |
| "learning_rate": 9.686252995020249e-05, | |
| "loss": 2.3301, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.09921455146754857, | |
| "grad_norm": 4.361770153045654, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 2.0583, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.10582885489871847, | |
| "grad_norm": 3.182706117630005, | |
| "learning_rate": 9.563836295460398e-05, | |
| "loss": 2.0367, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.11244315832988838, | |
| "grad_norm": 5.076944828033447, | |
| "learning_rate": 9.495483482810688e-05, | |
| "loss": 1.9523, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.11905746176105829, | |
| "grad_norm": 8.57449722290039, | |
| "learning_rate": 9.422472115147382e-05, | |
| "loss": 2.025, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1256717651922282, | |
| "grad_norm": 3.4628255367279053, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 2.0057, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.1322860686233981, | |
| "grad_norm": 2.956812620162964, | |
| "learning_rate": 9.2628195591462e-05, | |
| "loss": 2.006, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.138900372054568, | |
| "grad_norm": 9.580174446105957, | |
| "learning_rate": 9.176364518546989e-05, | |
| "loss": 2.0139, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1455146754857379, | |
| "grad_norm": 6.208186626434326, | |
| "learning_rate": 9.08562300137157e-05, | |
| "loss": 1.9206, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.15212897891690783, | |
| "grad_norm": 4.192629337310791, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 2.037, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.15874328234807772, | |
| "grad_norm": 7.658245086669922, | |
| "learning_rate": 8.891708613973126e-05, | |
| "loss": 2.3119, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1653575857792476, | |
| "grad_norm": 6.482032775878906, | |
| "learning_rate": 8.788761839251559e-05, | |
| "loss": 2.2091, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1653575857792476, | |
| "eval_loss": 2.0168991088867188, | |
| "eval_runtime": 4.0539, | |
| "eval_samples_per_second": 12.334, | |
| "eval_steps_per_second": 3.207, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 95, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.0661029570543616e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |