| { | |
| "best_metric": 1.2524471282958984, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.020525451559934318, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008210180623973727, | |
| "grad_norm": 7.479497909545898, | |
| "learning_rate": 2e-05, | |
| "loss": 6.8396, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008210180623973727, | |
| "eval_loss": 7.077064514160156, | |
| "eval_runtime": 55.7918, | |
| "eval_samples_per_second": 9.195, | |
| "eval_steps_per_second": 4.606, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016420361247947454, | |
| "grad_norm": 6.5878400802612305, | |
| "learning_rate": 4e-05, | |
| "loss": 6.7554, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0024630541871921183, | |
| "grad_norm": 7.17900276184082, | |
| "learning_rate": 6e-05, | |
| "loss": 7.4692, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003284072249589491, | |
| "grad_norm": 7.042717933654785, | |
| "learning_rate": 8e-05, | |
| "loss": 7.6165, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004105090311986864, | |
| "grad_norm": 8.648153305053711, | |
| "learning_rate": 0.0001, | |
| "loss": 7.2808, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004105090311986864, | |
| "eval_loss": 6.476822376251221, | |
| "eval_runtime": 55.4437, | |
| "eval_samples_per_second": 9.253, | |
| "eval_steps_per_second": 4.635, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0049261083743842365, | |
| "grad_norm": 8.955443382263184, | |
| "learning_rate": 0.00012, | |
| "loss": 5.9208, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005747126436781609, | |
| "grad_norm": 9.691061019897461, | |
| "learning_rate": 0.00014, | |
| "loss": 6.18, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006568144499178982, | |
| "grad_norm": 8.714971542358398, | |
| "learning_rate": 0.00016, | |
| "loss": 4.8694, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007389162561576354, | |
| "grad_norm": 10.449569702148438, | |
| "learning_rate": 0.00018, | |
| "loss": 4.5233, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008210180623973728, | |
| "grad_norm": 7.942665100097656, | |
| "learning_rate": 0.0002, | |
| "loss": 3.3926, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008210180623973728, | |
| "eval_loss": 3.5349371433258057, | |
| "eval_runtime": 55.2423, | |
| "eval_samples_per_second": 9.286, | |
| "eval_steps_per_second": 4.652, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0090311986863711, | |
| "grad_norm": 6.665732383728027, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 3.9181, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.009852216748768473, | |
| "grad_norm": 7.836021900177002, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 3.0558, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.010673234811165846, | |
| "grad_norm": 11.377631187438965, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 3.2821, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.011494252873563218, | |
| "grad_norm": 8.392828941345215, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 2.391, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.012315270935960592, | |
| "grad_norm": 7.50490665435791, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.895, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.012315270935960592, | |
| "eval_loss": 2.026073932647705, | |
| "eval_runtime": 55.3509, | |
| "eval_samples_per_second": 9.268, | |
| "eval_steps_per_second": 4.643, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.013136288998357963, | |
| "grad_norm": 7.33989143371582, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.9689, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.013957307060755337, | |
| "grad_norm": 9.091341018676758, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 1.6151, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.014778325123152709, | |
| "grad_norm": 7.225343227386475, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 1.8492, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.015599343185550082, | |
| "grad_norm": 9.886344909667969, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.9566, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.016420361247947456, | |
| "grad_norm": 6.689027786254883, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.2539, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.016420361247947456, | |
| "eval_loss": 1.3548338413238525, | |
| "eval_runtime": 56.0188, | |
| "eval_samples_per_second": 9.158, | |
| "eval_steps_per_second": 4.588, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.017241379310344827, | |
| "grad_norm": 8.534672737121582, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 1.5264, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0180623973727422, | |
| "grad_norm": 6.850774765014648, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 1.2807, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.018883415435139574, | |
| "grad_norm": 7.599748611450195, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 1.2068, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.019704433497536946, | |
| "grad_norm": 10.296943664550781, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 1.5661, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.020525451559934318, | |
| "grad_norm": 7.845312118530273, | |
| "learning_rate": 0.0, | |
| "loss": 1.4555, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.020525451559934318, | |
| "eval_loss": 1.2524471282958984, | |
| "eval_runtime": 59.8902, | |
| "eval_samples_per_second": 8.566, | |
| "eval_steps_per_second": 4.291, | |
| "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": 1223694483456000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |