| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.0851063829787235, | |
| "eval_steps": 25, | |
| "global_step": 44, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06808510638297872, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 2730.0667, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06808510638297872, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.3383, | |
| "eval_samples_per_second": 21.383, | |
| "eval_steps_per_second": 5.56, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.13617021276595745, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.20425531914893616, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.987417087315311e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.2723404255319149, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.949738718013078e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.3404255319148936, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.887175604818206e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.4085106382978723, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.800077626037634e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.4765957446808511, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.688931868898919e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5446808510638298, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.554359905560886e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.6127659574468085, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.6808510638297872, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.218074484421978e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7489361702127659, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.018241671106134e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.8170212765957446, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.798733423234218e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.8851063829787233, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.560777319969136e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.9531914893617022, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.305704108364301e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.0510638297872341, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.034940261286298e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.1191489361702127, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.1872340425531915, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.452476826029011e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.2553191489361701, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.14403460964878e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.323404255319149, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.82639828484907e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.3914893617021278, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.501344202803414e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.4595744680851064, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.170690197792785e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.527659574468085, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.83628542113891e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.5957446808510638, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.6638297872340426, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.163714578861091e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.7319148936170212, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.829309802207215e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.7319148936170212, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.688, | |
| "eval_samples_per_second": 29.622, | |
| "eval_steps_per_second": 7.702, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.498655797196586e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.8680851063829786, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.173601715150931e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.9361702127659575, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8559653903512224e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.0340425531914894, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.547523173970989e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.1021276595744682, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.1702127659574466, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9650597387137014e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.2382978723404254, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6942958916356998e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.3063829787234043, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4392226800308622e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.374468085106383, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2012665767657826e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.4425531914893615, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.981758328893866e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.5106382978723403, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.781925515578024e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.578723404255319, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.646808510638298, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4456400944391146e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.7148936170212767, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3110681311010814e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.7829787234042556, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1999223739623667e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.851063829787234, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1128243951817937e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.9191489361702128, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0502612819869217e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 3.0170212765957447, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0125829126846895e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 3.0851063829787235, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 44, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.9491708733711974e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |