| { | |
| "best_metric": 2.3560678958892822, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.0014119058964720001, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.05952948236e-05, | |
| "grad_norm": 0.5938254594802856, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3696, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.05952948236e-05, | |
| "eval_loss": 2.631307363510132, | |
| "eval_runtime": 1209.5683, | |
| "eval_samples_per_second": 4.932, | |
| "eval_steps_per_second": 2.466, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001411905896472, | |
| "grad_norm": 0.750202476978302, | |
| "learning_rate": 4e-05, | |
| "loss": 10.0175, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00021178588447080002, | |
| "grad_norm": 0.8228864073753357, | |
| "learning_rate": 6e-05, | |
| "loss": 10.493, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0002823811792944, | |
| "grad_norm": 0.6799088716506958, | |
| "learning_rate": 8e-05, | |
| "loss": 9.9595, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00035297647411800003, | |
| "grad_norm": 0.6376928091049194, | |
| "learning_rate": 0.0001, | |
| "loss": 10.2368, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00035297647411800003, | |
| "eval_loss": 2.6231281757354736, | |
| "eval_runtime": 1211.6781, | |
| "eval_samples_per_second": 4.923, | |
| "eval_steps_per_second": 2.462, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00042357176894160004, | |
| "grad_norm": 0.8045742511749268, | |
| "learning_rate": 0.00012, | |
| "loss": 11.0456, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0004941670637652, | |
| "grad_norm": 0.8661999106407166, | |
| "learning_rate": 0.00014, | |
| "loss": 10.7248, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0005647623585888, | |
| "grad_norm": 0.9354367256164551, | |
| "learning_rate": 0.00016, | |
| "loss": 10.8692, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006353576534124001, | |
| "grad_norm": 1.209215760231018, | |
| "learning_rate": 0.00018, | |
| "loss": 10.619, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007059529482360001, | |
| "grad_norm": 1.3076131343841553, | |
| "learning_rate": 0.0002, | |
| "loss": 11.5599, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007059529482360001, | |
| "eval_loss": 2.496121883392334, | |
| "eval_runtime": 1210.3864, | |
| "eval_samples_per_second": 4.928, | |
| "eval_steps_per_second": 2.465, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007765482430596001, | |
| "grad_norm": 1.0022832155227661, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 10.4845, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0008471435378832001, | |
| "grad_norm": 1.335647463798523, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 9.594, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0009177388327068001, | |
| "grad_norm": 1.406315565109253, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 9.5518, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0009883341275304, | |
| "grad_norm": 1.4746501445770264, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 9.6602, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0010589294223540002, | |
| "grad_norm": 1.2272251844406128, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 10.2344, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0010589294223540002, | |
| "eval_loss": 2.396404266357422, | |
| "eval_runtime": 1226.905, | |
| "eval_samples_per_second": 4.862, | |
| "eval_steps_per_second": 2.431, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0011295247171776, | |
| "grad_norm": 1.6236687898635864, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 9.3855, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0012001200120012002, | |
| "grad_norm": 1.5380558967590332, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 9.6669, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0012707153068248001, | |
| "grad_norm": 1.3339756727218628, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 9.0667, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0013413106016484002, | |
| "grad_norm": 1.3109127283096313, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 10.1132, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0014119058964720001, | |
| "grad_norm": 1.509404182434082, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 9.3982, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0014119058964720001, | |
| "eval_loss": 2.3560678958892822, | |
| "eval_runtime": 1219.3739, | |
| "eval_samples_per_second": 4.892, | |
| "eval_steps_per_second": 2.446, | |
| "step": 20 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6728226648883200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |