| { | |
| "best_metric": 0.8042117357254028, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.004366335552887239, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00021831677764436196, | |
| "grad_norm": 0.3638036251068115, | |
| "learning_rate": 2e-05, | |
| "loss": 3.3904, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00021831677764436196, | |
| "eval_loss": 0.9103171825408936, | |
| "eval_runtime": 391.1828, | |
| "eval_samples_per_second": 4.931, | |
| "eval_steps_per_second": 2.467, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00043663355528872393, | |
| "grad_norm": 0.31811970472335815, | |
| "learning_rate": 4e-05, | |
| "loss": 3.2452, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0006549503329330859, | |
| "grad_norm": 0.29703134298324585, | |
| "learning_rate": 6e-05, | |
| "loss": 4.0466, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008732671105774479, | |
| "grad_norm": 0.30085551738739014, | |
| "learning_rate": 8e-05, | |
| "loss": 3.8969, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0010915838882218098, | |
| "grad_norm": 0.33264318108558655, | |
| "learning_rate": 0.0001, | |
| "loss": 3.9808, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0010915838882218098, | |
| "eval_loss": 0.9086068868637085, | |
| "eval_runtime": 388.4984, | |
| "eval_samples_per_second": 4.965, | |
| "eval_steps_per_second": 2.484, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0013099006658661718, | |
| "grad_norm": 0.3267090618610382, | |
| "learning_rate": 0.00012, | |
| "loss": 3.5855, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0015282174435105338, | |
| "grad_norm": 0.4806075096130371, | |
| "learning_rate": 0.00014, | |
| "loss": 3.4188, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0017465342211548957, | |
| "grad_norm": 0.4512508511543274, | |
| "learning_rate": 0.00016, | |
| "loss": 3.3784, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.001964850998799258, | |
| "grad_norm": 0.47779935598373413, | |
| "learning_rate": 0.00018, | |
| "loss": 3.3985, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0021831677764436196, | |
| "grad_norm": 0.6501175761222839, | |
| "learning_rate": 0.0002, | |
| "loss": 3.6911, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0021831677764436196, | |
| "eval_loss": 0.8738162517547607, | |
| "eval_runtime": 386.608, | |
| "eval_samples_per_second": 4.99, | |
| "eval_steps_per_second": 2.496, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002401484554087982, | |
| "grad_norm": 0.6236119270324707, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 3.4257, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0026198013317323436, | |
| "grad_norm": 0.5396324396133423, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 2.8704, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0028381181093767058, | |
| "grad_norm": 0.6194649338722229, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 2.6484, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0030564348870210675, | |
| "grad_norm": 0.5360026955604553, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 3.3599, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0032747516646654297, | |
| "grad_norm": 0.6152706146240234, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 2.6307, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0032747516646654297, | |
| "eval_loss": 0.8243345618247986, | |
| "eval_runtime": 387.5187, | |
| "eval_samples_per_second": 4.978, | |
| "eval_steps_per_second": 2.49, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0034930684423097914, | |
| "grad_norm": 0.6975443959236145, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 3.3202, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0037113852199541536, | |
| "grad_norm": 0.7146017551422119, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 3.0276, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.003929701997598516, | |
| "grad_norm": 0.781614363193512, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 3.4729, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0041480187752428775, | |
| "grad_norm": 0.7023319602012634, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 3.08, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.004366335552887239, | |
| "grad_norm": 0.6755356788635254, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 3.0765, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004366335552887239, | |
| "eval_loss": 0.8042117357254028, | |
| "eval_runtime": 386.4152, | |
| "eval_samples_per_second": 4.992, | |
| "eval_steps_per_second": 2.497, | |
| "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": 6514996968161280.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |