| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-10", | |
| "epoch": 0.003871842028845223, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00019359210144226117, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00019359210144226117, | |
| "eval_loss": NaN, | |
| "eval_runtime": 404.3055, | |
| "eval_samples_per_second": 5.38, | |
| "eval_steps_per_second": 2.691, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00038718420288452233, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.6185, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005807763043267835, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 3.0594, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0007743684057690447, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0009679605072113057, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2295, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0009679605072113057, | |
| "eval_loss": NaN, | |
| "eval_runtime": 403.243, | |
| "eval_samples_per_second": 5.394, | |
| "eval_steps_per_second": 2.698, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001161552608653567, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 3.2499, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001355144710095828, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014, | |
| "loss": 0.8479, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0015487368115380893, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0017423289129803504, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.3807, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0019359210144226115, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0019359210144226115, | |
| "eval_loss": NaN, | |
| "eval_runtime": 403.6178, | |
| "eval_samples_per_second": 5.389, | |
| "eval_steps_per_second": 2.696, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002129513115864873, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.002323105217307134, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002516697318749395, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.9932, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.002710289420191656, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 0.7767, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.002903881521633917, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.6115, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002903881521633917, | |
| "eval_loss": NaN, | |
| "eval_runtime": 404.0315, | |
| "eval_samples_per_second": 5.383, | |
| "eval_steps_per_second": 2.693, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0030974736230761787, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0032910657245184397, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 0.4516, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.003484657825960701, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 0.4837, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003678249927402962, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.003871842028845223, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003871842028845223, | |
| "eval_loss": NaN, | |
| "eval_runtime": 403.0733, | |
| "eval_samples_per_second": 5.396, | |
| "eval_steps_per_second": 2.699, | |
| "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": 2 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6408340481507328.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |