| { | |
| "best_metric": 1.9425504207611084, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.0020751731472594746, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00010375865736297373, | |
| "eval_loss": 2.1052863597869873, | |
| "eval_runtime": 216.5295, | |
| "eval_samples_per_second": 18.741, | |
| "eval_steps_per_second": 9.371, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00031127597208892115, | |
| "grad_norm": 1.6018730401992798, | |
| "learning_rate": 6e-05, | |
| "loss": 2.0671, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005187932868148687, | |
| "eval_loss": 2.039992332458496, | |
| "eval_runtime": 218.4118, | |
| "eval_samples_per_second": 18.58, | |
| "eval_steps_per_second": 9.29, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0006225519441778423, | |
| "grad_norm": 0.8942574858665466, | |
| "learning_rate": 9.96057350657239e-05, | |
| "loss": 2.0492, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0009338279162667636, | |
| "grad_norm": 1.0134786367416382, | |
| "learning_rate": 9.381533400219318e-05, | |
| "loss": 1.8796, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0010375865736297373, | |
| "eval_loss": 1.9791643619537354, | |
| "eval_runtime": 217.7856, | |
| "eval_samples_per_second": 18.633, | |
| "eval_steps_per_second": 9.317, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0012451038883556846, | |
| "grad_norm": 0.7417125105857849, | |
| "learning_rate": 8.18711994874345e-05, | |
| "loss": 1.9186, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0015563798604446059, | |
| "grad_norm": 0.8706774711608887, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.9334, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0015563798604446059, | |
| "eval_loss": 1.9557490348815918, | |
| "eval_runtime": 219.1222, | |
| "eval_samples_per_second": 18.519, | |
| "eval_steps_per_second": 9.26, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0018676558325335271, | |
| "grad_norm": 0.9030641317367554, | |
| "learning_rate": 4.6860474023534335e-05, | |
| "loss": 1.9011, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0020751731472594746, | |
| "eval_loss": 1.9425504207611084, | |
| "eval_runtime": 218.7571, | |
| "eval_samples_per_second": 18.55, | |
| "eval_steps_per_second": 9.275, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 720954300825600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |