| { | |
| "best_metric": 1.517770528793335, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.030959752321981424, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0015479876160990713, | |
| "eval_loss": 1.8055871725082397, | |
| "eval_runtime": 44.9917, | |
| "eval_samples_per_second": 12.113, | |
| "eval_steps_per_second": 3.045, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0046439628482972135, | |
| "grad_norm": 0.9175963997840881, | |
| "learning_rate": 0.00012, | |
| "loss": 3.3353, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007739938080495356, | |
| "eval_loss": 1.7960776090621948, | |
| "eval_runtime": 44.8731, | |
| "eval_samples_per_second": 12.145, | |
| "eval_steps_per_second": 3.053, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009287925696594427, | |
| "grad_norm": 0.622268795967102, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 4.1973, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01393188854489164, | |
| "grad_norm": 0.5725258588790894, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 4.5034, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.015479876160990712, | |
| "eval_loss": 1.697222113609314, | |
| "eval_runtime": 45.2649, | |
| "eval_samples_per_second": 12.04, | |
| "eval_steps_per_second": 3.027, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.018575851393188854, | |
| "grad_norm": 0.893426775932312, | |
| "learning_rate": 0.000163742398974869, | |
| "loss": 5.2009, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02321981424148607, | |
| "grad_norm": 1.1135708093643188, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 5.5095, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02321981424148607, | |
| "eval_loss": 1.5802924633026123, | |
| "eval_runtime": 44.6107, | |
| "eval_samples_per_second": 12.217, | |
| "eval_steps_per_second": 3.071, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02786377708978328, | |
| "grad_norm": 1.0101398229599, | |
| "learning_rate": 9.372094804706867e-05, | |
| "loss": 5.7148, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.030959752321981424, | |
| "eval_loss": 1.517770528793335, | |
| "eval_runtime": 44.9777, | |
| "eval_samples_per_second": 12.117, | |
| "eval_steps_per_second": 3.046, | |
| "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": 1.8460376203001856e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |