| { | |
| "best_metric": 1.2432726621627808, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-30", | |
| "epoch": 0.0050729232720355105, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001690974424011837, | |
| "eval_loss": 1.4077675342559814, | |
| "eval_runtime": 176.3171, | |
| "eval_samples_per_second": 14.122, | |
| "eval_steps_per_second": 7.061, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000507292327203551, | |
| "grad_norm": 0.5090880393981934, | |
| "learning_rate": 0.00012, | |
| "loss": 1.3482, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008454872120059184, | |
| "eval_loss": 1.357488989830017, | |
| "eval_runtime": 175.9636, | |
| "eval_samples_per_second": 14.151, | |
| "eval_steps_per_second": 7.075, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001014584654407102, | |
| "grad_norm": 0.43426570296287537, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 1.3285, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0015218769816106531, | |
| "grad_norm": 0.4685356616973877, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 1.3682, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0016909744240118367, | |
| "eval_loss": 1.2989118099212646, | |
| "eval_runtime": 175.9695, | |
| "eval_samples_per_second": 14.15, | |
| "eval_steps_per_second": 7.075, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002029169308814204, | |
| "grad_norm": 0.4550609588623047, | |
| "learning_rate": 0.000163742398974869, | |
| "loss": 1.3542, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0025364616360177552, | |
| "grad_norm": 0.4199211299419403, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.3569, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0025364616360177552, | |
| "eval_loss": 1.263357162475586, | |
| "eval_runtime": 175.9689, | |
| "eval_samples_per_second": 14.15, | |
| "eval_steps_per_second": 7.075, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0030437539632213063, | |
| "grad_norm": 0.40665045380592346, | |
| "learning_rate": 9.372094804706867e-05, | |
| "loss": 1.1759, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0033819488480236735, | |
| "eval_loss": 1.249632477760315, | |
| "eval_runtime": 175.9054, | |
| "eval_samples_per_second": 14.155, | |
| "eval_steps_per_second": 7.078, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0035510462904248573, | |
| "grad_norm": 0.4052756428718567, | |
| "learning_rate": 5.7422070843492734e-05, | |
| "loss": 1.2445, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.004058338617628408, | |
| "grad_norm": 0.46778208017349243, | |
| "learning_rate": 2.7103137257858868e-05, | |
| "loss": 1.2339, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004227436060029592, | |
| "eval_loss": 1.2444090843200684, | |
| "eval_runtime": 175.9887, | |
| "eval_samples_per_second": 14.149, | |
| "eval_steps_per_second": 7.074, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004565630944831959, | |
| "grad_norm": 0.466905802488327, | |
| "learning_rate": 7.022351411174866e-06, | |
| "loss": 1.1967, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0050729232720355105, | |
| "grad_norm": 0.46483084559440613, | |
| "learning_rate": 0.0, | |
| "loss": 1.2324, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0050729232720355105, | |
| "eval_loss": 1.2432726621627808, | |
| "eval_runtime": 175.9673, | |
| "eval_samples_per_second": 14.15, | |
| "eval_steps_per_second": 7.075, | |
| "step": 30 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.3261235193643008e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |