| { | |
| "best_metric": 1.8466840982437134, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.0009409440020700768, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.704720010350384e-05, | |
| "eval_loss": 2.2353053092956543, | |
| "eval_runtime": 181.4964, | |
| "eval_samples_per_second": 49.312, | |
| "eval_steps_per_second": 24.656, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00014114160031051152, | |
| "grad_norm": 1.5987310409545898, | |
| "learning_rate": 0.00012, | |
| "loss": 9.1019, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0002352360005175192, | |
| "eval_loss": 2.1338295936584473, | |
| "eval_runtime": 181.8253, | |
| "eval_samples_per_second": 49.223, | |
| "eval_steps_per_second": 24.612, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00028228320062102303, | |
| "grad_norm": 1.2341041564941406, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 8.3582, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00042342480093153457, | |
| "grad_norm": 2.91778564453125, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 8.3926, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0004704720010350384, | |
| "eval_loss": 1.9878301620483398, | |
| "eval_runtime": 181.3652, | |
| "eval_samples_per_second": 49.348, | |
| "eval_steps_per_second": 24.674, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0005645664012420461, | |
| "grad_norm": 1.742458462715149, | |
| "learning_rate": 0.000163742398974869, | |
| "loss": 7.9287, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0007057080015525577, | |
| "grad_norm": 1.63875412940979, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 7.7748, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0007057080015525577, | |
| "eval_loss": 1.886610507965088, | |
| "eval_runtime": 181.8183, | |
| "eval_samples_per_second": 49.225, | |
| "eval_steps_per_second": 24.612, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0008468496018630691, | |
| "grad_norm": 1.5715354681015015, | |
| "learning_rate": 9.372094804706867e-05, | |
| "loss": 7.4585, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0009409440020700768, | |
| "eval_loss": 1.8466840982437134, | |
| "eval_runtime": 181.3421, | |
| "eval_samples_per_second": 49.354, | |
| "eval_steps_per_second": 24.677, | |
| "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": 1431278607925248.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |