| { | |
| "best_metric": 10.361613273620605, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-30", | |
| "epoch": 0.004519263360072308, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00015064211200241026, | |
| "eval_loss": 10.36961555480957, | |
| "eval_runtime": 19.7164, | |
| "eval_samples_per_second": 283.521, | |
| "eval_steps_per_second": 70.906, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00045192633600723084, | |
| "grad_norm": 0.0662083774805069, | |
| "learning_rate": 0.00012, | |
| "loss": 10.3727, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0007532105600120514, | |
| "eval_loss": 10.368705749511719, | |
| "eval_runtime": 19.6497, | |
| "eval_samples_per_second": 284.483, | |
| "eval_steps_per_second": 71.146, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0009038526720144617, | |
| "grad_norm": 0.0660574659705162, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 10.3722, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0013557790080216926, | |
| "grad_norm": 0.07763201743364334, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 10.3704, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0015064211200241028, | |
| "eval_loss": 10.366350173950195, | |
| "eval_runtime": 19.6814, | |
| "eval_samples_per_second": 284.025, | |
| "eval_steps_per_second": 71.032, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0018077053440289234, | |
| "grad_norm": 0.07582756876945496, | |
| "learning_rate": 0.000163742398974869, | |
| "loss": 10.3683, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002259631680036154, | |
| "grad_norm": 0.08869104087352753, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 10.3667, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002259631680036154, | |
| "eval_loss": 10.364151954650879, | |
| "eval_runtime": 19.8651, | |
| "eval_samples_per_second": 281.398, | |
| "eval_steps_per_second": 70.375, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002711558016043385, | |
| "grad_norm": 0.09177450835704803, | |
| "learning_rate": 9.372094804706867e-05, | |
| "loss": 10.3665, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0030128422400482057, | |
| "eval_loss": 10.362568855285645, | |
| "eval_runtime": 19.983, | |
| "eval_samples_per_second": 279.738, | |
| "eval_steps_per_second": 69.96, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003163484352050616, | |
| "grad_norm": 0.11058437079191208, | |
| "learning_rate": 5.7422070843492734e-05, | |
| "loss": 10.3638, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0036154106880578467, | |
| "grad_norm": 0.1200045794248581, | |
| "learning_rate": 2.7103137257858868e-05, | |
| "loss": 10.3641, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.003766052800060257, | |
| "eval_loss": 10.361776351928711, | |
| "eval_runtime": 19.728, | |
| "eval_samples_per_second": 283.353, | |
| "eval_steps_per_second": 70.864, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004067337024065077, | |
| "grad_norm": 0.11940017342567444, | |
| "learning_rate": 7.022351411174866e-06, | |
| "loss": 10.3617, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.004519263360072308, | |
| "grad_norm": 0.12489710003137589, | |
| "learning_rate": 0.0, | |
| "loss": 10.3614, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004519263360072308, | |
| "eval_loss": 10.361613273620605, | |
| "eval_runtime": 20.2969, | |
| "eval_samples_per_second": 275.412, | |
| "eval_steps_per_second": 68.878, | |
| "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": 1569073397760.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |