| { | |
| "best_metric": 10.34113883972168, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-30", | |
| "epoch": 0.0017866448298965235, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.955482766321745e-05, | |
| "eval_loss": 10.379169464111328, | |
| "eval_runtime": 92.2052, | |
| "eval_samples_per_second": 76.677, | |
| "eval_steps_per_second": 38.338, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00017866448298965235, | |
| "grad_norm": 0.4623793959617615, | |
| "learning_rate": 0.00012, | |
| "loss": 10.3803, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00029777413831608726, | |
| "eval_loss": 10.374878883361816, | |
| "eval_runtime": 92.1991, | |
| "eval_samples_per_second": 76.682, | |
| "eval_steps_per_second": 38.341, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0003573289659793047, | |
| "grad_norm": 0.42609864473342896, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 10.3743, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005359934489689571, | |
| "grad_norm": 0.554931640625, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 10.3702, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0005955482766321745, | |
| "eval_loss": 10.363765716552734, | |
| "eval_runtime": 92.8254, | |
| "eval_samples_per_second": 76.165, | |
| "eval_steps_per_second": 38.082, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007146579319586094, | |
| "grad_norm": 0.5134620666503906, | |
| "learning_rate": 0.000163742398974869, | |
| "loss": 10.3646, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0008933224149482617, | |
| "grad_norm": 0.5371794104576111, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 10.358, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0008933224149482617, | |
| "eval_loss": 10.353273391723633, | |
| "eval_runtime": 92.7021, | |
| "eval_samples_per_second": 76.266, | |
| "eval_steps_per_second": 38.133, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0010719868979379142, | |
| "grad_norm": 0.5245136022567749, | |
| "learning_rate": 9.372094804706867e-05, | |
| "loss": 10.3507, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.001191096553264349, | |
| "eval_loss": 10.345518112182617, | |
| "eval_runtime": 92.4325, | |
| "eval_samples_per_second": 76.488, | |
| "eval_steps_per_second": 38.244, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0012506513809275664, | |
| "grad_norm": 0.5899909138679504, | |
| "learning_rate": 5.7422070843492734e-05, | |
| "loss": 10.3461, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0014293158639172188, | |
| "grad_norm": 0.6252912878990173, | |
| "learning_rate": 2.7103137257858868e-05, | |
| "loss": 10.3438, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0014888706915804361, | |
| "eval_loss": 10.341778755187988, | |
| "eval_runtime": 92.4785, | |
| "eval_samples_per_second": 76.45, | |
| "eval_steps_per_second": 38.225, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0016079803469068712, | |
| "grad_norm": 0.7194218635559082, | |
| "learning_rate": 7.022351411174866e-06, | |
| "loss": 10.3413, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0017866448298965235, | |
| "grad_norm": 0.5840440392494202, | |
| "learning_rate": 0.0, | |
| "loss": 10.3425, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0017866448298965235, | |
| "eval_loss": 10.34113883972168, | |
| "eval_runtime": 92.4377, | |
| "eval_samples_per_second": 76.484, | |
| "eval_steps_per_second": 38.242, | |
| "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": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |