| { | |
| "best_metric": 2.4154489040374756, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-30", | |
| "epoch": 0.08368200836820083, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002789400278940028, | |
| "eval_loss": 2.7523610591888428, | |
| "eval_runtime": 17.2055, | |
| "eval_samples_per_second": 17.553, | |
| "eval_steps_per_second": 4.417, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008368200836820083, | |
| "grad_norm": 0.8586562871932983, | |
| "learning_rate": 0.00012, | |
| "loss": 2.6669, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01394700139470014, | |
| "eval_loss": 2.6161580085754395, | |
| "eval_runtime": 16.3976, | |
| "eval_samples_per_second": 18.417, | |
| "eval_steps_per_second": 4.635, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.016736401673640166, | |
| "grad_norm": 0.6275702118873596, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 2.6169, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02510460251046025, | |
| "grad_norm": 0.4219728708267212, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 2.4237, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02789400278940028, | |
| "eval_loss": 2.5152595043182373, | |
| "eval_runtime": 16.4075, | |
| "eval_samples_per_second": 18.406, | |
| "eval_steps_per_second": 4.632, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03347280334728033, | |
| "grad_norm": 0.858866810798645, | |
| "learning_rate": 0.000163742398974869, | |
| "loss": 2.4774, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04184100418410042, | |
| "grad_norm": 0.6612495183944702, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.5047, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04184100418410042, | |
| "eval_loss": 2.4529712200164795, | |
| "eval_runtime": 16.4489, | |
| "eval_samples_per_second": 18.36, | |
| "eval_steps_per_second": 4.62, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0502092050209205, | |
| "grad_norm": 0.446765273809433, | |
| "learning_rate": 9.372094804706867e-05, | |
| "loss": 2.3788, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05578800557880056, | |
| "eval_loss": 2.433013916015625, | |
| "eval_runtime": 16.4157, | |
| "eval_samples_per_second": 18.397, | |
| "eval_steps_per_second": 4.63, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.058577405857740586, | |
| "grad_norm": 0.44271254539489746, | |
| "learning_rate": 5.7422070843492734e-05, | |
| "loss": 2.3624, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06694560669456066, | |
| "grad_norm": 0.5158822536468506, | |
| "learning_rate": 2.7103137257858868e-05, | |
| "loss": 2.4431, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0697350069735007, | |
| "eval_loss": 2.41864275932312, | |
| "eval_runtime": 16.4348, | |
| "eval_samples_per_second": 18.376, | |
| "eval_steps_per_second": 4.624, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07531380753138076, | |
| "grad_norm": 0.5707768201828003, | |
| "learning_rate": 7.022351411174866e-06, | |
| "loss": 2.3969, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.08368200836820083, | |
| "grad_norm": 0.6488481760025024, | |
| "learning_rate": 0.0, | |
| "loss": 2.3919, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08368200836820083, | |
| "eval_loss": 2.4154489040374756, | |
| "eval_runtime": 16.4365, | |
| "eval_samples_per_second": 18.374, | |
| "eval_steps_per_second": 4.624, | |
| "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": 2.225700505387008e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |