| { | |
| "best_metric": 10.374972343444824, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-30", | |
| "epoch": 0.01100715465052284, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000366905155017428, | |
| "eval_loss": 10.376959800720215, | |
| "eval_runtime": 5.1387, | |
| "eval_samples_per_second": 446.809, | |
| "eval_steps_per_second": 111.702, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001100715465052284, | |
| "grad_norm": 0.01980590634047985, | |
| "learning_rate": 0.00012, | |
| "loss": 10.3787, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00183452577508714, | |
| "eval_loss": 10.376710891723633, | |
| "eval_runtime": 5.1785, | |
| "eval_samples_per_second": 443.373, | |
| "eval_steps_per_second": 110.843, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002201430930104568, | |
| "grad_norm": 0.01779431477189064, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 10.3775, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003302146395156852, | |
| "grad_norm": 0.020001715049147606, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 10.3767, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00366905155017428, | |
| "eval_loss": 10.376076698303223, | |
| "eval_runtime": 5.1821, | |
| "eval_samples_per_second": 443.068, | |
| "eval_steps_per_second": 110.767, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004402861860209136, | |
| "grad_norm": 0.01696758158504963, | |
| "learning_rate": 0.000163742398974869, | |
| "loss": 10.376, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00550357732526142, | |
| "grad_norm": 0.019351821392774582, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 10.3757, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00550357732526142, | |
| "eval_loss": 10.375539779663086, | |
| "eval_runtime": 5.2474, | |
| "eval_samples_per_second": 437.548, | |
| "eval_steps_per_second": 109.387, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006604292790313704, | |
| "grad_norm": 0.016618570312857628, | |
| "learning_rate": 9.372094804706867e-05, | |
| "loss": 10.3744, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00733810310034856, | |
| "eval_loss": 10.375173568725586, | |
| "eval_runtime": 5.1303, | |
| "eval_samples_per_second": 447.539, | |
| "eval_steps_per_second": 111.885, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007705008255365988, | |
| "grad_norm": 0.01956956274807453, | |
| "learning_rate": 5.7422070843492734e-05, | |
| "loss": 10.3751, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.008805723720418272, | |
| "grad_norm": 0.018741020932793617, | |
| "learning_rate": 2.7103137257858868e-05, | |
| "loss": 10.3748, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0091726288754357, | |
| "eval_loss": 10.374998092651367, | |
| "eval_runtime": 5.1303, | |
| "eval_samples_per_second": 447.538, | |
| "eval_steps_per_second": 111.884, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.009906439185470555, | |
| "grad_norm": 0.01948084868490696, | |
| "learning_rate": 7.022351411174866e-06, | |
| "loss": 10.3736, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.01100715465052284, | |
| "grad_norm": 0.017541740089654922, | |
| "learning_rate": 0.0, | |
| "loss": 10.3767, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01100715465052284, | |
| "eval_loss": 10.374972343444824, | |
| "eval_runtime": 5.1203, | |
| "eval_samples_per_second": 448.407, | |
| "eval_steps_per_second": 112.102, | |
| "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 | |
| } | |