| { | |
| "best_metric": 1.6999015808105469, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.003440919413667332, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00013763677654669328, | |
| "grad_norm": 1.6997119188308716, | |
| "learning_rate": 2e-05, | |
| "loss": 1.7218, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00013763677654669328, | |
| "eval_loss": 2.2520158290863037, | |
| "eval_runtime": 107.0786, | |
| "eval_samples_per_second": 114.281, | |
| "eval_steps_per_second": 14.289, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00027527355309338655, | |
| "grad_norm": 2.0101189613342285, | |
| "learning_rate": 4e-05, | |
| "loss": 1.878, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00041291032964007983, | |
| "grad_norm": 2.2274413108825684, | |
| "learning_rate": 6e-05, | |
| "loss": 1.907, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005505471061867731, | |
| "grad_norm": 2.1547329425811768, | |
| "learning_rate": 8e-05, | |
| "loss": 1.7926, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0006881838827334664, | |
| "grad_norm": 1.9299261569976807, | |
| "learning_rate": 0.0001, | |
| "loss": 1.745, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008258206592801597, | |
| "grad_norm": 3.3802757263183594, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 1.7049, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0009634574358268529, | |
| "grad_norm": 2.1889641284942627, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 1.7071, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0011010942123735462, | |
| "grad_norm": 2.441528558731079, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.7626, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0012387309889202395, | |
| "grad_norm": 1.9906419515609741, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 1.608, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0013763677654669328, | |
| "grad_norm": 1.8393973112106323, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.631, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001514004542013626, | |
| "grad_norm": 2.144554615020752, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.6357, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0016516413185603193, | |
| "grad_norm": 1.8670458793640137, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.6572, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0017892780951070126, | |
| "grad_norm": 1.8215337991714478, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 1.6589, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0019269148716537059, | |
| "grad_norm": 1.9283150434494019, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.5841, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.002064551648200399, | |
| "grad_norm": 1.7328020334243774, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 1.4759, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0022021884247470924, | |
| "grad_norm": 1.8184937238693237, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 1.7213, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0023398252012937857, | |
| "grad_norm": 1.801923155784607, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 1.659, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.002477461977840479, | |
| "grad_norm": 1.8036466836929321, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 1.5719, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0026150987543871723, | |
| "grad_norm": 1.817987084388733, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 1.6654, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0027527355309338655, | |
| "grad_norm": 1.7608566284179688, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.6226, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002890372307480559, | |
| "grad_norm": 1.8072353601455688, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 1.6093, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.003028009084027252, | |
| "grad_norm": 1.7272999286651611, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 1.5039, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0031656458605739454, | |
| "grad_norm": 1.6731868982315063, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.5475, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0033032826371206386, | |
| "grad_norm": 1.7655938863754272, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 1.6075, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.003440919413667332, | |
| "grad_norm": 1.7938225269317627, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 1.5805, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.003440919413667332, | |
| "eval_loss": 1.6999015808105469, | |
| "eval_runtime": 107.0243, | |
| "eval_samples_per_second": 114.339, | |
| "eval_steps_per_second": 14.296, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": 975720907014144.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |