| { | |
| "best_metric": 0.8112471699714661, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.01677500524218914, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000838750262109457, | |
| "grad_norm": 0.6344337463378906, | |
| "learning_rate": 2e-05, | |
| "loss": 1.196, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000838750262109457, | |
| "eval_loss": 1.217626929283142, | |
| "eval_runtime": 98.3846, | |
| "eval_samples_per_second": 5.102, | |
| "eval_steps_per_second": 2.551, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001677500524218914, | |
| "grad_norm": 0.6836957931518555, | |
| "learning_rate": 4e-05, | |
| "loss": 1.2018, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0025162507863283707, | |
| "grad_norm": 0.6746562123298645, | |
| "learning_rate": 6e-05, | |
| "loss": 0.9483, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003355001048437828, | |
| "grad_norm": 0.7328519225120544, | |
| "learning_rate": 8e-05, | |
| "loss": 1.3021, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004193751310547285, | |
| "grad_norm": 0.8275501728057861, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0829, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004193751310547285, | |
| "eval_loss": 1.177491307258606, | |
| "eval_runtime": 97.8706, | |
| "eval_samples_per_second": 5.129, | |
| "eval_steps_per_second": 2.565, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0050325015726567415, | |
| "grad_norm": 0.894822895526886, | |
| "learning_rate": 0.00012, | |
| "loss": 1.1111, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005871251834766198, | |
| "grad_norm": 1.0566819906234741, | |
| "learning_rate": 0.00014, | |
| "loss": 1.1776, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006710002096875656, | |
| "grad_norm": 0.9000824689865112, | |
| "learning_rate": 0.00016, | |
| "loss": 1.0858, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007548752358985112, | |
| "grad_norm": 0.9300816655158997, | |
| "learning_rate": 0.00018, | |
| "loss": 1.006, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00838750262109457, | |
| "grad_norm": 0.7693649530410767, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9386, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00838750262109457, | |
| "eval_loss": 0.9136923551559448, | |
| "eval_runtime": 98.0239, | |
| "eval_samples_per_second": 5.121, | |
| "eval_steps_per_second": 2.561, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009226252883204026, | |
| "grad_norm": 1.2141906023025513, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 0.9539, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.010065003145313483, | |
| "grad_norm": 1.953701376914978, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 1.204, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01090375340742294, | |
| "grad_norm": 1.3392918109893799, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.8446, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.011742503669532396, | |
| "grad_norm": 1.0798664093017578, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 0.8109, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.012581253931641853, | |
| "grad_norm": 0.9665652513504028, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.1213, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.012581253931641853, | |
| "eval_loss": 0.8347001671791077, | |
| "eval_runtime": 97.1517, | |
| "eval_samples_per_second": 5.167, | |
| "eval_steps_per_second": 2.584, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.013420004193751311, | |
| "grad_norm": 0.8632697463035583, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.0509, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.014258754455860768, | |
| "grad_norm": 0.7541304230690002, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 0.6265, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.015097504717970224, | |
| "grad_norm": 0.6944363713264465, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 0.6215, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01593625498007968, | |
| "grad_norm": 0.7226666808128357, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.036, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01677500524218914, | |
| "grad_norm": 0.722159206867218, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.8276, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01677500524218914, | |
| "eval_loss": 0.8112471699714661, | |
| "eval_runtime": 96.8615, | |
| "eval_samples_per_second": 5.183, | |
| "eval_steps_per_second": 2.591, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "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": 3699128496291840.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |