| { | |
| "best_metric": 0.798811137676239, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.020968756552736424, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000838750262109457, | |
| "grad_norm": 0.6197941303253174, | |
| "learning_rate": 2e-05, | |
| "loss": 1.196, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000838750262109457, | |
| "eval_loss": 1.217626929283142, | |
| "eval_runtime": 74.7404, | |
| "eval_samples_per_second": 6.717, | |
| "eval_steps_per_second": 3.358, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001677500524218914, | |
| "grad_norm": 0.6892435550689697, | |
| "learning_rate": 4e-05, | |
| "loss": 1.2018, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0025162507863283707, | |
| "grad_norm": 0.669283926486969, | |
| "learning_rate": 6e-05, | |
| "loss": 0.9482, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003355001048437828, | |
| "grad_norm": 0.7161260843276978, | |
| "learning_rate": 8e-05, | |
| "loss": 1.2944, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004193751310547285, | |
| "grad_norm": 0.7779492735862732, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0871, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004193751310547285, | |
| "eval_loss": 1.1792304515838623, | |
| "eval_runtime": 74.5901, | |
| "eval_samples_per_second": 6.73, | |
| "eval_steps_per_second": 3.365, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0050325015726567415, | |
| "grad_norm": 0.8927095532417297, | |
| "learning_rate": 0.00012, | |
| "loss": 1.1159, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005871251834766198, | |
| "grad_norm": 1.0481284856796265, | |
| "learning_rate": 0.00014, | |
| "loss": 1.1768, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006710002096875656, | |
| "grad_norm": 0.9043128490447998, | |
| "learning_rate": 0.00016, | |
| "loss": 1.0929, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007548752358985112, | |
| "grad_norm": 0.9198662042617798, | |
| "learning_rate": 0.00018, | |
| "loss": 1.0042, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00838750262109457, | |
| "grad_norm": 0.7714982628822327, | |
| "learning_rate": 0.0002, | |
| "loss": 0.937, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00838750262109457, | |
| "eval_loss": 0.9114500284194946, | |
| "eval_runtime": 73.8357, | |
| "eval_samples_per_second": 6.799, | |
| "eval_steps_per_second": 3.399, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009226252883204026, | |
| "grad_norm": 1.1174073219299316, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 0.9513, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.010065003145313483, | |
| "grad_norm": 1.9251739978790283, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 1.2011, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01090375340742294, | |
| "grad_norm": 1.3824429512023926, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.8529, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.011742503669532396, | |
| "grad_norm": 1.0818190574645996, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 0.8132, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.012581253931641853, | |
| "grad_norm": 1.0789353847503662, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.1362, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.012581253931641853, | |
| "eval_loss": 0.8341509699821472, | |
| "eval_runtime": 74.4973, | |
| "eval_samples_per_second": 6.739, | |
| "eval_steps_per_second": 3.369, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.013420004193751311, | |
| "grad_norm": 0.9023324251174927, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.0547, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.014258754455860768, | |
| "grad_norm": 0.7309832572937012, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 0.6256, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.015097504717970224, | |
| "grad_norm": 0.7801679968833923, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 0.6251, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01593625498007968, | |
| "grad_norm": 0.7093712091445923, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.0333, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01677500524218914, | |
| "grad_norm": 0.7100306749343872, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.8271, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01677500524218914, | |
| "eval_loss": 0.810635507106781, | |
| "eval_runtime": 73.6054, | |
| "eval_samples_per_second": 6.82, | |
| "eval_steps_per_second": 3.41, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.017613755504298594, | |
| "grad_norm": 1.9000037908554077, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 0.7495, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.018452505766408053, | |
| "grad_norm": 0.6952345967292786, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.8508, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.019291256028517507, | |
| "grad_norm": 0.6956720352172852, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 0.7993, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.020130006290626966, | |
| "grad_norm": 0.6497891545295715, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 0.8036, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.020968756552736424, | |
| "grad_norm": 0.7134623527526855, | |
| "learning_rate": 0.0, | |
| "loss": 0.7515, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.020968756552736424, | |
| "eval_loss": 0.798811137676239, | |
| "eval_runtime": 74.0655, | |
| "eval_samples_per_second": 6.778, | |
| "eval_steps_per_second": 3.389, | |
| "step": 25 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4623910620364800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |