| { | |
| "best_metric": 1.003777027130127, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.004711425206124852, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001884570082449941, | |
| "grad_norm": 2.0747249126434326, | |
| "learning_rate": 2e-05, | |
| "loss": 6.3544, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001884570082449941, | |
| "eval_loss": 1.5150550603866577, | |
| "eval_runtime": 307.9693, | |
| "eval_samples_per_second": 7.257, | |
| "eval_steps_per_second": 3.63, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003769140164899882, | |
| "grad_norm": 1.9556933641433716, | |
| "learning_rate": 4e-05, | |
| "loss": 6.3491, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005653710247349824, | |
| "grad_norm": 1.9274996519088745, | |
| "learning_rate": 6e-05, | |
| "loss": 6.392, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0007538280329799764, | |
| "grad_norm": 1.7811566591262817, | |
| "learning_rate": 8e-05, | |
| "loss": 5.7683, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0009422850412249705, | |
| "grad_norm": 1.9588291645050049, | |
| "learning_rate": 0.0001, | |
| "loss": 6.0994, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0009422850412249705, | |
| "eval_loss": 1.4551900625228882, | |
| "eval_runtime": 304.5211, | |
| "eval_samples_per_second": 7.339, | |
| "eval_steps_per_second": 3.671, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0011307420494699647, | |
| "grad_norm": 2.0589075088500977, | |
| "learning_rate": 0.00012, | |
| "loss": 5.1873, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0013191990577149587, | |
| "grad_norm": 2.3529481887817383, | |
| "learning_rate": 0.00014, | |
| "loss": 5.8327, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0015076560659599528, | |
| "grad_norm": 2.5120608806610107, | |
| "learning_rate": 0.00016, | |
| "loss": 5.6017, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.001696113074204947, | |
| "grad_norm": 2.16925311088562, | |
| "learning_rate": 0.00018, | |
| "loss": 5.3702, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.001884570082449941, | |
| "grad_norm": 2.18813157081604, | |
| "learning_rate": 0.0002, | |
| "loss": 5.3102, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001884570082449941, | |
| "eval_loss": 1.2248835563659668, | |
| "eval_runtime": 303.7153, | |
| "eval_samples_per_second": 7.359, | |
| "eval_steps_per_second": 3.681, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0020730270906949354, | |
| "grad_norm": 1.9571467638015747, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 5.2611, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0022614840989399294, | |
| "grad_norm": 2.674177885055542, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 5.136, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0024499411071849234, | |
| "grad_norm": 3.918393850326538, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 4.7382, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0026383981154299175, | |
| "grad_norm": 3.2529351711273193, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 4.2274, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0028268551236749115, | |
| "grad_norm": 3.0015501976013184, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 4.9855, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0028268551236749115, | |
| "eval_loss": 1.0979372262954712, | |
| "eval_runtime": 303.6779, | |
| "eval_samples_per_second": 7.36, | |
| "eval_steps_per_second": 3.682, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0030153121319199056, | |
| "grad_norm": 2.5914523601531982, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 4.8228, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0032037691401649, | |
| "grad_norm": 2.8210129737854004, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 4.5255, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.003392226148409894, | |
| "grad_norm": 2.186068534851074, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 4.4055, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003580683156654888, | |
| "grad_norm": 2.8630177974700928, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 4.3739, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.003769140164899882, | |
| "grad_norm": 2.374098539352417, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 4.2284, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003769140164899882, | |
| "eval_loss": 1.0215682983398438, | |
| "eval_runtime": 304.7006, | |
| "eval_samples_per_second": 7.335, | |
| "eval_steps_per_second": 3.669, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003957597173144876, | |
| "grad_norm": 1.8999024629592896, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 4.0118, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.004146054181389871, | |
| "grad_norm": 2.3246095180511475, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 3.8845, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.004334511189634864, | |
| "grad_norm": 2.1159679889678955, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 3.7619, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.004522968197879859, | |
| "grad_norm": 2.50178599357605, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 4.4033, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004711425206124852, | |
| "grad_norm": 2.0925161838531494, | |
| "learning_rate": 0.0, | |
| "loss": 3.8412, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004711425206124852, | |
| "eval_loss": 1.003777027130127, | |
| "eval_runtime": 305.195, | |
| "eval_samples_per_second": 7.323, | |
| "eval_steps_per_second": 3.663, | |
| "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": 7132013395968000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |