| { | |
| "best_metric": 1.077322244644165, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.0007506662162669369, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.0026648650677475e-05, | |
| "grad_norm": 2.352576494216919, | |
| "learning_rate": 2e-05, | |
| "loss": 3.318, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.0026648650677475e-05, | |
| "eval_loss": 4.371880054473877, | |
| "eval_runtime": 2999.042, | |
| "eval_samples_per_second": 4.676, | |
| "eval_steps_per_second": 2.338, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.005329730135495e-05, | |
| "grad_norm": 2.5255136489868164, | |
| "learning_rate": 4e-05, | |
| "loss": 4.8858, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 9.007994595203243e-05, | |
| "grad_norm": 2.765211582183838, | |
| "learning_rate": 6e-05, | |
| "loss": 4.4405, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0001201065946027099, | |
| "grad_norm": 6.600826263427734, | |
| "learning_rate": 8e-05, | |
| "loss": 4.1842, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00015013324325338737, | |
| "grad_norm": 3.3555500507354736, | |
| "learning_rate": 0.0001, | |
| "loss": 4.9198, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00015013324325338737, | |
| "eval_loss": 4.285114765167236, | |
| "eval_runtime": 3005.5661, | |
| "eval_samples_per_second": 4.666, | |
| "eval_steps_per_second": 2.333, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00018015989190406487, | |
| "grad_norm": 3.466583490371704, | |
| "learning_rate": 0.00012, | |
| "loss": 4.7072, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00021018654055474234, | |
| "grad_norm": 4.56377649307251, | |
| "learning_rate": 0.00014, | |
| "loss": 3.4378, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0002402131892054198, | |
| "grad_norm": 4.839247226715088, | |
| "learning_rate": 0.00016, | |
| "loss": 3.7934, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0002702398378560973, | |
| "grad_norm": 5.9515886306762695, | |
| "learning_rate": 0.00018, | |
| "loss": 3.91, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00030026648650677474, | |
| "grad_norm": 4.76386022567749, | |
| "learning_rate": 0.0002, | |
| "loss": 2.5843, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00030026648650677474, | |
| "eval_loss": 2.4816670417785645, | |
| "eval_runtime": 2988.7824, | |
| "eval_samples_per_second": 4.692, | |
| "eval_steps_per_second": 2.346, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00033029313515745224, | |
| "grad_norm": 3.4956119060516357, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 2.2861, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00036031978380812973, | |
| "grad_norm": 3.3594372272491455, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 1.5061, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0003903464324588072, | |
| "grad_norm": 4.1526994705200195, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 2.3948, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00042037308110948467, | |
| "grad_norm": 2.729642629623413, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 1.487, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00045039972976016217, | |
| "grad_norm": 2.9560699462890625, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.0658, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00045039972976016217, | |
| "eval_loss": 1.3512855768203735, | |
| "eval_runtime": 3002.1108, | |
| "eval_samples_per_second": 4.671, | |
| "eval_steps_per_second": 2.336, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0004804263784108396, | |
| "grad_norm": 3.1448676586151123, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.6595, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0005104530270615171, | |
| "grad_norm": 7.779876708984375, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 1.5521, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0005404796757121946, | |
| "grad_norm": 3.0016863346099854, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 1.2587, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0005705063243628721, | |
| "grad_norm": 2.96671724319458, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.9777, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0006005329730135495, | |
| "grad_norm": 2.7571752071380615, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.993, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0006005329730135495, | |
| "eval_loss": 1.108259916305542, | |
| "eval_runtime": 3005.5794, | |
| "eval_samples_per_second": 4.666, | |
| "eval_steps_per_second": 2.333, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.000630559621664227, | |
| "grad_norm": 2.9704768657684326, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 1.0222, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0006605862703149045, | |
| "grad_norm": 2.5651001930236816, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.9873, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.000690612918965582, | |
| "grad_norm": 2.4585671424865723, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 0.8469, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0007206395676162595, | |
| "grad_norm": 2.9926390647888184, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 1.0686, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0007506662162669369, | |
| "grad_norm": 3.01412034034729, | |
| "learning_rate": 0.0, | |
| "loss": 1.1191, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0007506662162669369, | |
| "eval_loss": 1.077322244644165, | |
| "eval_runtime": 2962.2095, | |
| "eval_samples_per_second": 4.734, | |
| "eval_steps_per_second": 2.367, | |
| "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": 1.044847376990208e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |