| { | |
| "best_metric": 1.7297241687774658, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.01994813484939158, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007979253939756633, | |
| "grad_norm": 2.772995948791504, | |
| "learning_rate": 2e-05, | |
| "loss": 3.5275, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007979253939756633, | |
| "eval_loss": 3.5597481727600098, | |
| "eval_runtime": 78.8498, | |
| "eval_samples_per_second": 6.696, | |
| "eval_steps_per_second": 3.348, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015958507879513266, | |
| "grad_norm": 2.269935131072998, | |
| "learning_rate": 4e-05, | |
| "loss": 3.7981, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0023937761819269898, | |
| "grad_norm": 2.2695231437683105, | |
| "learning_rate": 6e-05, | |
| "loss": 3.4833, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003191701575902653, | |
| "grad_norm": 2.998789072036743, | |
| "learning_rate": 8e-05, | |
| "loss": 4.3072, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003989626969878316, | |
| "grad_norm": 2.6959280967712402, | |
| "learning_rate": 0.0001, | |
| "loss": 3.6473, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003989626969878316, | |
| "eval_loss": 3.4500303268432617, | |
| "eval_runtime": 78.1455, | |
| "eval_samples_per_second": 6.757, | |
| "eval_steps_per_second": 3.378, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0047875523638539795, | |
| "grad_norm": 2.4744179248809814, | |
| "learning_rate": 0.00012, | |
| "loss": 3.4849, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005585477757829643, | |
| "grad_norm": 3.4778478145599365, | |
| "learning_rate": 0.00014, | |
| "loss": 3.6244, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006383403151805306, | |
| "grad_norm": 4.8786797523498535, | |
| "learning_rate": 0.00016, | |
| "loss": 3.2167, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00718132854578097, | |
| "grad_norm": 2.5125324726104736, | |
| "learning_rate": 0.00018, | |
| "loss": 2.7227, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007979253939756632, | |
| "grad_norm": 3.2316300868988037, | |
| "learning_rate": 0.0002, | |
| "loss": 2.7852, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007979253939756632, | |
| "eval_loss": 2.518630266189575, | |
| "eval_runtime": 78.4087, | |
| "eval_samples_per_second": 6.734, | |
| "eval_steps_per_second": 3.367, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008777179333732297, | |
| "grad_norm": 3.283538818359375, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 2.6401, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.009575104727707959, | |
| "grad_norm": 3.5200719833374023, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 2.4038, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.010373030121683623, | |
| "grad_norm": 3.327225685119629, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.8051, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.011170955515659286, | |
| "grad_norm": 3.6973745822906494, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 2.0058, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.011968880909634948, | |
| "grad_norm": 4.162341594696045, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.9943, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.011968880909634948, | |
| "eval_loss": 1.8908601999282837, | |
| "eval_runtime": 77.3751, | |
| "eval_samples_per_second": 6.824, | |
| "eval_steps_per_second": 3.412, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.012766806303610613, | |
| "grad_norm": 3.85834002494812, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.0078, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.013564731697586275, | |
| "grad_norm": 3.9787638187408447, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 1.7308, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01436265709156194, | |
| "grad_norm": 2.864772081375122, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 1.5955, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.015160582485537602, | |
| "grad_norm": 2.9417033195495605, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.7731, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.015958507879513265, | |
| "grad_norm": 3.152362585067749, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.4819, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.015958507879513265, | |
| "eval_loss": 1.7598896026611328, | |
| "eval_runtime": 77.2455, | |
| "eval_samples_per_second": 6.835, | |
| "eval_steps_per_second": 3.418, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.016756433273488927, | |
| "grad_norm": 3.4833950996398926, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 1.9758, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.017554358667464593, | |
| "grad_norm": 3.8444583415985107, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 2.025, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.018352284061440256, | |
| "grad_norm": 2.9565610885620117, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 1.6026, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.019150209455415918, | |
| "grad_norm": 3.334594964981079, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 1.9002, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01994813484939158, | |
| "grad_norm": 2.8627727031707764, | |
| "learning_rate": 0.0, | |
| "loss": 1.4609, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01994813484939158, | |
| "eval_loss": 1.7297241687774658, | |
| "eval_runtime": 77.1994, | |
| "eval_samples_per_second": 6.839, | |
| "eval_steps_per_second": 3.42, | |
| "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 | |
| } | |