| { | |
| "best_metric": 3.155805826187134, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.06983240223463687, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002793296089385475, | |
| "grad_norm": 1448.4268798828125, | |
| "learning_rate": 2e-05, | |
| "loss": 12.7662, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002793296089385475, | |
| "eval_loss": 3.3325388431549072, | |
| "eval_runtime": 6.0267, | |
| "eval_samples_per_second": 25.055, | |
| "eval_steps_per_second": 12.611, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00558659217877095, | |
| "grad_norm": 1353.778076171875, | |
| "learning_rate": 4e-05, | |
| "loss": 12.4396, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.008379888268156424, | |
| "grad_norm": 806.8947143554688, | |
| "learning_rate": 6e-05, | |
| "loss": 13.0645, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0111731843575419, | |
| "grad_norm": 999.5733032226562, | |
| "learning_rate": 8e-05, | |
| "loss": 12.6938, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013966480446927373, | |
| "grad_norm": 1524.6124267578125, | |
| "learning_rate": 0.0001, | |
| "loss": 12.2966, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.013966480446927373, | |
| "eval_loss": 3.323124885559082, | |
| "eval_runtime": 4.753, | |
| "eval_samples_per_second": 31.769, | |
| "eval_steps_per_second": 15.99, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01675977653631285, | |
| "grad_norm": 1987.1434326171875, | |
| "learning_rate": 0.00012, | |
| "loss": 13.0857, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.019553072625698324, | |
| "grad_norm": 1016.9581909179688, | |
| "learning_rate": 0.00014, | |
| "loss": 12.7557, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0223463687150838, | |
| "grad_norm": 847.552490234375, | |
| "learning_rate": 0.00016, | |
| "loss": 13.379, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.025139664804469275, | |
| "grad_norm": 1183.8375244140625, | |
| "learning_rate": 0.00018, | |
| "loss": 12.5125, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.027932960893854747, | |
| "grad_norm": 1316.9891357421875, | |
| "learning_rate": 0.0002, | |
| "loss": 12.9677, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.027932960893854747, | |
| "eval_loss": 3.275075674057007, | |
| "eval_runtime": 4.8015, | |
| "eval_samples_per_second": 31.448, | |
| "eval_steps_per_second": 15.828, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.030726256983240222, | |
| "grad_norm": 2734.73876953125, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 13.0272, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0335195530726257, | |
| "grad_norm": 1246.3319091796875, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 14.1851, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.036312849162011177, | |
| "grad_norm": 959.4293212890625, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 12.7241, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03910614525139665, | |
| "grad_norm": 1641.6357421875, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 13.6186, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04189944134078212, | |
| "grad_norm": 1507.56640625, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 11.9316, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04189944134078212, | |
| "eval_loss": 3.233804702758789, | |
| "eval_runtime": 4.8696, | |
| "eval_samples_per_second": 31.009, | |
| "eval_steps_per_second": 15.607, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0446927374301676, | |
| "grad_norm": 2713.677001953125, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 13.57, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04748603351955307, | |
| "grad_norm": 1984.106689453125, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 11.9724, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05027932960893855, | |
| "grad_norm": 851.5194702148438, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 12.0016, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05307262569832402, | |
| "grad_norm": 986.9415893554688, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 12.7948, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.055865921787709494, | |
| "grad_norm": 939.6593017578125, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 13.3214, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.055865921787709494, | |
| "eval_loss": 3.155805826187134, | |
| "eval_runtime": 5.0184, | |
| "eval_samples_per_second": 30.089, | |
| "eval_steps_per_second": 15.144, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05865921787709497, | |
| "grad_norm": 665.962646484375, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 13.8204, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.061452513966480445, | |
| "grad_norm": 1509.6649169921875, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 13.2364, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.06424581005586592, | |
| "grad_norm": 1729.46875, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 13.1418, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0670391061452514, | |
| "grad_norm": 1822.8065185546875, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 11.3855, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06983240223463687, | |
| "grad_norm": 1578.525146484375, | |
| "learning_rate": 0.0, | |
| "loss": 12.9873, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06983240223463687, | |
| "eval_loss": 3.159228563308716, | |
| "eval_runtime": 4.9163, | |
| "eval_samples_per_second": 30.714, | |
| "eval_steps_per_second": 15.459, | |
| "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": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 76719587328000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |