| { | |
| "best_metric": 11.083807945251465, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.002130787752232, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.523151008928e-05, | |
| "grad_norm": 0.4231654405593872, | |
| "learning_rate": 2e-05, | |
| "loss": 44.3729, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.523151008928e-05, | |
| "eval_loss": 11.08980941772461, | |
| "eval_runtime": 53.2271, | |
| "eval_samples_per_second": 92.829, | |
| "eval_steps_per_second": 46.424, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00017046302017856, | |
| "grad_norm": 0.5282648801803589, | |
| "learning_rate": 4e-05, | |
| "loss": 44.3586, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00025569453026784, | |
| "grad_norm": 0.45394039154052734, | |
| "learning_rate": 6e-05, | |
| "loss": 44.3495, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00034092604035712, | |
| "grad_norm": 0.5408138632774353, | |
| "learning_rate": 8e-05, | |
| "loss": 44.3812, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00042615755044640003, | |
| "grad_norm": 0.42006009817123413, | |
| "learning_rate": 0.0001, | |
| "loss": 44.3593, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00042615755044640003, | |
| "eval_loss": 11.089314460754395, | |
| "eval_runtime": 52.9511, | |
| "eval_samples_per_second": 93.312, | |
| "eval_steps_per_second": 46.666, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00051138906053568, | |
| "grad_norm": 0.4231087565422058, | |
| "learning_rate": 0.00012, | |
| "loss": 44.3554, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00059662057062496, | |
| "grad_norm": 0.4843730926513672, | |
| "learning_rate": 0.00014, | |
| "loss": 44.3573, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00068185208071424, | |
| "grad_norm": 0.5100414156913757, | |
| "learning_rate": 0.00016, | |
| "loss": 44.3468, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00076708359080352, | |
| "grad_norm": 0.43205395340919495, | |
| "learning_rate": 0.00018, | |
| "loss": 44.3455, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0008523151008928001, | |
| "grad_norm": 0.4004482924938202, | |
| "learning_rate": 0.0002, | |
| "loss": 44.3392, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008523151008928001, | |
| "eval_loss": 11.087959289550781, | |
| "eval_runtime": 53.2367, | |
| "eval_samples_per_second": 92.812, | |
| "eval_steps_per_second": 46.415, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0009375466109820801, | |
| "grad_norm": 0.5480057597160339, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 44.3582, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00102277812107136, | |
| "grad_norm": 0.36656516790390015, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 44.3306, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00110800963116064, | |
| "grad_norm": 0.40991735458374023, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 44.3434, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00119324114124992, | |
| "grad_norm": 0.5007737874984741, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 44.3493, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0012784726513392001, | |
| "grad_norm": 0.5267063975334167, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 44.34, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0012784726513392001, | |
| "eval_loss": 11.085758209228516, | |
| "eval_runtime": 52.3465, | |
| "eval_samples_per_second": 94.39, | |
| "eval_steps_per_second": 47.205, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00136370416142848, | |
| "grad_norm": 0.47328367829322815, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 44.325, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0014489356715177602, | |
| "grad_norm": 0.4337502121925354, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 44.36, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.00153416718160704, | |
| "grad_norm": 0.578646183013916, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 44.3353, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0016193986916963202, | |
| "grad_norm": 0.44878435134887695, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 44.3153, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0017046302017856001, | |
| "grad_norm": 0.5139074325561523, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 44.3443, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0017046302017856001, | |
| "eval_loss": 11.084075927734375, | |
| "eval_runtime": 51.5632, | |
| "eval_samples_per_second": 95.824, | |
| "eval_steps_per_second": 47.922, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0017898617118748802, | |
| "grad_norm": 0.5952379703521729, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 44.3498, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0018750932219641601, | |
| "grad_norm": 0.48162856698036194, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 44.3237, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0019603247320534403, | |
| "grad_norm": 0.5268715620040894, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 44.3326, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.00204555624214272, | |
| "grad_norm": 0.4241119623184204, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 44.3351, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.002130787752232, | |
| "grad_norm": 0.5421972274780273, | |
| "learning_rate": 0.0, | |
| "loss": 44.326, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.002130787752232, | |
| "eval_loss": 11.083807945251465, | |
| "eval_runtime": 53.227, | |
| "eval_samples_per_second": 92.829, | |
| "eval_steps_per_second": 46.424, | |
| "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": 21852979200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |