| { | |
| "best_metric": 2.3117122650146484, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.01448225923244026, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005792903692976104, | |
| "grad_norm": 2.838529109954834, | |
| "learning_rate": 2e-05, | |
| "loss": 12.5795, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005792903692976104, | |
| "eval_loss": 3.121882677078247, | |
| "eval_runtime": 104.4145, | |
| "eval_samples_per_second": 6.963, | |
| "eval_steps_per_second": 3.486, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011585807385952208, | |
| "grad_norm": 3.1008856296539307, | |
| "learning_rate": 4e-05, | |
| "loss": 12.8641, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0017378711078928314, | |
| "grad_norm": 3.484205484390259, | |
| "learning_rate": 6e-05, | |
| "loss": 11.9847, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0023171614771904415, | |
| "grad_norm": 3.1738972663879395, | |
| "learning_rate": 8e-05, | |
| "loss": 13.3681, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002896451846488052, | |
| "grad_norm": 2.6525840759277344, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3859, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002896451846488052, | |
| "eval_loss": 3.0464909076690674, | |
| "eval_runtime": 102.3038, | |
| "eval_samples_per_second": 7.106, | |
| "eval_steps_per_second": 3.558, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0034757422157856628, | |
| "grad_norm": 4.349057197570801, | |
| "learning_rate": 0.00012, | |
| "loss": 13.4115, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004055032585083273, | |
| "grad_norm": 4.680722236633301, | |
| "learning_rate": 0.00014, | |
| "loss": 12.9696, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004634322954380883, | |
| "grad_norm": 3.7882301807403564, | |
| "learning_rate": 0.00016, | |
| "loss": 10.0891, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0052136133236784935, | |
| "grad_norm": 4.43908166885376, | |
| "learning_rate": 0.00018, | |
| "loss": 12.1125, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005792903692976104, | |
| "grad_norm": 3.733471393585205, | |
| "learning_rate": 0.0002, | |
| "loss": 9.6618, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005792903692976104, | |
| "eval_loss": 2.685049295425415, | |
| "eval_runtime": 101.5745, | |
| "eval_samples_per_second": 7.157, | |
| "eval_steps_per_second": 3.584, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006372194062273715, | |
| "grad_norm": 3.624699592590332, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 10.4661, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0069514844315713255, | |
| "grad_norm": 4.032886981964111, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 11.1481, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.007530774800868936, | |
| "grad_norm": 3.667426347732544, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 10.4183, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.008110065170166545, | |
| "grad_norm": 3.7377707958221436, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 10.7956, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.008689355539464157, | |
| "grad_norm": 5.357843399047852, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 9.9671, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008689355539464157, | |
| "eval_loss": 2.4640743732452393, | |
| "eval_runtime": 101.2592, | |
| "eval_samples_per_second": 7.18, | |
| "eval_steps_per_second": 3.595, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009268645908761766, | |
| "grad_norm": 3.6775741577148438, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 8.4698, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.009847936278059377, | |
| "grad_norm": 4.87345027923584, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 9.1637, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.010427226647356987, | |
| "grad_norm": 5.144161224365234, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 10.2837, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.011006517016654598, | |
| "grad_norm": 4.957813262939453, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 9.8878, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.011585807385952208, | |
| "grad_norm": 4.979409694671631, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 8.0892, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011585807385952208, | |
| "eval_loss": 2.3354403972625732, | |
| "eval_runtime": 101.2972, | |
| "eval_samples_per_second": 7.177, | |
| "eval_steps_per_second": 3.593, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.012165097755249819, | |
| "grad_norm": 4.596272945404053, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 9.8555, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01274438812454743, | |
| "grad_norm": 6.18507194519043, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 10.8075, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01332367849384504, | |
| "grad_norm": 3.897860288619995, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 9.3181, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.013902968863142651, | |
| "grad_norm": 4.420831680297852, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 10.5026, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01448225923244026, | |
| "grad_norm": 4.4558892250061035, | |
| "learning_rate": 0.0, | |
| "loss": 10.2569, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01448225923244026, | |
| "eval_loss": 2.3117122650146484, | |
| "eval_runtime": 101.5659, | |
| "eval_samples_per_second": 7.158, | |
| "eval_steps_per_second": 3.584, | |
| "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": 7203333529927680.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |