| { | |
| "best_metric": 1.0854774713516235, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.00834306691139663, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003337226764558652, | |
| "grad_norm": 1.4185889959335327, | |
| "learning_rate": 2e-05, | |
| "loss": 1.6652, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003337226764558652, | |
| "eval_loss": 1.5032130479812622, | |
| "eval_runtime": 252.9693, | |
| "eval_samples_per_second": 4.989, | |
| "eval_steps_per_second": 2.494, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006674453529117303, | |
| "grad_norm": 2.214141845703125, | |
| "learning_rate": 4e-05, | |
| "loss": 1.6247, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0010011680293675956, | |
| "grad_norm": 1.2290294170379639, | |
| "learning_rate": 6e-05, | |
| "loss": 1.5109, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0013348907058234607, | |
| "grad_norm": 1.1162751913070679, | |
| "learning_rate": 8e-05, | |
| "loss": 1.5202, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0016686133822793258, | |
| "grad_norm": 1.38582444190979, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5744, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0016686133822793258, | |
| "eval_loss": 1.4625636339187622, | |
| "eval_runtime": 255.1271, | |
| "eval_samples_per_second": 4.947, | |
| "eval_steps_per_second": 2.473, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002002336058735191, | |
| "grad_norm": 1.4630192518234253, | |
| "learning_rate": 0.00012, | |
| "loss": 1.4896, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0023360587351910563, | |
| "grad_norm": 1.2989553213119507, | |
| "learning_rate": 0.00014, | |
| "loss": 1.7244, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0026697814116469214, | |
| "grad_norm": 1.4467432498931885, | |
| "learning_rate": 0.00016, | |
| "loss": 1.5124, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0030035040881027865, | |
| "grad_norm": 1.4784836769104004, | |
| "learning_rate": 0.00018, | |
| "loss": 1.2348, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0033372267645586516, | |
| "grad_norm": 1.8772659301757812, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0065, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0033372267645586516, | |
| "eval_loss": 1.269775629043579, | |
| "eval_runtime": 260.2207, | |
| "eval_samples_per_second": 4.85, | |
| "eval_steps_per_second": 2.425, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0036709494410145167, | |
| "grad_norm": 1.6614469289779663, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 1.1528, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.004004672117470382, | |
| "grad_norm": 1.981618881225586, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 1.1977, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004338394793926247, | |
| "grad_norm": 1.486528992652893, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.5026, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0046721174703821125, | |
| "grad_norm": 1.6402559280395508, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 1.1142, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.005005840146837978, | |
| "grad_norm": 1.3209269046783447, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.1646, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005005840146837978, | |
| "eval_loss": 1.155595302581787, | |
| "eval_runtime": 252.949, | |
| "eval_samples_per_second": 4.989, | |
| "eval_steps_per_second": 2.495, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005339562823293843, | |
| "grad_norm": 2.333162546157837, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.1195, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.005673285499749708, | |
| "grad_norm": 2.045006036758423, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 1.0723, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.006007008176205573, | |
| "grad_norm": 1.8176156282424927, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 0.9343, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.006340730852661438, | |
| "grad_norm": 1.4949177503585815, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.8503, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.006674453529117303, | |
| "grad_norm": 1.62705397605896, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.9284, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006674453529117303, | |
| "eval_loss": 1.1000429391860962, | |
| "eval_runtime": 252.7668, | |
| "eval_samples_per_second": 4.993, | |
| "eval_steps_per_second": 2.496, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007008176205573168, | |
| "grad_norm": 1.4837185144424438, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 1.0674, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0073418988820290335, | |
| "grad_norm": 2.0792458057403564, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.831, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0076756215584848995, | |
| "grad_norm": 1.5812562704086304, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 0.9214, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.008009344234940765, | |
| "grad_norm": 1.3324098587036133, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 0.8728, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00834306691139663, | |
| "grad_norm": 2.443147897720337, | |
| "learning_rate": 0.0, | |
| "loss": 0.7592, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00834306691139663, | |
| "eval_loss": 1.0854774713516235, | |
| "eval_runtime": 252.0802, | |
| "eval_samples_per_second": 5.006, | |
| "eval_steps_per_second": 2.503, | |
| "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": 9247821240729600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |