| { | |
| "best_metric": 1.6042733192443848, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.0011519675605934938, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.607870242373975e-05, | |
| "grad_norm": 0.588746190071106, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 6.5064, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.607870242373975e-05, | |
| "eval_loss": 1.6421566009521484, | |
| "eval_runtime": 4288.6025, | |
| "eval_samples_per_second": 2.131, | |
| "eval_steps_per_second": 1.065, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.21574048474795e-05, | |
| "grad_norm": 0.5073788166046143, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 5.3471, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00013823610727121925, | |
| "grad_norm": 0.5721762180328369, | |
| "learning_rate": 6e-06, | |
| "loss": 6.3213, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000184314809694959, | |
| "grad_norm": 0.5545344352722168, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 5.2701, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00023039351211869873, | |
| "grad_norm": 0.5406827926635742, | |
| "learning_rate": 1e-05, | |
| "loss": 5.9878, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00023039351211869873, | |
| "eval_loss": 1.642135500907898, | |
| "eval_runtime": 1312.5288, | |
| "eval_samples_per_second": 6.962, | |
| "eval_steps_per_second": 3.481, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0002764722145424385, | |
| "grad_norm": 0.5396299362182617, | |
| "learning_rate": 1.2e-05, | |
| "loss": 5.6497, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00032255091696617823, | |
| "grad_norm": 0.47290557622909546, | |
| "learning_rate": 1.4e-05, | |
| "loss": 5.5207, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.000368629619389918, | |
| "grad_norm": 0.9972706437110901, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 6.8762, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0004147083218136577, | |
| "grad_norm": 0.5820791721343994, | |
| "learning_rate": 1.8e-05, | |
| "loss": 6.8037, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00046078702423739745, | |
| "grad_norm": 0.5647141337394714, | |
| "learning_rate": 2e-05, | |
| "loss": 6.4019, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00046078702423739745, | |
| "eval_loss": 1.638012170791626, | |
| "eval_runtime": 1312.2279, | |
| "eval_samples_per_second": 6.964, | |
| "eval_steps_per_second": 3.482, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0005068657266611372, | |
| "grad_norm": 1.0510690212249756, | |
| "learning_rate": 1.9781476007338058e-05, | |
| "loss": 8.4169, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.000552944429084877, | |
| "grad_norm": 0.5502700209617615, | |
| "learning_rate": 1.913545457642601e-05, | |
| "loss": 5.4723, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0005990231315086167, | |
| "grad_norm": 1.5494643449783325, | |
| "learning_rate": 1.8090169943749477e-05, | |
| "loss": 7.7394, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0006451018339323565, | |
| "grad_norm": 0.8573722243309021, | |
| "learning_rate": 1.6691306063588583e-05, | |
| "loss": 6.3292, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0006911805363560963, | |
| "grad_norm": 0.9812471270561218, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 6.437, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0006911805363560963, | |
| "eval_loss": 1.6242995262145996, | |
| "eval_runtime": 1312.4542, | |
| "eval_samples_per_second": 6.963, | |
| "eval_steps_per_second": 3.481, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.000737259238779836, | |
| "grad_norm": 1.0276433229446411, | |
| "learning_rate": 1.3090169943749475e-05, | |
| "loss": 6.6531, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0007833379412035757, | |
| "grad_norm": 1.0183649063110352, | |
| "learning_rate": 1.1045284632676535e-05, | |
| "loss": 6.6236, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0008294166436273154, | |
| "grad_norm": 1.4187095165252686, | |
| "learning_rate": 8.954715367323468e-06, | |
| "loss": 6.489, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0008754953460510552, | |
| "grad_norm": 0.8043063282966614, | |
| "learning_rate": 6.909830056250527e-06, | |
| "loss": 6.186, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0009215740484747949, | |
| "grad_norm": 1.7660255432128906, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 6.6414, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0009215740484747949, | |
| "eval_loss": 1.608821153640747, | |
| "eval_runtime": 3307.9824, | |
| "eval_samples_per_second": 2.762, | |
| "eval_steps_per_second": 1.381, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0009676527508985347, | |
| "grad_norm": 1.247157096862793, | |
| "learning_rate": 3.308693936411421e-06, | |
| "loss": 5.8863, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0010137314533222744, | |
| "grad_norm": 1.7679110765457153, | |
| "learning_rate": 1.9098300562505266e-06, | |
| "loss": 5.8775, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0010598101557460142, | |
| "grad_norm": 1.592766284942627, | |
| "learning_rate": 8.645454235739903e-07, | |
| "loss": 5.9673, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.001105888858169754, | |
| "grad_norm": 1.4257538318634033, | |
| "learning_rate": 2.1852399266194312e-07, | |
| "loss": 6.3244, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0011519675605934938, | |
| "grad_norm": 1.1082109212875366, | |
| "learning_rate": 0.0, | |
| "loss": 5.128, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0011519675605934938, | |
| "eval_loss": 1.6042733192443848, | |
| "eval_runtime": 1312.2555, | |
| "eval_samples_per_second": 6.964, | |
| "eval_steps_per_second": 3.482, | |
| "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": 1.211080796798976e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |