| { | |
| "best_metric": 2.4592623710632324, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.02857959416976279, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011431837667905116, | |
| "grad_norm": 5.08370304107666, | |
| "learning_rate": 2e-05, | |
| "loss": 16.5546, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011431837667905116, | |
| "eval_loss": 4.0086774826049805, | |
| "eval_runtime": 68.1057, | |
| "eval_samples_per_second": 5.418, | |
| "eval_steps_per_second": 2.716, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002286367533581023, | |
| "grad_norm": 4.6169304847717285, | |
| "learning_rate": 4e-05, | |
| "loss": 14.4938, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003429551300371535, | |
| "grad_norm": 3.9980452060699463, | |
| "learning_rate": 6e-05, | |
| "loss": 15.4817, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004572735067162046, | |
| "grad_norm": 5.561739444732666, | |
| "learning_rate": 8e-05, | |
| "loss": 14.7683, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005715918833952558, | |
| "grad_norm": 3.723816394805908, | |
| "learning_rate": 0.0001, | |
| "loss": 14.5941, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005715918833952558, | |
| "eval_loss": 3.934452772140503, | |
| "eval_runtime": 67.1504, | |
| "eval_samples_per_second": 5.495, | |
| "eval_steps_per_second": 2.755, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00685910260074307, | |
| "grad_norm": 7.259289741516113, | |
| "learning_rate": 0.00012, | |
| "loss": 17.6895, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00800228636753358, | |
| "grad_norm": 9.807666778564453, | |
| "learning_rate": 0.00014, | |
| "loss": 17.1144, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.009145470134324093, | |
| "grad_norm": 8.382555961608887, | |
| "learning_rate": 0.00016, | |
| "loss": 14.5067, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.010288653901114605, | |
| "grad_norm": 6.742790222167969, | |
| "learning_rate": 0.00018, | |
| "loss": 11.457, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011431837667905115, | |
| "grad_norm": 8.512904167175293, | |
| "learning_rate": 0.0002, | |
| "loss": 11.6258, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.011431837667905115, | |
| "eval_loss": 2.9601454734802246, | |
| "eval_runtime": 68.7087, | |
| "eval_samples_per_second": 5.37, | |
| "eval_steps_per_second": 2.693, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012575021434695627, | |
| "grad_norm": 9.215521812438965, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 11.6118, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01371820520148614, | |
| "grad_norm": 10.720466613769531, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 11.387, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.014861388968276651, | |
| "grad_norm": 9.58012866973877, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 12.0335, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01600457273506716, | |
| "grad_norm": 8.0549955368042, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 11.5604, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.017147756501857674, | |
| "grad_norm": 6.788261413574219, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 11.255, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.017147756501857674, | |
| "eval_loss": 2.5551671981811523, | |
| "eval_runtime": 67.9449, | |
| "eval_samples_per_second": 5.431, | |
| "eval_steps_per_second": 2.723, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.018290940268648186, | |
| "grad_norm": 6.838973522186279, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 11.1901, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.019434124035438698, | |
| "grad_norm": 8.572029113769531, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 10.9187, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02057730780222921, | |
| "grad_norm": 11.447615623474121, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 10.5933, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.021720491569019718, | |
| "grad_norm": 11.014549255371094, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 12.2246, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02286367533581023, | |
| "grad_norm": 10.644768714904785, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 9.7867, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02286367533581023, | |
| "eval_loss": 2.4806277751922607, | |
| "eval_runtime": 67.9043, | |
| "eval_samples_per_second": 5.434, | |
| "eval_steps_per_second": 2.724, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.024006859102600742, | |
| "grad_norm": 7.599691390991211, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 8.5645, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.025150042869391254, | |
| "grad_norm": 7.398324966430664, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 9.0756, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.026293226636181766, | |
| "grad_norm": 8.772193908691406, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 9.3727, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.02743641040297228, | |
| "grad_norm": 11.05912971496582, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 8.183, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02857959416976279, | |
| "grad_norm": 6.729010105133057, | |
| "learning_rate": 0.0, | |
| "loss": 8.6281, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02857959416976279, | |
| "eval_loss": 2.4592623710632324, | |
| "eval_runtime": 67.5037, | |
| "eval_samples_per_second": 5.466, | |
| "eval_steps_per_second": 2.741, | |
| "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": 7915560763392000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |