| { | |
| "best_metric": 10.368098258972168, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.011638395065320493, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004655358026128197, | |
| "grad_norm": 0.08034619688987732, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3766, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004655358026128197, | |
| "eval_loss": 10.37507438659668, | |
| "eval_runtime": 0.1056, | |
| "eval_samples_per_second": 473.46, | |
| "eval_steps_per_second": 123.1, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009310716052256394, | |
| "grad_norm": 0.0749102234840393, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3809, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001396607407838459, | |
| "grad_norm": 0.06931249797344208, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 10.3767, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0018621432104512787, | |
| "grad_norm": 0.06932879984378815, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 10.3765, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0023276790130640984, | |
| "grad_norm": 0.06687504798173904, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 10.374, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002793214815676918, | |
| "grad_norm": 0.06729339063167572, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 10.3737, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003258750618289738, | |
| "grad_norm": 0.06792795658111572, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 10.3732, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0037242864209025574, | |
| "grad_norm": 0.06860123574733734, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 10.3749, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004189822223515377, | |
| "grad_norm": 0.07388696074485779, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 10.3734, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004655358026128197, | |
| "grad_norm": 0.0747343897819519, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 10.3742, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005120893828741016, | |
| "grad_norm": 0.07938987761735916, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 10.3728, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005586429631353836, | |
| "grad_norm": 0.07385125011205673, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 10.3744, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006051965433966656, | |
| "grad_norm": 0.08533329516649246, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 10.3741, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006517501236579476, | |
| "grad_norm": 0.08624856919050217, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 10.3741, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.006983037039192295, | |
| "grad_norm": 0.08045453578233719, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 10.3729, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007448572841805115, | |
| "grad_norm": 0.07829487323760986, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 10.373, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.007914108644417935, | |
| "grad_norm": 0.08200827240943909, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 10.3736, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.008379644447030755, | |
| "grad_norm": 0.0861327275633812, | |
| "learning_rate": 7.75e-05, | |
| "loss": 10.3708, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.008845180249643574, | |
| "grad_norm": 0.08856945484876633, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 10.3701, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.009310716052256394, | |
| "grad_norm": 0.08527480810880661, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 10.3688, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009776251854869213, | |
| "grad_norm": 0.09549330174922943, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 10.3692, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.010241787657482033, | |
| "grad_norm": 0.09057743847370148, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 10.3644, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.010707323460094852, | |
| "grad_norm": 0.09438870847225189, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 10.3678, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.011172859262707672, | |
| "grad_norm": 0.10676027089357376, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 10.3717, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.011638395065320493, | |
| "grad_norm": 0.12098844349384308, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 10.3726, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.011638395065320493, | |
| "eval_loss": 10.368098258972168, | |
| "eval_runtime": 0.1133, | |
| "eval_samples_per_second": 441.427, | |
| "eval_steps_per_second": 114.771, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 21384029798400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |