| { | |
| "best_metric": 0.12360001355409622, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-20", | |
| "epoch": 0.0033819488480236735, | |
| "eval_steps": 5, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001690974424011837, | |
| "grad_norm": 1.6888561248779297, | |
| "learning_rate": 2e-05, | |
| "loss": 2.3699, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001690974424011837, | |
| "eval_loss": 0.6129927039146423, | |
| "eval_runtime": 337.6416, | |
| "eval_samples_per_second": 7.375, | |
| "eval_steps_per_second": 3.687, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003381948848023674, | |
| "grad_norm": 1.8399994373321533, | |
| "learning_rate": 4e-05, | |
| "loss": 2.9006, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000507292327203551, | |
| "grad_norm": 1.72530996799469, | |
| "learning_rate": 6e-05, | |
| "loss": 2.3048, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006763897696047348, | |
| "grad_norm": 2.1376140117645264, | |
| "learning_rate": 8e-05, | |
| "loss": 2.4657, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008454872120059184, | |
| "grad_norm": 2.0416014194488525, | |
| "learning_rate": 0.0001, | |
| "loss": 2.4925, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008454872120059184, | |
| "eval_loss": 0.5692313313484192, | |
| "eval_runtime": 352.1584, | |
| "eval_samples_per_second": 7.071, | |
| "eval_steps_per_second": 3.535, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001014584654407102, | |
| "grad_norm": 2.4221572875976562, | |
| "learning_rate": 0.00012, | |
| "loss": 2.2069, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011836820968082857, | |
| "grad_norm": 3.3926279544830322, | |
| "learning_rate": 0.00014, | |
| "loss": 2.0034, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0013527795392094695, | |
| "grad_norm": 7.158604145050049, | |
| "learning_rate": 0.00016, | |
| "loss": 1.6199, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0015218769816106531, | |
| "grad_norm": 2.8731706142425537, | |
| "learning_rate": 0.00018, | |
| "loss": 1.3804, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0016909744240118367, | |
| "grad_norm": 2.1480000019073486, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2307, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0016909744240118367, | |
| "eval_loss": 0.22240450978279114, | |
| "eval_runtime": 340.116, | |
| "eval_samples_per_second": 7.321, | |
| "eval_steps_per_second": 3.661, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0018600718664130206, | |
| "grad_norm": 1.8090850114822388, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 0.8868, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.002029169308814204, | |
| "grad_norm": 1.3949517011642456, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 0.7729, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002198266751215388, | |
| "grad_norm": 1.1241109371185303, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.5519, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0023673641936165714, | |
| "grad_norm": 0.6692907810211182, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 0.4599, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0025364616360177552, | |
| "grad_norm": 0.9926350712776184, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.5148, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0025364616360177552, | |
| "eval_loss": 0.13447795808315277, | |
| "eval_runtime": 350.1072, | |
| "eval_samples_per_second": 7.112, | |
| "eval_steps_per_second": 3.556, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002705559078418939, | |
| "grad_norm": 1.3928656578063965, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.5929, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0028746565208201224, | |
| "grad_norm": 1.48099684715271, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 0.6033, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0030437539632213063, | |
| "grad_norm": 0.833182156085968, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 0.5041, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00321285140562249, | |
| "grad_norm": 0.5916072130203247, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.5098, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0033819488480236735, | |
| "grad_norm": 0.5035240650177002, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.4717, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0033819488480236735, | |
| "eval_loss": 0.12360001355409622, | |
| "eval_runtime": 334.5636, | |
| "eval_samples_per_second": 7.443, | |
| "eval_steps_per_second": 3.721, | |
| "step": 20 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3298217215131648.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |