| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 14.989939637826962, | |
| "eval_steps": 500, | |
| "global_step": 3720, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.4024144869215292, | |
| "grad_norm": 0.1414330005645752, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8177, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8048289738430584, | |
| "grad_norm": 0.1557430922985077, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7179, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.2072434607645874, | |
| "grad_norm": 0.19957831501960754, | |
| "learning_rate": 0.0002, | |
| "loss": 0.676, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.6096579476861166, | |
| "grad_norm": 0.23390892148017883, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6436, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.0120724346076457, | |
| "grad_norm": 0.22036917507648468, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6293, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.414486921529175, | |
| "grad_norm": 0.23049889504909515, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5812, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.816901408450704, | |
| "grad_norm": 0.2435583770275116, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5789, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3.219315895372233, | |
| "grad_norm": 0.2674865126609802, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5455, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.6217303822937623, | |
| "grad_norm": 0.2517271339893341, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5281, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 4.0241448692152915, | |
| "grad_norm": 0.27737826108932495, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5117, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.426559356136821, | |
| "grad_norm": 0.2797327935695648, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4646, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 4.82897384305835, | |
| "grad_norm": 0.2902151644229889, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4705, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 5.241448692152917, | |
| "grad_norm": 0.3148166239261627, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4095, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 5.6438631790744465, | |
| "grad_norm": 0.34497711062431335, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4081, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 6.046277665995976, | |
| "grad_norm": 0.3478667736053467, | |
| "learning_rate": 0.0002, | |
| "loss": 0.403, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 6.448692152917505, | |
| "grad_norm": 0.3573280870914459, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3532, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 6.851106639839034, | |
| "grad_norm": 0.423519492149353, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3552, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 7.253521126760563, | |
| "grad_norm": 0.39140382409095764, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3265, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 7.655935613682092, | |
| "grad_norm": 0.42240509390830994, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3078, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 8.058350100603622, | |
| "grad_norm": 0.41395705938339233, | |
| "learning_rate": 0.0002, | |
| "loss": 0.301, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 8.460764587525151, | |
| "grad_norm": 0.4344163239002228, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2637, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 8.86317907444668, | |
| "grad_norm": 0.4379712641239166, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2684, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 9.26559356136821, | |
| "grad_norm": 0.37764859199523926, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2411, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 9.668008048289739, | |
| "grad_norm": 0.4754630923271179, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2334, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 10.080482897384305, | |
| "grad_norm": 0.39889901876449585, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1951, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 10.482897384305835, | |
| "grad_norm": 0.4438158869743347, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2041, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 10.885311871227364, | |
| "grad_norm": 0.46953314542770386, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2066, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 11.287726358148893, | |
| "grad_norm": 0.4034820795059204, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1857, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 11.690140845070422, | |
| "grad_norm": 0.44169268012046814, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1859, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 12.092555331991951, | |
| "grad_norm": 0.3979734480381012, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1799, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 12.49496981891348, | |
| "grad_norm": 0.38474753499031067, | |
| "learning_rate": 0.0002, | |
| "loss": 0.165, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 12.89738430583501, | |
| "grad_norm": 0.40796715021133423, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1706, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 13.299798792756539, | |
| "grad_norm": 0.42144036293029785, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1563, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 13.702213279678068, | |
| "grad_norm": 0.40393030643463135, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1555, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 14.104627766599597, | |
| "grad_norm": 0.3850514888763428, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1537, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 14.507042253521126, | |
| "grad_norm": 0.3872847855091095, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1427, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 14.909456740442655, | |
| "grad_norm": 0.3384864032268524, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1471, | |
| "step": 3700 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 3720, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 15, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.606624189428531e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |