| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.5073170731707317, | |
| "eval_steps": 500, | |
| "global_step": 260, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01951219512195122, | |
| "grad_norm": 0.14488260447978973, | |
| "learning_rate": 0.00019934683213585893, | |
| "loss": 0.6356, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03902439024390244, | |
| "grad_norm": 0.1634250283241272, | |
| "learning_rate": 0.00019804049640757677, | |
| "loss": 0.4368, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05853658536585366, | |
| "grad_norm": 0.1504327356815338, | |
| "learning_rate": 0.0001967341606792946, | |
| "loss": 0.407, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07804878048780488, | |
| "grad_norm": 0.16282524168491364, | |
| "learning_rate": 0.00019542782495101242, | |
| "loss": 0.3788, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0975609756097561, | |
| "grad_norm": 0.17505913972854614, | |
| "learning_rate": 0.00019412148922273026, | |
| "loss": 0.3705, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11707317073170732, | |
| "grad_norm": 0.18271876871585846, | |
| "learning_rate": 0.00019281515349444807, | |
| "loss": 0.3654, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.13658536585365855, | |
| "grad_norm": 0.1547907590866089, | |
| "learning_rate": 0.0001915088177661659, | |
| "loss": 0.3845, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.15609756097560976, | |
| "grad_norm": 0.1806977242231369, | |
| "learning_rate": 0.00019020248203788375, | |
| "loss": 0.362, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.17560975609756097, | |
| "grad_norm": 0.16502083837985992, | |
| "learning_rate": 0.00018889614630960156, | |
| "loss": 0.3436, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.1951219512195122, | |
| "grad_norm": 0.15947739779949188, | |
| "learning_rate": 0.0001875898105813194, | |
| "loss": 0.3221, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2146341463414634, | |
| "grad_norm": 0.16028478741645813, | |
| "learning_rate": 0.00018628347485303724, | |
| "loss": 0.3291, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.23414634146341465, | |
| "grad_norm": 0.16755621135234833, | |
| "learning_rate": 0.00018497713912475508, | |
| "loss": 0.3454, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.25365853658536586, | |
| "grad_norm": 0.17687192559242249, | |
| "learning_rate": 0.00018367080339647292, | |
| "loss": 0.3265, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.2731707317073171, | |
| "grad_norm": 0.12853658199310303, | |
| "learning_rate": 0.00018236446766819073, | |
| "loss": 0.3136, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.2926829268292683, | |
| "grad_norm": 0.15641653537750244, | |
| "learning_rate": 0.00018105813193990857, | |
| "loss": 0.3124, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3121951219512195, | |
| "grad_norm": 0.1840222179889679, | |
| "learning_rate": 0.00017975179621162638, | |
| "loss": 0.3308, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.33170731707317075, | |
| "grad_norm": 0.16983111202716827, | |
| "learning_rate": 0.00017844546048334422, | |
| "loss": 0.3116, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.35121951219512193, | |
| "grad_norm": 0.18679502606391907, | |
| "learning_rate": 0.00017713912475506206, | |
| "loss": 0.3458, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.37073170731707317, | |
| "grad_norm": 0.1655397266149521, | |
| "learning_rate": 0.0001758327890267799, | |
| "loss": 0.3041, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.3902439024390244, | |
| "grad_norm": 0.16899655759334564, | |
| "learning_rate": 0.00017452645329849774, | |
| "loss": 0.3179, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4097560975609756, | |
| "grad_norm": 0.14320065081119537, | |
| "learning_rate": 0.00017322011757021555, | |
| "loss": 0.2896, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.4292682926829268, | |
| "grad_norm": 0.18079160153865814, | |
| "learning_rate": 0.0001719137818419334, | |
| "loss": 0.3121, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.44878048780487806, | |
| "grad_norm": 0.15252567827701569, | |
| "learning_rate": 0.00017060744611365123, | |
| "loss": 0.3054, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.4682926829268293, | |
| "grad_norm": 0.1688212901353836, | |
| "learning_rate": 0.00016930111038536904, | |
| "loss": 0.316, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.4878048780487805, | |
| "grad_norm": 0.1604667603969574, | |
| "learning_rate": 0.00016799477465708688, | |
| "loss": 0.3174, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5073170731707317, | |
| "grad_norm": 0.19493722915649414, | |
| "learning_rate": 0.0001666884389288047, | |
| "loss": 0.307, | |
| "step": 260 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1536, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 20, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.7416088186290176e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |