| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.934306569343065, | |
| "eval_steps": 500, | |
| "global_step": 340, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.145985401459854, | |
| "grad_norm": 0.1969512701034546, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6345, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.291970802919708, | |
| "grad_norm": 0.17513811588287354, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4433, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.43795620437956206, | |
| "grad_norm": 0.17957448959350586, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4281, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.583941605839416, | |
| "grad_norm": 0.16534289717674255, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3108, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7299270072992701, | |
| "grad_norm": 0.1696271151304245, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3387, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8759124087591241, | |
| "grad_norm": 0.14049474895000458, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3062, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.0145985401459854, | |
| "grad_norm": 0.14177313446998596, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3354, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.1605839416058394, | |
| "grad_norm": 0.18519847095012665, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1708, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.3065693430656935, | |
| "grad_norm": 0.1618432253599167, | |
| "learning_rate": 0.0002, | |
| "loss": 1.09, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.4525547445255476, | |
| "grad_norm": 0.22861599922180176, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1921, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.5985401459854014, | |
| "grad_norm": 0.18863703310489655, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1883, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.7445255474452555, | |
| "grad_norm": 0.21330659091472626, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1134, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.8905109489051095, | |
| "grad_norm": 0.16281643509864807, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1218, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.0291970802919708, | |
| "grad_norm": 0.1913510113954544, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0937, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.1751824817518246, | |
| "grad_norm": 0.258828729391098, | |
| "learning_rate": 0.0002, | |
| "loss": 0.844, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.321167883211679, | |
| "grad_norm": 0.2650935649871826, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9038, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.4671532846715327, | |
| "grad_norm": 0.21534548699855804, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8955, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.613138686131387, | |
| "grad_norm": 0.28936412930488586, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9623, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.759124087591241, | |
| "grad_norm": 0.22461599111557007, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9206, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.905109489051095, | |
| "grad_norm": 0.2333170771598816, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9143, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.0437956204379564, | |
| "grad_norm": 0.23609858751296997, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8417, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.18978102189781, | |
| "grad_norm": 0.2533261477947235, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6803, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.335766423357664, | |
| "grad_norm": 0.28708019852638245, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6947, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.4817518248175183, | |
| "grad_norm": 0.2757578194141388, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6416, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.627737226277372, | |
| "grad_norm": 0.29800841212272644, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6616, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.7737226277372264, | |
| "grad_norm": 0.28990235924720764, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6788, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.9197080291970803, | |
| "grad_norm": 0.2645922303199768, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6891, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.0583941605839415, | |
| "grad_norm": 0.2718052864074707, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6122, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.204379562043796, | |
| "grad_norm": 0.2716304063796997, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4449, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.350364963503649, | |
| "grad_norm": 0.30169153213500977, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4474, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.4963503649635035, | |
| "grad_norm": 0.29635927081108093, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4637, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.642335766423358, | |
| "grad_norm": 0.3702072501182556, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4961, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 4.788321167883212, | |
| "grad_norm": 0.3127199709415436, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4497, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 4.934306569343065, | |
| "grad_norm": 0.2875048816204071, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4823, | |
| "step": 340 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 340, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "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": 3.364208997702451e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |