| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9412650602409639, | |
| "eval_steps": 500, | |
| "global_step": 625, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03765060240963856, | |
| "grad_norm": 0.29182711243629456, | |
| "learning_rate": 0.0002, | |
| "loss": 2.048, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07530120481927711, | |
| "grad_norm": 0.355770081281662, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9254, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11295180722891567, | |
| "grad_norm": 0.24575483798980713, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8281, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.15060240963855423, | |
| "grad_norm": 0.370360791683197, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8354, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.18825301204819278, | |
| "grad_norm": 0.30005237460136414, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8066, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.22590361445783133, | |
| "grad_norm": 0.4004781246185303, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0024, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.2635542168674699, | |
| "grad_norm": 0.37836953997612, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9717, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.30120481927710846, | |
| "grad_norm": 0.38621386885643005, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0938, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.338855421686747, | |
| "grad_norm": 0.32652556896209717, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9128, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.37650602409638556, | |
| "grad_norm": 0.3783712387084961, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7907, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.4141566265060241, | |
| "grad_norm": 0.2575533390045166, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8501, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.45180722891566266, | |
| "grad_norm": 0.37206143140792847, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7147, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.4894578313253012, | |
| "grad_norm": 0.3018392324447632, | |
| "learning_rate": 0.0002, | |
| "loss": 1.602, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.5271084337349398, | |
| "grad_norm": 0.45196229219436646, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8455, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.5647590361445783, | |
| "grad_norm": 0.250590443611145, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9206, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.6024096385542169, | |
| "grad_norm": 0.314155638217926, | |
| "learning_rate": 0.0002, | |
| "loss": 1.908, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.6400602409638554, | |
| "grad_norm": 0.319771409034729, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6045, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.677710843373494, | |
| "grad_norm": 0.4088861346244812, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7106, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.7153614457831325, | |
| "grad_norm": 0.29917973279953003, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7349, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.7530120481927711, | |
| "grad_norm": 0.6233075857162476, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9191, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.7906626506024096, | |
| "grad_norm": 0.24983790516853333, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6759, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.8283132530120482, | |
| "grad_norm": 0.42871519923210144, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7982, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.8659638554216867, | |
| "grad_norm": 0.3003176748752594, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7154, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.9036144578313253, | |
| "grad_norm": 0.4300028681755066, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6376, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.9412650602409639, | |
| "grad_norm": 0.38282954692840576, | |
| "learning_rate": 0.0002, | |
| "loss": 1.545, | |
| "step": 625 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 664, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.109390150045696e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |