| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00487685930260912, | |
| "eval_steps": 5, | |
| "global_step": 15, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003251239535072746, | |
| "grad_norm": 0.024652473628520966, | |
| "learning_rate": 1e-05, | |
| "loss": 11.7645, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003251239535072746, | |
| "eval_loss": 11.76447582244873, | |
| "eval_runtime": 276.626, | |
| "eval_samples_per_second": 37.455, | |
| "eval_steps_per_second": 18.729, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006502479070145493, | |
| "grad_norm": 0.027672940865159035, | |
| "learning_rate": 2e-05, | |
| "loss": 11.7658, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000975371860521824, | |
| "grad_norm": 0.025643622502684593, | |
| "learning_rate": 3e-05, | |
| "loss": 11.7649, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0013004958140290985, | |
| "grad_norm": 0.025678519159555435, | |
| "learning_rate": 4e-05, | |
| "loss": 11.7648, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0016256197675363732, | |
| "grad_norm": 0.02572811394929886, | |
| "learning_rate": 5e-05, | |
| "loss": 11.7649, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0016256197675363732, | |
| "eval_loss": 11.764395713806152, | |
| "eval_runtime": 276.5749, | |
| "eval_samples_per_second": 37.462, | |
| "eval_steps_per_second": 18.733, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001950743721043648, | |
| "grad_norm": 0.026358768343925476, | |
| "learning_rate": 6e-05, | |
| "loss": 11.7634, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0022758676745509225, | |
| "grad_norm": 0.026500564068555832, | |
| "learning_rate": 7e-05, | |
| "loss": 11.7654, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002600991628058197, | |
| "grad_norm": 0.02642131596803665, | |
| "learning_rate": 8e-05, | |
| "loss": 11.7644, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002926115581565472, | |
| "grad_norm": 0.02585265040397644, | |
| "learning_rate": 9e-05, | |
| "loss": 11.7658, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0032512395350727465, | |
| "grad_norm": 0.024854907765984535, | |
| "learning_rate": 0.0001, | |
| "loss": 11.7641, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0032512395350727465, | |
| "eval_loss": 11.76411247253418, | |
| "eval_runtime": 276.5048, | |
| "eval_samples_per_second": 37.471, | |
| "eval_steps_per_second": 18.737, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003576363488580021, | |
| "grad_norm": 0.02757527120411396, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 11.7652, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.003901487442087296, | |
| "grad_norm": 0.028088003396987915, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 11.7641, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00422661139559457, | |
| "grad_norm": 0.02876427210867405, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 11.7642, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.004551735349101845, | |
| "grad_norm": 0.027249282225966454, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 11.7638, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00487685930260912, | |
| "grad_norm": 0.025040265172719955, | |
| "learning_rate": 5e-05, | |
| "loss": 11.763, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00487685930260912, | |
| "eval_loss": 11.763741493225098, | |
| "eval_runtime": 276.3837, | |
| "eval_samples_per_second": 37.488, | |
| "eval_steps_per_second": 18.746, | |
| "step": 15 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 20, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 48888010506240.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |