| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0217391304347827, | |
| "eval_steps": 4, | |
| "global_step": 13, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07729468599033816, | |
| "grad_norm": 29.966806411743164, | |
| "learning_rate": 5e-05, | |
| "loss": 354.7632, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07729468599033816, | |
| "eval_loss": 11.087127685546875, | |
| "eval_runtime": 0.8448, | |
| "eval_samples_per_second": 104.163, | |
| "eval_steps_per_second": 26.041, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.15458937198067632, | |
| "grad_norm": 31.932706832885742, | |
| "learning_rate": 0.0001, | |
| "loss": 354.9215, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2318840579710145, | |
| "grad_norm": 30.634830474853516, | |
| "learning_rate": 9.797464868072488e-05, | |
| "loss": 354.4944, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.30917874396135264, | |
| "grad_norm": 31.755876541137695, | |
| "learning_rate": 9.206267664155907e-05, | |
| "loss": 354.2277, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.30917874396135264, | |
| "eval_loss": 11.05913257598877, | |
| "eval_runtime": 0.3543, | |
| "eval_samples_per_second": 248.368, | |
| "eval_steps_per_second": 62.092, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.3864734299516908, | |
| "grad_norm": 31.669504165649414, | |
| "learning_rate": 8.274303669726426e-05, | |
| "loss": 353.9269, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.463768115942029, | |
| "grad_norm": 32.336524963378906, | |
| "learning_rate": 7.077075065009433e-05, | |
| "loss": 353.4835, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.5410628019323671, | |
| "grad_norm": 31.395036697387695, | |
| "learning_rate": 5.7115741913664264e-05, | |
| "loss": 353.1369, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.6183574879227053, | |
| "grad_norm": 31.216983795166016, | |
| "learning_rate": 4.288425808633575e-05, | |
| "loss": 352.7697, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.6183574879227053, | |
| "eval_loss": 11.021666526794434, | |
| "eval_runtime": 0.3549, | |
| "eval_samples_per_second": 247.956, | |
| "eval_steps_per_second": 61.989, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.6956521739130435, | |
| "grad_norm": 32.23792266845703, | |
| "learning_rate": 2.9229249349905684e-05, | |
| "loss": 352.3179, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.7729468599033816, | |
| "grad_norm": 32.02090072631836, | |
| "learning_rate": 1.725696330273575e-05, | |
| "loss": 352.533, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.8502415458937198, | |
| "grad_norm": 31.508159637451172, | |
| "learning_rate": 7.937323358440935e-06, | |
| "loss": 352.3194, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.927536231884058, | |
| "grad_norm": 32.63449478149414, | |
| "learning_rate": 2.0253513192751373e-06, | |
| "loss": 352.3684, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.927536231884058, | |
| "eval_loss": 11.013041496276855, | |
| "eval_runtime": 0.3545, | |
| "eval_samples_per_second": 248.25, | |
| "eval_steps_per_second": 62.062, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.0217391304347827, | |
| "grad_norm": 32.89696502685547, | |
| "learning_rate": 0.0, | |
| "loss": 352.2435, | |
| "step": 13 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 13, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 4, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 17305228541952.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |