| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02844950213371266, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005689900426742532, | |
| "eval_loss": 2.3201534748077393, | |
| "eval_runtime": 26.0977, | |
| "eval_samples_per_second": 28.355, | |
| "eval_steps_per_second": 14.177, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002844950213371266, | |
| "grad_norm": 1.2677528858184814, | |
| "learning_rate": 5e-05, | |
| "loss": 2.073, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005689900426742532, | |
| "grad_norm": 1.1822943687438965, | |
| "learning_rate": 0.0001, | |
| "loss": 2.1458, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005689900426742532, | |
| "eval_loss": 2.2814557552337646, | |
| "eval_runtime": 24.6819, | |
| "eval_samples_per_second": 29.981, | |
| "eval_steps_per_second": 14.991, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008534850640113799, | |
| "grad_norm": 1.1251591444015503, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.321, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.011379800853485065, | |
| "grad_norm": 1.4248967170715332, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.1071, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011379800853485065, | |
| "eval_loss": 2.175661563873291, | |
| "eval_runtime": 24.7074, | |
| "eval_samples_per_second": 29.951, | |
| "eval_steps_per_second": 14.975, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01422475106685633, | |
| "grad_norm": 1.6990677118301392, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.0976, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.017069701280227598, | |
| "grad_norm": 1.3707565069198608, | |
| "learning_rate": 5e-05, | |
| "loss": 2.16, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.017069701280227598, | |
| "eval_loss": 2.133972644805908, | |
| "eval_runtime": 24.4512, | |
| "eval_samples_per_second": 30.264, | |
| "eval_steps_per_second": 15.132, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01991465149359886, | |
| "grad_norm": 1.2129231691360474, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.9256, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02275960170697013, | |
| "grad_norm": 1.7803326845169067, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.3078, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02275960170697013, | |
| "eval_loss": 2.1224875450134277, | |
| "eval_runtime": 24.6578, | |
| "eval_samples_per_second": 30.011, | |
| "eval_steps_per_second": 15.005, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.025604551920341393, | |
| "grad_norm": 1.49332594871521, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.8645, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02844950213371266, | |
| "grad_norm": 1.537865400314331, | |
| "learning_rate": 0.0, | |
| "loss": 2.118, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02844950213371266, | |
| "eval_loss": 2.120621681213379, | |
| "eval_runtime": 24.5138, | |
| "eval_samples_per_second": 30.187, | |
| "eval_steps_per_second": 15.094, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 462998451781632.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |