| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.002807096339546373, | |
| "eval_steps": 7, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00011228385358185493, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 40.0946, | |
| "eval_samples_per_second": 93.529, | |
| "eval_steps_per_second": 46.764, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00033685156074556477, | |
| "grad_norm": 1.9103919839835726e-05, | |
| "learning_rate": 6e-05, | |
| "loss": 46.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006737031214911295, | |
| "grad_norm": 1.3594163647212554e-05, | |
| "learning_rate": 0.00012, | |
| "loss": 46.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0007859869750729845, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 39.8451, | |
| "eval_samples_per_second": 94.114, | |
| "eval_steps_per_second": 47.057, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0010105546822366943, | |
| "grad_norm": 1.7370919522363693e-05, | |
| "learning_rate": 0.00018, | |
| "loss": 46.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.001347406242982259, | |
| "grad_norm": 1.6248943211394362e-05, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 46.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.001571973950145969, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 39.6547, | |
| "eval_samples_per_second": 94.566, | |
| "eval_steps_per_second": 47.283, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0016842578037278239, | |
| "grad_norm": 1.0620135071803816e-05, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 46.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0020211093644733886, | |
| "grad_norm": 1.4074231330596376e-05, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 46.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0023579609252189536, | |
| "grad_norm": 1.7780568668968044e-05, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 46.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0023579609252189536, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 39.8123, | |
| "eval_samples_per_second": 94.192, | |
| "eval_steps_per_second": 47.096, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.002694812485964518, | |
| "grad_norm": 1.709483694867231e-05, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 46.0, | |
| "step": 24 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1007376236544.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |