| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.008216926869350863, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008216926869350862, | |
| "grad_norm": 5.969214916229248, | |
| "learning_rate": 2e-05, | |
| "loss": 9.3911, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008216926869350862, | |
| "eval_loss": 3.261870861053467, | |
| "eval_runtime": 18.4236, | |
| "eval_samples_per_second": 27.845, | |
| "eval_steps_per_second": 13.949, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016433853738701725, | |
| "grad_norm": 6.192751884460449, | |
| "learning_rate": 4e-05, | |
| "loss": 13.3037, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0024650780608052587, | |
| "grad_norm": 7.065100193023682, | |
| "learning_rate": 6e-05, | |
| "loss": 10.902, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0024650780608052587, | |
| "eval_loss": 3.2496984004974365, | |
| "eval_runtime": 18.2261, | |
| "eval_samples_per_second": 28.147, | |
| "eval_steps_per_second": 14.101, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003286770747740345, | |
| "grad_norm": 5.882843017578125, | |
| "learning_rate": 8e-05, | |
| "loss": 13.6395, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004108463434675432, | |
| "grad_norm": 7.812251567840576, | |
| "learning_rate": 0.0001, | |
| "loss": 14.5091, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0049301561216105174, | |
| "grad_norm": 9.07049560546875, | |
| "learning_rate": 0.00012, | |
| "loss": 12.8213, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0049301561216105174, | |
| "eval_loss": 3.0105860233306885, | |
| "eval_runtime": 18.4472, | |
| "eval_samples_per_second": 27.809, | |
| "eval_steps_per_second": 13.932, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005751848808545604, | |
| "grad_norm": 9.629091262817383, | |
| "learning_rate": 0.00014, | |
| "loss": 9.3842, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00657354149548069, | |
| "grad_norm": 5.702896595001221, | |
| "learning_rate": 0.00016, | |
| "loss": 9.1424, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007395234182415777, | |
| "grad_norm": 6.87904691696167, | |
| "learning_rate": 0.00018, | |
| "loss": 11.0016, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007395234182415777, | |
| "eval_loss": 2.6285359859466553, | |
| "eval_runtime": 18.3305, | |
| "eval_samples_per_second": 27.986, | |
| "eval_steps_per_second": 14.02, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008216926869350863, | |
| "grad_norm": 7.468935966491699, | |
| "learning_rate": 0.0002, | |
| "loss": 11.6847, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1628733135912960.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |