| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.2886783942264321, | |
| "eval_steps": 40, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0014433919711321606, | |
| "eval_loss": NaN, | |
| "eval_runtime": 72.8566, | |
| "eval_samples_per_second": 16.018, | |
| "eval_steps_per_second": 8.016, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05773567884528642, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05773567884528642, | |
| "eval_loss": NaN, | |
| "eval_runtime": 71.4586, | |
| "eval_samples_per_second": 16.331, | |
| "eval_steps_per_second": 8.173, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11547135769057285, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.11547135769057285, | |
| "eval_loss": NaN, | |
| "eval_runtime": 71.4847, | |
| "eval_samples_per_second": 16.325, | |
| "eval_steps_per_second": 8.17, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.17320703653585928, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 0.0215, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.17320703653585928, | |
| "eval_loss": NaN, | |
| "eval_runtime": 71.5081, | |
| "eval_samples_per_second": 16.32, | |
| "eval_steps_per_second": 8.167, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2309427153811457, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 0.071, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.2309427153811457, | |
| "eval_loss": NaN, | |
| "eval_runtime": 71.4346, | |
| "eval_samples_per_second": 16.337, | |
| "eval_steps_per_second": 8.175, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.2886783942264321, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2886783942264321, | |
| "eval_loss": NaN, | |
| "eval_runtime": 71.434, | |
| "eval_samples_per_second": 16.337, | |
| "eval_steps_per_second": 8.175, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 40, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 40, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.459457688600576e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |