| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9882352941176471, | |
| "eval_steps": 500, | |
| "global_step": 42, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11764705882352941, | |
| "grad_norm": 3.502065765112122, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2955, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": 1.0166353187103343, | |
| "learning_rate": 4.77807122597034e-05, | |
| "loss": 0.5761, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.35294117647058826, | |
| "grad_norm": 2.0609265403495867, | |
| "learning_rate": 4.151686808475204e-05, | |
| "loss": 0.4265, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": 0.42584227426186005, | |
| "learning_rate": 3.232056928191376e-05, | |
| "loss": 0.3626, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5882352941176471, | |
| "grad_norm": 0.31196594170810965, | |
| "learning_rate": 2.182455450632803e-05, | |
| "loss": 0.337, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7058823529411765, | |
| "grad_norm": 0.2951365308766864, | |
| "learning_rate": 1.1892317911069212e-05, | |
| "loss": 0.3255, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.8235294117647058, | |
| "grad_norm": 0.2794268174086481, | |
| "learning_rate": 4.2872587689039484e-06, | |
| "loss": 0.3152, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.9411764705882353, | |
| "grad_norm": 0.27293344082468357, | |
| "learning_rate": 3.5960224130728857e-07, | |
| "loss": 0.3135, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.9882352941176471, | |
| "step": 42, | |
| "total_flos": 8684660632584192.0, | |
| "train_loss": 0.4845818508239019, | |
| "train_runtime": 2191.8228, | |
| "train_samples_per_second": 2.468, | |
| "train_steps_per_second": 0.019 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 42, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8684660632584192.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |