| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.009283135636926251, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0010314595152140279, | |
| "grad_norm": 1.1577364206314087, | |
| "learning_rate": 2e-05, | |
| "loss": 9.1156, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010314595152140279, | |
| "eval_loss": 2.375784158706665, | |
| "eval_runtime": 26.6501, | |
| "eval_samples_per_second": 15.347, | |
| "eval_steps_per_second": 7.692, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0020629190304280558, | |
| "grad_norm": 1.0980221033096313, | |
| "learning_rate": 4e-05, | |
| "loss": 8.4767, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0030943785456420837, | |
| "grad_norm": 1.3524521589279175, | |
| "learning_rate": 6e-05, | |
| "loss": 9.3445, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0030943785456420837, | |
| "eval_loss": 2.3743410110473633, | |
| "eval_runtime": 26.8093, | |
| "eval_samples_per_second": 15.256, | |
| "eval_steps_per_second": 7.647, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0041258380608561115, | |
| "grad_norm": 1.3186827898025513, | |
| "learning_rate": 8e-05, | |
| "loss": 10.0087, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005157297576070139, | |
| "grad_norm": 1.2354528903961182, | |
| "learning_rate": 0.0001, | |
| "loss": 8.5305, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006188757091284167, | |
| "grad_norm": 1.6300536394119263, | |
| "learning_rate": 0.00012, | |
| "loss": 9.3115, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006188757091284167, | |
| "eval_loss": 2.355851173400879, | |
| "eval_runtime": 27.0062, | |
| "eval_samples_per_second": 15.145, | |
| "eval_steps_per_second": 7.591, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007220216606498195, | |
| "grad_norm": 2.2471773624420166, | |
| "learning_rate": 0.00014, | |
| "loss": 9.3809, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.008251676121712223, | |
| "grad_norm": 1.7351436614990234, | |
| "learning_rate": 0.00016, | |
| "loss": 8.6866, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.009283135636926251, | |
| "grad_norm": 2.199270248413086, | |
| "learning_rate": 0.00018, | |
| "loss": 9.6241, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.009283135636926251, | |
| "eval_loss": 2.258143424987793, | |
| "eval_runtime": 27.0241, | |
| "eval_samples_per_second": 15.135, | |
| "eval_steps_per_second": 7.586, | |
| "step": 9 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3312433181491200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |