| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.034340659340659344, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006868131868131869, | |
| "eval_loss": 11.931960105895996, | |
| "eval_runtime": 6.0229, | |
| "eval_samples_per_second": 101.944, | |
| "eval_steps_per_second": 50.972, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003434065934065934, | |
| "grad_norm": 0.01643933355808258, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9324, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006868131868131868, | |
| "grad_norm": 0.023675480857491493, | |
| "learning_rate": 0.0001, | |
| "loss": 11.933, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006868131868131868, | |
| "eval_loss": 11.931863784790039, | |
| "eval_runtime": 6.1026, | |
| "eval_samples_per_second": 100.613, | |
| "eval_steps_per_second": 50.306, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010302197802197802, | |
| "grad_norm": 0.01706523261964321, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.9319, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.013736263736263736, | |
| "grad_norm": 0.02669455297291279, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.9315, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.013736263736263736, | |
| "eval_loss": 11.931612014770508, | |
| "eval_runtime": 6.099, | |
| "eval_samples_per_second": 100.673, | |
| "eval_steps_per_second": 50.336, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.017170329670329672, | |
| "grad_norm": 0.018381647765636444, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 11.9309, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.020604395604395604, | |
| "grad_norm": 0.02004670910537243, | |
| "learning_rate": 5e-05, | |
| "loss": 11.933, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.020604395604395604, | |
| "eval_loss": 11.931435585021973, | |
| "eval_runtime": 6.1717, | |
| "eval_samples_per_second": 99.486, | |
| "eval_steps_per_second": 49.743, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02403846153846154, | |
| "grad_norm": 0.019301248714327812, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 11.931, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.027472527472527472, | |
| "grad_norm": 0.034245315939188004, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 11.9315, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.027472527472527472, | |
| "eval_loss": 11.931343078613281, | |
| "eval_runtime": 6.171, | |
| "eval_samples_per_second": 99.497, | |
| "eval_steps_per_second": 49.749, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.030906593406593408, | |
| "grad_norm": 0.019847964867949486, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 11.9317, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.034340659340659344, | |
| "grad_norm": 0.025872528553009033, | |
| "learning_rate": 0.0, | |
| "loss": 11.9311, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.034340659340659344, | |
| "eval_loss": 11.931325912475586, | |
| "eval_runtime": 5.994, | |
| "eval_samples_per_second": 102.436, | |
| "eval_steps_per_second": 51.218, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5908070400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |