| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.012395413696932134, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012395413696932136, | |
| "grad_norm": 1.264307975769043, | |
| "learning_rate": 2e-05, | |
| "loss": 2.3117, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012395413696932136, | |
| "eval_loss": 2.7555320262908936, | |
| "eval_runtime": 19.9355, | |
| "eval_samples_per_second": 17.055, | |
| "eval_steps_per_second": 8.527, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002479082739386427, | |
| "grad_norm": 1.586591362953186, | |
| "learning_rate": 4e-05, | |
| "loss": 2.7647, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0037186241090796405, | |
| "grad_norm": 1.6568021774291992, | |
| "learning_rate": 6e-05, | |
| "loss": 2.4478, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0037186241090796405, | |
| "eval_loss": 2.741788864135742, | |
| "eval_runtime": 19.9468, | |
| "eval_samples_per_second": 17.045, | |
| "eval_steps_per_second": 8.523, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004958165478772854, | |
| "grad_norm": 1.6222755908966064, | |
| "learning_rate": 8e-05, | |
| "loss": 2.7416, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006197706848466067, | |
| "grad_norm": 1.750022530555725, | |
| "learning_rate": 0.0001, | |
| "loss": 3.0701, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007437248218159281, | |
| "grad_norm": 1.825591802597046, | |
| "learning_rate": 0.00012, | |
| "loss": 2.5405, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007437248218159281, | |
| "eval_loss": 2.5064351558685303, | |
| "eval_runtime": 19.9576, | |
| "eval_samples_per_second": 17.036, | |
| "eval_steps_per_second": 8.518, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008676789587852495, | |
| "grad_norm": 1.930959939956665, | |
| "learning_rate": 0.00014, | |
| "loss": 2.4442, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.009916330957545709, | |
| "grad_norm": 2.057973623275757, | |
| "learning_rate": 0.00016, | |
| "loss": 2.4612, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.011155872327238922, | |
| "grad_norm": 1.8501269817352295, | |
| "learning_rate": 0.00018, | |
| "loss": 2.289, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011155872327238922, | |
| "eval_loss": 1.9082000255584717, | |
| "eval_runtime": 19.9515, | |
| "eval_samples_per_second": 17.041, | |
| "eval_steps_per_second": 8.521, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012395413696932134, | |
| "grad_norm": 1.5175899267196655, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9956, | |
| "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": 1599094896721920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |