| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.8888888888888888, | |
| "eval_steps": 9, | |
| "global_step": 36, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.024691358024691357, | |
| "eval_loss": 2.1480655670166016, | |
| "eval_runtime": 1.0117, | |
| "eval_samples_per_second": 68.202, | |
| "eval_steps_per_second": 8.896, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07407407407407407, | |
| "grad_norm": 0.17830029129981995, | |
| "learning_rate": 1.5e-05, | |
| "loss": 2.2572, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.14814814814814814, | |
| "grad_norm": 0.21468417346477509, | |
| "learning_rate": 3e-05, | |
| "loss": 2.2267, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 0.22635942697525024, | |
| "learning_rate": 4.5e-05, | |
| "loss": 2.271, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "eval_loss": 2.143685817718506, | |
| "eval_runtime": 1.0061, | |
| "eval_samples_per_second": 68.58, | |
| "eval_steps_per_second": 8.945, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.2962962962962963, | |
| "grad_norm": 0.1852104514837265, | |
| "learning_rate": 4.993910125649561e-05, | |
| "loss": 2.2203, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.37037037037037035, | |
| "grad_norm": 0.24263235926628113, | |
| "learning_rate": 4.962019382530521e-05, | |
| "loss": 2.165, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 0.24341049790382385, | |
| "learning_rate": 4.9031542398457974e-05, | |
| "loss": 2.2557, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "eval_loss": 2.1180965900421143, | |
| "eval_runtime": 1.0063, | |
| "eval_samples_per_second": 68.568, | |
| "eval_steps_per_second": 8.944, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.5185185185185185, | |
| "grad_norm": 0.2104165405035019, | |
| "learning_rate": 4.817959636416969e-05, | |
| "loss": 2.2173, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 0.1979183554649353, | |
| "learning_rate": 4.707368982147318e-05, | |
| "loss": 2.1982, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 0.23016861081123352, | |
| "learning_rate": 4.572593931387604e-05, | |
| "loss": 2.2124, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "eval_loss": 2.072659730911255, | |
| "eval_runtime": 1.0059, | |
| "eval_samples_per_second": 68.595, | |
| "eval_steps_per_second": 8.947, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.7407407407407407, | |
| "grad_norm": 0.14867456257343292, | |
| "learning_rate": 4.415111107797445e-05, | |
| "loss": 2.1073, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.8148148148148148, | |
| "grad_norm": 0.20560601353645325, | |
| "learning_rate": 4.2366459261474933e-05, | |
| "loss": 2.1231, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.20878741145133972, | |
| "learning_rate": 4.039153688314145e-05, | |
| "loss": 2.1412, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "eval_loss": 2.027235746383667, | |
| "eval_runtime": 1.0148, | |
| "eval_samples_per_second": 67.995, | |
| "eval_steps_per_second": 8.869, | |
| "step": 36 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2288413688463360.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |