| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.946236559139785, | |
| "eval_steps": 500, | |
| "global_step": 138, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.21505376344086022, | |
| "grad_norm": 7.996015926817187, | |
| "learning_rate": 7.1428571428571436e-06, | |
| "loss": 2.2981, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.43010752688172044, | |
| "grad_norm": 2.962707682143447, | |
| "learning_rate": 9.942341621640558e-06, | |
| "loss": 1.0994, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6451612903225806, | |
| "grad_norm": 1.7445658767729006, | |
| "learning_rate": 9.594789058101154e-06, | |
| "loss": 0.9707, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.8602150537634409, | |
| "grad_norm": 1.5507007800350687, | |
| "learning_rate": 8.953878684688492e-06, | |
| "loss": 0.9301, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.064516129032258, | |
| "grad_norm": 1.7262461771482085, | |
| "learning_rate": 8.060529912738316e-06, | |
| "loss": 0.8727, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.2795698924731183, | |
| "grad_norm": 1.677061241367903, | |
| "learning_rate": 6.971779275566593e-06, | |
| "loss": 0.7903, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.4946236559139785, | |
| "grad_norm": 1.6964854513828154, | |
| "learning_rate": 5.757138887522884e-06, | |
| "loss": 0.7514, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.7096774193548387, | |
| "grad_norm": 1.7463783101137778, | |
| "learning_rate": 4.49415839006284e-06, | |
| "loss": 0.7546, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.924731182795699, | |
| "grad_norm": 1.79920542020065, | |
| "learning_rate": 3.2634737357758994e-06, | |
| "loss": 0.7558, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.129032258064516, | |
| "grad_norm": 3.698924921571074, | |
| "learning_rate": 2.1436589245260375e-06, | |
| "loss": 0.6577, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.3440860215053765, | |
| "grad_norm": 1.9212954432010707, | |
| "learning_rate": 1.2062093865360458e-06, | |
| "loss": 0.5443, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.5591397849462365, | |
| "grad_norm": 1.7906293486232936, | |
| "learning_rate": 5.109773021462921e-07, | |
| "loss": 0.5612, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.774193548387097, | |
| "grad_norm": 1.8644011572770092, | |
| "learning_rate": 1.0235029373752758e-07, | |
| "loss": 0.5485, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.946236559139785, | |
| "step": 138, | |
| "total_flos": 3904168919040.0, | |
| "train_loss": 0.8688372978265735, | |
| "train_runtime": 1181.3244, | |
| "train_samples_per_second": 1.877, | |
| "train_steps_per_second": 0.117 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 138, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 3904168919040.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |