| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 50, | |
| "global_step": 520, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9615384615384616, | |
| "eval_accuracy": 0.8201973056115414, | |
| "eval_f1": 0.012405237767057204, | |
| "eval_loss": 0.3012058436870575, | |
| "eval_precision": 0.015254237288135594, | |
| "eval_recall": 0.010452961672473868, | |
| "eval_runtime": 2.9167, | |
| "eval_samples_per_second": 31.542, | |
| "eval_steps_per_second": 4.114, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9230769230769231, | |
| "grad_norm": 1.078125, | |
| "learning_rate": 8.076923076923078e-05, | |
| "loss": 0.4442, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.9230769230769231, | |
| "eval_accuracy": 0.8290018033308582, | |
| "eval_f1": 0.01993355481727575, | |
| "eval_loss": 0.27755603194236755, | |
| "eval_precision": 0.03498542274052478, | |
| "eval_recall": 0.013937282229965157, | |
| "eval_runtime": 2.9435, | |
| "eval_samples_per_second": 31.255, | |
| "eval_steps_per_second": 4.077, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.8846153846153846, | |
| "eval_accuracy": 0.8282592553304339, | |
| "eval_f1": 0.020833333333333336, | |
| "eval_loss": 0.25815218687057495, | |
| "eval_precision": 0.03359173126614987, | |
| "eval_recall": 0.015098722415795587, | |
| "eval_runtime": 2.941, | |
| "eval_samples_per_second": 31.282, | |
| "eval_steps_per_second": 4.08, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 3.8461538461538463, | |
| "grad_norm": 1.171875, | |
| "learning_rate": 6.153846153846155e-05, | |
| "loss": 0.2901, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.8461538461538463, | |
| "eval_accuracy": 0.8308051341890315, | |
| "eval_f1": 0.02389078498293516, | |
| "eval_loss": 0.25513756275177, | |
| "eval_precision": 0.04501607717041801, | |
| "eval_recall": 0.016260162601626018, | |
| "eval_runtime": 2.9552, | |
| "eval_samples_per_second": 31.132, | |
| "eval_steps_per_second": 4.061, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 4.8076923076923075, | |
| "eval_accuracy": 0.8308051341890315, | |
| "eval_f1": 0.022298456260720412, | |
| "eval_loss": 0.2511464059352875, | |
| "eval_precision": 0.04262295081967213, | |
| "eval_recall": 0.015098722415795587, | |
| "eval_runtime": 2.9617, | |
| "eval_samples_per_second": 31.064, | |
| "eval_steps_per_second": 4.052, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 5.769230769230769, | |
| "grad_norm": 1.3515625, | |
| "learning_rate": 4.230769230769231e-05, | |
| "loss": 0.2775, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 5.769230769230769, | |
| "eval_accuracy": 0.8308051341890315, | |
| "eval_f1": 0.02181208053691275, | |
| "eval_loss": 0.24583899974822998, | |
| "eval_precision": 0.03927492447129909, | |
| "eval_recall": 0.015098722415795587, | |
| "eval_runtime": 2.9496, | |
| "eval_samples_per_second": 31.19, | |
| "eval_steps_per_second": 4.068, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 6.730769230769231, | |
| "eval_accuracy": 0.8309112124748064, | |
| "eval_f1": 0.020477815699658706, | |
| "eval_loss": 0.24579653143882751, | |
| "eval_precision": 0.03858520900321544, | |
| "eval_recall": 0.013937282229965157, | |
| "eval_runtime": 2.9607, | |
| "eval_samples_per_second": 31.074, | |
| "eval_steps_per_second": 4.053, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 7.6923076923076925, | |
| "grad_norm": 1.5625, | |
| "learning_rate": 2.307692307692308e-05, | |
| "loss": 0.2677, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 7.6923076923076925, | |
| "eval_accuracy": 0.8305929776174817, | |
| "eval_f1": 0.020168067226890754, | |
| "eval_loss": 0.24363110959529877, | |
| "eval_precision": 0.0364741641337386, | |
| "eval_recall": 0.013937282229965157, | |
| "eval_runtime": 2.955, | |
| "eval_samples_per_second": 31.133, | |
| "eval_steps_per_second": 4.061, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 8.653846153846153, | |
| "eval_accuracy": 0.8306990559032567, | |
| "eval_f1": 0.020202020202020204, | |
| "eval_loss": 0.24341881275177002, | |
| "eval_precision": 0.03669724770642202, | |
| "eval_recall": 0.013937282229965157, | |
| "eval_runtime": 2.9545, | |
| "eval_samples_per_second": 31.138, | |
| "eval_steps_per_second": 4.062, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 9.615384615384615, | |
| "grad_norm": 1.9453125, | |
| "learning_rate": 3.846153846153847e-06, | |
| "loss": 0.2664, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 9.615384615384615, | |
| "eval_accuracy": 0.8309112124748064, | |
| "eval_f1": 0.02027027027027027, | |
| "eval_loss": 0.24354620277881622, | |
| "eval_precision": 0.03715170278637771, | |
| "eval_recall": 0.013937282229965157, | |
| "eval_runtime": 3.1385, | |
| "eval_samples_per_second": 29.313, | |
| "eval_steps_per_second": 3.823, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 520, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "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": 4.476838693139221e+16, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |