| { | |
| "best_metric": 0.555886736214605, | |
| "best_model_checkpoint": "test/checkpoint-1000", | |
| "epoch": 114.28571428571429, | |
| "eval_steps": 100, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 11.428571428571429, | |
| "eval_accuracy": 0.5990491283676703, | |
| "eval_f1": 0.0, | |
| "eval_loss": 2.2935469150543213, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 8.6961, | |
| "eval_samples_per_second": 4.025, | |
| "eval_steps_per_second": 2.07, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 22.857142857142858, | |
| "eval_accuracy": 0.6756471209720021, | |
| "eval_f1": 0.24677716390423574, | |
| "eval_loss": 1.4737745523452759, | |
| "eval_precision": 0.3284313725490196, | |
| "eval_recall": 0.1976401179941003, | |
| "eval_runtime": 8.62, | |
| "eval_samples_per_second": 4.06, | |
| "eval_steps_per_second": 2.088, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 34.285714285714285, | |
| "eval_accuracy": 0.7221341785525621, | |
| "eval_f1": 0.4099378881987578, | |
| "eval_loss": 1.2425366640090942, | |
| "eval_precision": 0.43278688524590164, | |
| "eval_recall": 0.3893805309734513, | |
| "eval_runtime": 9.0324, | |
| "eval_samples_per_second": 3.875, | |
| "eval_steps_per_second": 1.993, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 45.714285714285715, | |
| "eval_accuracy": 0.745905969360803, | |
| "eval_f1": 0.46960486322188444, | |
| "eval_loss": 1.106683611869812, | |
| "eval_precision": 0.4843260188087774, | |
| "eval_recall": 0.4557522123893805, | |
| "eval_runtime": 8.5893, | |
| "eval_samples_per_second": 4.075, | |
| "eval_steps_per_second": 2.096, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 57.142857142857146, | |
| "grad_norm": 0.6594957709312439, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 1.5451, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 57.142857142857146, | |
| "eval_accuracy": 0.7606973058637084, | |
| "eval_f1": 0.5052316890881914, | |
| "eval_loss": 1.0804147720336914, | |
| "eval_precision": 0.5121212121212121, | |
| "eval_recall": 0.49852507374631266, | |
| "eval_runtime": 8.9633, | |
| "eval_samples_per_second": 3.905, | |
| "eval_steps_per_second": 2.008, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 68.57142857142857, | |
| "eval_accuracy": 0.768621236133122, | |
| "eval_f1": 0.5156847742922723, | |
| "eval_loss": 1.0736337900161743, | |
| "eval_precision": 0.5357710651828299, | |
| "eval_recall": 0.4970501474926254, | |
| "eval_runtime": 8.9497, | |
| "eval_samples_per_second": 3.911, | |
| "eval_steps_per_second": 2.011, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_accuracy": 0.7739038563127311, | |
| "eval_f1": 0.5367316341829085, | |
| "eval_loss": 1.0631266832351685, | |
| "eval_precision": 0.5457317073170732, | |
| "eval_recall": 0.528023598820059, | |
| "eval_runtime": 8.5483, | |
| "eval_samples_per_second": 4.094, | |
| "eval_steps_per_second": 2.106, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 91.42857142857143, | |
| "eval_accuracy": 0.780243000528262, | |
| "eval_f1": 0.548314606741573, | |
| "eval_loss": 1.0633281469345093, | |
| "eval_precision": 0.5570776255707762, | |
| "eval_recall": 0.5398230088495575, | |
| "eval_runtime": 8.5977, | |
| "eval_samples_per_second": 4.071, | |
| "eval_steps_per_second": 2.094, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 102.85714285714286, | |
| "eval_accuracy": 0.7823560486001057, | |
| "eval_f1": 0.5561338289962826, | |
| "eval_loss": 1.0636277198791504, | |
| "eval_precision": 0.56071964017991, | |
| "eval_recall": 0.551622418879056, | |
| "eval_runtime": 8.6698, | |
| "eval_samples_per_second": 4.037, | |
| "eval_steps_per_second": 2.076, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 114.28571428571429, | |
| "grad_norm": 0.5495575666427612, | |
| "learning_rate": 0.0, | |
| "loss": 0.2997, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 114.28571428571429, | |
| "eval_accuracy": 0.7834125726360275, | |
| "eval_f1": 0.555886736214605, | |
| "eval_loss": 1.0617624521255493, | |
| "eval_precision": 0.5617469879518072, | |
| "eval_recall": 0.5501474926253688, | |
| "eval_runtime": 8.6165, | |
| "eval_samples_per_second": 4.062, | |
| "eval_steps_per_second": 2.089, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 125, | |
| "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": 1.478527859088384e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |