{ "best_metric": 0.6086956521739131, "best_model_checkpoint": "finetuned-Accident-SingleLabel-Final-v2/checkpoint-16", "epoch": 12.04, "eval_steps": 500, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.08, "eval_accuracy": 0.13043478260869565, "eval_loss": 1.8601624965667725, "eval_runtime": 178.1909, "eval_samples_per_second": 0.067, "eval_steps_per_second": 0.006, "step": 4 }, { "epoch": 1.08, "eval_accuracy": 0.4782608695652174, "eval_loss": 1.6211293935775757, "eval_runtime": 176.592, "eval_samples_per_second": 0.068, "eval_steps_per_second": 0.006, "step": 8 }, { "epoch": 2.04, "learning_rate": 4.4444444444444447e-05, "loss": 1.7588, "step": 10 }, { "epoch": 2.08, "eval_accuracy": 0.5652173913043478, "eval_loss": 1.4449537992477417, "eval_runtime": 176.0462, "eval_samples_per_second": 0.068, "eval_steps_per_second": 0.006, "step": 12 }, { "epoch": 3.08, "eval_accuracy": 0.6086956521739131, "eval_loss": 1.2475712299346924, "eval_runtime": 173.2256, "eval_samples_per_second": 0.069, "eval_steps_per_second": 0.006, "step": 16 }, { "epoch": 4.08, "learning_rate": 3.3333333333333335e-05, "loss": 1.0616, "step": 20 }, { "epoch": 4.08, "eval_accuracy": 0.6086956521739131, "eval_loss": 1.146136999130249, "eval_runtime": 175.0973, "eval_samples_per_second": 0.069, "eval_steps_per_second": 0.006, "step": 20 }, { "epoch": 5.08, "eval_accuracy": 0.5217391304347826, "eval_loss": 1.0130609273910522, "eval_runtime": 153.4833, "eval_samples_per_second": 0.078, "eval_steps_per_second": 0.007, "step": 24 }, { "epoch": 6.08, "eval_accuracy": 0.6086956521739131, "eval_loss": 0.9022569060325623, "eval_runtime": 155.7404, "eval_samples_per_second": 0.077, "eval_steps_per_second": 0.006, "step": 28 }, { "epoch": 7.04, "learning_rate": 2.2222222222222223e-05, "loss": 0.9537, "step": 30 }, { "epoch": 7.08, "eval_accuracy": 0.6086956521739131, "eval_loss": 0.9932180643081665, "eval_runtime": 153.8344, "eval_samples_per_second": 0.078, "eval_steps_per_second": 0.007, "step": 32 }, { "epoch": 8.08, "eval_accuracy": 0.6086956521739131, "eval_loss": 0.9546610713005066, "eval_runtime": 152.5962, "eval_samples_per_second": 0.079, "eval_steps_per_second": 0.007, "step": 36 }, { "epoch": 9.08, "learning_rate": 1.1111111111111112e-05, "loss": 0.7395, "step": 40 }, { "epoch": 9.08, "eval_accuracy": 0.6086956521739131, "eval_loss": 1.0173721313476562, "eval_runtime": 152.3986, "eval_samples_per_second": 0.079, "eval_steps_per_second": 0.007, "step": 40 }, { "epoch": 10.08, "eval_accuracy": 0.6086956521739131, "eval_loss": 0.9636380672454834, "eval_runtime": 155.5133, "eval_samples_per_second": 0.077, "eval_steps_per_second": 0.006, "step": 44 }, { "epoch": 11.08, "eval_accuracy": 0.5652173913043478, "eval_loss": 0.9022343754768372, "eval_runtime": 152.7748, "eval_samples_per_second": 0.079, "eval_steps_per_second": 0.007, "step": 48 }, { "epoch": 12.04, "learning_rate": 0.0, "loss": 0.7531, "step": 50 }, { "epoch": 12.04, "eval_accuracy": 0.5652173913043478, "eval_loss": 0.9311092495918274, "eval_runtime": 153.7998, "eval_samples_per_second": 0.078, "eval_steps_per_second": 0.007, "step": 50 }, { "epoch": 12.04, "step": 50, "total_flos": 7.875408929100923e+17, "train_loss": 1.053352165222168, "train_runtime": 9266.6352, "train_samples_per_second": 0.086, "train_steps_per_second": 0.005 }, { "epoch": 12.04, "eval_accuracy": 0.5588235294117647, "eval_loss": 1.2327362298965454, "eval_runtime": 217.2315, "eval_samples_per_second": 0.078, "eval_steps_per_second": 0.009, "step": 50 }, { "epoch": 12.04, "eval_accuracy": 0.5588235294117647, "eval_loss": 1.276799201965332, "eval_runtime": 217.4472, "eval_samples_per_second": 0.078, "eval_steps_per_second": 0.009, "step": 50 } ], "logging_steps": 10, "max_steps": 50, "num_train_epochs": 9223372036854775807, "save_steps": 500, "total_flos": 7.875408929100923e+17, "trial_name": null, "trial_params": null }