| { |
| "best_global_step": null, |
| "best_metric": 1.7856266498565674, |
| "best_model_checkpoint": "/home/haji80as/invariant-LM2/BioMistral-7B-merged-server-10000/checkpoint-10000", |
| "epoch": null, |
| "eval_steps": 500, |
| "global_step": 0, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "eval_loss": 1.8743267059326172, |
| "eval_model_preparation_time": 0.0252, |
| "eval_runtime": 482.614, |
| "eval_samples_per_second": 17.045, |
| "eval_steps_per_second": 2.132, |
| "step": 0 |
| }, |
| { |
| "eval_loss": 1.8743267059326172, |
| "eval_model_preparation_time": 0.0252, |
| "eval_runtime": 482.614, |
| "eval_samples_per_second": 17.045, |
| "eval_steps_per_second": 2.132, |
| "step": 0 |
| }, |
| { |
| "eval_loss": 1.904608130455017, |
| "eval_model_preparation_time": 0.0252, |
| "eval_runtime": 473.697, |
| "eval_samples_per_second": 17.366, |
| "eval_steps_per_second": 2.172, |
| "step": 0 |
| }, |
| { |
| "eval_loss": 1.904608130455017, |
| "eval_model_preparation_time": 0.0252, |
| "eval_runtime": 473.697, |
| "eval_samples_per_second": 17.366, |
| "eval_steps_per_second": 2.172, |
| "step": 0 |
| }, |
| { |
| "eval_loss": 1.9130403995513916, |
| "eval_model_preparation_time": 0.0252, |
| "eval_runtime": 470.5904, |
| "eval_samples_per_second": 17.48, |
| "eval_steps_per_second": 2.187, |
| "step": 0 |
| }, |
| { |
| "eval_loss": 1.9130403995513916, |
| "eval_model_preparation_time": 0.0252, |
| "eval_runtime": 470.5904, |
| "eval_samples_per_second": 17.48, |
| "eval_steps_per_second": 2.187, |
| "step": 0 |
| }, |
| { |
| "eval_loss": 1.9170527458190918, |
| "eval_model_preparation_time": 0.0252, |
| "eval_runtime": 475.5854, |
| "eval_samples_per_second": 17.297, |
| "eval_steps_per_second": 2.164, |
| "step": 0 |
| }, |
| { |
| "eval_loss": 1.9170527458190918, |
| "eval_model_preparation_time": 0.0252, |
| "eval_runtime": 475.5854, |
| "eval_samples_per_second": 17.297, |
| "eval_steps_per_second": 2.164, |
| "step": 0 |
| }, |
| { |
| "eval_loss": 1.9460963010787964, |
| "eval_model_preparation_time": 0.0252, |
| "eval_runtime": 479.3938, |
| "eval_samples_per_second": 17.159, |
| "eval_steps_per_second": 2.146, |
| "step": 0 |
| }, |
| { |
| "eval_loss": 1.9460963010787964, |
| "eval_model_preparation_time": 0.0252, |
| "eval_runtime": 479.3938, |
| "eval_samples_per_second": 17.159, |
| "eval_steps_per_second": 2.146, |
| "step": 0 |
| }, |
| { |
| "eval_loss": 1.928282618522644, |
| "eval_model_preparation_time": 0.0252, |
| "eval_runtime": 461.2283, |
| "eval_samples_per_second": 17.835, |
| "eval_steps_per_second": 2.231, |
| "step": 0 |
| }, |
| { |
| "eval_loss": 1.928282618522644, |
| "eval_model_preparation_time": 0.0252, |
| "eval_runtime": 461.2283, |
| "eval_samples_per_second": 17.835, |
| "eval_steps_per_second": 2.231, |
| "step": 0 |
| }, |
| { |
| "eval_loss": 1.9074980020523071, |
| "eval_model_preparation_time": 0.0252, |
| "eval_runtime": 461.1381, |
| "eval_samples_per_second": 17.838, |
| "eval_steps_per_second": 2.231, |
| "step": 0 |
| }, |
| { |
| "eval_loss": 1.9074980020523071, |
| "eval_model_preparation_time": 0.0252, |
| "eval_runtime": 461.1381, |
| "eval_samples_per_second": 17.838, |
| "eval_steps_per_second": 2.231, |
| "step": 0 |
| }, |
| { |
| "eval_loss": 1.9039336442947388, |
| "eval_model_preparation_time": 0.0252, |
| "eval_runtime": 461.138, |
| "eval_samples_per_second": 17.838, |
| "eval_steps_per_second": 2.231, |
| "step": 0 |
| }, |
| { |
| "eval_loss": 1.9039336442947388, |
| "eval_model_preparation_time": 0.0252, |
| "eval_runtime": 461.138, |
| "eval_samples_per_second": 17.838, |
| "eval_steps_per_second": 2.231, |
| "step": 0 |
| }, |
| { |
| "eval_loss": 1.8650752305984497, |
| "eval_model_preparation_time": 0.0252, |
| "eval_runtime": 465.4106, |
| "eval_samples_per_second": 17.675, |
| "eval_steps_per_second": 2.211, |
| "step": 0 |
| }, |
| { |
| "eval_loss": 1.8650752305984497, |
| "eval_model_preparation_time": 0.0252, |
| "eval_runtime": 465.4106, |
| "eval_samples_per_second": 17.675, |
| "eval_steps_per_second": 2.211, |
| "step": 0 |
| }, |
| { |
| "eval_loss": 1.841698408126831, |
| "eval_model_preparation_time": 0.0252, |
| "eval_runtime": 461.0916, |
| "eval_samples_per_second": 17.84, |
| "eval_steps_per_second": 2.232, |
| "step": 0 |
| }, |
| { |
| "eval_loss": 1.841698408126831, |
| "eval_model_preparation_time": 0.0252, |
| "eval_runtime": 461.0916, |
| "eval_samples_per_second": 17.84, |
| "eval_steps_per_second": 2.232, |
| "step": 0 |
| }, |
| { |
| "eval_loss": 1.8204604387283325, |
| "eval_model_preparation_time": 0.0252, |
| "eval_runtime": 461.2365, |
| "eval_samples_per_second": 17.835, |
| "eval_steps_per_second": 2.231, |
| "step": 0 |
| }, |
| { |
| "eval_loss": 1.8204604387283325, |
| "eval_model_preparation_time": 0.0252, |
| "eval_runtime": 461.2365, |
| "eval_samples_per_second": 17.835, |
| "eval_steps_per_second": 2.231, |
| "step": 0 |
| }, |
| { |
| "eval_loss": 1.8339213132858276, |
| "eval_model_preparation_time": 0.0252, |
| "eval_runtime": 461.1973, |
| "eval_samples_per_second": 17.836, |
| "eval_steps_per_second": 2.231, |
| "step": 0 |
| }, |
| { |
| "eval_loss": 1.8339213132858276, |
| "eval_model_preparation_time": 0.0252, |
| "eval_runtime": 461.1973, |
| "eval_samples_per_second": 17.836, |
| "eval_steps_per_second": 2.231, |
| "step": 0 |
| }, |
| { |
| "eval_loss": 1.8116841316223145, |
| "eval_model_preparation_time": 0.0252, |
| "eval_runtime": 461.3888, |
| "eval_samples_per_second": 17.829, |
| "eval_steps_per_second": 2.23, |
| "step": 0 |
| }, |
| { |
| "eval_loss": 1.8116841316223145, |
| "eval_model_preparation_time": 0.0252, |
| "eval_runtime": 461.3888, |
| "eval_samples_per_second": 17.829, |
| "eval_steps_per_second": 2.23, |
| "step": 0 |
| }, |
| { |
| "eval_loss": 1.8126027584075928, |
| "eval_model_preparation_time": 0.0252, |
| "eval_runtime": 461.2044, |
| "eval_samples_per_second": 17.836, |
| "eval_steps_per_second": 2.231, |
| "step": 0 |
| }, |
| { |
| "eval_loss": 1.8126027584075928, |
| "eval_model_preparation_time": 0.0252, |
| "eval_runtime": 461.2044, |
| "eval_samples_per_second": 17.836, |
| "eval_steps_per_second": 2.231, |
| "step": 0 |
| }, |
| { |
| "eval_loss": 1.7994815111160278, |
| "eval_model_preparation_time": 0.0252, |
| "eval_runtime": 464.7739, |
| "eval_samples_per_second": 17.699, |
| "eval_steps_per_second": 2.214, |
| "step": 0 |
| }, |
| { |
| "eval_loss": 1.7994815111160278, |
| "eval_model_preparation_time": 0.0252, |
| "eval_runtime": 464.7739, |
| "eval_samples_per_second": 17.699, |
| "eval_steps_per_second": 2.214, |
| "step": 0 |
| }, |
| { |
| "eval_loss": 1.7974251508712769, |
| "eval_model_preparation_time": 0.0252, |
| "eval_runtime": 461.2176, |
| "eval_samples_per_second": 17.835, |
| "eval_steps_per_second": 2.231, |
| "step": 0 |
| }, |
| { |
| "eval_loss": 1.7974251508712769, |
| "eval_model_preparation_time": 0.0252, |
| "eval_runtime": 461.2176, |
| "eval_samples_per_second": 17.835, |
| "eval_steps_per_second": 2.231, |
| "step": 0 |
| }, |
| { |
| "eval_loss": 1.7886863946914673, |
| "eval_model_preparation_time": 0.0252, |
| "eval_runtime": 461.2775, |
| "eval_samples_per_second": 17.833, |
| "eval_steps_per_second": 2.231, |
| "step": 0 |
| }, |
| { |
| "eval_loss": 1.7886863946914673, |
| "eval_model_preparation_time": 0.0252, |
| "eval_runtime": 461.2775, |
| "eval_samples_per_second": 17.833, |
| "eval_steps_per_second": 2.231, |
| "step": 0 |
| }, |
| { |
| "eval_loss": 1.7869404554367065, |
| "eval_model_preparation_time": 0.0252, |
| "eval_runtime": 461.2402, |
| "eval_samples_per_second": 17.835, |
| "eval_steps_per_second": 2.231, |
| "step": 0 |
| }, |
| { |
| "eval_loss": 1.7869404554367065, |
| "eval_model_preparation_time": 0.0252, |
| "eval_runtime": 461.2402, |
| "eval_samples_per_second": 17.835, |
| "eval_steps_per_second": 2.231, |
| "step": 0 |
| }, |
| { |
| "eval_loss": 1.7859430313110352, |
| "eval_model_preparation_time": 0.0252, |
| "eval_runtime": 483.5151, |
| "eval_samples_per_second": 17.013, |
| "eval_steps_per_second": 2.128, |
| "step": 0 |
| }, |
| { |
| "eval_loss": 1.7859430313110352, |
| "eval_model_preparation_time": 0.0252, |
| "eval_runtime": 483.5151, |
| "eval_samples_per_second": 17.013, |
| "eval_steps_per_second": 2.128, |
| "step": 0 |
| }, |
| { |
| "eval_loss": 1.7856266498565674, |
| "eval_model_preparation_time": 0.0252, |
| "eval_runtime": 461.1594, |
| "eval_samples_per_second": 17.838, |
| "eval_steps_per_second": 2.231, |
| "step": 0 |
| }, |
| { |
| "eval_loss": 1.7856266498565674, |
| "eval_model_preparation_time": 0.0252, |
| "eval_runtime": 461.1594, |
| "eval_samples_per_second": 17.838, |
| "eval_steps_per_second": 2.231, |
| "step": 0 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 0, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 0, |
| "save_steps": 500, |
| "stateful_callbacks": {}, |
| "total_flos": 0, |
| "train_batch_size": null, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
