| { | |
| "best_metric": 0.5354864001274109, | |
| "best_model_checkpoint": "saves/Mistral-7B/lora/train_1/checkpoint-200", | |
| "epoch": 1.3125512715340442, | |
| "eval_steps": 200, | |
| "global_step": 1200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.21875854525567404, | |
| "grad_norm": 0.38192033767700195, | |
| "learning_rate": 0.00029856911617379416, | |
| "loss": 0.4441, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.21875854525567404, | |
| "eval_loss": 0.5354864001274109, | |
| "eval_runtime": 2190.7796, | |
| "eval_samples_per_second": 21.508, | |
| "eval_steps_per_second": 0.672, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4375170905113481, | |
| "grad_norm": 0.6002383232116699, | |
| "learning_rate": 0.0002896017519370078, | |
| "loss": 0.2562, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.4375170905113481, | |
| "eval_loss": 0.6111302971839905, | |
| "eval_runtime": 2191.5198, | |
| "eval_samples_per_second": 21.501, | |
| "eval_steps_per_second": 0.672, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.6562756357670222, | |
| "grad_norm": 0.913849949836731, | |
| "learning_rate": 0.0002728756302319302, | |
| "loss": 0.1736, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.6562756357670222, | |
| "eval_loss": 0.7389799356460571, | |
| "eval_runtime": 2191.6271, | |
| "eval_samples_per_second": 21.5, | |
| "eval_steps_per_second": 0.672, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.8750341810226961, | |
| "grad_norm": 0.9672319293022156, | |
| "learning_rate": 0.00024932035201194605, | |
| "loss": 0.0946, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.8750341810226961, | |
| "eval_loss": 0.8541895151138306, | |
| "eval_runtime": 2193.7603, | |
| "eval_samples_per_second": 21.479, | |
| "eval_steps_per_second": 0.671, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.0937927262783702, | |
| "grad_norm": 0.8369513750076294, | |
| "learning_rate": 0.00022024506768721243, | |
| "loss": 0.0477, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.0937927262783702, | |
| "eval_loss": 1.010321021080017, | |
| "eval_runtime": 2193.5651, | |
| "eval_samples_per_second": 21.481, | |
| "eval_steps_per_second": 0.672, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.3125512715340442, | |
| "grad_norm": 0.8144668340682983, | |
| "learning_rate": 0.0001872657174323126, | |
| "loss": 0.0275, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.3125512715340442, | |
| "eval_loss": 1.1369109153747559, | |
| "eval_runtime": 2191.5102, | |
| "eval_samples_per_second": 21.501, | |
| "eval_steps_per_second": 0.672, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.3125512715340442, | |
| "step": 1200, | |
| "total_flos": 2.3027143417496863e+18, | |
| "train_loss": 0.17396480162938435, | |
| "train_runtime": 69952.3324, | |
| "train_samples_per_second": 10.037, | |
| "train_steps_per_second": 0.039 | |
| } | |
| ], | |
| "logging_steps": 200, | |
| "max_steps": 2742, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.3027143417496863e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |