| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9230769230769231, | |
| "eval_steps": 10, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 2.272727272727273e-05, | |
| "loss": 1.7413, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 1.4019958972930908, | |
| "eval_runtime": 165.0144, | |
| "eval_samples_per_second": 0.303, | |
| "eval_steps_per_second": 0.042, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 2.0202020202020203e-05, | |
| "loss": 1.0507, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 0.691331148147583, | |
| "eval_runtime": 164.1293, | |
| "eval_samples_per_second": 0.305, | |
| "eval_steps_per_second": 0.043, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 1.7676767676767676e-05, | |
| "loss": 0.5098, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 0.3474924862384796, | |
| "eval_runtime": 164.6576, | |
| "eval_samples_per_second": 0.304, | |
| "eval_steps_per_second": 0.043, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.5151515151515153e-05, | |
| "loss": 0.3533, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 0.31796133518218994, | |
| "eval_runtime": 164.8492, | |
| "eval_samples_per_second": 0.303, | |
| "eval_steps_per_second": 0.042, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.2626262626262628e-05, | |
| "loss": 0.3157, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 0.30177488923072815, | |
| "eval_runtime": 164.838, | |
| "eval_samples_per_second": 0.303, | |
| "eval_steps_per_second": 0.042, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 1.0101010101010101e-05, | |
| "loss": 0.3206, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_loss": 0.2928408682346344, | |
| "eval_runtime": 164.7503, | |
| "eval_samples_per_second": 0.303, | |
| "eval_steps_per_second": 0.042, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 7.5757575757575764e-06, | |
| "loss": 0.2726, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "eval_loss": 0.2865614593029022, | |
| "eval_runtime": 164.2932, | |
| "eval_samples_per_second": 0.304, | |
| "eval_steps_per_second": 0.043, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 5.050505050505051e-06, | |
| "loss": 0.2469, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "eval_loss": 0.2797877788543701, | |
| "eval_runtime": 164.5941, | |
| "eval_samples_per_second": 0.304, | |
| "eval_steps_per_second": 0.043, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 2.5252525252525253e-06, | |
| "loss": 0.2724, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "eval_loss": 0.2762667238712311, | |
| "eval_runtime": 164.8568, | |
| "eval_samples_per_second": 0.303, | |
| "eval_steps_per_second": 0.042, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.0, | |
| "loss": 0.2511, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_loss": 0.2749767303466797, | |
| "eval_runtime": 164.5464, | |
| "eval_samples_per_second": 0.304, | |
| "eval_steps_per_second": 0.043, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 10, | |
| "total_flos": 4359942624509952.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |