| { | |
| "best_metric": 1.2748572826385498, | |
| "best_model_checkpoint": "./outputs/checkpoint-2200", | |
| "epoch": 2.9333333333333336, | |
| "eval_steps": 100, | |
| "global_step": 2200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0002, | |
| "loss": 1.357, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.4659545421600342, | |
| "eval_runtime": 114.978, | |
| "eval_samples_per_second": 12.62, | |
| "eval_steps_per_second": 1.583, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1954, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.4343539476394653, | |
| "eval_runtime": 112.6008, | |
| "eval_samples_per_second": 12.886, | |
| "eval_steps_per_second": 1.616, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1774, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.4164679050445557, | |
| "eval_runtime": 112.4536, | |
| "eval_samples_per_second": 12.903, | |
| "eval_steps_per_second": 1.618, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1691, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.4017506837844849, | |
| "eval_runtime": 112.3429, | |
| "eval_samples_per_second": 12.916, | |
| "eval_steps_per_second": 1.62, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1554, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.3869292736053467, | |
| "eval_runtime": 112.4263, | |
| "eval_samples_per_second": 12.906, | |
| "eval_steps_per_second": 1.619, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1389, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 1.3736246824264526, | |
| "eval_runtime": 112.3926, | |
| "eval_samples_per_second": 12.91, | |
| "eval_steps_per_second": 1.619, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1305, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 1.3629770278930664, | |
| "eval_runtime": 112.4413, | |
| "eval_samples_per_second": 12.905, | |
| "eval_steps_per_second": 1.619, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1184, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_loss": 1.3554208278656006, | |
| "eval_runtime": 112.4809, | |
| "eval_samples_per_second": 12.9, | |
| "eval_steps_per_second": 1.618, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1018, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 1.3454769849777222, | |
| "eval_runtime": 112.189, | |
| "eval_samples_per_second": 12.934, | |
| "eval_steps_per_second": 1.622, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0964, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_loss": 1.3380351066589355, | |
| "eval_runtime": 112.5152, | |
| "eval_samples_per_second": 12.896, | |
| "eval_steps_per_second": 1.618, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0941, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_loss": 1.3308976888656616, | |
| "eval_runtime": 112.3169, | |
| "eval_samples_per_second": 12.919, | |
| "eval_steps_per_second": 1.62, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0816, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 1.3270059823989868, | |
| "eval_runtime": 112.5104, | |
| "eval_samples_per_second": 12.897, | |
| "eval_steps_per_second": 1.618, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0921, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "eval_loss": 1.3173606395721436, | |
| "eval_runtime": 112.4585, | |
| "eval_samples_per_second": 12.903, | |
| "eval_steps_per_second": 1.618, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0799, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_loss": 1.3096227645874023, | |
| "eval_runtime": 112.3567, | |
| "eval_samples_per_second": 12.914, | |
| "eval_steps_per_second": 1.62, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0778, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.3063220977783203, | |
| "eval_runtime": 112.5325, | |
| "eval_samples_per_second": 12.894, | |
| "eval_steps_per_second": 1.617, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0584, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "eval_loss": 1.3022856712341309, | |
| "eval_runtime": 112.433, | |
| "eval_samples_per_second": 12.905, | |
| "eval_steps_per_second": 1.619, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0494, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "eval_loss": 1.2983750104904175, | |
| "eval_runtime": 112.4723, | |
| "eval_samples_per_second": 12.901, | |
| "eval_steps_per_second": 1.618, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0441, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_loss": 1.29191255569458, | |
| "eval_runtime": 112.4345, | |
| "eval_samples_per_second": 12.905, | |
| "eval_steps_per_second": 1.619, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0486, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "eval_loss": 1.2864296436309814, | |
| "eval_runtime": 112.377, | |
| "eval_samples_per_second": 12.912, | |
| "eval_steps_per_second": 1.62, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 0.0002, | |
| "loss": 1.049, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "eval_loss": 1.2813292741775513, | |
| "eval_runtime": 112.6047, | |
| "eval_samples_per_second": 12.886, | |
| "eval_steps_per_second": 1.616, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0479, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "eval_loss": 1.2773118019104004, | |
| "eval_runtime": 112.6322, | |
| "eval_samples_per_second": 12.883, | |
| "eval_steps_per_second": 1.616, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0327, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "eval_loss": 1.2748572826385498, | |
| "eval_runtime": 112.6112, | |
| "eval_samples_per_second": 12.885, | |
| "eval_steps_per_second": 1.616, | |
| "step": 2200 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 2250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 1.399789696241664e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |