| { | |
| "best_metric": 1.0691347122192383, | |
| "best_model_checkpoint": "./outputs/checkpoint-2100", | |
| "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": 1.2907, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.179780125617981, | |
| "eval_runtime": 187.6093, | |
| "eval_samples_per_second": 10.287, | |
| "eval_steps_per_second": 1.29, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0103, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.1445424556732178, | |
| "eval_runtime": 243.5241, | |
| "eval_samples_per_second": 7.925, | |
| "eval_steps_per_second": 0.994, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9907, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.1306055784225464, | |
| "eval_runtime": 187.9568, | |
| "eval_samples_per_second": 10.268, | |
| "eval_steps_per_second": 1.288, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9792, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.1213247776031494, | |
| "eval_runtime": 186.5858, | |
| "eval_samples_per_second": 10.344, | |
| "eval_steps_per_second": 1.297, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9652, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.1149897575378418, | |
| "eval_runtime": 186.6184, | |
| "eval_samples_per_second": 10.342, | |
| "eval_steps_per_second": 1.297, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0002, | |
| "loss": 0.967, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 1.1105140447616577, | |
| "eval_runtime": 186.7963, | |
| "eval_samples_per_second": 10.332, | |
| "eval_steps_per_second": 1.296, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9632, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 1.1065897941589355, | |
| "eval_runtime": 186.8426, | |
| "eval_samples_per_second": 10.33, | |
| "eval_steps_per_second": 1.295, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9527, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_loss": 1.1026440858840942, | |
| "eval_runtime": 186.6422, | |
| "eval_samples_per_second": 10.341, | |
| "eval_steps_per_second": 1.297, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9512, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 1.0985503196716309, | |
| "eval_runtime": 187.0748, | |
| "eval_samples_per_second": 10.317, | |
| "eval_steps_per_second": 1.294, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9484, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_loss": 1.097111463546753, | |
| "eval_runtime": 186.7842, | |
| "eval_samples_per_second": 10.333, | |
| "eval_steps_per_second": 1.296, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9441, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_loss": 1.0937378406524658, | |
| "eval_runtime": 187.1868, | |
| "eval_samples_per_second": 10.311, | |
| "eval_steps_per_second": 1.293, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.0002, | |
| "loss": 0.937, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 1.0900678634643555, | |
| "eval_runtime": 187.1061, | |
| "eval_samples_per_second": 10.315, | |
| "eval_steps_per_second": 1.293, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9412, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "eval_loss": 1.0862796306610107, | |
| "eval_runtime": 186.0905, | |
| "eval_samples_per_second": 10.371, | |
| "eval_steps_per_second": 1.3, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9422, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_loss": 1.0846831798553467, | |
| "eval_runtime": 186.1843, | |
| "eval_samples_per_second": 10.366, | |
| "eval_steps_per_second": 1.3, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9352, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.084228515625, | |
| "eval_runtime": 187.2013, | |
| "eval_samples_per_second": 10.31, | |
| "eval_steps_per_second": 1.293, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9328, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "eval_loss": 1.082168459892273, | |
| "eval_runtime": 186.7075, | |
| "eval_samples_per_second": 10.337, | |
| "eval_steps_per_second": 1.296, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9306, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "eval_loss": 1.0760979652404785, | |
| "eval_runtime": 186.6832, | |
| "eval_samples_per_second": 10.338, | |
| "eval_steps_per_second": 1.296, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 0.0002, | |
| "loss": 0.926, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_loss": 1.0768243074417114, | |
| "eval_runtime": 186.9887, | |
| "eval_samples_per_second": 10.321, | |
| "eval_steps_per_second": 1.294, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9209, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "eval_loss": 1.07276451587677, | |
| "eval_runtime": 186.5526, | |
| "eval_samples_per_second": 10.346, | |
| "eval_steps_per_second": 1.297, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9309, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "eval_loss": 1.0723668336868286, | |
| "eval_runtime": 187.3011, | |
| "eval_samples_per_second": 10.304, | |
| "eval_steps_per_second": 1.292, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9257, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "eval_loss": 1.0691347122192383, | |
| "eval_runtime": 253.1645, | |
| "eval_samples_per_second": 7.624, | |
| "eval_steps_per_second": 0.956, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9177, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "eval_loss": 1.0692988634109497, | |
| "eval_runtime": 258.072, | |
| "eval_samples_per_second": 7.479, | |
| "eval_steps_per_second": 0.938, | |
| "step": 2200 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 2250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 3.110307163440169e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |