| { | |
| "best_metric": 1.1806031465530396, | |
| "best_model_checkpoint": "./outputs/checkpoint-2100", | |
| "epoch": 2.8, | |
| "eval_steps": 100, | |
| "global_step": 2100, | |
| "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": 1.2648, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.3499459028244019, | |
| "eval_runtime": 466.0769, | |
| "eval_samples_per_second": 4.141, | |
| "eval_steps_per_second": 0.519, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1034, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.3190627098083496, | |
| "eval_runtime": 466.6597, | |
| "eval_samples_per_second": 4.136, | |
| "eval_steps_per_second": 0.519, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0002, | |
| "loss": 1.085, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.2993828058242798, | |
| "eval_runtime": 470.7014, | |
| "eval_samples_per_second": 4.1, | |
| "eval_steps_per_second": 0.514, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0692, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.2881134748458862, | |
| "eval_runtime": 470.2444, | |
| "eval_samples_per_second": 4.104, | |
| "eval_steps_per_second": 0.515, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0558, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.274288535118103, | |
| "eval_runtime": 467.1885, | |
| "eval_samples_per_second": 4.131, | |
| "eval_steps_per_second": 0.518, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0502, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 1.2627606391906738, | |
| "eval_runtime": 465.7624, | |
| "eval_samples_per_second": 4.144, | |
| "eval_steps_per_second": 0.52, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0419, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 1.256902813911438, | |
| "eval_runtime": 459.9211, | |
| "eval_samples_per_second": 4.196, | |
| "eval_steps_per_second": 0.526, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0301, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_loss": 1.2442457675933838, | |
| "eval_runtime": 457.8978, | |
| "eval_samples_per_second": 4.215, | |
| "eval_steps_per_second": 0.529, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0199, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 1.2393821477890015, | |
| "eval_runtime": 467.9251, | |
| "eval_samples_per_second": 4.125, | |
| "eval_steps_per_second": 0.517, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0077, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_loss": 1.232779622077942, | |
| "eval_runtime": 473.1709, | |
| "eval_samples_per_second": 4.079, | |
| "eval_steps_per_second": 0.511, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0152, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_loss": 1.2266021966934204, | |
| "eval_runtime": 468.5166, | |
| "eval_samples_per_second": 4.119, | |
| "eval_steps_per_second": 0.517, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0027, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 1.2204071283340454, | |
| "eval_runtime": 475.1214, | |
| "eval_samples_per_second": 4.062, | |
| "eval_steps_per_second": 0.509, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9923, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "eval_loss": 1.2131980657577515, | |
| "eval_runtime": 472.507, | |
| "eval_samples_per_second": 4.085, | |
| "eval_steps_per_second": 0.512, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9934, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_loss": 1.2085801362991333, | |
| "eval_runtime": 469.7498, | |
| "eval_samples_per_second": 4.109, | |
| "eval_steps_per_second": 0.515, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9818, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.2038506269454956, | |
| "eval_runtime": 470.1258, | |
| "eval_samples_per_second": 4.105, | |
| "eval_steps_per_second": 0.515, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9761, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "eval_loss": 1.2020516395568848, | |
| "eval_runtime": 466.7038, | |
| "eval_samples_per_second": 4.135, | |
| "eval_steps_per_second": 0.519, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9724, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "eval_loss": 1.1988099813461304, | |
| "eval_runtime": 469.2999, | |
| "eval_samples_per_second": 4.113, | |
| "eval_steps_per_second": 0.516, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9711, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_loss": 1.1918971538543701, | |
| "eval_runtime": 470.4302, | |
| "eval_samples_per_second": 4.103, | |
| "eval_steps_per_second": 0.514, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9631, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "eval_loss": 1.1869046688079834, | |
| "eval_runtime": 486.0919, | |
| "eval_samples_per_second": 3.97, | |
| "eval_steps_per_second": 0.498, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9568, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "eval_loss": 1.1853452920913696, | |
| "eval_runtime": 469.1887, | |
| "eval_samples_per_second": 4.113, | |
| "eval_steps_per_second": 0.516, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9666, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "eval_loss": 1.1806031465530396, | |
| "eval_runtime": 492.4038, | |
| "eval_samples_per_second": 3.92, | |
| "eval_steps_per_second": 0.491, | |
| "step": 2100 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 2250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 6.987573836110234e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |