| { | |
| "best_metric": 0.9420180916786194, | |
| "best_model_checkpoint": "./outputs/checkpoint-2100", | |
| "epoch": 2.9829545454545454, | |
| "eval_steps": 100, | |
| "global_step": 2100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0002, | |
| "loss": 1.5808, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 1.0812042951583862, | |
| "eval_runtime": 127.4925, | |
| "eval_samples_per_second": 11.703, | |
| "eval_steps_per_second": 1.467, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2145, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 1.0592867136001587, | |
| "eval_runtime": 124.4418, | |
| "eval_samples_per_second": 11.99, | |
| "eval_steps_per_second": 1.503, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0002, | |
| "loss": 1.201, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 1.0460368394851685, | |
| "eval_runtime": 124.1855, | |
| "eval_samples_per_second": 12.014, | |
| "eval_steps_per_second": 1.506, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1833, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 1.0355255603790283, | |
| "eval_runtime": 124.2488, | |
| "eval_samples_per_second": 12.008, | |
| "eval_steps_per_second": 1.505, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1733, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 1.0230828523635864, | |
| "eval_runtime": 124.322, | |
| "eval_samples_per_second": 12.001, | |
| "eval_steps_per_second": 1.504, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1612, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 1.0142004489898682, | |
| "eval_runtime": 124.2613, | |
| "eval_samples_per_second": 12.007, | |
| "eval_steps_per_second": 1.505, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1492, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 1.0080314874649048, | |
| "eval_runtime": 124.2662, | |
| "eval_samples_per_second": 12.006, | |
| "eval_steps_per_second": 1.505, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1391, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "eval_loss": 1.0012787580490112, | |
| "eval_runtime": 124.3175, | |
| "eval_samples_per_second": 12.002, | |
| "eval_steps_per_second": 1.504, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1154, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_loss": 0.9947501420974731, | |
| "eval_runtime": 124.3492, | |
| "eval_samples_per_second": 11.998, | |
| "eval_steps_per_second": 1.504, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1179, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "eval_loss": 0.9894721508026123, | |
| "eval_runtime": 124.1464, | |
| "eval_samples_per_second": 12.018, | |
| "eval_steps_per_second": 1.506, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1196, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "eval_loss": 0.9814682006835938, | |
| "eval_runtime": 124.3036, | |
| "eval_samples_per_second": 12.003, | |
| "eval_steps_per_second": 1.504, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1074, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "eval_loss": 0.9781661033630371, | |
| "eval_runtime": 119.7103, | |
| "eval_samples_per_second": 12.463, | |
| "eval_steps_per_second": 1.562, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.0002, | |
| "loss": 1.099, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "eval_loss": 0.9716654419898987, | |
| "eval_runtime": 119.6105, | |
| "eval_samples_per_second": 12.474, | |
| "eval_steps_per_second": 1.563, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1021, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_loss": 0.9676819443702698, | |
| "eval_runtime": 119.9473, | |
| "eval_samples_per_second": 12.439, | |
| "eval_steps_per_second": 1.559, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 0.0002, | |
| "loss": 1.08, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "eval_loss": 0.9654238224029541, | |
| "eval_runtime": 120.0799, | |
| "eval_samples_per_second": 12.425, | |
| "eval_steps_per_second": 1.557, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0807, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "eval_loss": 0.9602729082107544, | |
| "eval_runtime": 120.231, | |
| "eval_samples_per_second": 12.409, | |
| "eval_steps_per_second": 1.555, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 0.0002, | |
| "loss": 1.062, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "eval_loss": 0.9569491744041443, | |
| "eval_runtime": 120.1655, | |
| "eval_samples_per_second": 12.416, | |
| "eval_steps_per_second": 1.556, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0627, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "eval_loss": 0.9535185098648071, | |
| "eval_runtime": 120.202, | |
| "eval_samples_per_second": 12.412, | |
| "eval_steps_per_second": 1.556, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0671, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "eval_loss": 0.9502108693122864, | |
| "eval_runtime": 124.6118, | |
| "eval_samples_per_second": 11.973, | |
| "eval_steps_per_second": 1.501, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0644, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "eval_loss": 0.946110725402832, | |
| "eval_runtime": 124.5826, | |
| "eval_samples_per_second": 11.976, | |
| "eval_steps_per_second": 1.501, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0606, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "eval_loss": 0.9420180916786194, | |
| "eval_runtime": 124.5044, | |
| "eval_samples_per_second": 11.984, | |
| "eval_steps_per_second": 1.502, | |
| "step": 2100 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 2112, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 1.180506237539328e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |