| { | |
| "best_metric": 1.17391836643219, | |
| "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": 1.2656, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.350274920463562, | |
| "eval_runtime": 546.2738, | |
| "eval_samples_per_second": 3.533, | |
| "eval_steps_per_second": 0.443, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002, | |
| "loss": 1.103, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.3182251453399658, | |
| "eval_runtime": 459.6303, | |
| "eval_samples_per_second": 4.199, | |
| "eval_steps_per_second": 0.527, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0834, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.299042820930481, | |
| "eval_runtime": 457.0511, | |
| "eval_samples_per_second": 4.223, | |
| "eval_steps_per_second": 0.529, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0678, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.287185788154602, | |
| "eval_runtime": 463.8545, | |
| "eval_samples_per_second": 4.161, | |
| "eval_steps_per_second": 0.522, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0544, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.273476243019104, | |
| "eval_runtime": 461.7034, | |
| "eval_samples_per_second": 4.18, | |
| "eval_steps_per_second": 0.524, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0495, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 1.2602167129516602, | |
| "eval_runtime": 455.1997, | |
| "eval_samples_per_second": 4.24, | |
| "eval_steps_per_second": 0.532, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0406, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 1.2561663389205933, | |
| "eval_runtime": 449.9152, | |
| "eval_samples_per_second": 4.29, | |
| "eval_steps_per_second": 0.538, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0282, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_loss": 1.2437876462936401, | |
| "eval_runtime": 451.2737, | |
| "eval_samples_per_second": 4.277, | |
| "eval_steps_per_second": 0.536, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0168, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 1.2371761798858643, | |
| "eval_runtime": 452.8697, | |
| "eval_samples_per_second": 4.262, | |
| "eval_steps_per_second": 0.534, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0056, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_loss": 1.2295143604278564, | |
| "eval_runtime": 453.1971, | |
| "eval_samples_per_second": 4.259, | |
| "eval_steps_per_second": 0.534, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0137, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_loss": 1.224471092224121, | |
| "eval_runtime": 452.058, | |
| "eval_samples_per_second": 4.269, | |
| "eval_steps_per_second": 0.535, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.0002, | |
| "loss": 1.001, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 1.2201058864593506, | |
| "eval_runtime": 451.8545, | |
| "eval_samples_per_second": 4.271, | |
| "eval_steps_per_second": 0.536, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.0002, | |
| "loss": 0.991, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "eval_loss": 1.2112103700637817, | |
| "eval_runtime": 449.46, | |
| "eval_samples_per_second": 4.294, | |
| "eval_steps_per_second": 0.538, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9919, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_loss": 1.2065283060073853, | |
| "eval_runtime": 451.912, | |
| "eval_samples_per_second": 4.271, | |
| "eval_steps_per_second": 0.536, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9797, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.2011693716049194, | |
| "eval_runtime": 452.3637, | |
| "eval_samples_per_second": 4.266, | |
| "eval_steps_per_second": 0.535, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9734, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "eval_loss": 1.1984320878982544, | |
| "eval_runtime": 455.5044, | |
| "eval_samples_per_second": 4.237, | |
| "eval_steps_per_second": 0.531, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9694, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "eval_loss": 1.1960954666137695, | |
| "eval_runtime": 454.7892, | |
| "eval_samples_per_second": 4.244, | |
| "eval_steps_per_second": 0.532, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9693, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_loss": 1.1902049779891968, | |
| "eval_runtime": 453.32, | |
| "eval_samples_per_second": 4.257, | |
| "eval_steps_per_second": 0.534, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9606, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "eval_loss": 1.183451771736145, | |
| "eval_runtime": 452.8791, | |
| "eval_samples_per_second": 4.262, | |
| "eval_steps_per_second": 0.534, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9541, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "eval_loss": 1.1814736127853394, | |
| "eval_runtime": 456.1407, | |
| "eval_samples_per_second": 4.231, | |
| "eval_steps_per_second": 0.531, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9638, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "eval_loss": 1.1796127557754517, | |
| "eval_runtime": 454.0476, | |
| "eval_samples_per_second": 4.251, | |
| "eval_steps_per_second": 0.533, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9646, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "eval_loss": 1.17391836643219, | |
| "eval_runtime": 453.8066, | |
| "eval_samples_per_second": 4.253, | |
| "eval_steps_per_second": 0.533, | |
| "step": 2200 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 2250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 7.321308131141222e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |