| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 39, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.07692307692307693, |
| "grad_norm": 0.01362229132281847, |
| "learning_rate": 2e-05, |
| "loss": 0.214, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.15384615384615385, |
| "grad_norm": 0.015491360693982626, |
| "learning_rate": 4e-05, |
| "loss": 0.1883, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.23076923076923078, |
| "grad_norm": 0.013092231354423438, |
| "learning_rate": 6.000000000000001e-05, |
| "loss": 0.2559, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.3076923076923077, |
| "grad_norm": 0.011865468733559145, |
| "learning_rate": 8e-05, |
| "loss": 0.2318, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.38461538461538464, |
| "grad_norm": 0.01445707101996402, |
| "learning_rate": 7.983897175980957e-05, |
| "loss": 0.2356, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.46153846153846156, |
| "grad_norm": 0.022082670925174443, |
| "learning_rate": 7.93571835439452e-05, |
| "loss": 0.1849, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.5384615384615384, |
| "grad_norm": 0.016571143681459406, |
| "learning_rate": 7.855851442783414e-05, |
| "loss": 0.2368, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.6153846153846154, |
| "grad_norm": 0.013032821444579379, |
| "learning_rate": 7.74493948255895e-05, |
| "loss": 0.2375, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.6923076923076923, |
| "grad_norm": 0.00951504921068226, |
| "learning_rate": 7.603875471609677e-05, |
| "loss": 0.1866, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.7692307692307693, |
| "grad_norm": 0.013412897451087466, |
| "learning_rate": 7.433795174407465e-05, |
| "loss": 0.1767, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.8461538461538461, |
| "grad_norm": 0.015303084580261235, |
| "learning_rate": 7.236067977499791e-05, |
| "loss": 0.1619, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.9230769230769231, |
| "grad_norm": 0.02245685317077549, |
| "learning_rate": 7.012285864014445e-05, |
| "loss": 0.2166, |
| "step": 12 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.020885068977789367, |
| "learning_rate": 6.76425059594746e-05, |
| "loss": 0.1882, |
| "step": 13 |
| }, |
| { |
| "epoch": 1.0769230769230769, |
| "grad_norm": 0.013390527346974263, |
| "learning_rate": 6.493959207434934e-05, |
| "loss": 0.1718, |
| "step": 14 |
| }, |
| { |
| "epoch": 1.1538461538461537, |
| "grad_norm": 0.008606296416287816, |
| "learning_rate": 6.20358792580841e-05, |
| "loss": 0.1861, |
| "step": 15 |
| }, |
| { |
| "epoch": 1.2307692307692308, |
| "grad_norm": 0.007326851444871209, |
| "learning_rate": 5.895474649891995e-05, |
| "loss": 0.2026, |
| "step": 16 |
| }, |
| { |
| "epoch": 1.3076923076923077, |
| "grad_norm": 0.007635686241940803, |
| "learning_rate": 5.572100126615695e-05, |
| "loss": 0.2013, |
| "step": 17 |
| }, |
| { |
| "epoch": 1.3846153846153846, |
| "grad_norm": 0.008869623285318975, |
| "learning_rate": 5.23606797749979e-05, |
| "loss": 0.165, |
| "step": 18 |
| }, |
| { |
| "epoch": 1.4615384615384617, |
| "grad_norm": 0.00788271564927161, |
| "learning_rate": 4.890083735825258e-05, |
| "loss": 0.1787, |
| "step": 19 |
| }, |
| { |
| "epoch": 1.5384615384615383, |
| "grad_norm": 0.00870116469993209, |
| "learning_rate": 4.5369330632706223e-05, |
| "loss": 0.206, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.6153846153846154, |
| "grad_norm": 0.008346588642191923, |
| "learning_rate": 4.17945932140206e-05, |
| "loss": 0.1671, |
| "step": 21 |
| }, |
| { |
| "epoch": 1.6923076923076923, |
| "grad_norm": 0.009658075777869769, |
| "learning_rate": 3.820540678597942e-05, |
| "loss": 0.1543, |
| "step": 22 |
| }, |
| { |
| "epoch": 1.7692307692307692, |
| "grad_norm": 0.009152433347331993, |
| "learning_rate": 3.4630669367293797e-05, |
| "loss": 0.1792, |
| "step": 23 |
| }, |
| { |
| "epoch": 1.8461538461538463, |
| "grad_norm": 0.007938383638920925, |
| "learning_rate": 3.109916264174743e-05, |
| "loss": 0.1727, |
| "step": 24 |
| }, |
| { |
| "epoch": 1.9230769230769231, |
| "grad_norm": 0.01060506500300255, |
| "learning_rate": 2.7639320225002108e-05, |
| "loss": 0.1388, |
| "step": 25 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.0086968658862576, |
| "learning_rate": 2.427899873384306e-05, |
| "loss": 0.1332, |
| "step": 26 |
| }, |
| { |
| "epoch": 2.076923076923077, |
| "grad_norm": 0.007920756244716599, |
| "learning_rate": 2.1045253501080058e-05, |
| "loss": 0.1602, |
| "step": 27 |
| }, |
| { |
| "epoch": 2.1538461538461537, |
| "grad_norm": 0.007030121363460224, |
| "learning_rate": 1.7964120741915905e-05, |
| "loss": 0.1589, |
| "step": 28 |
| }, |
| { |
| "epoch": 2.230769230769231, |
| "grad_norm": 0.006685402907818994, |
| "learning_rate": 1.5060407925650662e-05, |
| "loss": 0.17, |
| "step": 29 |
| }, |
| { |
| "epoch": 2.3076923076923075, |
| "grad_norm": 0.00769942388133665, |
| "learning_rate": 1.2357494040525416e-05, |
| "loss": 0.1375, |
| "step": 30 |
| }, |
| { |
| "epoch": 2.3846153846153846, |
| "grad_norm": 0.0069255157912131325, |
| "learning_rate": 9.877141359855567e-06, |
| "loss": 0.151, |
| "step": 31 |
| }, |
| { |
| "epoch": 2.4615384615384617, |
| "grad_norm": 0.007528440807236487, |
| "learning_rate": 7.639320225002106e-06, |
| "loss": 0.174, |
| "step": 32 |
| }, |
| { |
| "epoch": 2.5384615384615383, |
| "grad_norm": 0.0068365831505659, |
| "learning_rate": 5.662048255925357e-06, |
| "loss": 0.1893, |
| "step": 33 |
| }, |
| { |
| "epoch": 2.6153846153846154, |
| "grad_norm": 0.007259620939406601, |
| "learning_rate": 3.961245283903239e-06, |
| "loss": 0.1394, |
| "step": 34 |
| }, |
| { |
| "epoch": 2.6923076923076925, |
| "grad_norm": 0.007387131018832008, |
| "learning_rate": 2.550605174410512e-06, |
| "loss": 0.171, |
| "step": 35 |
| }, |
| { |
| "epoch": 2.769230769230769, |
| "grad_norm": 0.006999784513200382, |
| "learning_rate": 1.4414855721658705e-06, |
| "loss": 0.169, |
| "step": 36 |
| }, |
| { |
| "epoch": 2.8461538461538463, |
| "grad_norm": 0.0070987738461534035, |
| "learning_rate": 6.428164560548134e-07, |
| "loss": 0.1483, |
| "step": 37 |
| }, |
| { |
| "epoch": 2.9230769230769234, |
| "grad_norm": 0.007128694543877027, |
| "learning_rate": 1.6102824019043728e-07, |
| "loss": 0.1311, |
| "step": 38 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.007308301272398886, |
| "learning_rate": 0.0, |
| "loss": 0.166, |
| "step": 39 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 39, |
| "total_flos": 88512452100096.0, |
| "train_loss": 0.18044410951626608, |
| "train_runtime": 1311.1394, |
| "train_samples_per_second": 0.458, |
| "train_steps_per_second": 0.03 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 39, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 88512452100096.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
