| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9979035639412998, |
| "eval_steps": 500, |
| "global_step": 119, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.041928721174004195, |
| "grad_norm": 0.011030412279069424, |
| "learning_rate": 0.00025, |
| "loss": 11.9318, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.08385744234800839, |
| "grad_norm": 0.014100322499871254, |
| "learning_rate": 0.00024465811965811965, |
| "loss": 11.9305, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.12578616352201258, |
| "grad_norm": 0.017396269366145134, |
| "learning_rate": 0.00023931623931623932, |
| "loss": 11.9291, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.16771488469601678, |
| "grad_norm": 0.022825436666607857, |
| "learning_rate": 0.000233974358974359, |
| "loss": 11.9293, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.20964360587002095, |
| "grad_norm": 0.030763259157538414, |
| "learning_rate": 0.00022863247863247864, |
| "loss": 11.928, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.25157232704402516, |
| "grad_norm": 0.05623968690633774, |
| "learning_rate": 0.0002232905982905983, |
| "loss": 11.9273, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.29350104821802936, |
| "grad_norm": 0.0468871183693409, |
| "learning_rate": 0.00021794871794871795, |
| "loss": 11.9263, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.33542976939203356, |
| "grad_norm": 0.05555358901619911, |
| "learning_rate": 0.0002126068376068376, |
| "loss": 11.9248, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.37735849056603776, |
| "grad_norm": 0.0784514918923378, |
| "learning_rate": 0.00020726495726495727, |
| "loss": 11.9244, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.4192872117400419, |
| "grad_norm": 0.05951184406876564, |
| "learning_rate": 0.00020192307692307694, |
| "loss": 11.9228, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.4612159329140461, |
| "grad_norm": 0.057042159140110016, |
| "learning_rate": 0.00019658119658119659, |
| "loss": 11.9221, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.5031446540880503, |
| "grad_norm": 0.04163195937871933, |
| "learning_rate": 0.00019123931623931623, |
| "loss": 11.9225, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.5450733752620545, |
| "grad_norm": 0.03262303024530411, |
| "learning_rate": 0.0001858974358974359, |
| "loss": 11.9226, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.5870020964360587, |
| "grad_norm": 0.05241989716887474, |
| "learning_rate": 0.00018055555555555555, |
| "loss": 11.922, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.6289308176100629, |
| "grad_norm": 0.06784799695014954, |
| "learning_rate": 0.00017521367521367522, |
| "loss": 11.9214, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.6708595387840671, |
| "grad_norm": 0.042793747037649155, |
| "learning_rate": 0.0001698717948717949, |
| "loss": 11.9183, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.7127882599580713, |
| "grad_norm": 0.0430237241089344, |
| "learning_rate": 0.00016452991452991454, |
| "loss": 11.9216, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.7547169811320755, |
| "grad_norm": 0.03868071734905243, |
| "learning_rate": 0.00015918803418803418, |
| "loss": 11.9194, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.7966457023060797, |
| "grad_norm": 0.024328265339136124, |
| "learning_rate": 0.00015384615384615385, |
| "loss": 11.9217, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.8385744234800838, |
| "grad_norm": 0.04353172332048416, |
| "learning_rate": 0.0001485042735042735, |
| "loss": 11.9212, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.8805031446540881, |
| "grad_norm": 0.057023949921131134, |
| "learning_rate": 0.00014316239316239317, |
| "loss": 11.92, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.9224318658280922, |
| "grad_norm": 0.039732299745082855, |
| "learning_rate": 0.00013782051282051284, |
| "loss": 11.9183, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.9643605870020965, |
| "grad_norm": 0.0544021911919117, |
| "learning_rate": 0.00013247863247863248, |
| "loss": 11.9203, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.9979035639412998, |
| "eval_loss": 11.919066429138184, |
| "eval_runtime": 0.416, |
| "eval_samples_per_second": 242.779, |
| "eval_steps_per_second": 62.498, |
| "step": 119 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 239, |
| "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": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 134180413440.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
