| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02868617326448652, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011474469305794606, | |
| "grad_norm": 0.38680994510650635, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1883, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011474469305794606, | |
| "eval_loss": 0.1828075647354126, | |
| "eval_runtime": 41.2292, | |
| "eval_samples_per_second": 17.803, | |
| "eval_steps_per_second": 2.231, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002294893861158921, | |
| "grad_norm": 0.23735938966274261, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1251, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0034423407917383822, | |
| "grad_norm": 0.34126752614974976, | |
| "learning_rate": 3e-05, | |
| "loss": 0.1768, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004589787722317842, | |
| "grad_norm": 0.28753432631492615, | |
| "learning_rate": 4e-05, | |
| "loss": 0.163, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005737234652897304, | |
| "grad_norm": 0.3324357271194458, | |
| "learning_rate": 5e-05, | |
| "loss": 0.154, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0068846815834767644, | |
| "grad_norm": 0.39487388730049133, | |
| "learning_rate": 6e-05, | |
| "loss": 0.1812, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008032128514056224, | |
| "grad_norm": 0.30962827801704407, | |
| "learning_rate": 7e-05, | |
| "loss": 0.16, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.009179575444635685, | |
| "grad_norm": 0.2848067283630371, | |
| "learning_rate": 8e-05, | |
| "loss": 0.1206, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.010327022375215147, | |
| "grad_norm": 0.3864418864250183, | |
| "learning_rate": 9e-05, | |
| "loss": 0.1463, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010327022375215147, | |
| "eval_loss": 0.11602957546710968, | |
| "eval_runtime": 41.6147, | |
| "eval_samples_per_second": 17.638, | |
| "eval_steps_per_second": 2.211, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011474469305794608, | |
| "grad_norm": 0.3642881214618683, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1295, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012621916236374068, | |
| "grad_norm": 0.2669277489185333, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 0.0931, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.013769363166953529, | |
| "grad_norm": 0.26793304085731506, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.0807, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01491681009753299, | |
| "grad_norm": 0.206680566072464, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 0.0522, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01606425702811245, | |
| "grad_norm": 0.285326212644577, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 0.0604, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01721170395869191, | |
| "grad_norm": 0.20402389764785767, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.0536, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01835915088927137, | |
| "grad_norm": 0.20810100436210632, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.0516, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.019506597819850834, | |
| "grad_norm": 0.23139941692352295, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 0.055, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.020654044750430294, | |
| "grad_norm": 0.256534218788147, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.0443, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.020654044750430294, | |
| "eval_loss": 0.04736759513616562, | |
| "eval_runtime": 41.8479, | |
| "eval_samples_per_second": 17.54, | |
| "eval_steps_per_second": 2.198, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.021801491681009755, | |
| "grad_norm": 0.25051283836364746, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.0444, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.022948938611589215, | |
| "grad_norm": 0.17016364634037018, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.0412, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.024096385542168676, | |
| "grad_norm": 0.1935800015926361, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 0.0393, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.025243832472748137, | |
| "grad_norm": 0.232066810131073, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.0594, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.026391279403327597, | |
| "grad_norm": 0.19686104357242584, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 0.0262, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.027538726333907058, | |
| "grad_norm": 0.21382786333560944, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.0294, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02868617326448652, | |
| "grad_norm": 0.17204894125461578, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.0404, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4112820920647680.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |