| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.041701417848206836, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0016680567139282735, | |
| "grad_norm": 6.4218597412109375, | |
| "learning_rate": 1e-05, | |
| "loss": 8.8157, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016680567139282735, | |
| "eval_loss": 10.53897476196289, | |
| "eval_runtime": 5.0335, | |
| "eval_samples_per_second": 100.327, | |
| "eval_steps_per_second": 12.715, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003336113427856547, | |
| "grad_norm": 8.344048500061035, | |
| "learning_rate": 2e-05, | |
| "loss": 9.9237, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0050041701417848205, | |
| "grad_norm": 5.752366065979004, | |
| "learning_rate": 3e-05, | |
| "loss": 10.2868, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006672226855713094, | |
| "grad_norm": 12.08169174194336, | |
| "learning_rate": 4e-05, | |
| "loss": 11.6577, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008340283569641367, | |
| "grad_norm": 7.6307902336120605, | |
| "learning_rate": 5e-05, | |
| "loss": 11.6049, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010008340283569641, | |
| "grad_norm": 13.488511085510254, | |
| "learning_rate": 6e-05, | |
| "loss": 11.6571, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011676396997497914, | |
| "grad_norm": 6.870922565460205, | |
| "learning_rate": 7e-05, | |
| "loss": 10.9165, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.013344453711426188, | |
| "grad_norm": 6.744866371154785, | |
| "learning_rate": 8e-05, | |
| "loss": 9.6312, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.015012510425354461, | |
| "grad_norm": 8.185052871704102, | |
| "learning_rate": 9e-05, | |
| "loss": 9.159, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.015012510425354461, | |
| "eval_loss": 9.887859344482422, | |
| "eval_runtime": 4.3895, | |
| "eval_samples_per_second": 115.047, | |
| "eval_steps_per_second": 14.58, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.016680567139282735, | |
| "grad_norm": 9.440922737121582, | |
| "learning_rate": 0.0001, | |
| "loss": 10.1835, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01834862385321101, | |
| "grad_norm": 5.682453155517578, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 9.355, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.020016680567139282, | |
| "grad_norm": 5.6532368659973145, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 9.1637, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.021684737281067557, | |
| "grad_norm": 8.35978889465332, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 8.5444, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.02335279399499583, | |
| "grad_norm": 7.7980217933654785, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 9.1922, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.025020850708924104, | |
| "grad_norm": 7.174959659576416, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 9.0129, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.026688907422852376, | |
| "grad_norm": 5.547351837158203, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 7.7701, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.02835696413678065, | |
| "grad_norm": 5.53154993057251, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 7.7904, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.030025020850708923, | |
| "grad_norm": 5.278870105743408, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 8.5489, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.030025020850708923, | |
| "eval_loss": 7.729805946350098, | |
| "eval_runtime": 4.3901, | |
| "eval_samples_per_second": 115.03, | |
| "eval_steps_per_second": 14.578, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0316930775646372, | |
| "grad_norm": 6.058969497680664, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 7.761, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03336113427856547, | |
| "grad_norm": 4.8587822914123535, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 7.8479, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03502919099249374, | |
| "grad_norm": 8.1661376953125, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 8.6839, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03669724770642202, | |
| "grad_norm": 5.563140392303467, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 7.5815, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03836530442035029, | |
| "grad_norm": 6.0711350440979, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 7.1114, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.040033361134278564, | |
| "grad_norm": 4.127212047576904, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 5.8192, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.041701417848206836, | |
| "grad_norm": 6.469174861907959, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 5.9953, | |
| "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": 347093965209600.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |