| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1984126984126984, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007936507936507936, | |
| "grad_norm": 0.5940561294555664, | |
| "learning_rate": 1e-05, | |
| "loss": 0.7819, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007936507936507936, | |
| "eval_loss": 0.7385377883911133, | |
| "eval_runtime": 12.4705, | |
| "eval_samples_per_second": 8.5, | |
| "eval_steps_per_second": 1.123, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.015873015873015872, | |
| "grad_norm": 0.5844579339027405, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5743, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.023809523809523808, | |
| "grad_norm": 0.6142908334732056, | |
| "learning_rate": 3e-05, | |
| "loss": 0.7856, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.031746031746031744, | |
| "grad_norm": 1.1579065322875977, | |
| "learning_rate": 4e-05, | |
| "loss": 1.0332, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03968253968253968, | |
| "grad_norm": 0.6027746796607971, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6717, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.047619047619047616, | |
| "grad_norm": 0.9417018294334412, | |
| "learning_rate": 6e-05, | |
| "loss": 0.7161, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.05555555555555555, | |
| "grad_norm": 0.8347136974334717, | |
| "learning_rate": 7e-05, | |
| "loss": 0.7583, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06349206349206349, | |
| "grad_norm": 1.023072361946106, | |
| "learning_rate": 8e-05, | |
| "loss": 0.5415, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07142857142857142, | |
| "grad_norm": 0.4929274022579193, | |
| "learning_rate": 9e-05, | |
| "loss": 0.4157, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07142857142857142, | |
| "eval_loss": 0.4522353708744049, | |
| "eval_runtime": 11.789, | |
| "eval_samples_per_second": 8.991, | |
| "eval_steps_per_second": 1.188, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07936507936507936, | |
| "grad_norm": 0.5577216148376465, | |
| "learning_rate": 0.0001, | |
| "loss": 0.4259, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0873015873015873, | |
| "grad_norm": 0.7210971117019653, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 0.4377, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.09523809523809523, | |
| "grad_norm": 0.4076630473136902, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.3398, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.10317460317460317, | |
| "grad_norm": 0.6704097986221313, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 0.3923, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1111111111111111, | |
| "grad_norm": 0.6116910576820374, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 0.2966, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.11904761904761904, | |
| "grad_norm": 0.9248013496398926, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.3506, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.12698412698412698, | |
| "grad_norm": 0.7895079851150513, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.2511, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1349206349206349, | |
| "grad_norm": 0.4172516167163849, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 0.2474, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.14285714285714285, | |
| "grad_norm": 0.4765908718109131, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.2699, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.14285714285714285, | |
| "eval_loss": 0.2643006443977356, | |
| "eval_runtime": 11.7881, | |
| "eval_samples_per_second": 8.992, | |
| "eval_steps_per_second": 1.188, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.15079365079365079, | |
| "grad_norm": 0.5411407947540283, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.2662, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.15873015873015872, | |
| "grad_norm": 0.3574010729789734, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.2805, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.16666666666666666, | |
| "grad_norm": 0.7612572312355042, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 0.3236, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1746031746031746, | |
| "grad_norm": 0.3988335132598877, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.2418, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.18253968253968253, | |
| "grad_norm": 0.39348870515823364, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 0.2039, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.19047619047619047, | |
| "grad_norm": 0.6038708090782166, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.2575, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1984126984126984, | |
| "grad_norm": 0.6375281810760498, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.2512, | |
| "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": 1.966001301435187e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |