| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 21, |
| "global_step": 21, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.047619047619047616, |
| "grad_norm": 1.4989429712295532, |
| "learning_rate": 1e-05, |
| "loss": 1.4072265625, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.09523809523809523, |
| "grad_norm": 1.614056944847107, |
| "learning_rate": 9.944154131125643e-06, |
| "loss": 1.49609375, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.14285714285714285, |
| "grad_norm": 1.63851797580719, |
| "learning_rate": 9.777864028930705e-06, |
| "loss": 1.4755859375, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.19047619047619047, |
| "grad_norm": 1.5077990293502808, |
| "learning_rate": 9.504844339512096e-06, |
| "loss": 1.27734375, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.23809523809523808, |
| "grad_norm": 1.449641466140747, |
| "learning_rate": 9.131193871579975e-06, |
| "loss": 1.154296875, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.2857142857142857, |
| "grad_norm": 1.0753552913665771, |
| "learning_rate": 8.665259359149132e-06, |
| "loss": 0.90966796875, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.3333333333333333, |
| "grad_norm": 1.003565788269043, |
| "learning_rate": 8.117449009293668e-06, |
| "loss": 0.89794921875, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.38095238095238093, |
| "grad_norm": 0.8084003925323486, |
| "learning_rate": 7.500000000000001e-06, |
| "loss": 0.7490234375, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.42857142857142855, |
| "grad_norm": 0.8131781220436096, |
| "learning_rate": 6.8267051218319766e-06, |
| "loss": 0.7548828125, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.47619047619047616, |
| "grad_norm": 0.5898401141166687, |
| "learning_rate": 6.112604669781572e-06, |
| "loss": 0.611328125, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.5238095238095238, |
| "grad_norm": 0.6303607821464539, |
| "learning_rate": 5.373650467932122e-06, |
| "loss": 0.622314453125, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.5714285714285714, |
| "grad_norm": 0.5455021262168884, |
| "learning_rate": 4.626349532067879e-06, |
| "loss": 0.55126953125, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.6190476190476191, |
| "grad_norm": 0.6703805327415466, |
| "learning_rate": 3.887395330218429e-06, |
| "loss": 0.5859375, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.6666666666666666, |
| "grad_norm": 0.4904954433441162, |
| "learning_rate": 3.173294878168025e-06, |
| "loss": 0.49169921875, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.7142857142857143, |
| "grad_norm": 0.6331518888473511, |
| "learning_rate": 2.5000000000000015e-06, |
| "loss": 0.564453125, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.7619047619047619, |
| "grad_norm": 0.5232410430908203, |
| "learning_rate": 1.8825509907063328e-06, |
| "loss": 0.493408203125, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.8095238095238095, |
| "grad_norm": 0.3978940546512604, |
| "learning_rate": 1.3347406408508695e-06, |
| "loss": 0.430419921875, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.8571428571428571, |
| "grad_norm": 0.510210394859314, |
| "learning_rate": 8.688061284200266e-07, |
| "loss": 0.47900390625, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.9047619047619048, |
| "grad_norm": 0.49041983485221863, |
| "learning_rate": 4.951556604879049e-07, |
| "loss": 0.474853515625, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.9523809523809523, |
| "grad_norm": 0.4750329852104187, |
| "learning_rate": 2.2213597106929608e-07, |
| "loss": 0.47412109375, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.520028829574585, |
| "learning_rate": 5.584586887435739e-08, |
| "loss": 0.48974609375, |
| "step": 21 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.439208984375, |
| "eval_runtime": 1.0544, |
| "eval_samples_per_second": 5.69, |
| "eval_steps_per_second": 0.948, |
| "step": 21 |
| } |
| ], |
| "logging_steps": 1.0, |
| "max_steps": 21, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 0, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 7.534343782976717e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
