| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 4, |
| "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": 1.869510531425476, |
| "learning_rate": 0.0, |
| "loss": 1.6582717895507812, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.09523809523809523, |
| "grad_norm": 1.4465402364730835, |
| "learning_rate": 1e-05, |
| "loss": 1.39208984375, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.14285714285714285, |
| "grad_norm": 2.276446580886841, |
| "learning_rate": 9.94459753267812e-06, |
| "loss": 1.953125, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.19047619047619047, |
| "grad_norm": 2.215484380722046, |
| "learning_rate": 9.779754323328192e-06, |
| "loss": 1.899658203125, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.23809523809523808, |
| "grad_norm": 1.9182502031326294, |
| "learning_rate": 9.509529358847655e-06, |
| "loss": 1.667724609375, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.23809523809523808, |
| "eval_loss": 2.453125, |
| "eval_runtime": 10.6216, |
| "eval_samples_per_second": 0.094, |
| "eval_steps_per_second": 0.094, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.2857142857142857, |
| "grad_norm": 2.0919392108917236, |
| "learning_rate": 9.140576474687263e-06, |
| "loss": 1.90869140625, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.3333333333333333, |
| "grad_norm": 2.093019962310791, |
| "learning_rate": 8.681980515339464e-06, |
| "loss": 1.7752685546875, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.38095238095238093, |
| "grad_norm": 1.9170184135437012, |
| "learning_rate": 8.14503363531613e-06, |
| "loss": 1.70947265625, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.42857142857142855, |
| "grad_norm": 1.925852656364441, |
| "learning_rate": 7.5429572488279615e-06, |
| "loss": 1.809814453125, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.42857142857142855, |
| "eval_loss": 2.390625, |
| "eval_runtime": 0.829, |
| "eval_samples_per_second": 1.206, |
| "eval_steps_per_second": 1.206, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.47619047619047616, |
| "grad_norm": 2.0689780712127686, |
| "learning_rate": 6.890576474687264e-06, |
| "loss": 1.87548828125, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.5238095238095238, |
| "grad_norm": 2.0856761932373047, |
| "learning_rate": 6.20395509268104e-06, |
| "loss": 1.931640625, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.5714285714285714, |
| "grad_norm": 1.7902768850326538, |
| "learning_rate": 5.500000000000001e-06, |
| "loss": 1.6474609375, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.6190476190476191, |
| "grad_norm": 1.6947816610336304, |
| "learning_rate": 4.796044907318961e-06, |
| "loss": 1.75390625, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.6190476190476191, |
| "eval_loss": 2.328125, |
| "eval_runtime": 0.8257, |
| "eval_samples_per_second": 1.211, |
| "eval_steps_per_second": 1.211, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.6666666666666666, |
| "grad_norm": 1.8652945756912231, |
| "learning_rate": 4.109423525312738e-06, |
| "loss": 1.800048828125, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.7142857142857143, |
| "grad_norm": 1.87651526927948, |
| "learning_rate": 3.45704275117204e-06, |
| "loss": 1.70166015625, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.7619047619047619, |
| "grad_norm": 1.8096357583999634, |
| "learning_rate": 2.854966364683872e-06, |
| "loss": 1.751953125, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.8095238095238095, |
| "grad_norm": 1.9394772052764893, |
| "learning_rate": 2.3180194846605367e-06, |
| "loss": 1.868896484375, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.8095238095238095, |
| "eval_loss": 2.296875, |
| "eval_runtime": 0.8266, |
| "eval_samples_per_second": 1.21, |
| "eval_steps_per_second": 1.21, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.8571428571428571, |
| "grad_norm": 1.7789219617843628, |
| "learning_rate": 1.8594235253127373e-06, |
| "loss": 1.80322265625, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.9047619047619048, |
| "grad_norm": 1.8745474815368652, |
| "learning_rate": 1.490470641152345e-06, |
| "loss": 1.703369140625, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.9523809523809523, |
| "grad_norm": 1.7236051559448242, |
| "learning_rate": 1.2202456766718092e-06, |
| "loss": 1.692138671875, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 1.77152681350708, |
| "learning_rate": 1.0554024673218808e-06, |
| "loss": 1.63671875, |
| "step": 21 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 2.28125, |
| "eval_runtime": 0.8292, |
| "eval_samples_per_second": 1.206, |
| "eval_steps_per_second": 1.206, |
| "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": 7489904145596416.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
