| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0020688415093653464, | |
| "eval_steps": 500, | |
| "global_step": 32, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.465129716766708e-05, | |
| "grad_norm": 52.735591888427734, | |
| "learning_rate": 6.451612903225807e-08, | |
| "loss": 1.9276, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00012930259433533415, | |
| "grad_norm": 54.205406188964844, | |
| "learning_rate": 1.2903225806451614e-07, | |
| "loss": 1.8498, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00019395389150300124, | |
| "grad_norm": 55.422950744628906, | |
| "learning_rate": 1.935483870967742e-07, | |
| "loss": 2.0204, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0002586051886706683, | |
| "grad_norm": 52.57908248901367, | |
| "learning_rate": 2.580645161290323e-07, | |
| "loss": 1.9851, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0003232564858383354, | |
| "grad_norm": 53.102073669433594, | |
| "learning_rate": 3.2258064516129035e-07, | |
| "loss": 1.9575, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0003879077830060025, | |
| "grad_norm": 39.96001052856445, | |
| "learning_rate": 3.870967741935484e-07, | |
| "loss": 1.9575, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00045255908017366957, | |
| "grad_norm": 32.277435302734375, | |
| "learning_rate": 4.5161290322580644e-07, | |
| "loss": 1.8748, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0005172103773413366, | |
| "grad_norm": 35.69306945800781, | |
| "learning_rate": 5.161290322580646e-07, | |
| "loss": 1.8319, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0005818616745090037, | |
| "grad_norm": 32.267822265625, | |
| "learning_rate": 5.806451612903227e-07, | |
| "loss": 1.8492, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0006465129716766708, | |
| "grad_norm": 15.390063285827637, | |
| "learning_rate": 6.451612903225807e-07, | |
| "loss": 1.8046, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007111642688443379, | |
| "grad_norm": 25.763904571533203, | |
| "learning_rate": 7.096774193548388e-07, | |
| "loss": 1.7649, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.000775815566012005, | |
| "grad_norm": 29.1771297454834, | |
| "learning_rate": 7.741935483870968e-07, | |
| "loss": 1.7684, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.000840466863179672, | |
| "grad_norm": 19.140987396240234, | |
| "learning_rate": 8.38709677419355e-07, | |
| "loss": 1.7782, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0009051181603473391, | |
| "grad_norm": 13.840346336364746, | |
| "learning_rate": 9.032258064516129e-07, | |
| "loss": 1.8303, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0009697694575150061, | |
| "grad_norm": 26.080778121948242, | |
| "learning_rate": 9.67741935483871e-07, | |
| "loss": 1.776, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0010344207546826732, | |
| "grad_norm": 34.16382598876953, | |
| "learning_rate": 1.0322580645161291e-06, | |
| "loss": 1.6359, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0010990720518503404, | |
| "grad_norm": 25.75543785095215, | |
| "learning_rate": 1.0967741935483872e-06, | |
| "loss": 1.6014, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0011637233490180074, | |
| "grad_norm": 11.885198593139648, | |
| "learning_rate": 1.1612903225806454e-06, | |
| "loss": 1.6831, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0012283746461856746, | |
| "grad_norm": 14.924345016479492, | |
| "learning_rate": 1.2258064516129033e-06, | |
| "loss": 1.7223, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0012930259433533416, | |
| "grad_norm": 18.01887321472168, | |
| "learning_rate": 1.2903225806451614e-06, | |
| "loss": 1.6811, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0013576772405210086, | |
| "grad_norm": 12.34964656829834, | |
| "learning_rate": 1.3548387096774195e-06, | |
| "loss": 1.6169, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0014223285376886757, | |
| "grad_norm": 11.162965774536133, | |
| "learning_rate": 1.4193548387096776e-06, | |
| "loss": 1.6814, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0014869798348563427, | |
| "grad_norm": 8.694445610046387, | |
| "learning_rate": 1.4838709677419356e-06, | |
| "loss": 1.5999, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.00155163113202401, | |
| "grad_norm": 9.510068893432617, | |
| "learning_rate": 1.5483870967741937e-06, | |
| "loss": 1.6327, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.001616282429191677, | |
| "grad_norm": 9.788911819458008, | |
| "learning_rate": 1.6129032258064516e-06, | |
| "loss": 1.6985, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.001680933726359344, | |
| "grad_norm": 8.04429817199707, | |
| "learning_rate": 1.67741935483871e-06, | |
| "loss": 1.6618, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.001745585023527011, | |
| "grad_norm": 7.545624256134033, | |
| "learning_rate": 1.7419354838709678e-06, | |
| "loss": 1.5472, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0018102363206946783, | |
| "grad_norm": 7.069305419921875, | |
| "learning_rate": 1.8064516129032258e-06, | |
| "loss": 1.643, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0018748876178623453, | |
| "grad_norm": 9.195314407348633, | |
| "learning_rate": 1.870967741935484e-06, | |
| "loss": 1.5956, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0019395389150300122, | |
| "grad_norm": 6.884894371032715, | |
| "learning_rate": 1.935483870967742e-06, | |
| "loss": 1.5752, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0020041902121976794, | |
| "grad_norm": 7.165380477905273, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 1.5812, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0020688415093653464, | |
| "grad_norm": 6.563286781311035, | |
| "learning_rate": 2.0645161290322582e-06, | |
| "loss": 1.5938, | |
| "step": 32 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 15467, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 16, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.068879221404467e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |