| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 51, | |
| "global_step": 51, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0196078431372549, | |
| "grad_norm": 6.204692840576172, | |
| "learning_rate": 1e-05, | |
| "loss": 3.7169, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0392156862745098, | |
| "grad_norm": 5.544524192810059, | |
| "learning_rate": 9.803921568627451e-06, | |
| "loss": 3.5651, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.058823529411764705, | |
| "grad_norm": 4.741919040679932, | |
| "learning_rate": 9.607843137254903e-06, | |
| "loss": 3.3635, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0784313725490196, | |
| "grad_norm": 3.850552797317505, | |
| "learning_rate": 9.411764705882354e-06, | |
| "loss": 3.1543, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.09803921568627451, | |
| "grad_norm": 3.0620617866516113, | |
| "learning_rate": 9.215686274509804e-06, | |
| "loss": 2.9776, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.11764705882352941, | |
| "grad_norm": 2.6284866333007812, | |
| "learning_rate": 9.019607843137256e-06, | |
| "loss": 2.8738, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.13725490196078433, | |
| "grad_norm": 2.1033711433410645, | |
| "learning_rate": 8.823529411764707e-06, | |
| "loss": 2.7088, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1568627450980392, | |
| "grad_norm": 1.9232524633407593, | |
| "learning_rate": 8.627450980392157e-06, | |
| "loss": 2.6702, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.17647058823529413, | |
| "grad_norm": 1.697329044342041, | |
| "learning_rate": 8.43137254901961e-06, | |
| "loss": 2.5798, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.19607843137254902, | |
| "grad_norm": 1.4369592666625977, | |
| "learning_rate": 8.23529411764706e-06, | |
| "loss": 2.3988, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.21568627450980393, | |
| "grad_norm": 1.4095876216888428, | |
| "learning_rate": 8.03921568627451e-06, | |
| "loss": 2.4501, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": 1.2679307460784912, | |
| "learning_rate": 7.84313725490196e-06, | |
| "loss": 2.3684, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2549019607843137, | |
| "grad_norm": 1.2137434482574463, | |
| "learning_rate": 7.647058823529411e-06, | |
| "loss": 2.3421, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.27450980392156865, | |
| "grad_norm": 1.1062148809432983, | |
| "learning_rate": 7.450980392156863e-06, | |
| "loss": 2.2561, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.29411764705882354, | |
| "grad_norm": 1.1174410581588745, | |
| "learning_rate": 7.2549019607843145e-06, | |
| "loss": 2.2687, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3137254901960784, | |
| "grad_norm": 1.0426009893417358, | |
| "learning_rate": 7.058823529411766e-06, | |
| "loss": 2.1751, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 1.0049128532409668, | |
| "learning_rate": 6.862745098039216e-06, | |
| "loss": 2.1172, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.35294117647058826, | |
| "grad_norm": 1.0266010761260986, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 2.1423, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.37254901960784315, | |
| "grad_norm": 0.9556562304496765, | |
| "learning_rate": 6.470588235294119e-06, | |
| "loss": 1.998, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.39215686274509803, | |
| "grad_norm": 0.9744943380355835, | |
| "learning_rate": 6.274509803921569e-06, | |
| "loss": 2.0312, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4117647058823529, | |
| "grad_norm": 0.9564470648765564, | |
| "learning_rate": 6.07843137254902e-06, | |
| "loss": 2.0036, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.43137254901960786, | |
| "grad_norm": 0.9479807615280151, | |
| "learning_rate": 5.882352941176471e-06, | |
| "loss": 1.9646, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.45098039215686275, | |
| "grad_norm": 0.9132607579231262, | |
| "learning_rate": 5.686274509803922e-06, | |
| "loss": 1.9377, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": 0.8846307396888733, | |
| "learning_rate": 5.4901960784313735e-06, | |
| "loss": 1.8844, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.49019607843137253, | |
| "grad_norm": 0.8600879311561584, | |
| "learning_rate": 5.294117647058824e-06, | |
| "loss": 1.8365, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5098039215686274, | |
| "grad_norm": 0.8480931520462036, | |
| "learning_rate": 5.098039215686274e-06, | |
| "loss": 1.8456, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.5294117647058824, | |
| "grad_norm": 0.8326075673103333, | |
| "learning_rate": 4.901960784313726e-06, | |
| "loss": 1.842, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.5490196078431373, | |
| "grad_norm": 0.8022368550300598, | |
| "learning_rate": 4.705882352941177e-06, | |
| "loss": 1.793, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.5686274509803921, | |
| "grad_norm": 0.7787200212478638, | |
| "learning_rate": 4.509803921568628e-06, | |
| "loss": 1.7824, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.5882352941176471, | |
| "grad_norm": 0.7797530293464661, | |
| "learning_rate": 4.313725490196079e-06, | |
| "loss": 1.7885, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6078431372549019, | |
| "grad_norm": 0.754288911819458, | |
| "learning_rate": 4.11764705882353e-06, | |
| "loss": 1.7418, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.6274509803921569, | |
| "grad_norm": 0.7509904503822327, | |
| "learning_rate": 3.92156862745098e-06, | |
| "loss": 1.7535, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.6470588235294118, | |
| "grad_norm": 0.7244371771812439, | |
| "learning_rate": 3.7254901960784316e-06, | |
| "loss": 1.7225, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 0.7066894769668579, | |
| "learning_rate": 3.529411764705883e-06, | |
| "loss": 1.7148, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.6862745098039216, | |
| "grad_norm": 0.6999155282974243, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 1.6988, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.7058823529411765, | |
| "grad_norm": 0.6919957995414734, | |
| "learning_rate": 3.1372549019607846e-06, | |
| "loss": 1.6716, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.7254901960784313, | |
| "grad_norm": 0.6656088829040527, | |
| "learning_rate": 2.9411764705882355e-06, | |
| "loss": 1.6497, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.7450980392156863, | |
| "grad_norm": 0.662615180015564, | |
| "learning_rate": 2.7450980392156867e-06, | |
| "loss": 1.6416, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.7647058823529411, | |
| "grad_norm": 0.6523113250732422, | |
| "learning_rate": 2.549019607843137e-06, | |
| "loss": 1.6252, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.7843137254901961, | |
| "grad_norm": 0.6525292992591858, | |
| "learning_rate": 2.3529411764705885e-06, | |
| "loss": 1.6153, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.803921568627451, | |
| "grad_norm": 0.6456802487373352, | |
| "learning_rate": 2.1568627450980393e-06, | |
| "loss": 1.6071, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.8235294117647058, | |
| "grad_norm": 0.6324870586395264, | |
| "learning_rate": 1.96078431372549e-06, | |
| "loss": 1.5709, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.8431372549019608, | |
| "grad_norm": 0.6390767693519592, | |
| "learning_rate": 1.7647058823529414e-06, | |
| "loss": 1.588, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.8627450980392157, | |
| "grad_norm": 0.6343661546707153, | |
| "learning_rate": 1.5686274509803923e-06, | |
| "loss": 1.5631, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.8823529411764706, | |
| "grad_norm": 0.633243978023529, | |
| "learning_rate": 1.3725490196078434e-06, | |
| "loss": 1.5654, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.9019607843137255, | |
| "grad_norm": 0.6330836415290833, | |
| "learning_rate": 1.1764705882352942e-06, | |
| "loss": 1.5721, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.9215686274509803, | |
| "grad_norm": 0.6343224048614502, | |
| "learning_rate": 9.80392156862745e-07, | |
| "loss": 1.5629, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.9411764705882353, | |
| "grad_norm": 0.6233211159706116, | |
| "learning_rate": 7.843137254901962e-07, | |
| "loss": 1.5648, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.9607843137254902, | |
| "grad_norm": 0.6273109316825867, | |
| "learning_rate": 5.882352941176471e-07, | |
| "loss": 1.5701, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.9803921568627451, | |
| "grad_norm": 0.6393752694129944, | |
| "learning_rate": 3.921568627450981e-07, | |
| "loss": 1.5762, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.6112051606178284, | |
| "learning_rate": 1.9607843137254904e-07, | |
| "loss": 1.5457, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.5631208419799805, | |
| "eval_runtime": 16.2004, | |
| "eval_samples_per_second": 0.37, | |
| "eval_steps_per_second": 0.062, | |
| "step": 51 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 51, | |
| "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": 2.6061603639341875e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |