| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 34, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.029411764705882353, | |
| "grad_norm": 0.734375, | |
| "learning_rate": 2e-05, | |
| "loss": 2.0227, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.058823529411764705, | |
| "grad_norm": 0.59765625, | |
| "learning_rate": 4e-05, | |
| "loss": 1.6615, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.08823529411764706, | |
| "grad_norm": 0.6640625, | |
| "learning_rate": 6e-05, | |
| "loss": 1.9138, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.11764705882352941, | |
| "grad_norm": 0.9375, | |
| "learning_rate": 8e-05, | |
| "loss": 2.2948, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.14705882352941177, | |
| "grad_norm": 0.9453125, | |
| "learning_rate": 0.0001, | |
| "loss": 2.0388, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.17647058823529413, | |
| "grad_norm": 0.7734375, | |
| "learning_rate": 0.00012, | |
| "loss": 1.9193, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.20588235294117646, | |
| "grad_norm": 0.8203125, | |
| "learning_rate": 0.00014, | |
| "loss": 1.7604, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": 0.734375, | |
| "learning_rate": 0.00016, | |
| "loss": 1.6406, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2647058823529412, | |
| "grad_norm": 0.83984375, | |
| "learning_rate": 0.00018, | |
| "loss": 1.528, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.29411764705882354, | |
| "grad_norm": 0.71875, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4681, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3235294117647059, | |
| "grad_norm": 1.015625, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 1.4515, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.35294117647058826, | |
| "grad_norm": 0.8984375, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 1.4636, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.38235294117647056, | |
| "grad_norm": 0.9140625, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 1.1527, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.4117647058823529, | |
| "grad_norm": 0.86328125, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 1.1761, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.4411764705882353, | |
| "grad_norm": 1.078125, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 1.3331, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": 0.98828125, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.3777, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.90234375, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 1.1361, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.5294117647058824, | |
| "grad_norm": 1.0234375, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.0423, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.5588235294117647, | |
| "grad_norm": 1.125, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 1.0441, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.5882352941176471, | |
| "grad_norm": 0.91796875, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 0.9957, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6176470588235294, | |
| "grad_norm": 1.1328125, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 1.0449, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.6470588235294118, | |
| "grad_norm": 1.109375, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0147, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.6764705882352942, | |
| "grad_norm": 1.140625, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 0.9797, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.7058823529411765, | |
| "grad_norm": 1.09375, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 0.8892, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.7352941176470589, | |
| "grad_norm": 1.171875, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 0.7879, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7647058823529411, | |
| "grad_norm": 1.0546875, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.8614, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.7941176470588235, | |
| "grad_norm": 1.328125, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 1.0043, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.8235294117647058, | |
| "grad_norm": 1.0234375, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.9867, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.8529411764705882, | |
| "grad_norm": 0.96484375, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 0.892, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.8823529411764706, | |
| "grad_norm": 1.0078125, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 0.8257, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.9117647058823529, | |
| "grad_norm": 0.8359375, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 0.8757, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.9411764705882353, | |
| "grad_norm": 1.359375, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 1.098, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.9705882352941176, | |
| "grad_norm": 1.2265625, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 1.0088, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.4921875, | |
| "learning_rate": 0.0, | |
| "loss": 0.9341, | |
| "step": 34 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 34, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 12, | |
| "total_flos": 9.946320738818458e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |