| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 273, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14652014652014653, | |
| "grad_norm": 63.75182342529297, | |
| "learning_rate": 0.00019705882352941177, | |
| "loss": 13.3784, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.29304029304029305, | |
| "grad_norm": 33.430416107177734, | |
| "learning_rate": 0.0001911764705882353, | |
| "loss": 4.1258, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.43956043956043955, | |
| "grad_norm": 0.4142046570777893, | |
| "learning_rate": 0.00018529411764705883, | |
| "loss": 0.6903, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5860805860805861, | |
| "grad_norm": 0.27323105931282043, | |
| "learning_rate": 0.00017941176470588236, | |
| "loss": 0.5677, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7326007326007326, | |
| "grad_norm": 0.2076171338558197, | |
| "learning_rate": 0.0001735294117647059, | |
| "loss": 0.4418, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8791208791208791, | |
| "grad_norm": 0.325761079788208, | |
| "learning_rate": 0.00016764705882352942, | |
| "loss": 0.4442, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.0256410256410255, | |
| "grad_norm": 0.741830050945282, | |
| "learning_rate": 0.00016176470588235295, | |
| "loss": 0.3808, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.1721611721611722, | |
| "grad_norm": 0.7903043031692505, | |
| "learning_rate": 0.00015588235294117648, | |
| "loss": 0.3212, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.3186813186813187, | |
| "grad_norm": 0.726527214050293, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.2756, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.4652014652014653, | |
| "grad_norm": 0.4178701937198639, | |
| "learning_rate": 0.00014411764705882354, | |
| "loss": 0.2395, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.6117216117216118, | |
| "grad_norm": 0.29514220356941223, | |
| "learning_rate": 0.00013823529411764707, | |
| "loss": 0.206, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.7582417582417582, | |
| "grad_norm": 0.334573894739151, | |
| "learning_rate": 0.0001323529411764706, | |
| "loss": 0.2336, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.9047619047619047, | |
| "grad_norm": 0.22454310953617096, | |
| "learning_rate": 0.0001264705882352941, | |
| "loss": 0.2333, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.051282051282051, | |
| "grad_norm": 0.3633638918399811, | |
| "learning_rate": 0.00012058823529411765, | |
| "loss": 0.21, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.197802197802198, | |
| "grad_norm": 0.26258039474487305, | |
| "learning_rate": 0.00011470588235294118, | |
| "loss": 0.1804, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.3443223443223444, | |
| "grad_norm": 0.2950953543186188, | |
| "learning_rate": 0.0001088235294117647, | |
| "loss": 0.2074, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.490842490842491, | |
| "grad_norm": 0.24581202864646912, | |
| "learning_rate": 0.00010294117647058823, | |
| "loss": 0.2233, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.6373626373626373, | |
| "grad_norm": 0.3232247829437256, | |
| "learning_rate": 9.705882352941177e-05, | |
| "loss": 0.1909, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.7838827838827838, | |
| "grad_norm": 0.31195566058158875, | |
| "learning_rate": 9.11764705882353e-05, | |
| "loss": 0.2135, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.9304029304029307, | |
| "grad_norm": 0.3059927225112915, | |
| "learning_rate": 8.529411764705883e-05, | |
| "loss": 0.1813, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.076923076923077, | |
| "grad_norm": 0.2599155306816101, | |
| "learning_rate": 7.941176470588235e-05, | |
| "loss": 0.1721, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.2234432234432235, | |
| "grad_norm": 0.3562494218349457, | |
| "learning_rate": 7.352941176470589e-05, | |
| "loss": 0.18, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.36996336996337, | |
| "grad_norm": 0.3098445534706116, | |
| "learning_rate": 6.764705882352942e-05, | |
| "loss": 0.1621, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.5164835164835164, | |
| "grad_norm": 0.32583731412887573, | |
| "learning_rate": 6.176470588235295e-05, | |
| "loss": 0.1577, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.663003663003663, | |
| "grad_norm": 0.23592990636825562, | |
| "learning_rate": 5.588235294117647e-05, | |
| "loss": 0.2229, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.8095238095238093, | |
| "grad_norm": 0.33576756715774536, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1959, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.956043956043956, | |
| "grad_norm": 0.26419597864151, | |
| "learning_rate": 4.411764705882353e-05, | |
| "loss": 0.1917, | |
| "step": 270 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 340, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 0.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |