| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9063717937097797, | |
| "eval_steps": 500, | |
| "global_step": 5000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.999549488698767e-05, | |
| "loss": 0.9367, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.998198117163414e-05, | |
| "loss": 0.8539, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.995946372440459e-05, | |
| "loss": 0.8563, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.99279506607906e-05, | |
| "loss": 0.8552, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.9887453338385195e-05, | |
| "loss": 0.8377, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.98379863527895e-05, | |
| "loss": 0.8346, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.9779567532352364e-05, | |
| "loss": 0.8338, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.971221793174483e-05, | |
| "loss": 0.8176, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.9635961824371865e-05, | |
| "loss": 0.8297, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.9550826693624e-05, | |
| "loss": 0.8337, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.945684322297207e-05, | |
| "loss": 0.8243, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.935404528490858e-05, | |
| "loss": 0.8289, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.924246992873982e-05, | |
| "loss": 0.818, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.9122157367232894e-05, | |
| "loss": 0.8361, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.899315096212272e-05, | |
| "loss": 0.8055, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.8855497208484046e-05, | |
| "loss": 0.8284, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.8709245717974204e-05, | |
| "loss": 0.8214, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 4.8554449200952635e-05, | |
| "loss": 0.8243, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.8391163447483587e-05, | |
| "loss": 0.8191, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.821944730722887e-05, | |
| "loss": 0.8106, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.803936266823792e-05, | |
| "loss": 0.8217, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.785097443464276e-05, | |
| "loss": 0.8071, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.765435050326602e-05, | |
| "loss": 0.8164, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.744956173915022e-05, | |
| "loss": 0.8264, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.7236681950017445e-05, | |
| "loss": 0.8183, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.701578785966834e-05, | |
| "loss": 0.8035, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.678695908033017e-05, | |
| "loss": 0.8019, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.655027808396385e-05, | |
| "loss": 0.8084, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.6305830172540295e-05, | |
| "loss": 0.8124, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.6053703447296826e-05, | |
| "loss": 0.8206, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.579398877698471e-05, | |
| "loss": 0.8137, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.55267797651192e-05, | |
| "loss": 0.803, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.5252172716244e-05, | |
| "loss": 0.8108, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.4970266601222243e-05, | |
| "loss": 0.8154, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 4.4681163021566496e-05, | |
| "loss": 0.7998, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 4.4384966172820644e-05, | |
| "loss": 0.8109, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 4.40817828070069e-05, | |
| "loss": 0.8102, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 4.377172219415136e-05, | |
| "loss": 0.8119, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 4.345489608290216e-05, | |
| "loss": 0.8041, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 4.313141866025423e-05, | |
| "loss": 0.8149, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 4.280140651039522e-05, | |
| "loss": 0.8043, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.246497857268759e-05, | |
| "loss": 0.7933, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.2122256098801726e-05, | |
| "loss": 0.8022, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.177336260901578e-05, | |
| "loss": 0.8083, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 4.1418423847697786e-05, | |
| "loss": 0.8082, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 4.105756773798633e-05, | |
| "loss": 0.7956, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 4.0690924335685865e-05, | |
| "loss": 0.8072, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 4.031862578239338e-05, | |
| "loss": 0.7954, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.994080625787343e-05, | |
| "loss": 0.8025, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.955760193169851e-05, | |
| "loss": 0.796, | |
| "step": 5000 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 16548, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 1000, | |
| "total_flos": 4.5085523318173336e+19, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |