| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 9.964539007092199, | |
| "eval_steps": 500, | |
| "global_step": 170, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.28368794326241137, | |
| "grad_norm": 1.467705249786377, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.5187, | |
| "num_tokens": 634122.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5673758865248227, | |
| "grad_norm": 0.786109983921051, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4691, | |
| "num_tokens": 627314.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.851063829787234, | |
| "grad_norm": 0.529224157333374, | |
| "learning_rate": 4.989299698973645e-05, | |
| "loss": 0.4195, | |
| "num_tokens": 1266402.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.1702127659574468, | |
| "grad_norm": 0.36877477169036865, | |
| "learning_rate": 4.957300570509739e-05, | |
| "loss": 0.4707, | |
| "num_tokens": 721307.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.4539007092198581, | |
| "grad_norm": 0.3088724613189697, | |
| "learning_rate": 4.9043069704368563e-05, | |
| "loss": 0.3746, | |
| "num_tokens": 1347576.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.7375886524822695, | |
| "grad_norm": 0.25784584879875183, | |
| "learning_rate": 4.83082294095344e-05, | |
| "loss": 0.3654, | |
| "num_tokens": 1978085.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.23836882412433624, | |
| "learning_rate": 4.7375474164915813e-05, | |
| "loss": 0.3578, | |
| "num_tokens": 2571704.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.2836879432624113, | |
| "grad_norm": 0.20160914957523346, | |
| "learning_rate": 4.625367575886955e-05, | |
| "loss": 0.3419, | |
| "num_tokens": 3218590.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.5673758865248226, | |
| "grad_norm": 0.19208775460720062, | |
| "learning_rate": 4.4953504040849445e-05, | |
| "loss": 0.3445, | |
| "num_tokens": 3863566.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.851063829787234, | |
| "grad_norm": 0.16179953515529633, | |
| "learning_rate": 4.348732543642775e-05, | |
| "loss": 0.3352, | |
| "num_tokens": 4488605.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 3.1134751773049647, | |
| "grad_norm": 0.30722367763519287, | |
| "learning_rate": 4.1869085325538425e-05, | |
| "loss": 0.3326, | |
| "num_tokens": 5057805.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 3.397163120567376, | |
| "grad_norm": 0.1563473492860794, | |
| "learning_rate": 4.011417540268764e-05, | |
| "loss": 0.33, | |
| "num_tokens": 5676903.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.6808510638297873, | |
| "grad_norm": 0.13698497414588928, | |
| "learning_rate": 3.8239287280718634e-05, | |
| "loss": 0.3386, | |
| "num_tokens": 6321151.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 3.9645390070921986, | |
| "grad_norm": 0.2415415197610855, | |
| "learning_rate": 3.626225373056101e-05, | |
| "loss": 0.3162, | |
| "num_tokens": 6962012.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 4.226950354609929, | |
| "grad_norm": 0.13087180256843567, | |
| "learning_rate": 3.420187906699333e-05, | |
| "loss": 0.3179, | |
| "num_tokens": 7568220.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 4.51063829787234, | |
| "grad_norm": 0.13442984223365784, | |
| "learning_rate": 3.207776029368427e-05, | |
| "loss": 0.3153, | |
| "num_tokens": 8215106.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 4.794326241134752, | |
| "grad_norm": 0.13201209902763367, | |
| "learning_rate": 2.99101007086695e-05, | |
| "loss": 0.3088, | |
| "num_tokens": 8842420.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 5.056737588652482, | |
| "grad_norm": 1.6477094888687134, | |
| "learning_rate": 2.7719517743133312e-05, | |
| "loss": 0.3266, | |
| "num_tokens": 9397379.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 5.567375886524823, | |
| "grad_norm": 0.127790629863739, | |
| "learning_rate": 2.5526846861212987e-05, | |
| "loss": 0.3057, | |
| "num_tokens": 618338.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 5.851063829787234, | |
| "grad_norm": 0.12059980630874634, | |
| "learning_rate": 2.3352943386009223e-05, | |
| "loss": 0.3081, | |
| "num_tokens": 1273698.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 6.170212765957447, | |
| "grad_norm": 0.13467751443386078, | |
| "learning_rate": 2.1218484136710372e-05, | |
| "loss": 0.3696, | |
| "num_tokens": 1988765.0, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 6.453900709219858, | |
| "grad_norm": 0.12073035538196564, | |
| "learning_rate": 1.914377076353511e-05, | |
| "loss": 0.2971, | |
| "num_tokens": 625541.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 6.73758865248227, | |
| "grad_norm": 2.8106677532196045, | |
| "learning_rate": 1.7148536651049078e-05, | |
| "loss": 0.3054, | |
| "num_tokens": 1270517.0, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 7.056737588652482, | |
| "grad_norm": 0.21665821969509125, | |
| "learning_rate": 1.5251759226471556e-05, | |
| "loss": 0.3581, | |
| "num_tokens": 1987709.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 7.340425531914893, | |
| "grad_norm": 0.11727333068847656, | |
| "learning_rate": 1.3471479458178499e-05, | |
| "loss": 0.3057, | |
| "num_tokens": 2609416.0, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 7.624113475177305, | |
| "grad_norm": 0.13120116293430328, | |
| "learning_rate": 1.1824630261220466e-05, | |
| "loss": 0.304, | |
| "num_tokens": 3264776.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 7.907801418439716, | |
| "grad_norm": 0.11633836477994919, | |
| "learning_rate": 1.0326875441955191e-05, | |
| "loss": 0.3001, | |
| "num_tokens": 635071.0, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 8.22695035460993, | |
| "grad_norm": 0.17760534584522247, | |
| "learning_rate": 8.99246071365363e-06, | |
| "loss": 0.3615, | |
| "num_tokens": 1349625.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 8.51063829787234, | |
| "grad_norm": 0.2086412012577057, | |
| "learning_rate": 7.834078200126287e-06, | |
| "loss": 0.2978, | |
| "num_tokens": 1973689.0, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 8.794326241134751, | |
| "grad_norm": 0.1149413138628006, | |
| "learning_rate": 6.862745716127312e-06, | |
| "loss": 0.2979, | |
| "num_tokens": 634122.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 9.113475177304965, | |
| "grad_norm": 0.1138206422328949, | |
| "learning_rate": 6.087701972745999e-06, | |
| "loss": 0.3572, | |
| "num_tokens": 714739.0, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 9.397163120567376, | |
| "grad_norm": 0.1209757998585701, | |
| "learning_rate": 5.51631870452704e-06, | |
| "loss": 0.2932, | |
| "num_tokens": 1354872.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 9.680851063829786, | |
| "grad_norm": 0.11537827551364899, | |
| "learning_rate": 5.154030554111651e-06, | |
| "loss": 0.2973, | |
| "num_tokens": 2002733.0, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 9.964539007092199, | |
| "grad_norm": 1.9767428636550903, | |
| "learning_rate": 5.004283381293366e-06, | |
| "loss": 0.2981, | |
| "num_tokens": 2639235.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 9.964539007092199, | |
| "step": 170, | |
| "total_flos": 4.719554866967808e+16, | |
| "train_loss": 0.0366410073112039, | |
| "train_runtime": 308.342, | |
| "train_samples_per_second": 4.573, | |
| "train_steps_per_second": 0.551 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 170, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.719554866967808e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |