| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.05595970900951315, | |
| "eval_steps": 500, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001119194180190263, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002238388360380526, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003357582540570789, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.994647308096509e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004476776720761052, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.9786121534345265e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005595970900951315, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.951963201008076e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006715165081141578, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.914814565722671e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00783435926133184, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.867325323737765e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.008953553441522105, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8096988312782174e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.010072747621712367, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.742181853831721e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01119194180190263, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.665063509461097e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012311135982092894, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5786740307563636e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.013430330162283156, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.4833833507280884e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.014549524342473419, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.379599518697444e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01566871852266368, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.267766952966369e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.016787912702853944, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.148364537750172e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01790710688304421, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.021903572521802e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.019026301063234472, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.888925582549006e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.020145495243424735, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.021264689423614997, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6057217255475034e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02238388360380526, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.456708580912725e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.023503077783995522, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.303598663257904e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.024622271964185788, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.147047612756302e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.02574146614437605, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9877258050403212e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.026860660324566313, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8263154805501297e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.027979854504756575, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.663507823075358e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.029099048684946838, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0302182428651371, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3364921769246423e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03133743704532736, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.173684519449872e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.032456631225517625, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0122741949596797e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03357582540570789, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.852952387243698e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03469501958589815, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6964013367420966e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03581421376608842, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5432914190872757e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.03693340794627868, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3942782744524973e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.038052602126468944, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2500000000000006e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.03917179630665921, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1110744174509952e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04029099048684947, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.780964274781984e-06, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04141018466703973, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.51635462249828e-06, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.042529378847229994, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.3223304703363135e-06, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.04364857302742026, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.204004813025568e-06, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.04476776720761052, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.166166492719124e-06, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04588696138780078, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.213259692436367e-06, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.047006155567991044, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3493649053890326e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.048125349748181306, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.578181461682794e-06, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.049244543928371576, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9030116872178316e-06, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.05036373810856184, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3267467626223606e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0514829322887521, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.51854342773295e-07, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.05260212646894236, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.803679899192392e-07, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.053721320649132626, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1387846565474045e-07, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.05484051482932289, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.352691903491303e-08, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.05595970900951315, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.979454750844518e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |