| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9982174688057041, | |
| "eval_steps": 50, | |
| "global_step": 70, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0142602495543672, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0142602495543672, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.7976, | |
| "eval_samples_per_second": 49.4, | |
| "eval_steps_per_second": 12.506, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0285204991087344, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0427807486631016, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0570409982174688, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07130124777183601, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0855614973262032, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09982174688057041, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1140819964349376, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.12834224598930483, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.14260249554367202, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1568627450980392, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001998629534754574, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1711229946524064, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019945218953682734, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.18538324420677363, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019876883405951377, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.19964349376114082, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.21390374331550802, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2281639928698752, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.24242424242424243, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019335804264972018, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.25668449197860965, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2709447415329768, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001891006524188368, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.28520499108734404, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2994652406417112, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018386705679454242, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3137254901960784, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.32798573975044565, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001777145961456971, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3422459893048128, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017431448254773944, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.35650623885918004, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.37076648841354726, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3850267379679144, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016293203910498376, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.39928698752228164, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015877852522924732, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.41354723707664887, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015446390350150273, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.42780748663101603, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.44206773618538325, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014539904997395468, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.4563279857397504, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014067366430758004, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013583679495453, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.48484848484848486, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.49910873440285203, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5133689839572193, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012079116908177593, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5276292335115864, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001156434465040231, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5418894830659536, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5561497326203209, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001052335956242944, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5704099821746881, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5846702317290553, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.476640437570562e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5989304812834224, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6131907308377896, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6274509803921569, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.920883091822408e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6417112299465241, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6559714795008913, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6702317290552585, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.416320504546997e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6844919786096256, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.9326335692419995e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6987522281639929, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.4600950026045326e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.7130124777183601, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7130124777183601, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.0113, | |
| "eval_samples_per_second": 59.083, | |
| "eval_steps_per_second": 14.958, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5536096498497295e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.7415329768270945, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.7557932263814616, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7067960895016275e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.7700534759358288, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.7843137254901961, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.7985739750445633, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5685517452260567e-05, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.8128342245989305, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2285403854302912e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.8270944741532977, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.8413547237076648, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6132943205457606e-05, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.8556149732620321, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.8698752228163993, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.8841354723707665, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.8983957219251337, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.6419573502798374e-06, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.9126559714795008, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8943483704846475e-06, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.9269162210338681, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.9411764705882353, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.9554367201426025, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.231165940486234e-06, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.9696969696969697, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.478104631726711e-07, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.983957219251337, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3704652454261668e-07, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.9982174688057041, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 70 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 70, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 30, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9320518251970560.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |