| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0082904990880451, | |
| "eval_steps": 9, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000165809981760902, | |
| "grad_norm": 14.182147026062012, | |
| "learning_rate": 1e-05, | |
| "loss": 14.468, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000165809981760902, | |
| "eval_loss": 6.990629196166992, | |
| "eval_runtime": 1574.821, | |
| "eval_samples_per_second": 3.225, | |
| "eval_steps_per_second": 0.403, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000331619963521804, | |
| "grad_norm": 8.581724166870117, | |
| "learning_rate": 2e-05, | |
| "loss": 15.5583, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000497429945282706, | |
| "grad_norm": 7.9157562255859375, | |
| "learning_rate": 3e-05, | |
| "loss": 12.8037, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000663239927043608, | |
| "grad_norm": 10.532652854919434, | |
| "learning_rate": 4e-05, | |
| "loss": 12.7289, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00082904990880451, | |
| "grad_norm": 11.54885196685791, | |
| "learning_rate": 5e-05, | |
| "loss": 13.4162, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000994859890565412, | |
| "grad_norm": 13.328164100646973, | |
| "learning_rate": 6e-05, | |
| "loss": 13.5196, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001160669872326314, | |
| "grad_norm": 13.098895072937012, | |
| "learning_rate": 7e-05, | |
| "loss": 13.5123, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.001326479854087216, | |
| "grad_norm": 17.912372589111328, | |
| "learning_rate": 8e-05, | |
| "loss": 15.0786, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.001492289835848118, | |
| "grad_norm": 15.202522277832031, | |
| "learning_rate": 9e-05, | |
| "loss": 12.5367, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.001492289835848118, | |
| "eval_loss": 5.437175273895264, | |
| "eval_runtime": 1576.7592, | |
| "eval_samples_per_second": 3.221, | |
| "eval_steps_per_second": 0.403, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00165809981760902, | |
| "grad_norm": 12.19020938873291, | |
| "learning_rate": 0.0001, | |
| "loss": 11.8082, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0018239097993699221, | |
| "grad_norm": 8.83342170715332, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 8.8364, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.001989719781130824, | |
| "grad_norm": 9.820218086242676, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 7.822, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002155529762891726, | |
| "grad_norm": 10.754770278930664, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 7.0536, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.002321339744652628, | |
| "grad_norm": 7.895251750946045, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 8.1585, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00248714972641353, | |
| "grad_norm": 7.87087345123291, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 6.6577, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002652959708174432, | |
| "grad_norm": 6.906998634338379, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 5.3785, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.002818769689935334, | |
| "grad_norm": 8.356192588806152, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 4.6551, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.002984579671696236, | |
| "grad_norm": 16.607709884643555, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 3.9705, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.002984579671696236, | |
| "eval_loss": 1.9645012617111206, | |
| "eval_runtime": 1576.7584, | |
| "eval_samples_per_second": 3.221, | |
| "eval_steps_per_second": 0.403, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003150389653457138, | |
| "grad_norm": 15.812430381774902, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 3.9633, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.00331619963521804, | |
| "grad_norm": 6.731838226318359, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 2.7544, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003482009616978942, | |
| "grad_norm": 7.793019771575928, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 2.309, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0036478195987398442, | |
| "grad_norm": 9.872495651245117, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 2.5922, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0038136295805007462, | |
| "grad_norm": 4.2099223136901855, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 1.186, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.003979439562261648, | |
| "grad_norm": 10.548074722290039, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.5299, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00414524954402255, | |
| "grad_norm": 13.979026794433594, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.2871, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004311059525783452, | |
| "grad_norm": 7.218410968780518, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 1.1803, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.004476869507544354, | |
| "grad_norm": 7.529348850250244, | |
| "learning_rate": 9.145187862775209e-05, | |
| "loss": 1.1097, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.004476869507544354, | |
| "eval_loss": 0.4603639543056488, | |
| "eval_runtime": 1575.6175, | |
| "eval_samples_per_second": 3.223, | |
| "eval_steps_per_second": 0.403, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.004642679489305256, | |
| "grad_norm": 3.8550705909729004, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.7259, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.004808489471066158, | |
| "grad_norm": 4.565075874328613, | |
| "learning_rate": 8.940053768033609e-05, | |
| "loss": 0.865, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.00497429945282706, | |
| "grad_norm": 6.3500285148620605, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.7888, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005140109434587962, | |
| "grad_norm": 5.463298320770264, | |
| "learning_rate": 8.715724127386972e-05, | |
| "loss": 0.8169, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.005305919416348864, | |
| "grad_norm": 4.480053901672363, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 0.7127, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.005471729398109766, | |
| "grad_norm": 7.863976001739502, | |
| "learning_rate": 8.473291852294987e-05, | |
| "loss": 1.048, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.005637539379870668, | |
| "grad_norm": 4.669947624206543, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 0.6693, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.00580334936163157, | |
| "grad_norm": 3.4031758308410645, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 0.8024, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.005969159343392472, | |
| "grad_norm": 4.576297760009766, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 0.9314, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.005969159343392472, | |
| "eval_loss": 0.4227474331855774, | |
| "eval_runtime": 1576.0515, | |
| "eval_samples_per_second": 3.223, | |
| "eval_steps_per_second": 0.403, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.006134969325153374, | |
| "grad_norm": 4.564301490783691, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 1.1414, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.006300779306914276, | |
| "grad_norm": 2.7618212699890137, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 0.6578, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.006466589288675178, | |
| "grad_norm": 2.4349262714385986, | |
| "learning_rate": 7.649596321166024e-05, | |
| "loss": 0.6903, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.00663239927043608, | |
| "grad_norm": 2.0584237575531006, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.6042, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006798209252196982, | |
| "grad_norm": 3.166882038116455, | |
| "learning_rate": 7.347357813929454e-05, | |
| "loss": 0.8912, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.006964019233957884, | |
| "grad_norm": 3.8364858627319336, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 1.1009, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0071298292157187864, | |
| "grad_norm": 3.1330361366271973, | |
| "learning_rate": 7.033683215379002e-05, | |
| "loss": 0.8003, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0072956391974796884, | |
| "grad_norm": 2.2796144485473633, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 0.7073, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0074614491792405905, | |
| "grad_norm": 2.880812406539917, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 0.6036, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0074614491792405905, | |
| "eval_loss": 0.3314964473247528, | |
| "eval_runtime": 1575.6793, | |
| "eval_samples_per_second": 3.223, | |
| "eval_steps_per_second": 0.403, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0076272591610014925, | |
| "grad_norm": 2.4614827632904053, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.636, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0077930691427623945, | |
| "grad_norm": 1.988437294960022, | |
| "learning_rate": 6.378186779084995e-05, | |
| "loss": 0.5319, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.007958879124523296, | |
| "grad_norm": 2.654332160949707, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 0.4373, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.008124689106284198, | |
| "grad_norm": 1.7638773918151855, | |
| "learning_rate": 6.0395584540887963e-05, | |
| "loss": 0.4448, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0082904990880451, | |
| "grad_norm": 3.3107423782348633, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.5151, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.2695579394048e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |