| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.023820867079561697, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009528346831824678, | |
| "grad_norm": 1.299138069152832, | |
| "learning_rate": 1e-05, | |
| "loss": 2.8561, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009528346831824678, | |
| "eval_loss": 3.010896921157837, | |
| "eval_runtime": 195.3493, | |
| "eval_samples_per_second": 4.525, | |
| "eval_steps_per_second": 0.568, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0019056693663649356, | |
| "grad_norm": 1.0775965452194214, | |
| "learning_rate": 2e-05, | |
| "loss": 2.8611, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0028585040495474035, | |
| "grad_norm": 1.0691394805908203, | |
| "learning_rate": 3e-05, | |
| "loss": 2.9594, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003811338732729871, | |
| "grad_norm": 0.982935905456543, | |
| "learning_rate": 4e-05, | |
| "loss": 2.8709, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004764173415912339, | |
| "grad_norm": 1.0805885791778564, | |
| "learning_rate": 5e-05, | |
| "loss": 2.8401, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005717008099094807, | |
| "grad_norm": 1.0612759590148926, | |
| "learning_rate": 6e-05, | |
| "loss": 2.7195, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006669842782277275, | |
| "grad_norm": 1.2097413539886475, | |
| "learning_rate": 7e-05, | |
| "loss": 2.8155, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.007622677465459742, | |
| "grad_norm": 1.3245927095413208, | |
| "learning_rate": 8e-05, | |
| "loss": 2.6753, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00857551214864221, | |
| "grad_norm": 1.2737631797790527, | |
| "learning_rate": 9e-05, | |
| "loss": 2.7696, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00857551214864221, | |
| "eval_loss": 2.809389114379883, | |
| "eval_runtime": 195.5632, | |
| "eval_samples_per_second": 4.52, | |
| "eval_steps_per_second": 0.568, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.009528346831824679, | |
| "grad_norm": 1.277371883392334, | |
| "learning_rate": 0.0001, | |
| "loss": 2.8938, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010481181515007145, | |
| "grad_norm": 1.1133867502212524, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 2.7638, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.011434016198189614, | |
| "grad_norm": 1.2571532726287842, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 2.4968, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.012386850881372083, | |
| "grad_norm": 1.0732775926589966, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 2.3647, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01333968556455455, | |
| "grad_norm": 1.4276105165481567, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 2.6106, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.014292520247737018, | |
| "grad_norm": 1.4259613752365112, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 2.4836, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.015245354930919485, | |
| "grad_norm": 1.3352410793304443, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 2.4822, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.016198189614101955, | |
| "grad_norm": 1.274780035018921, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 2.4272, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01715102429728442, | |
| "grad_norm": 1.0535167455673218, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 2.465, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01715102429728442, | |
| "eval_loss": 2.526502847671509, | |
| "eval_runtime": 195.3502, | |
| "eval_samples_per_second": 4.525, | |
| "eval_steps_per_second": 0.568, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01810385898046689, | |
| "grad_norm": 1.1656160354614258, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 2.3156, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.019056693663649357, | |
| "grad_norm": 1.2742457389831543, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 2.4936, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.020009528346831826, | |
| "grad_norm": 1.2091561555862427, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 2.4467, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02096236303001429, | |
| "grad_norm": 1.6974114179611206, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 2.6585, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.02191519771319676, | |
| "grad_norm": 1.2182083129882812, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 2.0146, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.022868032396379228, | |
| "grad_norm": 1.3905271291732788, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 2.8601, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.023820867079561697, | |
| "grad_norm": 1.1157796382904053, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.2298, | |
| "step": 25 | |
| } | |
| ], | |
| "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": 3.70943641780224e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |