| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.04486316733961418, |
| "eval_steps": 500, |
| "global_step": 75, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0029908778226409452, |
| "grad_norm": 0.42996275424957275, |
| "learning_rate": 8e-05, |
| "loss": 1.3150932312011718, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.0059817556452818905, |
| "grad_norm": 0.34759286046028137, |
| "learning_rate": 0.00018, |
| "loss": 1.2311323165893555, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.008972633467922835, |
| "grad_norm": 0.23679782450199127, |
| "learning_rate": 0.00019724137931034484, |
| "loss": 0.929847240447998, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.011963511290563781, |
| "grad_norm": 0.7136238217353821, |
| "learning_rate": 0.00019379310344827587, |
| "loss": 0.7683926105499268, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.014954389113204725, |
| "grad_norm": 0.36432984471321106, |
| "learning_rate": 0.0001903448275862069, |
| "loss": 0.9011115074157715, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.01794526693584567, |
| "grad_norm": 0.1651686429977417, |
| "learning_rate": 0.00018689655172413793, |
| "loss": 0.7865235805511475, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.020936144758486618, |
| "grad_norm": 0.1793285608291626, |
| "learning_rate": 0.00018344827586206896, |
| "loss": 0.8000905036926269, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.023927022581127562, |
| "grad_norm": 0.34582534432411194, |
| "learning_rate": 0.00018, |
| "loss": 0.7572827339172363, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.026917900403768506, |
| "grad_norm": 0.19526240229606628, |
| "learning_rate": 0.00017655172413793104, |
| "loss": 0.6299063682556152, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.02990877822640945, |
| "grad_norm": 0.4273979067802429, |
| "learning_rate": 0.00017310344827586207, |
| "loss": 0.7798028945922851, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.032899656049050395, |
| "grad_norm": 0.22420509159564972, |
| "learning_rate": 0.00016965517241379312, |
| "loss": 0.7394870758056641, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.03589053387169134, |
| "grad_norm": 0.28808942437171936, |
| "learning_rate": 0.00016620689655172415, |
| "loss": 0.7851818561553955, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.038881411694332284, |
| "grad_norm": 0.24858111143112183, |
| "learning_rate": 0.00016275862068965518, |
| "loss": 0.9596908569335938, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.041872289516973235, |
| "grad_norm": 0.21952398121356964, |
| "learning_rate": 0.00015931034482758623, |
| "loss": 0.8098215103149414, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.04486316733961418, |
| "grad_norm": 0.19696944952011108, |
| "learning_rate": 0.00015586206896551724, |
| "loss": 0.7508728504180908, |
| "step": 75 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 300, |
| "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": 1.2196996419600384e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
