| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.2, |
| "eval_steps": 100, |
| "global_step": 400, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0125, |
| "grad_norm": 0.14092598855495453, |
| "learning_rate": 0.0004, |
| "loss": 1.1529, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.025, |
| "grad_norm": 0.14281609654426575, |
| "learning_rate": 0.0004998852503731983, |
| "loss": 1.0472, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.0375, |
| "grad_norm": 0.24040694534778595, |
| "learning_rate": 0.0004993848168027977, |
| "loss": 0.8532, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.05, |
| "grad_norm": 0.14735238254070282, |
| "learning_rate": 0.0004984880506341147, |
| "loss": 0.9761, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.05, |
| "eval_loss": 0.9448406100273132, |
| "eval_runtime": 322.186, |
| "eval_samples_per_second": 3.405, |
| "eval_steps_per_second": 0.056, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.0625, |
| "grad_norm": 0.1359478235244751, |
| "learning_rate": 0.0004971963770447935, |
| "loss": 0.9568, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.075, |
| "grad_norm": 0.17497147619724274, |
| "learning_rate": 0.0004955118488155782, |
| "loss": 0.7111, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.0875, |
| "grad_norm": 0.14382271468639374, |
| "learning_rate": 0.0004934371430679492, |
| "loss": 0.9413, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 0.16079047322273254, |
| "learning_rate": 0.0004909755570095319, |
| "loss": 0.8981, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.1, |
| "eval_loss": 0.9723050594329834, |
| "eval_runtime": 322.7576, |
| "eval_samples_per_second": 3.399, |
| "eval_steps_per_second": 0.056, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.1125, |
| "grad_norm": 0.14729101955890656, |
| "learning_rate": 0.0004881310026940389, |
| "loss": 0.6378, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.125, |
| "grad_norm": 0.15030288696289062, |
| "learning_rate": 0.0004849080008040734, |
| "loss": 0.9271, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.1375, |
| "grad_norm": 0.1613348424434662, |
| "learning_rate": 0.00048131167346667446, |
| "loss": 0.8457, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 0.15532569587230682, |
| "learning_rate": 0.00047734773611302284, |
| "loss": 0.603, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.15, |
| "eval_loss": 1.006589651107788, |
| "eval_runtime": 323.2105, |
| "eval_samples_per_second": 3.394, |
| "eval_steps_per_second": 0.056, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.1625, |
| "grad_norm": 0.16015686094760895, |
| "learning_rate": 0.0004730224883952422, |
| "loss": 0.9036, |
| "step": 325 |
| }, |
| { |
| "epoch": 0.175, |
| "grad_norm": 0.15767253935337067, |
| "learning_rate": 0.0004683428041747334, |
| "loss": 0.8283, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.1875, |
| "grad_norm": 0.17757417261600494, |
| "learning_rate": 0.0004633161205979517, |
| "loss": 0.5945, |
| "step": 375 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 0.17248600721359253, |
| "learning_rate": 0.0004579504262769877, |
| "loss": 0.8655, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.2, |
| "eval_loss": 1.0158599615097046, |
| "eval_runtime": 323.8034, |
| "eval_samples_per_second": 3.388, |
| "eval_steps_per_second": 0.056, |
| "step": 400 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 2000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 9223372036854775807, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4.031726173447782e+16, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
