| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.035214446952595936, | |
| "eval_steps": 10, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009029345372460496, | |
| "eval_loss": 4.4803690910339355, | |
| "eval_runtime": 32.9653, | |
| "eval_samples_per_second": 14.166, | |
| "eval_steps_per_second": 7.098, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004514672686230248, | |
| "grad_norm": 0.515048623085022, | |
| "learning_rate": 5e-05, | |
| "loss": 4.4363, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009029345372460496, | |
| "grad_norm": 0.810344398021698, | |
| "learning_rate": 0.0001, | |
| "loss": 4.5374, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009029345372460496, | |
| "eval_loss": 4.342668533325195, | |
| "eval_runtime": 31.7157, | |
| "eval_samples_per_second": 14.725, | |
| "eval_steps_per_second": 7.378, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013544018058690745, | |
| "grad_norm": 0.93119877576828, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.0774, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01805869074492099, | |
| "grad_norm": 1.139711618423462, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 4.0065, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01805869074492099, | |
| "eval_loss": 3.7838807106018066, | |
| "eval_runtime": 31.8951, | |
| "eval_samples_per_second": 14.642, | |
| "eval_steps_per_second": 7.337, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.022573363431151242, | |
| "grad_norm": 1.4093351364135742, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.7253, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02708803611738149, | |
| "grad_norm": 1.6034352779388428, | |
| "learning_rate": 5e-05, | |
| "loss": 3.6864, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02708803611738149, | |
| "eval_loss": 3.522407293319702, | |
| "eval_runtime": 32.0421, | |
| "eval_samples_per_second": 14.575, | |
| "eval_steps_per_second": 7.303, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03160270880361174, | |
| "grad_norm": 1.329637050628662, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.4754, | |
| "step": 35 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7188373690122240.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |