| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.017057569296375266, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005685856432125089, | |
| "eval_loss": 0.9208130836486816, | |
| "eval_runtime": 114.6042, | |
| "eval_samples_per_second": 6.466, | |
| "eval_steps_per_second": 3.237, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0017057569296375266, | |
| "grad_norm": 0.7181560397148132, | |
| "learning_rate": 6e-05, | |
| "loss": 0.881, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003411513859275053, | |
| "grad_norm": 0.7910261750221252, | |
| "learning_rate": 0.00012, | |
| "loss": 0.8153, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004548685145700071, | |
| "eval_loss": 0.8656640648841858, | |
| "eval_runtime": 113.9541, | |
| "eval_samples_per_second": 6.503, | |
| "eval_steps_per_second": 3.256, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00511727078891258, | |
| "grad_norm": 1.1405916213989258, | |
| "learning_rate": 0.00018, | |
| "loss": 0.7181, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006823027718550106, | |
| "grad_norm": 1.2551310062408447, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.8526, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.008528784648187633, | |
| "grad_norm": 1.1293219327926636, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.773, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009097370291400142, | |
| "eval_loss": 0.7999897003173828, | |
| "eval_runtime": 114.0138, | |
| "eval_samples_per_second": 6.499, | |
| "eval_steps_per_second": 3.254, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01023454157782516, | |
| "grad_norm": 0.77125084400177, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.748, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.011940298507462687, | |
| "grad_norm": 1.1109628677368164, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.7037, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.013646055437100213, | |
| "grad_norm": 0.7020811438560486, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.8286, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.013646055437100213, | |
| "eval_loss": 0.7709226012229919, | |
| "eval_runtime": 114.0197, | |
| "eval_samples_per_second": 6.499, | |
| "eval_steps_per_second": 3.254, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01535181236673774, | |
| "grad_norm": 0.6046702861785889, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.7433, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.017057569296375266, | |
| "grad_norm": 0.7539558410644531, | |
| "learning_rate": 0.0, | |
| "loss": 0.753, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 70, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.7385913394921472e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |