| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.009151223976206819, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0018302447952413636, | |
| "grad_norm": 32.50212478637695, | |
| "learning_rate": 1e-05, | |
| "loss": 5.1093, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018302447952413636, | |
| "eval_loss": 5.102637767791748, | |
| "eval_runtime": 93.0141, | |
| "eval_samples_per_second": 9.902, | |
| "eval_steps_per_second": 4.956, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0036604895904827272, | |
| "grad_norm": 30.392139434814453, | |
| "learning_rate": 2e-05, | |
| "loss": 4.6978, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0036604895904827272, | |
| "eval_loss": 4.581779956817627, | |
| "eval_runtime": 22.5882, | |
| "eval_samples_per_second": 40.774, | |
| "eval_steps_per_second": 20.409, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00549073438572409, | |
| "grad_norm": 29.827119827270508, | |
| "learning_rate": 3e-05, | |
| "loss": 4.214, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0073209791809654545, | |
| "grad_norm": 32.89384841918945, | |
| "learning_rate": 4e-05, | |
| "loss": 3.9507, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0073209791809654545, | |
| "eval_loss": 2.77341628074646, | |
| "eval_runtime": 22.6288, | |
| "eval_samples_per_second": 40.7, | |
| "eval_steps_per_second": 20.372, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.009151223976206819, | |
| "grad_norm": 29.287202835083008, | |
| "learning_rate": 5e-05, | |
| "loss": 2.9103, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3822182832537600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |