| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.002584236159427492, | |
| "eval_steps": 13, | |
| "global_step": 13, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00019878739687903787, | |
| "grad_norm": 2.414543867111206, | |
| "learning_rate": 5e-06, | |
| "loss": 13.1525, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00019878739687903787, | |
| "eval_loss": 3.2820167541503906, | |
| "eval_runtime": 75.5342, | |
| "eval_samples_per_second": 28.054, | |
| "eval_steps_per_second": 14.033, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00039757479375807575, | |
| "grad_norm": 2.2050728797912598, | |
| "learning_rate": 1e-05, | |
| "loss": 13.7228, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005963621906371136, | |
| "grad_norm": 2.5719025135040283, | |
| "learning_rate": 1.5e-05, | |
| "loss": 14.2385, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0007951495875161515, | |
| "grad_norm": 2.4067375659942627, | |
| "learning_rate": 2e-05, | |
| "loss": 12.0989, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0009939369843951894, | |
| "grad_norm": 2.902513027191162, | |
| "learning_rate": 2.5e-05, | |
| "loss": 13.3901, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0011927243812742273, | |
| "grad_norm": 2.1985535621643066, | |
| "learning_rate": 3e-05, | |
| "loss": 13.2702, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0013915117781532651, | |
| "grad_norm": 2.53352427482605, | |
| "learning_rate": 3.5e-05, | |
| "loss": 14.1685, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.001590299175032303, | |
| "grad_norm": 2.161381483078003, | |
| "learning_rate": 4e-05, | |
| "loss": 13.6176, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0017890865719113408, | |
| "grad_norm": 3.1022119522094727, | |
| "learning_rate": 4.5e-05, | |
| "loss": 15.6293, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.001987873968790379, | |
| "grad_norm": 2.5830698013305664, | |
| "learning_rate": 5e-05, | |
| "loss": 14.0974, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0021866613656694165, | |
| "grad_norm": 3.0659115314483643, | |
| "learning_rate": 4.99229333433282e-05, | |
| "loss": 13.9289, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0023854487625484546, | |
| "grad_norm": 3.4623639583587646, | |
| "learning_rate": 4.9692208514878444e-05, | |
| "loss": 13.4014, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002584236159427492, | |
| "grad_norm": 2.969046115875244, | |
| "learning_rate": 4.9309248009941914e-05, | |
| "loss": 11.8233, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.002584236159427492, | |
| "eval_loss": 3.2339165210723877, | |
| "eval_runtime": 74.0873, | |
| "eval_samples_per_second": 28.601, | |
| "eval_steps_per_second": 14.307, | |
| "step": 13 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "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": 2158071405084672.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |