| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01942690626517727, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001942690626517727, | |
| "grad_norm": 0.7082065343856812, | |
| "learning_rate": 2e-05, | |
| "loss": 2.2727, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001942690626517727, | |
| "eval_loss": 0.6706833243370056, | |
| "eval_runtime": 12.1816, | |
| "eval_samples_per_second": 17.814, | |
| "eval_steps_per_second": 8.948, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003885381253035454, | |
| "grad_norm": 0.6126853823661804, | |
| "learning_rate": 4e-05, | |
| "loss": 2.5076, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005828071879553181, | |
| "grad_norm": 0.5961718559265137, | |
| "learning_rate": 6e-05, | |
| "loss": 1.8968, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005828071879553181, | |
| "eval_loss": 0.6693085432052612, | |
| "eval_runtime": 12.1792, | |
| "eval_samples_per_second": 17.817, | |
| "eval_steps_per_second": 8.95, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007770762506070908, | |
| "grad_norm": 0.741155743598938, | |
| "learning_rate": 8e-05, | |
| "loss": 2.5345, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.009713453132588635, | |
| "grad_norm": 0.5367315411567688, | |
| "learning_rate": 0.0001, | |
| "loss": 2.2994, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.011656143759106362, | |
| "grad_norm": 0.9402748346328735, | |
| "learning_rate": 0.00012, | |
| "loss": 2.1218, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011656143759106362, | |
| "eval_loss": 0.6539478302001953, | |
| "eval_runtime": 12.248, | |
| "eval_samples_per_second": 17.717, | |
| "eval_steps_per_second": 8.899, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.013598834385624089, | |
| "grad_norm": 0.781460702419281, | |
| "learning_rate": 0.00014, | |
| "loss": 1.9115, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.015541525012141816, | |
| "grad_norm": 0.9737181067466736, | |
| "learning_rate": 0.00016, | |
| "loss": 2.1071, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.017484215638659543, | |
| "grad_norm": 1.433034896850586, | |
| "learning_rate": 0.00018, | |
| "loss": 2.4875, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.017484215638659543, | |
| "eval_loss": 0.5748686194419861, | |
| "eval_runtime": 12.3278, | |
| "eval_samples_per_second": 17.602, | |
| "eval_steps_per_second": 8.842, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01942690626517727, | |
| "grad_norm": 1.0972580909729004, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9674, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3166224305356800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |