| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0008322929671244278, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.322929671244278e-05, | |
| "grad_norm": 0.11874104291200638, | |
| "learning_rate": 2e-05, | |
| "loss": 6.9485, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.322929671244278e-05, | |
| "eval_loss": 6.943171977996826, | |
| "eval_runtime": 14.4544, | |
| "eval_samples_per_second": 349.997, | |
| "eval_steps_per_second": 175.033, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00016645859342488556, | |
| "grad_norm": 0.13921195268630981, | |
| "learning_rate": 4e-05, | |
| "loss": 6.9425, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00024968789013732833, | |
| "grad_norm": 0.13533537089824677, | |
| "learning_rate": 6e-05, | |
| "loss": 6.9457, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00024968789013732833, | |
| "eval_loss": 6.943038463592529, | |
| "eval_runtime": 12.949, | |
| "eval_samples_per_second": 390.686, | |
| "eval_steps_per_second": 195.382, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0003329171868497711, | |
| "grad_norm": 0.14525778591632843, | |
| "learning_rate": 8e-05, | |
| "loss": 6.9456, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0004161464835622139, | |
| "grad_norm": 0.1855430155992508, | |
| "learning_rate": 0.0001, | |
| "loss": 6.9386, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0004993757802746567, | |
| "grad_norm": 0.157642662525177, | |
| "learning_rate": 0.00012, | |
| "loss": 6.9336, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0004993757802746567, | |
| "eval_loss": 6.942324161529541, | |
| "eval_runtime": 12.8178, | |
| "eval_samples_per_second": 394.685, | |
| "eval_steps_per_second": 197.381, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005826050769870995, | |
| "grad_norm": 0.12620650231838226, | |
| "learning_rate": 0.00014, | |
| "loss": 6.9408, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0006658343736995423, | |
| "grad_norm": 0.1428166925907135, | |
| "learning_rate": 0.00016, | |
| "loss": 6.9393, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.000749063670411985, | |
| "grad_norm": 0.17838652431964874, | |
| "learning_rate": 0.00018, | |
| "loss": 6.9464, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.000749063670411985, | |
| "eval_loss": 6.9411492347717285, | |
| "eval_runtime": 12.8329, | |
| "eval_samples_per_second": 394.221, | |
| "eval_steps_per_second": 197.15, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0008322929671244278, | |
| "grad_norm": 0.13933014869689941, | |
| "learning_rate": 0.0002, | |
| "loss": 6.9371, | |
| "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": 24389111808.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |