| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.031413612565445025, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0010471204188481676, | |
| "eval_loss": NaN, | |
| "eval_runtime": 73.9103, | |
| "eval_samples_per_second": 5.453, | |
| "eval_steps_per_second": 2.733, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0031413612565445027, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0062827225130890054, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008376963350785341, | |
| "eval_loss": NaN, | |
| "eval_runtime": 74.2062, | |
| "eval_samples_per_second": 5.431, | |
| "eval_steps_per_second": 2.722, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.009424083769633508, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012565445026178011, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.015706806282722512, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.016753926701570682, | |
| "eval_loss": NaN, | |
| "eval_runtime": 74.2574, | |
| "eval_samples_per_second": 5.427, | |
| "eval_steps_per_second": 2.72, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.018848167539267015, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02198952879581152, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.025130890052356022, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.025130890052356022, | |
| "eval_loss": NaN, | |
| "eval_runtime": 74.1827, | |
| "eval_samples_per_second": 5.433, | |
| "eval_steps_per_second": 2.723, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.028272251308900525, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.031413612565445025, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.90858892673024e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |