| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00487685930260912, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001625619767536373, | |
| "eval_loss": 2.4479925632476807, | |
| "eval_runtime": 124.9101, | |
| "eval_samples_per_second": 20.743, | |
| "eval_steps_per_second": 10.375, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000487685930260912, | |
| "grad_norm": 0.6782153248786926, | |
| "learning_rate": 3e-05, | |
| "loss": 2.317, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000975371860521824, | |
| "grad_norm": 0.8126118779182434, | |
| "learning_rate": 6e-05, | |
| "loss": 2.3709, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0013004958140290985, | |
| "eval_loss": 2.388354778289795, | |
| "eval_runtime": 123.8952, | |
| "eval_samples_per_second": 20.913, | |
| "eval_steps_per_second": 10.46, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.001463057790782736, | |
| "grad_norm": 0.616838276386261, | |
| "learning_rate": 9e-05, | |
| "loss": 2.3347, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.001950743721043648, | |
| "grad_norm": 0.8412759900093079, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 2.2133, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00243842965130456, | |
| "grad_norm": 0.6916660666465759, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.2687, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002600991628058197, | |
| "eval_loss": 2.2324202060699463, | |
| "eval_runtime": 123.9346, | |
| "eval_samples_per_second": 20.906, | |
| "eval_steps_per_second": 10.457, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.002926115581565472, | |
| "grad_norm": 0.8547218441963196, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 2.2517, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003413801511826384, | |
| "grad_norm": 0.7542737126350403, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 2.0641, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.003901487442087296, | |
| "grad_norm": 0.7304168343544006, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 2.1134, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.003901487442087296, | |
| "eval_loss": 2.143785238265991, | |
| "eval_runtime": 123.9677, | |
| "eval_samples_per_second": 20.901, | |
| "eval_steps_per_second": 10.454, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0043891733723482075, | |
| "grad_norm": 0.6808849573135376, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 2.0507, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.00487685930260912, | |
| "grad_norm": 0.8048596978187561, | |
| "learning_rate": 0.0, | |
| "loss": 1.9766, | |
| "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": 5583207470727168.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |