| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004914004914004914, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004914004914004914, | |
| "grad_norm": 2.2695932388305664, | |
| "learning_rate": 2e-05, | |
| "loss": 2.1376, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004914004914004914, | |
| "eval_loss": 2.171025037765503, | |
| "eval_runtime": 100.0801, | |
| "eval_samples_per_second": 34.253, | |
| "eval_steps_per_second": 4.287, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009828009828009828, | |
| "grad_norm": 2.3359031677246094, | |
| "learning_rate": 4e-05, | |
| "loss": 2.2367, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0014742014742014742, | |
| "grad_norm": 2.451155424118042, | |
| "learning_rate": 6e-05, | |
| "loss": 2.1563, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0014742014742014742, | |
| "eval_loss": 1.9412680864334106, | |
| "eval_runtime": 99.4583, | |
| "eval_samples_per_second": 34.467, | |
| "eval_steps_per_second": 4.313, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0019656019656019656, | |
| "grad_norm": 2.4158289432525635, | |
| "learning_rate": 8e-05, | |
| "loss": 1.7711, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002457002457002457, | |
| "grad_norm": 2.4314262866973877, | |
| "learning_rate": 0.0001, | |
| "loss": 1.7378, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0029484029484029483, | |
| "grad_norm": 2.1631124019622803, | |
| "learning_rate": 0.00012, | |
| "loss": 1.2608, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0029484029484029483, | |
| "eval_loss": 1.0259674787521362, | |
| "eval_runtime": 99.4953, | |
| "eval_samples_per_second": 34.454, | |
| "eval_steps_per_second": 4.312, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0034398034398034397, | |
| "grad_norm": 2.0402650833129883, | |
| "learning_rate": 0.00014, | |
| "loss": 0.9874, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003931203931203931, | |
| "grad_norm": 2.1171467304229736, | |
| "learning_rate": 0.00016, | |
| "loss": 0.8686, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004422604422604423, | |
| "grad_norm": 0.8250740766525269, | |
| "learning_rate": 0.00018, | |
| "loss": 0.3323, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004422604422604423, | |
| "eval_loss": 0.29506635665893555, | |
| "eval_runtime": 99.5335, | |
| "eval_samples_per_second": 34.441, | |
| "eval_steps_per_second": 4.31, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004914004914004914, | |
| "grad_norm": 0.8358497023582458, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2944, | |
| "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": 5.592309412397056e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |