| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.007540625117822267, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00015081250235644535, | |
| "eval_loss": 1.3071143627166748, | |
| "eval_runtime": 320.9795, | |
| "eval_samples_per_second": 8.698, | |
| "eval_steps_per_second": 4.349, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007540625117822267, | |
| "grad_norm": 0.5119345784187317, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2994, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0015081250235644535, | |
| "grad_norm": 0.5956404209136963, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3244, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0015081250235644535, | |
| "eval_loss": 1.1867642402648926, | |
| "eval_runtime": 331.0879, | |
| "eval_samples_per_second": 8.433, | |
| "eval_steps_per_second": 4.216, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0022621875353466803, | |
| "grad_norm": 0.4660656154155731, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.0861, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003016250047128907, | |
| "grad_norm": 0.6588117480278015, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.1344, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003016250047128907, | |
| "eval_loss": 1.0804147720336914, | |
| "eval_runtime": 330.7342, | |
| "eval_samples_per_second": 8.442, | |
| "eval_steps_per_second": 4.221, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0037703125589111336, | |
| "grad_norm": 0.5345557332038879, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.0339, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004524375070693361, | |
| "grad_norm": 0.5636916160583496, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9928, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004524375070693361, | |
| "eval_loss": 1.0399361848831177, | |
| "eval_runtime": 331.227, | |
| "eval_samples_per_second": 8.429, | |
| "eval_steps_per_second": 4.215, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005278437582475587, | |
| "grad_norm": 0.4428461492061615, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.0398, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.006032500094257814, | |
| "grad_norm": 0.5028639435768127, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.0496, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006032500094257814, | |
| "eval_loss": 1.0300142765045166, | |
| "eval_runtime": 331.2297, | |
| "eval_samples_per_second": 8.429, | |
| "eval_steps_per_second": 4.215, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0067865626060400405, | |
| "grad_norm": 0.5888687968254089, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.0025, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.007540625117822267, | |
| "grad_norm": 0.5885831713676453, | |
| "learning_rate": 0.0, | |
| "loss": 1.0291, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.007540625117822267, | |
| "eval_loss": 1.0279818773269653, | |
| "eval_runtime": 331.2007, | |
| "eval_samples_per_second": 8.43, | |
| "eval_steps_per_second": 4.215, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.264704093683712e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |