| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01988466892026248, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00039769337840524953, | |
| "eval_loss": 10.654695510864258, | |
| "eval_runtime": 65.1814, | |
| "eval_samples_per_second": 16.247, | |
| "eval_steps_per_second": 8.131, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001988466892026248, | |
| "grad_norm": 6.9008917808532715, | |
| "learning_rate": 5e-05, | |
| "loss": 10.7859, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003976933784052496, | |
| "grad_norm": 18.198335647583008, | |
| "learning_rate": 0.0001, | |
| "loss": 10.4823, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003976933784052496, | |
| "eval_loss": 9.707829475402832, | |
| "eval_runtime": 65.5872, | |
| "eval_samples_per_second": 16.146, | |
| "eval_steps_per_second": 8.081, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005965400676078743, | |
| "grad_norm": 16.507511138916016, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 9.1686, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007953867568104992, | |
| "grad_norm": 7.460324287414551, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 6.4331, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007953867568104992, | |
| "eval_loss": 5.218746662139893, | |
| "eval_runtime": 65.7446, | |
| "eval_samples_per_second": 16.108, | |
| "eval_steps_per_second": 8.061, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00994233446013124, | |
| "grad_norm": 12.036908149719238, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 4.3067, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.011930801352157487, | |
| "grad_norm": 11.02371883392334, | |
| "learning_rate": 5e-05, | |
| "loss": 3.1429, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.011930801352157487, | |
| "eval_loss": 2.074090003967285, | |
| "eval_runtime": 65.8416, | |
| "eval_samples_per_second": 16.084, | |
| "eval_steps_per_second": 8.05, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.013919268244183734, | |
| "grad_norm": 12.443742752075195, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.3636, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.015907735136209984, | |
| "grad_norm": 8.593917846679688, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.1375, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.015907735136209984, | |
| "eval_loss": 1.040244221687317, | |
| "eval_runtime": 65.9616, | |
| "eval_samples_per_second": 16.055, | |
| "eval_steps_per_second": 8.035, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01789620202823623, | |
| "grad_norm": 4.671925067901611, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.8271, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01988466892026248, | |
| "grad_norm": 7.032400131225586, | |
| "learning_rate": 0.0, | |
| "loss": 0.8397, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01988466892026248, | |
| "eval_loss": 0.9359374046325684, | |
| "eval_runtime": 65.7919, | |
| "eval_samples_per_second": 16.096, | |
| "eval_steps_per_second": 8.056, | |
| "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": 8550933520711680.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |