| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.005663957407040299, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00011327914814080598, | |
| "eval_loss": 2.6746299266815186, | |
| "eval_runtime": 239.0017, | |
| "eval_samples_per_second": 15.552, | |
| "eval_steps_per_second": 7.778, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005663957407040299, | |
| "grad_norm": 0.9208196997642517, | |
| "learning_rate": 5e-05, | |
| "loss": 2.453, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0011327914814080599, | |
| "grad_norm": 1.2342981100082397, | |
| "learning_rate": 0.0001, | |
| "loss": 2.3742, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0011327914814080599, | |
| "eval_loss": 2.443814754486084, | |
| "eval_runtime": 239.1286, | |
| "eval_samples_per_second": 15.544, | |
| "eval_steps_per_second": 7.774, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0016991872221120898, | |
| "grad_norm": 1.2800140380859375, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.9989, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0022655829628161197, | |
| "grad_norm": 2.072373151779175, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.9089, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0022655829628161197, | |
| "eval_loss": 1.7018228769302368, | |
| "eval_runtime": 239.2255, | |
| "eval_samples_per_second": 15.538, | |
| "eval_steps_per_second": 7.771, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0028319787035201494, | |
| "grad_norm": 1.5718722343444824, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.6389, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0033983744442241796, | |
| "grad_norm": 1.6645965576171875, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3787, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0033983744442241796, | |
| "eval_loss": 1.4157291650772095, | |
| "eval_runtime": 238.4359, | |
| "eval_samples_per_second": 15.589, | |
| "eval_steps_per_second": 7.797, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.003964770184928209, | |
| "grad_norm": 1.7427442073822021, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.3513, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0045311659256322395, | |
| "grad_norm": 1.7891837358474731, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.2986, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0045311659256322395, | |
| "eval_loss": 1.3863377571105957, | |
| "eval_runtime": 238.1813, | |
| "eval_samples_per_second": 15.606, | |
| "eval_steps_per_second": 7.805, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.005097561666336269, | |
| "grad_norm": 1.6350563764572144, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.2097, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.005663957407040299, | |
| "grad_norm": 1.806128740310669, | |
| "learning_rate": 0.0, | |
| "loss": 1.3774, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.005663957407040299, | |
| "eval_loss": 1.38254714012146, | |
| "eval_runtime": 239.0077, | |
| "eval_samples_per_second": 15.552, | |
| "eval_steps_per_second": 7.778, | |
| "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": 9105273340821504.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |