| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.08836524300441827, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0029455081001472753, | |
| "eval_loss": 11.093908309936523, | |
| "eval_runtime": 1.637, | |
| "eval_samples_per_second": 87.353, | |
| "eval_steps_per_second": 43.982, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008836524300441826, | |
| "grad_norm": 0.8765349984169006, | |
| "learning_rate": 6e-05, | |
| "loss": 44.3572, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.017673048600883652, | |
| "grad_norm": 1.6185814142227173, | |
| "learning_rate": 0.00012, | |
| "loss": 44.3502, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.023564064801178203, | |
| "eval_loss": 11.09122371673584, | |
| "eval_runtime": 0.4695, | |
| "eval_samples_per_second": 304.575, | |
| "eval_steps_per_second": 153.352, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.026509572901325478, | |
| "grad_norm": 1.3236716985702515, | |
| "learning_rate": 0.00018, | |
| "loss": 44.3449, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.035346097201767304, | |
| "grad_norm": 1.3467508554458618, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 44.3303, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.044182621502209134, | |
| "grad_norm": 1.3141950368881226, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 44.3279, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.047128129602356406, | |
| "eval_loss": 11.083142280578613, | |
| "eval_runtime": 0.4894, | |
| "eval_samples_per_second": 292.218, | |
| "eval_steps_per_second": 147.131, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.053019145802650956, | |
| "grad_norm": 0.7421669960021973, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 44.3521, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.061855670103092786, | |
| "grad_norm": 1.1170566082000732, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 44.3169, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.07069219440353461, | |
| "grad_norm": 0.9036471247673035, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 44.3052, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.07069219440353461, | |
| "eval_loss": 11.079090118408203, | |
| "eval_runtime": 0.4734, | |
| "eval_samples_per_second": 302.069, | |
| "eval_steps_per_second": 152.091, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.07952871870397643, | |
| "grad_norm": 1.2545416355133057, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 44.3192, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.08836524300441827, | |
| "grad_norm": 1.2347007989883423, | |
| "learning_rate": 0.0, | |
| "loss": 44.2745, | |
| "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": 56151244800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |