| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 4, |
| "global_step": 22, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.04597701149425287, |
| "grad_norm": 0.6258180141448975, |
| "learning_rate": 0.0, |
| "loss": 2.2232, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.09195402298850575, |
| "grad_norm": 0.6560839414596558, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 2.3357, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.13793103448275862, |
| "grad_norm": 0.6459560990333557, |
| "learning_rate": 6.666666666666667e-05, |
| "loss": 2.2578, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.1839080459770115, |
| "grad_norm": 0.6299014091491699, |
| "learning_rate": 0.0001, |
| "loss": 2.1724, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.22988505747126436, |
| "grad_norm": 0.7396020889282227, |
| "learning_rate": 9.526315789473685e-05, |
| "loss": 2.1918, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.27586206896551724, |
| "grad_norm": 0.8523610830307007, |
| "learning_rate": 9.052631578947369e-05, |
| "loss": 2.1852, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.27586206896551724, |
| "eval_loss": 1.9329833984375, |
| "eval_runtime": 2.3678, |
| "eval_samples_per_second": 1.267, |
| "eval_steps_per_second": 0.422, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.3218390804597701, |
| "grad_norm": 0.8412789106369019, |
| "learning_rate": 8.578947368421054e-05, |
| "loss": 1.9734, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.367816091954023, |
| "grad_norm": 0.8718560934066772, |
| "learning_rate": 8.105263157894737e-05, |
| "loss": 1.9791, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.41379310344827586, |
| "grad_norm": 0.8543149828910828, |
| "learning_rate": 7.631578947368421e-05, |
| "loss": 1.8361, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.45977011494252873, |
| "grad_norm": 0.8103431463241577, |
| "learning_rate": 7.157894736842105e-05, |
| "loss": 1.7411, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.45977011494252873, |
| "eval_loss": 1.6474609375, |
| "eval_runtime": 2.3525, |
| "eval_samples_per_second": 1.275, |
| "eval_steps_per_second": 0.425, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.5057471264367817, |
| "grad_norm": 0.7526857256889343, |
| "learning_rate": 6.68421052631579e-05, |
| "loss": 1.6489, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.5517241379310345, |
| "grad_norm": 0.7403726577758789, |
| "learning_rate": 6.210526315789474e-05, |
| "loss": 1.6152, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.5977011494252874, |
| "grad_norm": 0.8051082491874695, |
| "learning_rate": 5.736842105263158e-05, |
| "loss": 1.6759, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.6436781609195402, |
| "grad_norm": 0.6479267477989197, |
| "learning_rate": 5.2631578947368424e-05, |
| "loss": 1.4395, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.6436781609195402, |
| "eval_loss": 1.5098876953125, |
| "eval_runtime": 2.3288, |
| "eval_samples_per_second": 1.288, |
| "eval_steps_per_second": 0.429, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.6896551724137931, |
| "grad_norm": 0.7364819645881653, |
| "learning_rate": 4.789473684210527e-05, |
| "loss": 1.5544, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.735632183908046, |
| "grad_norm": 0.6881729364395142, |
| "learning_rate": 4.3157894736842105e-05, |
| "loss": 1.5743, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.7816091954022989, |
| "grad_norm": 0.636885404586792, |
| "learning_rate": 3.842105263157895e-05, |
| "loss": 1.457, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.8275862068965517, |
| "grad_norm": 0.6316589117050171, |
| "learning_rate": 3.368421052631579e-05, |
| "loss": 1.5714, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.8275862068965517, |
| "eval_loss": 1.4373779296875, |
| "eval_runtime": 2.362, |
| "eval_samples_per_second": 1.27, |
| "eval_steps_per_second": 0.423, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.8735632183908046, |
| "grad_norm": 0.5898467302322388, |
| "learning_rate": 2.8947368421052634e-05, |
| "loss": 1.4883, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.9195402298850575, |
| "grad_norm": 0.5756623148918152, |
| "learning_rate": 2.4210526315789474e-05, |
| "loss": 1.4528, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.9655172413793104, |
| "grad_norm": 0.5258361101150513, |
| "learning_rate": 1.9473684210526315e-05, |
| "loss": 1.4182, |
| "step": 21 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.4895441234111786, |
| "learning_rate": 1.473684210526316e-05, |
| "loss": 1.3998, |
| "step": 22 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.40545654296875, |
| "eval_runtime": 2.6568, |
| "eval_samples_per_second": 1.129, |
| "eval_steps_per_second": 0.376, |
| "step": 22 |
| } |
| ], |
| "logging_steps": 1.0, |
| "max_steps": 22, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 0, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.1297281417605546e+19, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
