| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.014144271570014143, | |
| "eval_steps": 5, | |
| "global_step": 45, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003143171460003143, | |
| "eval_loss": 13.059508323669434, | |
| "eval_runtime": 187.9101, | |
| "eval_samples_per_second": 28.514, | |
| "eval_steps_per_second": 3.566, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000942951438000943, | |
| "grad_norm": 75.8877944946289, | |
| "learning_rate": 3e-05, | |
| "loss": 12.881, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0015715857300015717, | |
| "eval_loss": 5.635742664337158, | |
| "eval_runtime": 189.3855, | |
| "eval_samples_per_second": 28.292, | |
| "eval_steps_per_second": 3.538, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001885902876001886, | |
| "grad_norm": 43.98210144042969, | |
| "learning_rate": 6e-05, | |
| "loss": 7.6928, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002828854314002829, | |
| "grad_norm": 24.16446876525879, | |
| "learning_rate": 9e-05, | |
| "loss": 2.323, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0031431714600031434, | |
| "eval_loss": 0.45748162269592285, | |
| "eval_runtime": 189.1912, | |
| "eval_samples_per_second": 28.321, | |
| "eval_steps_per_second": 3.541, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003771805752003772, | |
| "grad_norm": 46.70669937133789, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 0.8778, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004714757190004715, | |
| "grad_norm": 16.055130004882812, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.4203, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004714757190004715, | |
| "eval_loss": 0.4140756130218506, | |
| "eval_runtime": 188.9791, | |
| "eval_samples_per_second": 28.352, | |
| "eval_steps_per_second": 3.545, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005657708628005658, | |
| "grad_norm": 17.71535873413086, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.4977, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.006286342920006287, | |
| "eval_loss": 0.5579892992973328, | |
| "eval_runtime": 188.9276, | |
| "eval_samples_per_second": 28.36, | |
| "eval_steps_per_second": 3.546, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006600660066006601, | |
| "grad_norm": 11.61266040802002, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 0.5078, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.007543611504007544, | |
| "grad_norm": 10.140732765197754, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 0.4071, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.007857928650007858, | |
| "eval_loss": 0.35243675112724304, | |
| "eval_runtime": 188.9749, | |
| "eval_samples_per_second": 28.353, | |
| "eval_steps_per_second": 3.545, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.008486562942008486, | |
| "grad_norm": 4.260001182556152, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 0.3264, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.00942951438000943, | |
| "grad_norm": 3.704922676086426, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3148, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00942951438000943, | |
| "eval_loss": 0.2736121416091919, | |
| "eval_runtime": 189.0749, | |
| "eval_samples_per_second": 28.338, | |
| "eval_steps_per_second": 3.544, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.010372465818010372, | |
| "grad_norm": 5.416778564453125, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 0.2178, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.011001100110011002, | |
| "eval_loss": 0.25446486473083496, | |
| "eval_runtime": 189.0079, | |
| "eval_samples_per_second": 28.348, | |
| "eval_steps_per_second": 3.545, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.011315417256011316, | |
| "grad_norm": 3.151252269744873, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 0.2044, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.012258368694012258, | |
| "grad_norm": 4.713849067687988, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 0.1608, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.012572685840012573, | |
| "eval_loss": 0.2181444615125656, | |
| "eval_runtime": 189.1182, | |
| "eval_samples_per_second": 28.331, | |
| "eval_steps_per_second": 3.543, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.013201320132013201, | |
| "grad_norm": 5.960506916046143, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.2082, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.014144271570014143, | |
| "grad_norm": 5.334136962890625, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.2383, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.014144271570014143, | |
| "eval_loss": 0.21025989949703217, | |
| "eval_runtime": 189.1168, | |
| "eval_samples_per_second": 28.332, | |
| "eval_steps_per_second": 3.543, | |
| "step": 45 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.822849014693888e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |