| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 4149, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.024102193299590263, | |
| "grad_norm": 0.10564957559108734, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 2.4343, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.048204386599180526, | |
| "grad_norm": 0.12436462193727493, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 2.4331, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.07230657989877079, | |
| "grad_norm": 0.17909838259220123, | |
| "learning_rate": 6e-06, | |
| "loss": 2.4138, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.09640877319836105, | |
| "grad_norm": 0.2627304196357727, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 2.4152, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.12051096649795132, | |
| "grad_norm": 0.3407520651817322, | |
| "learning_rate": 1e-05, | |
| "loss": 2.3356, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.14461315979754158, | |
| "grad_norm": 0.4051746428012848, | |
| "learning_rate": 1.2e-05, | |
| "loss": 2.2944, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.16871535309713184, | |
| "grad_norm": 0.4393845200538635, | |
| "learning_rate": 1.4e-05, | |
| "loss": 2.3165, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.1928175463967221, | |
| "grad_norm": 0.49629464745521545, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 2.3161, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.21691973969631237, | |
| "grad_norm": 0.5297220945358276, | |
| "learning_rate": 1.8e-05, | |
| "loss": 2.2482, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.24102193299590263, | |
| "grad_norm": 0.586216390132904, | |
| "learning_rate": 2e-05, | |
| "loss": 2.2301, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.26512412629549287, | |
| "grad_norm": 0.600564181804657, | |
| "learning_rate": 1.9950276214176393e-05, | |
| "loss": 2.1974, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.28922631959508316, | |
| "grad_norm": 0.6726705431938171, | |
| "learning_rate": 1.9801599347680883e-05, | |
| "loss": 2.187, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.3133285128946734, | |
| "grad_norm": 0.618769109249115, | |
| "learning_rate": 1.9555447955846792e-05, | |
| "loss": 2.1867, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.3374307061942637, | |
| "grad_norm": 0.7493981719017029, | |
| "learning_rate": 1.921426995449166e-05, | |
| "loss": 2.1705, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.3615328994938539, | |
| "grad_norm": 0.8110669255256653, | |
| "learning_rate": 1.8781458275988913e-05, | |
| "loss": 2.174, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.3856350927934442, | |
| "grad_norm": 0.7075093388557434, | |
| "learning_rate": 1.826131712737932e-05, | |
| "loss": 2.1311, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.40973728609303445, | |
| "grad_norm": 0.7727652192115784, | |
| "learning_rate": 1.7659019186077174e-05, | |
| "loss": 2.1228, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.43383947939262474, | |
| "grad_norm": 0.84642493724823, | |
| "learning_rate": 1.6980554158849546e-05, | |
| "loss": 2.1254, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.457941672692215, | |
| "grad_norm": 0.855783998966217, | |
| "learning_rate": 1.6232669215636963e-05, | |
| "loss": 2.1079, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.48204386599180526, | |
| "grad_norm": 0.7568260431289673, | |
| "learning_rate": 1.5422801890586833e-05, | |
| "loss": 2.0675, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.5061460592913956, | |
| "grad_norm": 1.03830885887146, | |
| "learning_rate": 1.4559006117582424e-05, | |
| "loss": 2.1163, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.5302482525909857, | |
| "grad_norm": 1.3009450435638428, | |
| "learning_rate": 1.3649872135826173e-05, | |
| "loss": 2.1031, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.554350445890576, | |
| "grad_norm": 0.9386299252510071, | |
| "learning_rate": 1.2704441061996842e-05, | |
| "loss": 2.0527, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.5784526391901663, | |
| "grad_norm": 0.8045169115066528, | |
| "learning_rate": 1.1732114978539648e-05, | |
| "loss": 2.0772, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.6025548324897566, | |
| "grad_norm": 0.8329111933708191, | |
| "learning_rate": 1.0742563432239503e-05, | |
| "loss": 2.0947, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.6266570257893468, | |
| "grad_norm": 0.9610249996185303, | |
| "learning_rate": 9.745627272926332e-06, | |
| "loss": 2.0799, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.6507592190889371, | |
| "grad_norm": 0.8086296319961548, | |
| "learning_rate": 8.751220788613237e-06, | |
| "loss": 2.0669, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.6748614123885274, | |
| "grad_norm": 0.8295447826385498, | |
| "learning_rate": 7.769233110309735e-06, | |
| "loss": 2.0666, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.6989636056881177, | |
| "grad_norm": 0.796343982219696, | |
| "learning_rate": 6.809429867015307e-06, | |
| "loss": 2.125, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.7230657989877078, | |
| "grad_norm": 0.9749905467033386, | |
| "learning_rate": 5.881356068910429e-06, | |
| "loss": 2.0724, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.7471679922872981, | |
| "grad_norm": 1.090606689453125, | |
| "learning_rate": 4.994241184548192e-06, | |
| "loss": 2.0116, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.7712701855868884, | |
| "grad_norm": 1.000171422958374, | |
| "learning_rate": 4.1569073560307905e-06, | |
| "loss": 2.0562, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.7953723788864787, | |
| "grad_norm": 0.9586558938026428, | |
| "learning_rate": 3.3776816649486378e-06, | |
| "loss": 2.0545, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.8194745721860689, | |
| "grad_norm": 0.949877917766571, | |
| "learning_rate": 2.6643133215760586e-06, | |
| "loss": 2.0571, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.8435767654856592, | |
| "grad_norm": 0.9553411602973938, | |
| "learning_rate": 2.0238966008568905e-06, | |
| "loss": 2.027, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.8676789587852495, | |
| "grad_norm": 0.9195176959037781, | |
| "learning_rate": 1.4628002915629202e-06, | |
| "loss": 2.0751, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.8917811520848398, | |
| "grad_norm": 0.9022210836410522, | |
| "learning_rate": 9.866043602360909e-07, | |
| "loss": 2.0573, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.91588334538443, | |
| "grad_norm": 0.7705771923065186, | |
| "learning_rate": 6.000444597762811e-07, | |
| "loss": 2.06, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.9399855386840202, | |
| "grad_norm": 1.009355902671814, | |
| "learning_rate": 3.069648345231813e-07, | |
| "loss": 2.0263, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.9640877319836105, | |
| "grad_norm": 0.9817578196525574, | |
| "learning_rate": 1.1028009017986174e-07, | |
| "loss": 2.0777, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.9881899252832008, | |
| "grad_norm": 1.0477696657180786, | |
| "learning_rate": 1.1946208766822066e-08, | |
| "loss": 2.0764, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 4149, | |
| "total_flos": 7.54868493877248e+16, | |
| "train_loss": 2.153304632613963, | |
| "train_runtime": 1112.8562, | |
| "train_samples_per_second": 7.456, | |
| "train_steps_per_second": 3.728 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 4149, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.54868493877248e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |