| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 5, | |
| "global_step": 2588, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.019319938176197836, | |
| "grad_norm": 0.00098650180734694, | |
| "learning_rate": 0.009615384615384616, | |
| "loss": 0.9907, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03863987635239567, | |
| "grad_norm": 0.000779022928327322, | |
| "learning_rate": 0.019230769230769232, | |
| "loss": 0.9647, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.05795981452859351, | |
| "grad_norm": 0.000611725845374167, | |
| "learning_rate": 0.028846153846153844, | |
| "loss": 0.9412, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.07727975270479134, | |
| "grad_norm": 0.0005838441429659724, | |
| "learning_rate": 0.029457236842105262, | |
| "loss": 0.9322, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.09659969088098919, | |
| "grad_norm": 0.0007691067876294255, | |
| "learning_rate": 0.028840460526315788, | |
| "loss": 0.9131, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.11591962905718702, | |
| "grad_norm": 0.0005935626104474068, | |
| "learning_rate": 0.028223684210526314, | |
| "loss": 0.9104, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.13523956723338484, | |
| "grad_norm": 0.0006890599033795297, | |
| "learning_rate": 0.02760690789473684, | |
| "loss": 0.9214, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.1545595054095827, | |
| "grad_norm": 0.0006042916793376207, | |
| "learning_rate": 0.02699013157894737, | |
| "loss": 0.9, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.17387944358578053, | |
| "grad_norm": 0.0005447549629025161, | |
| "learning_rate": 0.026373355263157892, | |
| "loss": 0.9097, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.19319938176197837, | |
| "grad_norm": 0.0004888740368187428, | |
| "learning_rate": 0.02575657894736842, | |
| "loss": 0.9037, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.2125193199381762, | |
| "grad_norm": 0.0008238813607022166, | |
| "learning_rate": 0.025139802631578945, | |
| "loss": 0.899, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.23183925811437403, | |
| "grad_norm": 0.000727724633179605, | |
| "learning_rate": 0.024523026315789474, | |
| "loss": 0.923, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.2511591962905719, | |
| "grad_norm": 0.0005605846527032554, | |
| "learning_rate": 0.02390625, | |
| "loss": 0.9031, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.2704791344667697, | |
| "grad_norm": 0.0007705381722189486, | |
| "learning_rate": 0.023289473684210523, | |
| "loss": 0.9013, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.28979907264296756, | |
| "grad_norm": 0.0007164838025346398, | |
| "learning_rate": 0.022672697368421053, | |
| "loss": 0.8971, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.3091190108191654, | |
| "grad_norm": 0.000717374321538955, | |
| "learning_rate": 0.02205592105263158, | |
| "loss": 0.8866, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.3284389489953632, | |
| "grad_norm": 0.0006394012016244233, | |
| "learning_rate": 0.021439144736842105, | |
| "loss": 0.899, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.34775888717156106, | |
| "grad_norm": 0.0006252205348573625, | |
| "learning_rate": 0.02082236842105263, | |
| "loss": 0.894, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.3670788253477589, | |
| "grad_norm": 0.0006903470493853092, | |
| "learning_rate": 0.020205592105263157, | |
| "loss": 0.8858, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.38639876352395675, | |
| "grad_norm": 0.0008341589127667248, | |
| "learning_rate": 0.019588815789473683, | |
| "loss": 0.9168, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.40571870170015456, | |
| "grad_norm": 0.0005771280848421156, | |
| "learning_rate": 0.01897203947368421, | |
| "loss": 0.9117, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.4250386398763524, | |
| "grad_norm": 0.000522978079970926, | |
| "learning_rate": 0.018355263157894736, | |
| "loss": 0.8939, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.44435857805255025, | |
| "grad_norm": 0.0005450574099086225, | |
| "learning_rate": 0.017738486842105265, | |
| "loss": 0.9049, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.46367851622874806, | |
| "grad_norm": 0.0005660468013957143, | |
| "learning_rate": 0.017121710526315788, | |
| "loss": 0.8944, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.48299845440494593, | |
| "grad_norm": 0.0006663696258328855, | |
| "learning_rate": 0.016504934210526314, | |
| "loss": 0.8971, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.5023183925811437, | |
| "grad_norm": 0.0005968479672446847, | |
| "learning_rate": 0.01588815789473684, | |
| "loss": 0.8917, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.5216383307573416, | |
| "grad_norm": 0.0007491153082810342, | |
| "learning_rate": 0.01527138157894737, | |
| "loss": 0.8829, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.5409582689335394, | |
| "grad_norm": 0.0006275599589571357, | |
| "learning_rate": 0.014654605263157894, | |
| "loss": 0.9058, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.5602782071097373, | |
| "grad_norm": 0.0007617810624651611, | |
| "learning_rate": 0.01403782894736842, | |
| "loss": 0.9051, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.5795981452859351, | |
| "grad_norm": 0.0006214394234120846, | |
| "learning_rate": 0.013421052631578946, | |
| "loss": 0.8879, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.5989180834621329, | |
| "grad_norm": 0.0006560624460689723, | |
| "learning_rate": 0.012804276315789473, | |
| "loss": 0.8991, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.6182380216383307, | |
| "grad_norm": 0.0007683933363296092, | |
| "learning_rate": 0.0121875, | |
| "loss": 0.9081, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.6375579598145286, | |
| "grad_norm": 0.0005783849046565592, | |
| "learning_rate": 0.011570723684210527, | |
| "loss": 0.9067, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.6568778979907264, | |
| "grad_norm": 0.0007958198548294604, | |
| "learning_rate": 0.010953947368421053, | |
| "loss": 0.885, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.6761978361669243, | |
| "grad_norm": 0.0006095783319324255, | |
| "learning_rate": 0.010337171052631579, | |
| "loss": 0.8928, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.6955177743431221, | |
| "grad_norm": 0.000699816329870373, | |
| "learning_rate": 0.009720394736842105, | |
| "loss": 0.903, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.7148377125193199, | |
| "grad_norm": 0.0008128538611344993, | |
| "learning_rate": 0.009103618421052631, | |
| "loss": 0.9036, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.7341576506955177, | |
| "grad_norm": 0.0006495247362181544, | |
| "learning_rate": 0.008486842105263157, | |
| "loss": 0.8907, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.7534775888717156, | |
| "grad_norm": 0.0005265743238851428, | |
| "learning_rate": 0.007870065789473685, | |
| "loss": 0.8843, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.7727975270479135, | |
| "grad_norm": 0.0006601494387723505, | |
| "learning_rate": 0.0072532894736842095, | |
| "loss": 0.8925, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.7921174652241113, | |
| "grad_norm": 0.0005823367391712964, | |
| "learning_rate": 0.0066365131578947365, | |
| "loss": 0.8954, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.8114374034003091, | |
| "grad_norm": 0.0005229181842878461, | |
| "learning_rate": 0.0060197368421052635, | |
| "loss": 0.903, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.8307573415765069, | |
| "grad_norm": 0.0005145368631929159, | |
| "learning_rate": 0.00540296052631579, | |
| "loss": 0.8923, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.8500772797527048, | |
| "grad_norm": 0.0006071292445994914, | |
| "learning_rate": 0.004786184210526316, | |
| "loss": 0.8804, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.8693972179289027, | |
| "grad_norm": 0.0006730407476425171, | |
| "learning_rate": 0.004169407894736842, | |
| "loss": 0.8919, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.8887171561051005, | |
| "grad_norm": 0.0006455178954638541, | |
| "learning_rate": 0.003552631578947368, | |
| "loss": 0.896, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.9080370942812983, | |
| "grad_norm": 0.0004997382056899369, | |
| "learning_rate": 0.002935855263157895, | |
| "loss": 0.8921, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.9273570324574961, | |
| "grad_norm": 0.00045192165998741984, | |
| "learning_rate": 0.002319078947368421, | |
| "loss": 0.8839, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.9466769706336939, | |
| "grad_norm": 0.0004822098126169294, | |
| "learning_rate": 0.0017023026315789475, | |
| "loss": 0.8988, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.9659969088098919, | |
| "grad_norm": 0.0005721400957554579, | |
| "learning_rate": 0.0010855263157894736, | |
| "loss": 0.9045, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.9853168469860897, | |
| "grad_norm": 0.0005698847235180438, | |
| "learning_rate": 0.00046875, | |
| "loss": 0.893, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.8954795002937317, | |
| "eval_runtime": 1619.6937, | |
| "eval_samples_per_second": 6.391, | |
| "eval_steps_per_second": 0.799, | |
| "step": 2588 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 2588, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.394319248976609e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |