| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.27481964960494676, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013740982480247338, | |
| "eval_loss": 1.8899611234664917, | |
| "eval_runtime": 22.0595, | |
| "eval_samples_per_second": 55.577, | |
| "eval_steps_per_second": 6.981, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006870491240123669, | |
| "grad_norm": 2.9780120849609375, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3292, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.013740982480247337, | |
| "grad_norm": 2.4439384937286377, | |
| "learning_rate": 0.0001, | |
| "loss": 1.7698, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.020611473720371008, | |
| "grad_norm": 1.4311202764511108, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 1.2086, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.027481964960494674, | |
| "grad_norm": 2.142937660217285, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 1.0188, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.034352456200618345, | |
| "grad_norm": 3.1501011848449707, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 0.9032, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.041222947440742015, | |
| "grad_norm": 1.5737018585205078, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 0.6516, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04809343868086568, | |
| "grad_norm": 2.364994525909424, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 0.7806, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.05496392992098935, | |
| "grad_norm": 1.5390338897705078, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 0.5795, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06183442116111302, | |
| "grad_norm": 1.4929436445236206, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 0.5754, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06870491240123669, | |
| "grad_norm": 2.5989840030670166, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 0.5669, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06870491240123669, | |
| "eval_loss": 0.5480884313583374, | |
| "eval_runtime": 24.1912, | |
| "eval_samples_per_second": 50.68, | |
| "eval_steps_per_second": 6.366, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07557540364136035, | |
| "grad_norm": 2.0532259941101074, | |
| "learning_rate": 8.678619553365659e-05, | |
| "loss": 0.5021, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.08244589488148403, | |
| "grad_norm": 2.156156063079834, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 0.5795, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0893163861216077, | |
| "grad_norm": 1.017999529838562, | |
| "learning_rate": 8.07106356344834e-05, | |
| "loss": 0.4443, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.09618687736173136, | |
| "grad_norm": 1.5915642976760864, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 0.4859, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.10305736860185503, | |
| "grad_norm": 2.771296977996826, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 0.4962, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.1099278598419787, | |
| "grad_norm": 1.728480339050293, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 0.4257, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.11679835108210238, | |
| "grad_norm": 2.0872411727905273, | |
| "learning_rate": 6.623497346023418e-05, | |
| "loss": 0.5132, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.12366884232222604, | |
| "grad_norm": 0.9818263053894043, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 0.384, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.1305393335623497, | |
| "grad_norm": 2.6964120864868164, | |
| "learning_rate": 5.8229729514036705e-05, | |
| "loss": 0.4728, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.13740982480247338, | |
| "grad_norm": 3.166550874710083, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 0.4542, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.13740982480247338, | |
| "eval_loss": 0.4625904858112335, | |
| "eval_runtime": 27.6513, | |
| "eval_samples_per_second": 44.338, | |
| "eval_steps_per_second": 5.569, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.14428031604259706, | |
| "grad_norm": 2.974519968032837, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3985, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.1511508072827207, | |
| "grad_norm": 2.1469390392303467, | |
| "learning_rate": 4.5871032726383386e-05, | |
| "loss": 0.4927, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.15802129852284438, | |
| "grad_norm": 1.4853178262710571, | |
| "learning_rate": 4.17702704859633e-05, | |
| "loss": 0.4224, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.16489178976296806, | |
| "grad_norm": 1.9782497882843018, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 0.4623, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.1717622810030917, | |
| "grad_norm": 2.6518592834472656, | |
| "learning_rate": 3.3765026539765834e-05, | |
| "loss": 0.446, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.1786327722432154, | |
| "grad_norm": 1.3509132862091064, | |
| "learning_rate": 2.991522876735154e-05, | |
| "loss": 0.3648, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.18550326348333906, | |
| "grad_norm": 2.0251638889312744, | |
| "learning_rate": 2.6202630348146324e-05, | |
| "loss": 0.4999, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.19237375472346271, | |
| "grad_norm": 0.9267457127571106, | |
| "learning_rate": 2.2652592093878666e-05, | |
| "loss": 0.3789, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.1992442459635864, | |
| "grad_norm": 1.439977765083313, | |
| "learning_rate": 1.928936436551661e-05, | |
| "loss": 0.4423, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.20611473720371007, | |
| "grad_norm": 2.450988292694092, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 0.415, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.20611473720371007, | |
| "eval_loss": 0.4055578112602234, | |
| "eval_runtime": 21.6843, | |
| "eval_samples_per_second": 56.539, | |
| "eval_steps_per_second": 7.102, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.21298522844383375, | |
| "grad_norm": 1.2217081785202026, | |
| "learning_rate": 1.3213804466343421e-05, | |
| "loss": 0.3577, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.2198557196839574, | |
| "grad_norm": 2.6271615028381348, | |
| "learning_rate": 1.0542974530180327e-05, | |
| "loss": 0.4839, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.22672621092408107, | |
| "grad_norm": 0.8500118255615234, | |
| "learning_rate": 8.141676086873572e-06, | |
| "loss": 0.3721, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.23359670216420475, | |
| "grad_norm": 1.427514910697937, | |
| "learning_rate": 6.026312439675552e-06, | |
| "loss": 0.3955, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.2404671934043284, | |
| "grad_norm": 3.0958852767944336, | |
| "learning_rate": 4.2113336672471245e-06, | |
| "loss": 0.4093, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.24733768464445208, | |
| "grad_norm": 1.190810203552246, | |
| "learning_rate": 2.7091379149682685e-06, | |
| "loss": 0.3362, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.2542081758845757, | |
| "grad_norm": 1.97514808177948, | |
| "learning_rate": 1.5299867030334814e-06, | |
| "loss": 0.4994, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.2610786671246994, | |
| "grad_norm": 0.8746953010559082, | |
| "learning_rate": 6.819348298638839e-07, | |
| "loss": 0.2927, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.2679491583648231, | |
| "grad_norm": 1.4259588718414307, | |
| "learning_rate": 1.7077534966650766e-07, | |
| "loss": 0.4396, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.27481964960494676, | |
| "grad_norm": 3.175976276397705, | |
| "learning_rate": 0.0, | |
| "loss": 0.4409, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.27481964960494676, | |
| "eval_loss": 0.3957661986351013, | |
| "eval_runtime": 21.9144, | |
| "eval_samples_per_second": 55.945, | |
| "eval_steps_per_second": 7.027, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 200, | |
| "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": 3.040337142229238e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |