| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.005173038125290984, | |
| "eval_steps": 9, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.173038125290983e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2304.9189, | |
| "eval_samples_per_second": 14.125, | |
| "eval_steps_per_second": 1.766, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001551911437587295, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000310382287517459, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00046557343127618853, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00046557343127618853, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2305.6529, | |
| "eval_samples_per_second": 14.121, | |
| "eval_steps_per_second": 1.765, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.000620764575034918, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.993910125649561e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0007759557187936475, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.962019382530521e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0009311468625523771, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.9031542398457974e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0009311468625523771, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2305.9209, | |
| "eval_samples_per_second": 14.119, | |
| "eval_steps_per_second": 1.765, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0010863380063111064, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.817959636416969e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.001241529150069836, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.707368982147318e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0013967202938285656, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.572593931387604e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0013967202938285656, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2306.1048, | |
| "eval_samples_per_second": 14.118, | |
| "eval_steps_per_second": 1.765, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.001551911437587295, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.415111107797445e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0017071025813460245, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2366459261474933e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0018622937251047541, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.039153688314145e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0018622937251047541, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2305.7764, | |
| "eval_samples_per_second": 14.12, | |
| "eval_steps_per_second": 1.765, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0020174848688634837, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.824798160583012e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.002172676012622213, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5959278669726935e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0023278671563809424, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.355050358314172e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0023278671563809424, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2306.1177, | |
| "eval_samples_per_second": 14.118, | |
| "eval_steps_per_second": 1.765, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.002483058300139672, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.104804738999169e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0026382494438984016, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8479327524001636e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.002793440587657131, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.587248741756253e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.002793440587657131, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2305.2813, | |
| "eval_samples_per_second": 14.123, | |
| "eval_steps_per_second": 1.766, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.0029486317314158603, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3256088156396868e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.00310382287517459, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0658795558326743e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0032590140189333195, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8109066104575023e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.0032590140189333195, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2305.4081, | |
| "eval_samples_per_second": 14.122, | |
| "eval_steps_per_second": 1.765, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.003414205162692049, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.56348351646022e-05, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.0035693963064507787, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3263210930352737e-05, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.0037245874502095083, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1020177413231334e-05, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.0037245874502095083, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2304.8244, | |
| "eval_samples_per_second": 14.126, | |
| "eval_steps_per_second": 1.766, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.0038797785939682374, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.930309757836517e-06, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.004034969737726967, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.016504991533726e-06, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.004190160881485696, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.299731159831953e-06, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.004190160881485696, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2305.7848, | |
| "eval_samples_per_second": 14.12, | |
| "eval_steps_per_second": 1.765, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.004345352025244426, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.798797596089351e-06, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.004500543169003155, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5301488425208296e-06, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.004655734312761885, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5076844803522922e-06, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.004655734312761885, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2304.7575, | |
| "eval_samples_per_second": 14.126, | |
| "eval_steps_per_second": 1.766, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0048109254565206145, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.426068431000882e-07, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.004966116600279344, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4329828146074095e-07, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.005121307744038074, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.522932452260595e-08, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.005121307744038074, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2305.688, | |
| "eval_samples_per_second": 14.121, | |
| "eval_steps_per_second": 1.765, | |
| "step": 99 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.306917209112576e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |