| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.32981530343007914, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.989006156552331e-05, | |
| "loss": 1.8193, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.978012313104662e-05, | |
| "loss": 1.7656, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.967018469656992e-05, | |
| "loss": 1.7573, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.956024626209323e-05, | |
| "loss": 1.6758, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.9450307827616535e-05, | |
| "loss": 1.5776, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.934036939313985e-05, | |
| "loss": 1.615, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.9230430958663146e-05, | |
| "loss": 1.5378, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.912049252418646e-05, | |
| "loss": 1.6188, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.901055408970976e-05, | |
| "loss": 1.5489, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.8900615655233075e-05, | |
| "loss": 1.5724, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.879067722075638e-05, | |
| "loss": 1.5262, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.8680738786279686e-05, | |
| "loss": 1.5224, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.857080035180299e-05, | |
| "loss": 1.5176, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.84608619173263e-05, | |
| "loss": 1.5263, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.835092348284961e-05, | |
| "loss": 1.5832, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.824098504837291e-05, | |
| "loss": 1.5403, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.813104661389622e-05, | |
| "loss": 1.5689, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.802110817941953e-05, | |
| "loss": 1.5389, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.7911169744942836e-05, | |
| "loss": 1.5593, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.780123131046614e-05, | |
| "loss": 1.52, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.7691292875989446e-05, | |
| "loss": 1.6009, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.758135444151275e-05, | |
| "loss": 1.5612, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.7471416007036063e-05, | |
| "loss": 1.5532, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.736147757255937e-05, | |
| "loss": 1.5636, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.7251539138082674e-05, | |
| "loss": 1.56, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.714160070360598e-05, | |
| "loss": 1.5406, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.703166226912929e-05, | |
| "loss": 1.4851, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.6921723834652596e-05, | |
| "loss": 1.5333, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.681178540017591e-05, | |
| "loss": 1.5684, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.670184696569921e-05, | |
| "loss": 1.5636, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.659190853122252e-05, | |
| "loss": 1.5434, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.6481970096745824e-05, | |
| "loss": 1.5002, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.6372031662269136e-05, | |
| "loss": 1.5413, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.6262093227792435e-05, | |
| "loss": 1.5275, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.615215479331575e-05, | |
| "loss": 1.508, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.604221635883905e-05, | |
| "loss": 1.5033, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.593227792436236e-05, | |
| "loss": 1.5416, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.582233948988567e-05, | |
| "loss": 1.5092, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.5712401055408974e-05, | |
| "loss": 1.5605, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.560246262093228e-05, | |
| "loss": 1.5624, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.5492524186455585e-05, | |
| "loss": 1.5394, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.53825857519789e-05, | |
| "loss": 1.476, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.52726473175022e-05, | |
| "loss": 1.5367, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.516270888302551e-05, | |
| "loss": 1.5041, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.505277044854881e-05, | |
| "loss": 1.5342, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.4942832014072125e-05, | |
| "loss": 1.5068, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.483289357959543e-05, | |
| "loss": 1.4912, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.4722955145118735e-05, | |
| "loss": 1.4893, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.461301671064204e-05, | |
| "loss": 1.5338, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 4.450307827616535e-05, | |
| "loss": 1.5258, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 4548, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 3.1601241096192e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |