| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 625, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.016, |
| "grad_norm": 0.0, |
| "learning_rate": 7.936507936507936e-06, |
| "loss": 0.103, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.032, |
| "grad_norm": 0.24380330741405487, |
| "learning_rate": 1.5873015873015872e-05, |
| "loss": 0.1262, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.048, |
| "grad_norm": 0.1586637645959854, |
| "learning_rate": 2.380952380952381e-05, |
| "loss": 0.2298, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.064, |
| "grad_norm": 0.282357394695282, |
| "learning_rate": 3.1746031746031745e-05, |
| "loss": 0.1866, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 0.23044410347938538, |
| "learning_rate": 3.968253968253968e-05, |
| "loss": 0.2232, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.096, |
| "grad_norm": 0.0, |
| "learning_rate": 4.761904761904762e-05, |
| "loss": 0.1182, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.112, |
| "grad_norm": 0.0, |
| "learning_rate": 4.9980862826611875e-05, |
| "loss": 0.1124, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.128, |
| "grad_norm": 0.37043747305870056, |
| "learning_rate": 4.988720025682995e-05, |
| "loss": 0.083, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.144, |
| "grad_norm": 0.0, |
| "learning_rate": 4.971578953735912e-05, |
| "loss": 0.0396, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 0.19477824866771698, |
| "learning_rate": 4.946716615897932e-05, |
| "loss": 0.0685, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.176, |
| "grad_norm": 0.0, |
| "learning_rate": 4.9142106826480114e-05, |
| "loss": 0.0525, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.192, |
| "grad_norm": 0.20189929008483887, |
| "learning_rate": 4.874162703221823e-05, |
| "loss": 0.0684, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.208, |
| "grad_norm": 0.2944314181804657, |
| "learning_rate": 4.8266977883697515e-05, |
| "loss": 0.0693, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.224, |
| "grad_norm": 0.0, |
| "learning_rate": 4.771964219508222e-05, |
| "loss": 0.0621, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 0.0, |
| "learning_rate": 4.710132985485355e-05, |
| "loss": 0.0185, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.256, |
| "grad_norm": 0.0, |
| "learning_rate": 4.6413972484081216e-05, |
| "loss": 0.0492, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.272, |
| "grad_norm": 0.18733273446559906, |
| "learning_rate": 4.5659717401997655e-05, |
| "loss": 0.0541, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.288, |
| "grad_norm": 0.0, |
| "learning_rate": 4.4840920917726426e-05, |
| "loss": 0.0409, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.304, |
| "grad_norm": 0.16774742305278778, |
| "learning_rate": 4.396014096912182e-05, |
| "loss": 0.0752, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 0.2138904631137848, |
| "learning_rate": 4.302012913171584e-05, |
| "loss": 0.0634, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.336, |
| "grad_norm": 0.16526997089385986, |
| "learning_rate": 4.2023822022737016e-05, |
| "loss": 0.0814, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.352, |
| "grad_norm": 0.0, |
| "learning_rate": 4.0974332127054914e-05, |
| "loss": 0.0329, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.368, |
| "grad_norm": 0.19396360218524933, |
| "learning_rate": 3.9874938073710336e-05, |
| "loss": 0.0575, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.384, |
| "grad_norm": 0.16870930790901184, |
| "learning_rate": 3.872907439340758e-05, |
| "loss": 0.0532, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.18818065524101257, |
| "learning_rate": 3.75403207889666e-05, |
| "loss": 0.0422, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.416, |
| "grad_norm": 0.2430911660194397, |
| "learning_rate": 3.631239095225417e-05, |
| "loss": 0.0733, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.432, |
| "grad_norm": 0.17143367230892181, |
| "learning_rate": 3.504912096253061e-05, |
| "loss": 0.059, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.448, |
| "grad_norm": 0.19384104013442993, |
| "learning_rate": 3.375445730245546e-05, |
| "loss": 0.0717, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.464, |
| "grad_norm": 0.0, |
| "learning_rate": 3.243244452919072e-05, |
| "loss": 0.0457, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 0.2219766527414322, |
| "learning_rate": 3.108721263911706e-05, |
| "loss": 0.0607, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.496, |
| "grad_norm": 0.0, |
| "learning_rate": 2.9722964165636264e-05, |
| "loss": 0.062, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.512, |
| "grad_norm": 0.2979666292667389, |
| "learning_rate": 2.8343961050366275e-05, |
| "loss": 0.0567, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.528, |
| "grad_norm": 0.2317102998495102, |
| "learning_rate": 2.695451132874385e-05, |
| "loss": 0.0493, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.544, |
| "grad_norm": 0.255515992641449, |
| "learning_rate": 2.5558955671628965e-05, |
| "loss": 0.029, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.56, |
| "grad_norm": 0.25291353464126587, |
| "learning_rate": 2.416165382495565e-05, |
| "loss": 0.0612, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.576, |
| "grad_norm": 0.0, |
| "learning_rate": 2.2766970989791696e-05, |
| "loss": 0.0281, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.592, |
| "grad_norm": 0.0, |
| "learning_rate": 2.1379264185356544e-05, |
| "loss": 0.0261, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.608, |
| "grad_norm": 0.3032894432544708, |
| "learning_rate": 2.000286863759934e-05, |
| "loss": 0.034, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.624, |
| "grad_norm": 0.27459245920181274, |
| "learning_rate": 1.8642084235859765e-05, |
| "loss": 0.0536, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 0.0, |
| "learning_rate": 1.7301162099921013e-05, |
| "loss": 0.0276, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.656, |
| "grad_norm": 0.0, |
| "learning_rate": 1.5984291299420117e-05, |
| "loss": 0.0536, |
| "step": 410 |
| }, |
| { |
| "epoch": 0.672, |
| "grad_norm": 0.0, |
| "learning_rate": 1.4695585767104092e-05, |
| "loss": 0.039, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.688, |
| "grad_norm": 0.0, |
| "learning_rate": 1.3439071446815452e-05, |
| "loss": 0.0548, |
| "step": 430 |
| }, |
| { |
| "epoch": 0.704, |
| "grad_norm": 0.18401296436786652, |
| "learning_rate": 1.2218673716356919e-05, |
| "loss": 0.0259, |
| "step": 440 |
| }, |
| { |
| "epoch": 0.72, |
| "grad_norm": 0.0, |
| "learning_rate": 1.103820512452661e-05, |
| "loss": 0.0562, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.736, |
| "grad_norm": 0.27832138538360596, |
| "learning_rate": 9.901353480633468e-06, |
| "loss": 0.0784, |
| "step": 460 |
| }, |
| { |
| "epoch": 0.752, |
| "grad_norm": 0.3106365203857422, |
| "learning_rate": 8.811670333701544e-06, |
| "loss": 0.0416, |
| "step": 470 |
| }, |
| { |
| "epoch": 0.768, |
| "grad_norm": 0.0, |
| "learning_rate": 7.77255987735434e-06, |
| "loss": 0.0327, |
| "step": 480 |
| }, |
| { |
| "epoch": 0.784, |
| "grad_norm": 0.19409137964248657, |
| "learning_rate": 6.787268315040604e-06, |
| "loss": 0.0695, |
| "step": 490 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.0, |
| "learning_rate": 5.8588737188248285e-06, |
| "loss": 0.0474, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.816, |
| "grad_norm": 0.0, |
| "learning_rate": 4.9902764134238165e-06, |
| "loss": 0.0434, |
| "step": 510 |
| }, |
| { |
| "epoch": 0.832, |
| "grad_norm": 0.22170156240463257, |
| "learning_rate": 4.184189915529796e-06, |
| "loss": 0.0694, |
| "step": 520 |
| }, |
| { |
| "epoch": 0.848, |
| "grad_norm": 0.3862822651863098, |
| "learning_rate": 3.443132456725817e-06, |
| "loss": 0.0396, |
| "step": 530 |
| }, |
| { |
| "epoch": 0.864, |
| "grad_norm": 0.0, |
| "learning_rate": 2.769419116476052e-06, |
| "loss": 0.0484, |
| "step": 540 |
| }, |
| { |
| "epoch": 0.88, |
| "grad_norm": 0.0, |
| "learning_rate": 2.165154589767651e-06, |
| "loss": 0.0598, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.896, |
| "grad_norm": 0.24787913262844086, |
| "learning_rate": 1.632226611998322e-06, |
| "loss": 0.0469, |
| "step": 560 |
| }, |
| { |
| "epoch": 0.912, |
| "grad_norm": 0.0, |
| "learning_rate": 1.1723000616502167e-06, |
| "loss": 0.0464, |
| "step": 570 |
| }, |
| { |
| "epoch": 0.928, |
| "grad_norm": 0.0, |
| "learning_rate": 7.868117591737583e-07, |
| "loss": 0.0571, |
| "step": 580 |
| }, |
| { |
| "epoch": 0.944, |
| "grad_norm": 0.2985147535800934, |
| "learning_rate": 4.769659783295383e-07, |
| "loss": 0.0645, |
| "step": 590 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 0.0, |
| "learning_rate": 2.4373068401120356e-07, |
| "loss": 0.0473, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.976, |
| "grad_norm": 0.1989932507276535, |
| "learning_rate": 8.783450830224249e-08, |
| "loss": 0.0658, |
| "step": 610 |
| }, |
| { |
| "epoch": 0.992, |
| "grad_norm": 0.25899210572242737, |
| "learning_rate": 9.764474213677654e-09, |
| "loss": 0.0438, |
| "step": 620 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 625, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 1000, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 7.713640389083136e+16, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
