| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 350, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.014285714285714285, |
| "grad_norm": 24.125, |
| "learning_rate": 9.789843888706694e-07, |
| "loss": 2.3634, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.02857142857142857, |
| "grad_norm": 12.5, |
| "learning_rate": 2.202714874959006e-06, |
| "loss": 2.2737, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.04285714285714286, |
| "grad_norm": 10.125, |
| "learning_rate": 3.4264453610473433e-06, |
| "loss": 2.2243, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.05714285714285714, |
| "grad_norm": 6.1875, |
| "learning_rate": 4.6501758471356796e-06, |
| "loss": 2.1777, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.07142857142857142, |
| "grad_norm": 7.90625, |
| "learning_rate": 5.873906333224017e-06, |
| "loss": 2.1515, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.08571428571428572, |
| "grad_norm": 5.8125, |
| "learning_rate": 7.097636819312354e-06, |
| "loss": 2.1361, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 4.875, |
| "learning_rate": 8.32136730540069e-06, |
| "loss": 2.1371, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.11428571428571428, |
| "grad_norm": 5.15625, |
| "learning_rate": 8.565867214444041e-06, |
| "loss": 2.1394, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.12857142857142856, |
| "grad_norm": 5.71875, |
| "learning_rate": 8.564867139659044e-06, |
| "loss": 2.1553, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.14285714285714285, |
| "grad_norm": 6.78125, |
| "learning_rate": 8.563098030832528e-06, |
| "loss": 2.135, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.15714285714285714, |
| "grad_norm": 6.9375, |
| "learning_rate": 8.560560311659701e-06, |
| "loss": 2.1494, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.17142857142857143, |
| "grad_norm": 6.09375, |
| "learning_rate": 8.557254589915187e-06, |
| "loss": 2.1446, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.18571428571428572, |
| "grad_norm": 5.1875, |
| "learning_rate": 8.553181657307465e-06, |
| "loss": 2.1517, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 5.125, |
| "learning_rate": 8.548342489289255e-06, |
| "loss": 2.12, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.21428571428571427, |
| "grad_norm": 4.875, |
| "learning_rate": 8.542738244823914e-06, |
| "loss": 2.1737, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.22857142857142856, |
| "grad_norm": 5.5625, |
| "learning_rate": 8.53637026610785e-06, |
| "loss": 2.1496, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.22857142857142856, |
| "eval_loss": 2.1535961627960205, |
| "eval_runtime": 1.2567, |
| "eval_samples_per_second": 16.71, |
| "eval_steps_per_second": 8.753, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.24285714285714285, |
| "grad_norm": 5.09375, |
| "learning_rate": 8.529240078249084e-06, |
| "loss": 2.1308, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.2571428571428571, |
| "grad_norm": 5.3125, |
| "learning_rate": 8.521349388901986e-06, |
| "loss": 2.1588, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.2714285714285714, |
| "grad_norm": 4.59375, |
| "learning_rate": 8.512700087858303e-06, |
| "loss": 2.144, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.2857142857142857, |
| "grad_norm": 4.8125, |
| "learning_rate": 8.503294246594551e-06, |
| "loss": 2.1222, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 4.8125, |
| "learning_rate": 8.493134117775916e-06, |
| "loss": 2.1261, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.3142857142857143, |
| "grad_norm": 4.9375, |
| "learning_rate": 8.482222134716743e-06, |
| "loss": 2.1477, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.32857142857142857, |
| "grad_norm": 5.21875, |
| "learning_rate": 8.470560910797759e-06, |
| "loss": 2.16, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.34285714285714286, |
| "grad_norm": 5.09375, |
| "learning_rate": 8.458153238840195e-06, |
| "loss": 2.1347, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.35714285714285715, |
| "grad_norm": 5.375, |
| "learning_rate": 8.445002090436896e-06, |
| "loss": 2.1438, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.37142857142857144, |
| "grad_norm": 5.53125, |
| "learning_rate": 8.431110615240647e-06, |
| "loss": 2.1603, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.38571428571428573, |
| "grad_norm": 5.0, |
| "learning_rate": 8.416482140209844e-06, |
| "loss": 2.1381, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 4.875, |
| "learning_rate": 8.401120168811687e-06, |
| "loss": 2.1386, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.4142857142857143, |
| "grad_norm": 5.21875, |
| "learning_rate": 8.385028380183127e-06, |
| "loss": 2.1461, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.42857142857142855, |
| "grad_norm": 4.9375, |
| "learning_rate": 8.368210628249719e-06, |
| "loss": 2.1229, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.44285714285714284, |
| "grad_norm": 4.8125, |
| "learning_rate": 8.350670940802612e-06, |
| "loss": 2.1335, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.45714285714285713, |
| "grad_norm": 5.3125, |
| "learning_rate": 8.33241351853393e-06, |
| "loss": 2.1415, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.4714285714285714, |
| "grad_norm": 4.71875, |
| "learning_rate": 8.313442734030699e-06, |
| "loss": 2.1261, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.4857142857142857, |
| "grad_norm": 5.65625, |
| "learning_rate": 8.293763130727635e-06, |
| "loss": 2.1244, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 4.5625, |
| "learning_rate": 8.273379421819017e-06, |
| "loss": 2.1322, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.5142857142857142, |
| "grad_norm": 4.65625, |
| "learning_rate": 8.252296489129878e-06, |
| "loss": 2.1575, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.5285714285714286, |
| "grad_norm": 5.0, |
| "learning_rate": 8.230519381946843e-06, |
| "loss": 2.1194, |
| "step": 185 |
| }, |
| { |
| "epoch": 0.5428571428571428, |
| "grad_norm": 4.625, |
| "learning_rate": 8.208053315808828e-06, |
| "loss": 2.1232, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.5571428571428572, |
| "grad_norm": 4.6875, |
| "learning_rate": 8.184903671257942e-06, |
| "loss": 2.1226, |
| "step": 195 |
| }, |
| { |
| "epoch": 0.5714285714285714, |
| "grad_norm": 4.8125, |
| "learning_rate": 8.161075992550872e-06, |
| "loss": 2.1488, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.5857142857142857, |
| "grad_norm": 4.59375, |
| "learning_rate": 8.136575986331045e-06, |
| "loss": 2.1211, |
| "step": 205 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 4.75, |
| "learning_rate": 8.111409520261913e-06, |
| "loss": 2.1438, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.6142857142857143, |
| "grad_norm": 5.0625, |
| "learning_rate": 8.08558262162167e-06, |
| "loss": 2.1282, |
| "step": 215 |
| }, |
| { |
| "epoch": 0.6285714285714286, |
| "grad_norm": 4.71875, |
| "learning_rate": 8.059101475859732e-06, |
| "loss": 2.1188, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.6428571428571429, |
| "grad_norm": 4.90625, |
| "learning_rate": 8.03197242511535e-06, |
| "loss": 2.1411, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.6571428571428571, |
| "grad_norm": 4.84375, |
| "learning_rate": 8.0042019666987e-06, |
| "loss": 2.1477, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.6714285714285714, |
| "grad_norm": 4.90625, |
| "learning_rate": 7.975796751534778e-06, |
| "loss": 2.1519, |
| "step": 235 |
| }, |
| { |
| "epoch": 0.6857142857142857, |
| "grad_norm": 4.84375, |
| "learning_rate": 7.946763582570545e-06, |
| "loss": 2.1364, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.7, |
| "grad_norm": 4.28125, |
| "learning_rate": 7.917109413145643e-06, |
| "loss": 2.1108, |
| "step": 245 |
| }, |
| { |
| "epoch": 0.7142857142857143, |
| "grad_norm": 5.0625, |
| "learning_rate": 7.88684134532709e-06, |
| "loss": 2.149, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.7285714285714285, |
| "grad_norm": 4.96875, |
| "learning_rate": 7.855966628208364e-06, |
| "loss": 2.1453, |
| "step": 255 |
| }, |
| { |
| "epoch": 0.7428571428571429, |
| "grad_norm": 5.0, |
| "learning_rate": 7.824492656173272e-06, |
| "loss": 2.1271, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.7571428571428571, |
| "grad_norm": 4.40625, |
| "learning_rate": 7.792426967125019e-06, |
| "loss": 2.1301, |
| "step": 265 |
| }, |
| { |
| "epoch": 0.7714285714285715, |
| "grad_norm": 5.03125, |
| "learning_rate": 7.759777240680905e-06, |
| "loss": 2.1464, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.7857142857142857, |
| "grad_norm": 4.6875, |
| "learning_rate": 7.726551296333093e-06, |
| "loss": 2.1404, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 4.6875, |
| "learning_rate": 7.692757091575864e-06, |
| "loss": 2.1292, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.8142857142857143, |
| "grad_norm": 4.71875, |
| "learning_rate": 7.658402719999816e-06, |
| "loss": 2.1242, |
| "step": 285 |
| }, |
| { |
| "epoch": 0.8285714285714286, |
| "grad_norm": 4.5625, |
| "learning_rate": 7.6234964093534964e-06, |
| "loss": 2.1357, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.8428571428571429, |
| "grad_norm": 4.625, |
| "learning_rate": 7.588046519572876e-06, |
| "loss": 2.1187, |
| "step": 295 |
| }, |
| { |
| "epoch": 0.8571428571428571, |
| "grad_norm": 4.9375, |
| "learning_rate": 7.55206154077917e-06, |
| "loss": 2.1289, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.8714285714285714, |
| "grad_norm": 4.625, |
| "learning_rate": 7.515550091245495e-06, |
| "loss": 2.1067, |
| "step": 305 |
| }, |
| { |
| "epoch": 0.8857142857142857, |
| "grad_norm": 4.875, |
| "learning_rate": 7.4785209153328105e-06, |
| "loss": 2.1358, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 4.78125, |
| "learning_rate": 7.440982881395693e-06, |
| "loss": 2.1356, |
| "step": 315 |
| }, |
| { |
| "epoch": 0.9142857142857143, |
| "grad_norm": 4.5625, |
| "learning_rate": 7.402944979658378e-06, |
| "loss": 2.1308, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.9285714285714286, |
| "grad_norm": 4.375, |
| "learning_rate": 7.364416320061651e-06, |
| "loss": 2.1369, |
| "step": 325 |
| }, |
| { |
| "epoch": 0.9428571428571428, |
| "grad_norm": 4.84375, |
| "learning_rate": 7.325406130081036e-06, |
| "loss": 2.1334, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.9571428571428572, |
| "grad_norm": 4.59375, |
| "learning_rate": 7.285923752516855e-06, |
| "loss": 2.1321, |
| "step": 335 |
| }, |
| { |
| "epoch": 0.9714285714285714, |
| "grad_norm": 4.3125, |
| "learning_rate": 7.2459786432566614e-06, |
| "loss": 2.1186, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.9857142857142858, |
| "grad_norm": 5.25, |
| "learning_rate": 7.205580369010584e-06, |
| "loss": 2.1272, |
| "step": 345 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 4.71875, |
| "learning_rate": 7.16473860502014e-06, |
| "loss": 2.126, |
| "step": 350 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 2.140592098236084, |
| "eval_runtime": 1.248, |
| "eval_samples_per_second": 16.828, |
| "eval_steps_per_second": 8.814, |
| "step": 350 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 1050, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.7125675286659072e+18, |
| "train_batch_size": 28, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
