| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9986130374479889, |
| "eval_steps": 500, |
| "global_step": 180, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.005547850208044383, |
| "grad_norm": 4.195843084105169, |
| "learning_rate": 1.1111111111111112e-05, |
| "loss": 1.4047, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.027739251040221916, |
| "grad_norm": 0.7369275637110823, |
| "learning_rate": 5.555555555555556e-05, |
| "loss": 1.331, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.05547850208044383, |
| "grad_norm": 0.4333227696075342, |
| "learning_rate": 0.00011111111111111112, |
| "loss": 1.2277, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.08321775312066575, |
| "grad_norm": 0.24055777481676408, |
| "learning_rate": 0.0001666666666666667, |
| "loss": 1.1721, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.11095700416088766, |
| "grad_norm": 0.21061480866876423, |
| "learning_rate": 0.00019992479525042303, |
| "loss": 1.1489, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.13869625520110956, |
| "grad_norm": 0.1977619665262726, |
| "learning_rate": 0.00019908004033648453, |
| "loss": 1.1261, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.1664355062413315, |
| "grad_norm": 0.19642061090412125, |
| "learning_rate": 0.00019730448705798239, |
| "loss": 1.1668, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.1941747572815534, |
| "grad_norm": 0.19926537287762208, |
| "learning_rate": 0.00019461481568757506, |
| "loss": 1.1308, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.22191400832177532, |
| "grad_norm": 0.18005042043286312, |
| "learning_rate": 0.0001910362940966147, |
| "loss": 1.1118, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.24965325936199723, |
| "grad_norm": 0.17482654378958667, |
| "learning_rate": 0.00018660254037844388, |
| "loss": 1.1127, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.27739251040221913, |
| "grad_norm": 0.17841493887510787, |
| "learning_rate": 0.00018135520702629675, |
| "loss": 1.0927, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.30513176144244103, |
| "grad_norm": 0.17654138755144574, |
| "learning_rate": 0.00017534358963276607, |
| "loss": 1.1281, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.332871012482663, |
| "grad_norm": 0.18093646794731982, |
| "learning_rate": 0.0001686241637868734, |
| "loss": 1.1027, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.3606102635228849, |
| "grad_norm": 0.17282395865206962, |
| "learning_rate": 0.0001612600545193203, |
| "loss": 1.0791, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.3883495145631068, |
| "grad_norm": 0.2130133899623223, |
| "learning_rate": 0.00015332044328016914, |
| "loss": 1.0707, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.4160887656033287, |
| "grad_norm": 0.17620893249441422, |
| "learning_rate": 0.00014487991802004623, |
| "loss": 1.0764, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.44382801664355065, |
| "grad_norm": 0.17824570150374044, |
| "learning_rate": 0.00013601777248047105, |
| "loss": 1.0786, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.47156726768377255, |
| "grad_norm": 0.17908199389292137, |
| "learning_rate": 0.00012681726127606376, |
| "loss": 1.075, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.49930651872399445, |
| "grad_norm": 0.16536298826240392, |
| "learning_rate": 0.00011736481776669306, |
| "loss": 1.0495, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.5270457697642164, |
| "grad_norm": 0.16772226493789477, |
| "learning_rate": 0.0001077492420671931, |
| "loss": 1.0621, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.5547850208044383, |
| "grad_norm": 0.16400769234594714, |
| "learning_rate": 9.806086682281758e-05, |
| "loss": 1.0733, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.5825242718446602, |
| "grad_norm": 0.17398111998791801, |
| "learning_rate": 8.839070858747697e-05, |
| "loss": 1.0807, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.6102635228848821, |
| "grad_norm": 0.1667519248225914, |
| "learning_rate": 7.882961277705895e-05, |
| "loss": 1.0587, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.6380027739251041, |
| "grad_norm": 0.17276811075234527, |
| "learning_rate": 6.94674002304887e-05, |
| "loss": 1.0696, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.665742024965326, |
| "grad_norm": 0.1778606830836011, |
| "learning_rate": 6.039202339608432e-05, |
| "loss": 1.0749, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.6934812760055479, |
| "grad_norm": 0.15999213488751612, |
| "learning_rate": 5.168874007033615e-05, |
| "loss": 1.0611, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.7212205270457698, |
| "grad_norm": 0.162094501109682, |
| "learning_rate": 4.343931245134616e-05, |
| "loss": 1.0655, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.7489597780859917, |
| "grad_norm": 0.16199274412290549, |
| "learning_rate": 3.5721239031346066e-05, |
| "loss": 1.0524, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.7766990291262136, |
| "grad_norm": 0.1641358791714059, |
| "learning_rate": 2.8607026544210114e-05, |
| "loss": 1.0519, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.8044382801664355, |
| "grad_norm": 0.17454488135701385, |
| "learning_rate": 2.2163508807583998e-05, |
| "loss": 1.0758, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.8321775312066574, |
| "grad_norm": 0.16940543249627216, |
| "learning_rate": 1.6451218858706374e-05, |
| "loss": 1.051, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.8599167822468793, |
| "grad_norm": 0.1699983346793352, |
| "learning_rate": 1.1523820282334219e-05, |
| "loss": 1.0548, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.8876560332871013, |
| "grad_norm": 0.16182400427483473, |
| "learning_rate": 7.427603073110967e-06, |
| "loss": 1.0578, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.9153952843273232, |
| "grad_norm": 0.16401094680605324, |
| "learning_rate": 4.20104876845111e-06, |
| "loss": 1.0958, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.9431345353675451, |
| "grad_norm": 0.1620592393374915, |
| "learning_rate": 1.874468937261531e-06, |
| "loss": 1.0457, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.970873786407767, |
| "grad_norm": 0.16185102522208447, |
| "learning_rate": 4.6972042068341714e-07, |
| "loss": 1.0434, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.9986130374479889, |
| "grad_norm": 0.16341103139774715, |
| "learning_rate": 0.0, |
| "loss": 1.0662, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.9986130374479889, |
| "eval_loss": 1.101938009262085, |
| "eval_runtime": 1905.3768, |
| "eval_samples_per_second": 3.52, |
| "eval_steps_per_second": 0.88, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.9986130374479889, |
| "step": 180, |
| "total_flos": 371612650045440.0, |
| "train_loss": 1.0954518543349372, |
| "train_runtime": 5437.2544, |
| "train_samples_per_second": 2.121, |
| "train_steps_per_second": 0.033 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 180, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 371612650045440.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
