| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0023502867349816676, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 9.401146939926671e-05, | |
| "grad_norm": 1.1071391105651855, | |
| "learning_rate": 1e-05, | |
| "loss": 3.1216, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.401146939926671e-05, | |
| "eval_loss": 2.95656681060791, | |
| "eval_runtime": 253.1318, | |
| "eval_samples_per_second": 35.389, | |
| "eval_steps_per_second": 4.425, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00018802293879853342, | |
| "grad_norm": 0.9681172370910645, | |
| "learning_rate": 2e-05, | |
| "loss": 2.9395, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0002820344081978001, | |
| "grad_norm": 0.9034966230392456, | |
| "learning_rate": 3e-05, | |
| "loss": 2.6474, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00037604587759706683, | |
| "grad_norm": 1.0967257022857666, | |
| "learning_rate": 4e-05, | |
| "loss": 2.9769, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00047005734699633354, | |
| "grad_norm": 0.9553994536399841, | |
| "learning_rate": 5e-05, | |
| "loss": 2.889, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005640688163956002, | |
| "grad_norm": 1.050720453262329, | |
| "learning_rate": 6e-05, | |
| "loss": 2.8748, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.000658080285794867, | |
| "grad_norm": 1.073960781097412, | |
| "learning_rate": 7e-05, | |
| "loss": 2.8886, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0007520917551941337, | |
| "grad_norm": 1.1246281862258911, | |
| "learning_rate": 8e-05, | |
| "loss": 3.0083, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0008461032245934004, | |
| "grad_norm": 1.4751750230789185, | |
| "learning_rate": 9e-05, | |
| "loss": 3.011, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0008461032245934004, | |
| "eval_loss": 2.774919033050537, | |
| "eval_runtime": 252.8918, | |
| "eval_samples_per_second": 35.422, | |
| "eval_steps_per_second": 4.429, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0009401146939926671, | |
| "grad_norm": 1.148061752319336, | |
| "learning_rate": 0.0001, | |
| "loss": 2.506, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001034126163391934, | |
| "grad_norm": 1.3042597770690918, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 2.517, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0011281376327912005, | |
| "grad_norm": 1.1282496452331543, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 2.5106, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0012221491021904673, | |
| "grad_norm": 1.2557356357574463, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 2.3613, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.001316160571589734, | |
| "grad_norm": 1.1485098600387573, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 2.3087, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0014101720409890007, | |
| "grad_norm": 1.3429392576217651, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 2.293, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0015041835103882673, | |
| "grad_norm": 1.2680690288543701, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 2.0638, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0015981949797875341, | |
| "grad_norm": 1.4249025583267212, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 2.19, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0016922064491868007, | |
| "grad_norm": 1.2500929832458496, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 2.0502, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0016922064491868007, | |
| "eval_loss": 1.9111806154251099, | |
| "eval_runtime": 252.9419, | |
| "eval_samples_per_second": 35.415, | |
| "eval_steps_per_second": 4.428, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0017862179185860676, | |
| "grad_norm": 1.1099755764007568, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 1.8685, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0018802293879853342, | |
| "grad_norm": 1.2947331666946411, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.8453, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0019742408573846008, | |
| "grad_norm": 1.0603139400482178, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 1.7496, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.002068252326783868, | |
| "grad_norm": 1.1734318733215332, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.6085, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0021622637961831344, | |
| "grad_norm": 1.0922938585281372, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 1.5754, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.002256275265582401, | |
| "grad_norm": 1.184679627418518, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.6059, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0023502867349816676, | |
| "grad_norm": 1.039542555809021, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.3529, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2573421930086400.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |