| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0356808349315374, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000178404174657687, | |
| "eval_loss": 2.6956348419189453, | |
| "eval_runtime": 121.1511, | |
| "eval_samples_per_second": 19.488, | |
| "eval_steps_per_second": 9.748, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0017840417465768699, | |
| "grad_norm": 0.8038879632949829, | |
| "learning_rate": 0.0002, | |
| "loss": 2.586, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0035680834931537397, | |
| "grad_norm": 0.6148825287818909, | |
| "learning_rate": 0.0002, | |
| "loss": 2.5222, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00535212523973061, | |
| "grad_norm": 0.6672957539558411, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4343, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0071361669863074795, | |
| "grad_norm": 0.5105198621749878, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4416, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.00892020873288435, | |
| "grad_norm": 0.48815396428108215, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4968, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.00892020873288435, | |
| "eval_loss": 2.423658847808838, | |
| "eval_runtime": 119.0947, | |
| "eval_samples_per_second": 19.825, | |
| "eval_steps_per_second": 9.916, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01070425047946122, | |
| "grad_norm": 0.45994818210601807, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3763, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.012488292226038089, | |
| "grad_norm": 0.5110970139503479, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4041, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.014272333972614959, | |
| "grad_norm": 0.45207974314689636, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4428, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.01605637571919183, | |
| "grad_norm": 0.4270719587802887, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4557, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0178404174657687, | |
| "grad_norm": 0.4447726905345917, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4455, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0178404174657687, | |
| "eval_loss": 2.4130163192749023, | |
| "eval_runtime": 119.1428, | |
| "eval_samples_per_second": 19.817, | |
| "eval_steps_per_second": 9.912, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01962445921234557, | |
| "grad_norm": 0.382270872592926, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3807, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.02140850095892244, | |
| "grad_norm": 0.4022645354270935, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3739, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.02319254270549931, | |
| "grad_norm": 0.4373781681060791, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3368, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.024976584452076178, | |
| "grad_norm": 0.4900830090045929, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4286, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.026760626198653048, | |
| "grad_norm": 0.5193880200386047, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4471, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.026760626198653048, | |
| "eval_loss": 2.4094161987304688, | |
| "eval_runtime": 119.1237, | |
| "eval_samples_per_second": 19.82, | |
| "eval_steps_per_second": 9.914, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.028544667945229918, | |
| "grad_norm": 0.46581530570983887, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3928, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.030328709691806788, | |
| "grad_norm": 0.41251781582832336, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3686, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.03211275143838366, | |
| "grad_norm": 0.3910543620586395, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3908, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.03389679318496053, | |
| "grad_norm": 0.46539127826690674, | |
| "learning_rate": 0.0002, | |
| "loss": 2.407, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.0356808349315374, | |
| "grad_norm": 0.46478888392448425, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3919, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.0356808349315374, | |
| "eval_loss": 2.406040668487549, | |
| "eval_runtime": 119.1228, | |
| "eval_samples_per_second": 19.82, | |
| "eval_steps_per_second": 9.914, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.523357780934656e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |