| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 392, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.1024, |
| "grad_norm": 0.6643874645233154, |
| "learning_rate": 3.8000000000000005e-06, |
| "loss": 6.914890289306641, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.2048, |
| "grad_norm": 0.6963622570037842, |
| "learning_rate": 7.800000000000002e-06, |
| "loss": 6.9171875, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.3072, |
| "grad_norm": 0.6798524260520935, |
| "learning_rate": 9.736842105263159e-06, |
| "loss": 6.913761901855469, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.4096, |
| "grad_norm": 0.5872651934623718, |
| "learning_rate": 9.152046783625732e-06, |
| "loss": 6.889324188232422, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.512, |
| "grad_norm": 0.6345335245132446, |
| "learning_rate": 8.567251461988305e-06, |
| "loss": 6.8931327819824215, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.6144, |
| "grad_norm": 0.672644853591919, |
| "learning_rate": 7.982456140350877e-06, |
| "loss": 6.873789978027344, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.7168, |
| "grad_norm": 0.6409351229667664, |
| "learning_rate": 7.397660818713451e-06, |
| "loss": 6.862256622314453, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.8192, |
| "grad_norm": 0.7224740982055664, |
| "learning_rate": 6.812865497076025e-06, |
| "loss": 6.871943664550781, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.9216, |
| "grad_norm": 0.8125230669975281, |
| "learning_rate": 6.2280701754385975e-06, |
| "loss": 6.865367889404297, |
| "step": 180 |
| }, |
| { |
| "epoch": 1.02048, |
| "grad_norm": 0.7702969908714294, |
| "learning_rate": 5.64327485380117e-06, |
| "loss": 6.855899810791016, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.12288, |
| "grad_norm": 0.591278076171875, |
| "learning_rate": 5.058479532163744e-06, |
| "loss": 6.86078109741211, |
| "step": 220 |
| }, |
| { |
| "epoch": 1.22528, |
| "grad_norm": 0.5725053548812866, |
| "learning_rate": 4.473684210526316e-06, |
| "loss": 6.845599365234375, |
| "step": 240 |
| }, |
| { |
| "epoch": 1.32768, |
| "grad_norm": 0.5741755962371826, |
| "learning_rate": 3.88888888888889e-06, |
| "loss": 6.850102233886719, |
| "step": 260 |
| }, |
| { |
| "epoch": 1.43008, |
| "grad_norm": 0.5692065358161926, |
| "learning_rate": 3.3040935672514624e-06, |
| "loss": 6.841368865966797, |
| "step": 280 |
| }, |
| { |
| "epoch": 1.53248, |
| "grad_norm": 0.7679271697998047, |
| "learning_rate": 2.7192982456140356e-06, |
| "loss": 6.853921508789062, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.6348799999999999, |
| "grad_norm": 0.5517163872718811, |
| "learning_rate": 2.1345029239766084e-06, |
| "loss": 6.8445579528808596, |
| "step": 320 |
| }, |
| { |
| "epoch": 1.7372800000000002, |
| "grad_norm": 0.5690770745277405, |
| "learning_rate": 1.5497076023391812e-06, |
| "loss": 6.840210723876953, |
| "step": 340 |
| }, |
| { |
| "epoch": 1.83968, |
| "grad_norm": 0.5253134965896606, |
| "learning_rate": 9.649122807017545e-07, |
| "loss": 6.8394020080566404, |
| "step": 360 |
| }, |
| { |
| "epoch": 1.94208, |
| "grad_norm": 0.5329280495643616, |
| "learning_rate": 3.801169590643275e-07, |
| "loss": 6.830560302734375, |
| "step": 380 |
| } |
| ], |
| "logging_steps": 20, |
| "max_steps": 392, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 174622256922624.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
