| { |
| "best_global_step": 1000, |
| "best_metric": 0.9919272661209106, |
| "best_model_checkpoint": "./sft-out/checkpoint-1000", |
| "epoch": 1.7673352118901597, |
| "eval_steps": 500, |
| "global_step": 1000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.08840267418089397, |
| "grad_norm": 2.867945432662964, |
| "learning_rate": 9.800000000000001e-06, |
| "loss": 1.6486561584472657, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.17680534836178793, |
| "grad_norm": 2.9991917610168457, |
| "learning_rate": 1.98e-05, |
| "loss": 1.33203125, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.26520802254268194, |
| "grad_norm": 2.570798635482788, |
| "learning_rate": 1.9854078984834904e-05, |
| "loss": 1.2356742858886718, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.35361069672357587, |
| "grad_norm": 2.5860543251037598, |
| "learning_rate": 1.9408807689542257e-05, |
| "loss": 1.2118841552734374, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.44201337090446985, |
| "grad_norm": 2.117816686630249, |
| "learning_rate": 1.8677654533689287e-05, |
| "loss": 1.1767095184326173, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.5304160450853639, |
| "grad_norm": 2.276134729385376, |
| "learning_rate": 1.7682835235935236e-05, |
| "loss": 1.1405416870117187, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.6188187192662578, |
| "grad_norm": 2.2516863346099854, |
| "learning_rate": 1.645457687723951e-05, |
| "loss": 1.128560562133789, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.7072213934471517, |
| "grad_norm": 2.084246873855591, |
| "learning_rate": 1.5030199466302354e-05, |
| "loss": 1.1079308319091796, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.7956240676280457, |
| "grad_norm": 2.195765495300293, |
| "learning_rate": 1.3452981989985347e-05, |
| "loss": 1.0333491516113282, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.8840267418089397, |
| "grad_norm": 2.2488884925842285, |
| "learning_rate": 1.1770847403195836e-05, |
| "loss": 1.0508524322509765, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.8840267418089397, |
| "eval_loss": 1.025797724723816, |
| "eval_runtime": 31.5114, |
| "eval_samples_per_second": 15.867, |
| "eval_steps_per_second": 1.999, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.9724294159898337, |
| "grad_norm": 2.3597640991210938, |
| "learning_rate": 1.0034906514152239e-05, |
| "loss": 1.0521656036376954, |
| "step": 550 |
| }, |
| { |
| "epoch": 1.060113818443008, |
| "grad_norm": 2.0308382511138916, |
| "learning_rate": 8.297905008339677e-06, |
| "loss": 0.8026390075683594, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.148516492623902, |
| "grad_norm": 2.3317034244537354, |
| "learning_rate": 6.612620797547087e-06, |
| "loss": 0.6939823150634765, |
| "step": 650 |
| }, |
| { |
| "epoch": 1.2369191668047959, |
| "grad_norm": 2.5876853466033936, |
| "learning_rate": 5.030260389724447e-06, |
| "loss": 0.6835686492919922, |
| "step": 700 |
| }, |
| { |
| "epoch": 1.3253218409856897, |
| "grad_norm": 2.342280149459839, |
| "learning_rate": 3.598903005150444e-06, |
| "loss": 0.6746553039550781, |
| "step": 750 |
| }, |
| { |
| "epoch": 1.4137245151665838, |
| "grad_norm": 2.354048728942871, |
| "learning_rate": 2.362039713653581e-06, |
| "loss": 0.6704821014404296, |
| "step": 800 |
| }, |
| { |
| "epoch": 1.502127189347478, |
| "grad_norm": 2.01891827583313, |
| "learning_rate": 1.3572519804629537e-06, |
| "loss": 0.6500045776367187, |
| "step": 850 |
| }, |
| { |
| "epoch": 1.5905298635283718, |
| "grad_norm": 2.010759115219116, |
| "learning_rate": 6.150697724044407e-07, |
| "loss": 0.6556130981445313, |
| "step": 900 |
| }, |
| { |
| "epoch": 1.6789325377092656, |
| "grad_norm": 2.3100311756134033, |
| "learning_rate": 1.580439203075812e-07, |
| "loss": 0.6622157287597656, |
| "step": 950 |
| }, |
| { |
| "epoch": 1.7673352118901597, |
| "grad_norm": 2.064932346343994, |
| "learning_rate": 6.092342209607083e-11, |
| "loss": 0.6651800537109375, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.7673352118901597, |
| "eval_loss": 0.9919272661209106, |
| "eval_runtime": 31.6701, |
| "eval_samples_per_second": 15.788, |
| "eval_steps_per_second": 1.989, |
| "step": 1000 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 1000, |
| "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": 3.876769443016704e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
