| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.96, | |
| "eval_steps": 3, | |
| "global_step": 12, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.08304641395807266, | |
| "learning_rate": 2e-05, | |
| "loss": 1.1343, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 1.0222772359848022, | |
| "eval_runtime": 6.5157, | |
| "eval_samples_per_second": 15.348, | |
| "eval_steps_per_second": 7.674, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.0838785395026207, | |
| "learning_rate": 4e-05, | |
| "loss": 1.0846, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.07938167452812195, | |
| "learning_rate": 6e-05, | |
| "loss": 1.0763, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 1.020249366760254, | |
| "eval_runtime": 6.4724, | |
| "eval_samples_per_second": 15.45, | |
| "eval_steps_per_second": 7.725, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.07606283575296402, | |
| "learning_rate": 8e-05, | |
| "loss": 0.924, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.08927913010120392, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0407, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.10650104284286499, | |
| "learning_rate": 0.00012, | |
| "loss": 1.0499, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 0.9897109866142273, | |
| "eval_runtime": 6.486, | |
| "eval_samples_per_second": 15.418, | |
| "eval_steps_per_second": 7.709, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.12166950851678848, | |
| "learning_rate": 0.00014, | |
| "loss": 0.9971, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.09095977246761322, | |
| "learning_rate": 0.00016, | |
| "loss": 1.0057, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.10113804042339325, | |
| "learning_rate": 0.00018, | |
| "loss": 0.9277, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 0.9292716979980469, | |
| "eval_runtime": 6.4678, | |
| "eval_samples_per_second": 15.461, | |
| "eval_steps_per_second": 7.731, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.06278682500123978, | |
| "learning_rate": 0.0002, | |
| "loss": 0.972, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.06470202654600143, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9421, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.0588940791785717, | |
| "learning_rate": 0.0, | |
| "loss": 0.9145, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 0.9193833470344543, | |
| "eval_runtime": 6.5151, | |
| "eval_samples_per_second": 15.349, | |
| "eval_steps_per_second": 7.674, | |
| "step": 12 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 12, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 1.5777314327494656e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |