| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.0020407746780677946, |
| "eval_steps": 10, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 4.081549356135589e-05, |
| "eval_loss": 1.783031940460205, |
| "eval_runtime": 1490.7954, |
| "eval_samples_per_second": 6.92, |
| "eval_steps_per_second": 3.46, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.00020407746780677944, |
| "grad_norm": 1.1358250379562378, |
| "learning_rate": 5e-05, |
| "loss": 1.8336, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.0004081549356135589, |
| "grad_norm": 1.4730448722839355, |
| "learning_rate": 0.0001, |
| "loss": 1.804, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.0004081549356135589, |
| "eval_loss": 1.7141697406768799, |
| "eval_runtime": 1496.0235, |
| "eval_samples_per_second": 6.896, |
| "eval_steps_per_second": 3.448, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.0006122324034203384, |
| "grad_norm": 1.3064950704574585, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 1.8378, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.0008163098712271178, |
| "grad_norm": 1.7653350830078125, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 1.5214, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0008163098712271178, |
| "eval_loss": 1.6844457387924194, |
| "eval_runtime": 1495.8243, |
| "eval_samples_per_second": 6.897, |
| "eval_steps_per_second": 3.448, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0010203873390338973, |
| "grad_norm": 1.158118724822998, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 1.69, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.0012244648068406767, |
| "grad_norm": 1.4648447036743164, |
| "learning_rate": 5e-05, |
| "loss": 1.753, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.0012244648068406767, |
| "eval_loss": 1.6742535829544067, |
| "eval_runtime": 1495.9089, |
| "eval_samples_per_second": 6.896, |
| "eval_steps_per_second": 3.448, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.0014285422746474561, |
| "grad_norm": 1.519839882850647, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 1.5664, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.0016326197424542355, |
| "grad_norm": 1.042401671409607, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 1.5862, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.0016326197424542355, |
| "eval_loss": 1.6705114841461182, |
| "eval_runtime": 1502.9965, |
| "eval_samples_per_second": 6.864, |
| "eval_steps_per_second": 3.432, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.0018366972102610152, |
| "grad_norm": 1.2911733388900757, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 1.6206, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.0020407746780677946, |
| "grad_norm": 1.0840606689453125, |
| "learning_rate": 0.0, |
| "loss": 1.5961, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.0020407746780677946, |
| "eval_loss": 1.6692533493041992, |
| "eval_runtime": 1501.158, |
| "eval_samples_per_second": 6.872, |
| "eval_steps_per_second": 3.436, |
| "step": 50 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 50, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 13, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.036767093325824e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
