| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.009523809523809525, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00019047619047619048, | |
| "eval_loss": 4.401525974273682, | |
| "eval_runtime": 130.5531, | |
| "eval_samples_per_second": 16.936, | |
| "eval_steps_per_second": 8.472, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009523809523809524, | |
| "grad_norm": 6.240159511566162, | |
| "learning_rate": 5e-05, | |
| "loss": 4.2135, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0019047619047619048, | |
| "grad_norm": 6.694627285003662, | |
| "learning_rate": 0.0001, | |
| "loss": 3.4093, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0019047619047619048, | |
| "eval_loss": 1.5426820516586304, | |
| "eval_runtime": 131.5409, | |
| "eval_samples_per_second": 16.808, | |
| "eval_steps_per_second": 8.408, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002857142857142857, | |
| "grad_norm": 0.39326727390289307, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.4722, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0038095238095238095, | |
| "grad_norm": 0.022698791697621346, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0098, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0038095238095238095, | |
| "eval_loss": 0.04538438841700554, | |
| "eval_runtime": 131.9858, | |
| "eval_samples_per_second": 16.752, | |
| "eval_steps_per_second": 8.38, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004761904761904762, | |
| "grad_norm": 0.0009007006883621216, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0006, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005714285714285714, | |
| "grad_norm": 0.00023861594672780484, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005714285714285714, | |
| "eval_loss": 0.03649113327264786, | |
| "eval_runtime": 131.3899, | |
| "eval_samples_per_second": 16.828, | |
| "eval_steps_per_second": 8.418, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006666666666666667, | |
| "grad_norm": 0.00019242503913119435, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0932, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.007619047619047619, | |
| "grad_norm": 0.0021921342704445124, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0002, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.007619047619047619, | |
| "eval_loss": 0.03374890238046646, | |
| "eval_runtime": 131.731, | |
| "eval_samples_per_second": 16.784, | |
| "eval_steps_per_second": 8.396, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.008571428571428572, | |
| "grad_norm": 0.00040338459075428545, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.009523809523809525, | |
| "grad_norm": 0.00989100057631731, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.009523809523809525, | |
| "eval_loss": 0.03334899991750717, | |
| "eval_runtime": 131.1678, | |
| "eval_samples_per_second": 16.856, | |
| "eval_steps_per_second": 8.432, | |
| "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": 8225102336360448.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |