| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0023054223533751383, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.610844706750277e-05, | |
| "eval_loss": 7.478056907653809, | |
| "eval_runtime": 633.6358, | |
| "eval_samples_per_second": 14.412, | |
| "eval_steps_per_second": 7.206, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00023054223533751383, | |
| "grad_norm": 235.84422302246094, | |
| "learning_rate": 5e-05, | |
| "loss": 30.1917, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00046108447067502766, | |
| "grad_norm": 112.99340057373047, | |
| "learning_rate": 0.0001, | |
| "loss": 8.5185, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00046108447067502766, | |
| "eval_loss": 0.7984493970870972, | |
| "eval_runtime": 638.2439, | |
| "eval_samples_per_second": 14.308, | |
| "eval_steps_per_second": 7.154, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0006916267060125415, | |
| "grad_norm": 4.243373394012451, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.7296, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0009221689413500553, | |
| "grad_norm": 0.13427194952964783, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.1732, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0009221689413500553, | |
| "eval_loss": 0.2060871124267578, | |
| "eval_runtime": 637.7861, | |
| "eval_samples_per_second": 14.318, | |
| "eval_steps_per_second": 7.159, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0011527111766875691, | |
| "grad_norm": 0.10090111941099167, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0025, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.001383253412025083, | |
| "grad_norm": 0.0038050950970500708, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5105, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.001383253412025083, | |
| "eval_loss": 0.1813499480485916, | |
| "eval_runtime": 639.5032, | |
| "eval_samples_per_second": 14.28, | |
| "eval_steps_per_second": 7.14, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0016137956473625968, | |
| "grad_norm": 0.07985703647136688, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.5504, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0018443378827001106, | |
| "grad_norm": 0.01825106330215931, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0768, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0018443378827001106, | |
| "eval_loss": 0.13046832382678986, | |
| "eval_runtime": 636.6658, | |
| "eval_samples_per_second": 14.343, | |
| "eval_steps_per_second": 7.172, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0020748801180376247, | |
| "grad_norm": 0.0023735379800200462, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.6668, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0023054223533751383, | |
| "grad_norm": 0.013666966930031776, | |
| "learning_rate": 0.0, | |
| "loss": 0.7447, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0023054223533751383, | |
| "eval_loss": 0.11738045513629913, | |
| "eval_runtime": 637.5012, | |
| "eval_samples_per_second": 14.325, | |
| "eval_steps_per_second": 7.162, | |
| "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": 9464427715756032.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |