| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 15.0, | |
| "eval_steps": 500, | |
| "global_step": 945, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.0049484120681881905, | |
| "eval_runtime": 86.2189, | |
| "eval_samples_per_second": 11.598, | |
| "eval_steps_per_second": 0.731, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.0015708731953054667, | |
| "eval_runtime": 82.6736, | |
| "eval_samples_per_second": 12.096, | |
| "eval_steps_per_second": 0.762, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.0008609762298874557, | |
| "eval_runtime": 86.3582, | |
| "eval_samples_per_second": 11.58, | |
| "eval_steps_per_second": 0.73, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.0005577785195782781, | |
| "eval_runtime": 83.2641, | |
| "eval_samples_per_second": 12.01, | |
| "eval_steps_per_second": 0.757, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.0003976120497100055, | |
| "eval_runtime": 120.3456, | |
| "eval_samples_per_second": 8.309, | |
| "eval_steps_per_second": 0.523, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.00029855340835638344, | |
| "eval_runtime": 1114.9335, | |
| "eval_samples_per_second": 0.897, | |
| "eval_steps_per_second": 0.057, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.00023258940200321376, | |
| "eval_runtime": 1077.4431, | |
| "eval_samples_per_second": 0.928, | |
| "eval_steps_per_second": 0.058, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 7.936507936507937, | |
| "grad_norm": 0.00615890184417367, | |
| "learning_rate": 9.417989417989418e-06, | |
| "loss": 0.0229, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.0001905104873003438, | |
| "eval_runtime": 92.7233, | |
| "eval_samples_per_second": 10.785, | |
| "eval_steps_per_second": 0.679, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.00016125467664096504, | |
| "eval_runtime": 157.6217, | |
| "eval_samples_per_second": 6.344, | |
| "eval_steps_per_second": 0.4, | |
| "step": 567 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.00014133936201687902, | |
| "eval_runtime": 253.9397, | |
| "eval_samples_per_second": 3.938, | |
| "eval_steps_per_second": 0.248, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 0.00012699734361376613, | |
| "eval_runtime": 290.6194, | |
| "eval_samples_per_second": 3.441, | |
| "eval_steps_per_second": 0.217, | |
| "step": 693 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 0.00011713778803823516, | |
| "eval_runtime": 89.5033, | |
| "eval_samples_per_second": 11.173, | |
| "eval_steps_per_second": 0.704, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 0.00011058501695515588, | |
| "eval_runtime": 81.9569, | |
| "eval_samples_per_second": 12.202, | |
| "eval_steps_per_second": 0.769, | |
| "step": 819 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 0.00010690685303416103, | |
| "eval_runtime": 82.071, | |
| "eval_samples_per_second": 12.185, | |
| "eval_steps_per_second": 0.768, | |
| "step": 882 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 945, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 15, | |
| "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": 1987010979840000.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |