| { | |
| "best_global_step": 9732, | |
| "best_metric": 3.264747381210327, | |
| "best_model_checkpoint": "./checkpoints_tweeteval_lora/checkpoint-9732", | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 9732, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.8289690017700195, | |
| "learning_rate": 0.00018001644060830252, | |
| "loss": 3.293, | |
| "step": 2433 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 3.3217873573303223, | |
| "eval_runtime": 215.2285, | |
| "eval_samples_per_second": 33.913, | |
| "eval_steps_per_second": 2.83, | |
| "step": 2433 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.8954250812530518, | |
| "learning_rate": 0.00016001644060830252, | |
| "loss": 3.1711, | |
| "step": 4866 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 3.2837774753570557, | |
| "eval_runtime": 214.9427, | |
| "eval_samples_per_second": 33.958, | |
| "eval_steps_per_second": 2.833, | |
| "step": 4866 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 1.1570912599563599, | |
| "learning_rate": 0.00014002466091245377, | |
| "loss": 3.1122, | |
| "step": 7299 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 3.268982172012329, | |
| "eval_runtime": 215.0597, | |
| "eval_samples_per_second": 33.939, | |
| "eval_steps_per_second": 2.832, | |
| "step": 7299 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 1.0732226371765137, | |
| "learning_rate": 0.00012003288121660504, | |
| "loss": 3.0648, | |
| "step": 9732 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 3.264747381210327, | |
| "eval_runtime": 215.0558, | |
| "eval_samples_per_second": 33.94, | |
| "eval_steps_per_second": 2.832, | |
| "step": 9732 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 24330, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.340655923795067e+17, | |
| "train_batch_size": 12, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |