| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.005583392984967788, | |
| "eval_steps": 13, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00014316392269148176, | |
| "eval_loss": 0.9938636422157288, | |
| "eval_runtime": 255.7053, | |
| "eval_samples_per_second": 11.505, | |
| "eval_steps_per_second": 5.753, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014316392269148174, | |
| "grad_norm": 0.5756565928459167, | |
| "learning_rate": 0.0002, | |
| "loss": 3.9306, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0018611309949892628, | |
| "eval_loss": 0.9162142872810364, | |
| "eval_runtime": 255.4436, | |
| "eval_samples_per_second": 11.517, | |
| "eval_steps_per_second": 5.759, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.002863278453829635, | |
| "grad_norm": 0.9709283709526062, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 3.6644, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0037222619899785255, | |
| "eval_loss": 0.8774906396865845, | |
| "eval_runtime": 255.6998, | |
| "eval_samples_per_second": 11.506, | |
| "eval_steps_per_second": 5.753, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.004294917680744453, | |
| "grad_norm": 0.9274352192878723, | |
| "learning_rate": 0.0001, | |
| "loss": 3.4613, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005583392984967788, | |
| "eval_loss": 0.8650556802749634, | |
| "eval_runtime": 255.7824, | |
| "eval_samples_per_second": 11.502, | |
| "eval_steps_per_second": 5.751, | |
| "step": 39 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.3746682290176e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |