| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 1, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1111111111111111, | |
| "eval_loss": 2.526536226272583, | |
| "eval_runtime": 0.0933, | |
| "eval_samples_per_second": 21.438, | |
| "eval_steps_per_second": 10.719, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "eval_loss": 2.433619499206543, | |
| "eval_runtime": 0.0542, | |
| "eval_samples_per_second": 36.91, | |
| "eval_steps_per_second": 18.455, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "eval_loss": 2.3056671619415283, | |
| "eval_runtime": 0.0553, | |
| "eval_samples_per_second": 36.166, | |
| "eval_steps_per_second": 18.083, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "eval_loss": 2.2071735858917236, | |
| "eval_runtime": 0.0496, | |
| "eval_samples_per_second": 40.292, | |
| "eval_steps_per_second": 20.146, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.5555555555555556, | |
| "eval_loss": 2.137558698654175, | |
| "eval_runtime": 0.0542, | |
| "eval_samples_per_second": 36.918, | |
| "eval_steps_per_second": 18.459, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "eval_loss": 2.0649843215942383, | |
| "eval_runtime": 0.0469, | |
| "eval_samples_per_second": 42.676, | |
| "eval_steps_per_second": 21.338, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.7777777777777778, | |
| "eval_loss": 2.011927604675293, | |
| "eval_runtime": 0.0511, | |
| "eval_samples_per_second": 39.137, | |
| "eval_steps_per_second": 19.569, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "eval_loss": 1.9691121578216553, | |
| "eval_runtime": 0.0625, | |
| "eval_samples_per_second": 31.982, | |
| "eval_steps_per_second": 15.991, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.9728047847747803, | |
| "eval_runtime": 0.0509, | |
| "eval_samples_per_second": 39.284, | |
| "eval_steps_per_second": 19.642, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 9, | |
| "total_flos": 5217079984128.0, | |
| "train_loss": 2.716358608669705, | |
| "train_runtime": 38.8025, | |
| "train_samples_per_second": 0.464, | |
| "train_steps_per_second": 0.232 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 9, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 1, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5217079984128.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |