| { | |
| "best_metric": 1.2393821477890015, | |
| "best_model_checkpoint": "./outputs/checkpoint-900", | |
| "epoch": 1.2, | |
| "eval_steps": 100, | |
| "global_step": 900, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2648, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.3499459028244019, | |
| "eval_runtime": 466.0769, | |
| "eval_samples_per_second": 4.141, | |
| "eval_steps_per_second": 0.519, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1034, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.3190627098083496, | |
| "eval_runtime": 466.6597, | |
| "eval_samples_per_second": 4.136, | |
| "eval_steps_per_second": 0.519, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0002, | |
| "loss": 1.085, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.2993828058242798, | |
| "eval_runtime": 470.7014, | |
| "eval_samples_per_second": 4.1, | |
| "eval_steps_per_second": 0.514, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0692, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.2881134748458862, | |
| "eval_runtime": 470.2444, | |
| "eval_samples_per_second": 4.104, | |
| "eval_steps_per_second": 0.515, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0558, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.274288535118103, | |
| "eval_runtime": 467.1885, | |
| "eval_samples_per_second": 4.131, | |
| "eval_steps_per_second": 0.518, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0502, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 1.2627606391906738, | |
| "eval_runtime": 465.7624, | |
| "eval_samples_per_second": 4.144, | |
| "eval_steps_per_second": 0.52, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0419, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 1.256902813911438, | |
| "eval_runtime": 459.9211, | |
| "eval_samples_per_second": 4.196, | |
| "eval_steps_per_second": 0.526, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0301, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_loss": 1.2442457675933838, | |
| "eval_runtime": 457.8978, | |
| "eval_samples_per_second": 4.215, | |
| "eval_steps_per_second": 0.529, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0199, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 1.2393821477890015, | |
| "eval_runtime": 467.9251, | |
| "eval_samples_per_second": 4.125, | |
| "eval_steps_per_second": 0.517, | |
| "step": 900 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 2250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 2.995607206497485e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |