| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01358695652173913, | |
| "eval_steps": 10, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001358695652173913, | |
| "eval_loss": 2.557396173477173, | |
| "eval_runtime": 22.5514, | |
| "eval_samples_per_second": 871.653, | |
| "eval_steps_per_second": 6.829, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002717391304347826, | |
| "eval_loss": 2.5474746227264404, | |
| "eval_runtime": 23.4021, | |
| "eval_samples_per_second": 839.969, | |
| "eval_steps_per_second": 6.581, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004076086956521739, | |
| "eval_loss": 2.5305492877960205, | |
| "eval_runtime": 23.6374, | |
| "eval_samples_per_second": 831.608, | |
| "eval_steps_per_second": 6.515, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005434782608695652, | |
| "eval_loss": 2.5070903301239014, | |
| "eval_runtime": 24.1483, | |
| "eval_samples_per_second": 814.011, | |
| "eval_steps_per_second": 6.377, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006793478260869565, | |
| "eval_loss": 2.4774248600006104, | |
| "eval_runtime": 24.079, | |
| "eval_samples_per_second": 816.353, | |
| "eval_steps_per_second": 6.396, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008152173913043478, | |
| "eval_loss": 2.4406001567840576, | |
| "eval_runtime": 24.1728, | |
| "eval_samples_per_second": 813.186, | |
| "eval_steps_per_second": 6.371, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.009510869565217392, | |
| "eval_loss": 2.3981375694274902, | |
| "eval_runtime": 24.4575, | |
| "eval_samples_per_second": 803.72, | |
| "eval_steps_per_second": 6.297, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.010869565217391304, | |
| "eval_loss": 2.3499698638916016, | |
| "eval_runtime": 24.4148, | |
| "eval_samples_per_second": 805.125, | |
| "eval_steps_per_second": 6.308, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.012228260869565218, | |
| "eval_loss": 2.296602964401245, | |
| "eval_runtime": 24.3099, | |
| "eval_samples_per_second": 808.6, | |
| "eval_steps_per_second": 6.335, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.01358695652173913, | |
| "grad_norm": 13.137834548950195, | |
| "learning_rate": 4.528985507246377e-07, | |
| "loss": 2.7614, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01358695652173913, | |
| "eval_loss": 2.236211061477661, | |
| "eval_runtime": 24.5166, | |
| "eval_samples_per_second": 801.784, | |
| "eval_steps_per_second": 6.281, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 22080, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 128, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |