| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 15.0, | |
| "global_step": 1470, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9e-07, | |
| "loss": 2.4836, | |
| "perplexity": 11.98433044208569, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9e-07, | |
| "loss": 2.5819, | |
| "perplexity": 13.222236558089785, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_runtime": 0.0023, | |
| "eval_samples_per_second": 0.0, | |
| "eval_steps_per_second": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 9e-07, | |
| "loss": 2.1794, | |
| "perplexity": 8.841000066982355, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_runtime": 0.0022, | |
| "eval_samples_per_second": 0.0, | |
| "eval_steps_per_second": 0.0, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 9e-07, | |
| "loss": 1.8523, | |
| "perplexity": 6.374463942130527, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_runtime": 0.0023, | |
| "eval_samples_per_second": 0.0, | |
| "eval_steps_per_second": 0.0, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 9e-07, | |
| "loss": 1.5639, | |
| "perplexity": 4.777416885923455, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_runtime": 0.0025, | |
| "eval_samples_per_second": 0.0, | |
| "eval_steps_per_second": 0.0, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 9e-07, | |
| "loss": 1.3052, | |
| "perplexity": 3.688426705282456, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_runtime": 0.0022, | |
| "eval_samples_per_second": 0.0, | |
| "eval_steps_per_second": 0.0, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 9e-07, | |
| "loss": 1.0804, | |
| "perplexity": 2.945857658491727, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_runtime": 0.0023, | |
| "eval_samples_per_second": 0.0, | |
| "eval_steps_per_second": 0.0, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 9e-07, | |
| "loss": 0.8983, | |
| "perplexity": 2.455425337981329, | |
| "step": 686 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_runtime": 0.003, | |
| "eval_samples_per_second": 0.0, | |
| "eval_steps_per_second": 0.0, | |
| "step": 686 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 9e-07, | |
| "loss": 0.7469, | |
| "perplexity": 2.1104474782431386, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_runtime": 0.0025, | |
| "eval_samples_per_second": 0.0, | |
| "eval_steps_per_second": 0.0, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 9e-07, | |
| "loss": 0.6196, | |
| "perplexity": 1.8581846193240203, | |
| "step": 882 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_runtime": 0.0023, | |
| "eval_samples_per_second": 0.0, | |
| "eval_steps_per_second": 0.0, | |
| "step": 882 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 9e-07, | |
| "loss": 0.5154, | |
| "perplexity": 1.6743080911071826, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_runtime": 0.0021, | |
| "eval_samples_per_second": 0.0, | |
| "eval_steps_per_second": 0.0, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 9e-07, | |
| "loss": 0.4301, | |
| "perplexity": 1.53741125698718, | |
| "step": 1078 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_runtime": 0.0027, | |
| "eval_samples_per_second": 0.0, | |
| "eval_steps_per_second": 0.0, | |
| "step": 1078 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 9e-07, | |
| "loss": 0.3466, | |
| "perplexity": 1.4142509118505286, | |
| "step": 1176 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_runtime": 0.0027, | |
| "eval_samples_per_second": 0.0, | |
| "eval_steps_per_second": 0.0, | |
| "step": 1176 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 9e-07, | |
| "loss": 0.2822, | |
| "perplexity": 1.3260439022481316, | |
| "step": 1274 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_runtime": 0.0031, | |
| "eval_samples_per_second": 0.0, | |
| "eval_steps_per_second": 0.0, | |
| "step": 1274 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 9e-07, | |
| "loss": 0.2263, | |
| "perplexity": 1.2539517943943168, | |
| "step": 1372 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_runtime": 0.002, | |
| "eval_samples_per_second": 0.0, | |
| "eval_steps_per_second": 0.0, | |
| "step": 1372 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 9e-07, | |
| "loss": 0.1815, | |
| "perplexity": 1.1990145367097138, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_runtime": 0.0024, | |
| "eval_samples_per_second": 0.0, | |
| "eval_steps_per_second": 0.0, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "step": 1470, | |
| "total_flos": 49376758071296.0, | |
| "train_loss": 0.9872670257983565, | |
| "train_runtime": 83520.7385, | |
| "train_samples_per_second": 0.07, | |
| "train_steps_per_second": 0.018 | |
| } | |
| ], | |
| "max_steps": 1470, | |
| "num_train_epochs": 15, | |
| "total_flos": 49376758071296.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |