| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "global_step": 480, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9e-07, | |
| "loss": 3.1382, | |
| "perplexity": 23.062317304193936, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9e-07, | |
| "loss": 2.6614, | |
| "perplexity": 14.316317920319525, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_runtime": 0.0024, | |
| "eval_samples_per_second": 0.0, | |
| "eval_steps_per_second": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 9e-07, | |
| "loss": 2.1364, | |
| "perplexity": 8.468894663745782, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_runtime": 0.0028, | |
| "eval_samples_per_second": 0.0, | |
| "eval_steps_per_second": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 9e-07, | |
| "loss": 1.7242, | |
| "perplexity": 5.608032808397292, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_runtime": 0.002, | |
| "eval_samples_per_second": 0.0, | |
| "eval_steps_per_second": 0.0, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 9e-07, | |
| "loss": 1.3783, | |
| "perplexity": 3.96815003520746, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_runtime": 0.0023, | |
| "eval_samples_per_second": 0.0, | |
| "eval_steps_per_second": 0.0, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 9e-07, | |
| "loss": 1.0366, | |
| "perplexity": 2.819614010859592, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_runtime": 0.0021, | |
| "eval_samples_per_second": 0.0, | |
| "eval_steps_per_second": 0.0, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 9e-07, | |
| "loss": 0.7703, | |
| "perplexity": 2.1604142808602513, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_runtime": 0.0032, | |
| "eval_samples_per_second": 0.0, | |
| "eval_steps_per_second": 0.0, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 9e-07, | |
| "loss": 0.5576, | |
| "perplexity": 1.7464759242010608, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_runtime": 0.0025, | |
| "eval_samples_per_second": 0.0, | |
| "eval_steps_per_second": 0.0, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 9e-07, | |
| "loss": 0.4029, | |
| "perplexity": 1.4961572684557012, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_runtime": 0.0025, | |
| "eval_samples_per_second": 0.0, | |
| "eval_steps_per_second": 0.0, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 9e-07, | |
| "loss": 0.2827, | |
| "perplexity": 1.3267070899823727, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_runtime": 0.0019, | |
| "eval_samples_per_second": 0.0, | |
| "eval_steps_per_second": 0.0, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 9e-07, | |
| "loss": 0.2, | |
| "perplexity": 1.2214027581601699, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_runtime": 0.0023, | |
| "eval_samples_per_second": 0.0, | |
| "eval_steps_per_second": 0.0, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 480, | |
| "total_flos": 5019068989440.0, | |
| "train_loss": 1.1160404185454051, | |
| "train_runtime": 51742.5542, | |
| "train_samples_per_second": 0.037, | |
| "train_steps_per_second": 0.009 | |
| } | |
| ], | |
| "max_steps": 480, | |
| "num_train_epochs": 10, | |
| "total_flos": 5019068989440.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |