| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 208, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.24096385542168675, | |
| "grad_norm": 0.17040389776229858, | |
| "learning_rate": 0.000511, | |
| "loss": 0.4303, | |
| "mean_token_accuracy": 0.8983636182546616, | |
| "num_tokens": 569446.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4819277108433735, | |
| "grad_norm": 0.19750550389289856, | |
| "learning_rate": 0.000511, | |
| "loss": 0.2953, | |
| "mean_token_accuracy": 0.9258013522624969, | |
| "num_tokens": 1138403.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7228915662650602, | |
| "grad_norm": 0.2441304326057434, | |
| "learning_rate": 0.000511, | |
| "loss": 0.2179, | |
| "mean_token_accuracy": 0.9427212655544281, | |
| "num_tokens": 1705606.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.963855421686747, | |
| "grad_norm": 0.19773538410663605, | |
| "learning_rate": 0.000511, | |
| "loss": 0.194, | |
| "mean_token_accuracy": 0.9479873812198639, | |
| "num_tokens": 2271060.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.1995953470468521, | |
| "eval_mean_token_accuracy": 0.9460804703387808, | |
| "eval_num_tokens": 2345411.0, | |
| "eval_runtime": 4.3258, | |
| "eval_samples_per_second": 85.303, | |
| "eval_steps_per_second": 10.865, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.202409638554217, | |
| "grad_norm": 0.0789426863193512, | |
| "learning_rate": 0.000511, | |
| "loss": 0.16, | |
| "mean_token_accuracy": 0.9584937607399141, | |
| "num_tokens": 2836512.0, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.4433734939759035, | |
| "grad_norm": 0.10643763095140457, | |
| "learning_rate": 0.000511, | |
| "loss": 0.1408, | |
| "mean_token_accuracy": 0.9620217531919479, | |
| "num_tokens": 3403395.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.6843373493975904, | |
| "grad_norm": 0.08403506129980087, | |
| "learning_rate": 0.000511, | |
| "loss": 0.1314, | |
| "mean_token_accuracy": 0.9630346685647965, | |
| "num_tokens": 3970344.0, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.9253012048192772, | |
| "grad_norm": 0.10631190985441208, | |
| "learning_rate": 0.000511, | |
| "loss": 0.1272, | |
| "mean_token_accuracy": 0.9646087974309921, | |
| "num_tokens": 4538034.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.14445580542087555, | |
| "eval_mean_token_accuracy": 0.9612192435467497, | |
| "eval_num_tokens": 4690349.0, | |
| "eval_runtime": 4.2683, | |
| "eval_samples_per_second": 86.451, | |
| "eval_steps_per_second": 11.011, | |
| "step": 208 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 1248, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 12, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.0511412313705677e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |