| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03537944454272068, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007075888908544136, | |
| "eval_loss": 10.43582820892334, | |
| "eval_runtime": 2.8667, | |
| "eval_samples_per_second": 207.554, | |
| "eval_steps_per_second": 103.951, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0035379444542720678, | |
| "grad_norm": 0.22758431732654572, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3964, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0070758889085441356, | |
| "grad_norm": 0.24311938881874084, | |
| "learning_rate": 0.0001, | |
| "loss": 10.4524, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0070758889085441356, | |
| "eval_loss": 10.433773040771484, | |
| "eval_runtime": 2.8845, | |
| "eval_samples_per_second": 206.272, | |
| "eval_steps_per_second": 103.309, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010613833362816204, | |
| "grad_norm": 0.20211586356163025, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.4143, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.014151777817088271, | |
| "grad_norm": 0.2647286057472229, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.4113, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.014151777817088271, | |
| "eval_loss": 10.42919921875, | |
| "eval_runtime": 3.0176, | |
| "eval_samples_per_second": 197.175, | |
| "eval_steps_per_second": 98.753, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01768972227136034, | |
| "grad_norm": 0.1938541829586029, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.458, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.021227666725632408, | |
| "grad_norm": 0.1667635440826416, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3971, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.021227666725632408, | |
| "eval_loss": 10.425599098205566, | |
| "eval_runtime": 3.0708, | |
| "eval_samples_per_second": 193.76, | |
| "eval_steps_per_second": 97.043, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.024765611179904477, | |
| "grad_norm": 0.17393247783184052, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 10.4128, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.028303555634176542, | |
| "grad_norm": 0.2921091318130493, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 10.4289, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.028303555634176542, | |
| "eval_loss": 10.423803329467773, | |
| "eval_runtime": 3.092, | |
| "eval_samples_per_second": 192.43, | |
| "eval_steps_per_second": 96.377, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03184150008844861, | |
| "grad_norm": 0.2559455335140228, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 10.427, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03537944454272068, | |
| "grad_norm": 0.2714591920375824, | |
| "learning_rate": 0.0, | |
| "loss": 10.4022, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03537944454272068, | |
| "eval_loss": 10.423460006713867, | |
| "eval_runtime": 2.9191, | |
| "eval_samples_per_second": 203.833, | |
| "eval_steps_per_second": 102.088, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 646545408000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |