| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.032388663967611336, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0010796221322537112, | |
| "eval_loss": NaN, | |
| "eval_runtime": 68.7764, | |
| "eval_samples_per_second": 5.671, | |
| "eval_steps_per_second": 2.835, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0032388663967611335, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005398110661268556, | |
| "eval_loss": NaN, | |
| "eval_runtime": 68.2499, | |
| "eval_samples_per_second": 5.714, | |
| "eval_steps_per_second": 2.857, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006477732793522267, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009716599190283401, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010796221322537112, | |
| "eval_loss": NaN, | |
| "eval_runtime": 68.2735, | |
| "eval_samples_per_second": 5.712, | |
| "eval_steps_per_second": 2.856, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012955465587044534, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.016194331983805668, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.016194331983805668, | |
| "eval_loss": NaN, | |
| "eval_runtime": 68.163, | |
| "eval_samples_per_second": 5.722, | |
| "eval_steps_per_second": 2.861, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.019433198380566803, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.021592442645074223, | |
| "eval_loss": NaN, | |
| "eval_runtime": 68.2924, | |
| "eval_samples_per_second": 5.711, | |
| "eval_steps_per_second": 2.855, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.022672064777327937, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.025910931174089068, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02699055330634278, | |
| "eval_loss": NaN, | |
| "eval_runtime": 68.1931, | |
| "eval_samples_per_second": 5.719, | |
| "eval_steps_per_second": 2.86, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.029149797570850202, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.032388663967611336, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.032388663967611336, | |
| "eval_loss": NaN, | |
| "eval_runtime": 68.229, | |
| "eval_samples_per_second": 5.716, | |
| "eval_steps_per_second": 2.858, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.152905235136512e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |