| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.46956521739130436, | |
| "eval_steps": 9, | |
| "global_step": 27, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.017391304347826087, | |
| "eval_loss": 1.59055495262146, | |
| "eval_runtime": 2.6995, | |
| "eval_samples_per_second": 35.932, | |
| "eval_steps_per_second": 4.816, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05217391304347826, | |
| "grad_norm": 0.5041409134864807, | |
| "learning_rate": 1.5e-05, | |
| "loss": 1.7739, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.10434782608695652, | |
| "grad_norm": 0.5414333343505859, | |
| "learning_rate": 3e-05, | |
| "loss": 1.402, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1565217391304348, | |
| "grad_norm": 0.3529357612133026, | |
| "learning_rate": 4.5e-05, | |
| "loss": 1.6939, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1565217391304348, | |
| "eval_loss": 1.5777380466461182, | |
| "eval_runtime": 2.6751, | |
| "eval_samples_per_second": 36.26, | |
| "eval_steps_per_second": 4.86, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.20869565217391303, | |
| "grad_norm": 0.3947656452655792, | |
| "learning_rate": 4.993910125649561e-05, | |
| "loss": 1.7722, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2608695652173913, | |
| "grad_norm": 0.4697956442832947, | |
| "learning_rate": 4.962019382530521e-05, | |
| "loss": 1.6984, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3130434782608696, | |
| "grad_norm": 0.34927043318748474, | |
| "learning_rate": 4.9031542398457974e-05, | |
| "loss": 1.7339, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3130434782608696, | |
| "eval_loss": 1.4486348628997803, | |
| "eval_runtime": 2.683, | |
| "eval_samples_per_second": 36.153, | |
| "eval_steps_per_second": 4.845, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3652173913043478, | |
| "grad_norm": 0.4831562042236328, | |
| "learning_rate": 4.817959636416969e-05, | |
| "loss": 1.7264, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.41739130434782606, | |
| "grad_norm": 0.56829833984375, | |
| "learning_rate": 4.707368982147318e-05, | |
| "loss": 1.7197, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.46956521739130436, | |
| "grad_norm": 0.5362353920936584, | |
| "learning_rate": 4.572593931387604e-05, | |
| "loss": 1.5556, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.46956521739130436, | |
| "eval_loss": 1.2610658407211304, | |
| "eval_runtime": 2.6707, | |
| "eval_samples_per_second": 36.32, | |
| "eval_steps_per_second": 4.868, | |
| "step": 27 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7119165160685568.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |