| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.012393109431156277, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00024786218862312553, | |
| "eval_loss": 3.3040616512298584, | |
| "eval_runtime": 30.0995, | |
| "eval_samples_per_second": 56.446, | |
| "eval_steps_per_second": 28.24, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012393109431156277, | |
| "grad_norm": 0.612124502658844, | |
| "learning_rate": 5e-05, | |
| "loss": 3.1742, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0024786218862312553, | |
| "grad_norm": 0.8830687999725342, | |
| "learning_rate": 0.0001, | |
| "loss": 3.2666, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0024786218862312553, | |
| "eval_loss": 3.2535722255706787, | |
| "eval_runtime": 30.1596, | |
| "eval_samples_per_second": 56.334, | |
| "eval_steps_per_second": 28.183, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003717932829346883, | |
| "grad_norm": 0.8132537603378296, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.2522, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004957243772462511, | |
| "grad_norm": 0.7359092831611633, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.0345, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004957243772462511, | |
| "eval_loss": 3.0423290729522705, | |
| "eval_runtime": 30.1065, | |
| "eval_samples_per_second": 56.433, | |
| "eval_steps_per_second": 28.233, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006196554715578138, | |
| "grad_norm": 0.7544383406639099, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.8972, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007435865658693766, | |
| "grad_norm": 0.8339029550552368, | |
| "learning_rate": 5e-05, | |
| "loss": 2.9029, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.007435865658693766, | |
| "eval_loss": 2.897880792617798, | |
| "eval_runtime": 30.1974, | |
| "eval_samples_per_second": 56.263, | |
| "eval_steps_per_second": 28.148, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008675176601809394, | |
| "grad_norm": 0.9288826584815979, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.8161, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.009914487544925021, | |
| "grad_norm": 0.9317106604576111, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.7674, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.009914487544925021, | |
| "eval_loss": 2.830029249191284, | |
| "eval_runtime": 30.134, | |
| "eval_samples_per_second": 56.382, | |
| "eval_steps_per_second": 28.207, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.011153798488040649, | |
| "grad_norm": 0.885162889957428, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.796, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.012393109431156277, | |
| "grad_norm": 0.9177526831626892, | |
| "learning_rate": 0.0, | |
| "loss": 2.8546, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.012393109431156277, | |
| "eval_loss": 2.817416191101074, | |
| "eval_runtime": 29.8903, | |
| "eval_samples_per_second": 56.841, | |
| "eval_steps_per_second": 28.437, | |
| "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": 184322996305920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |