| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0021899808376676703, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.379961675335341e-05, | |
| "eval_loss": 0.3729982376098633, | |
| "eval_runtime": 1205.9931, | |
| "eval_samples_per_second": 7.972, | |
| "eval_steps_per_second": 3.986, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00021899808376676705, | |
| "grad_norm": 0.3186088800430298, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3378, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0004379961675335341, | |
| "grad_norm": 0.2965073585510254, | |
| "learning_rate": 0.0001, | |
| "loss": 0.4345, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0004379961675335341, | |
| "eval_loss": 0.33912086486816406, | |
| "eval_runtime": 1202.4718, | |
| "eval_samples_per_second": 7.995, | |
| "eval_steps_per_second": 3.998, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0006569942513003011, | |
| "grad_norm": 0.32256799936294556, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.3154, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0008759923350670682, | |
| "grad_norm": 0.2605501413345337, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.2963, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0008759923350670682, | |
| "eval_loss": 0.2871706783771515, | |
| "eval_runtime": 1205.8712, | |
| "eval_samples_per_second": 7.973, | |
| "eval_steps_per_second": 3.986, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0010949904188338351, | |
| "grad_norm": 0.24902136623859406, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.248, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0013139885026006023, | |
| "grad_norm": 0.30294308066368103, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3313, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0013139885026006023, | |
| "eval_loss": 0.25491875410079956, | |
| "eval_runtime": 1209.8678, | |
| "eval_samples_per_second": 7.946, | |
| "eval_steps_per_second": 3.973, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0015329865863673692, | |
| "grad_norm": 0.2902165651321411, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.2247, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0017519846701341364, | |
| "grad_norm": 0.44431889057159424, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.2518, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0017519846701341364, | |
| "eval_loss": 0.24418461322784424, | |
| "eval_runtime": 1209.5775, | |
| "eval_samples_per_second": 7.948, | |
| "eval_steps_per_second": 3.974, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0019709827539009035, | |
| "grad_norm": 0.31688830256462097, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.2649, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0021899808376676703, | |
| "grad_norm": 0.24490441381931305, | |
| "learning_rate": 0.0, | |
| "loss": 0.268, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0021899808376676703, | |
| "eval_loss": 0.24244266748428345, | |
| "eval_runtime": 1205.0883, | |
| "eval_samples_per_second": 7.978, | |
| "eval_steps_per_second": 3.989, | |
| "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": 1.84956424814592e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |