| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.07202881152460984, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0024009603841536613, | |
| "eval_loss": NaN, | |
| "eval_runtime": 14.9348, | |
| "eval_samples_per_second": 11.785, | |
| "eval_steps_per_second": 5.892, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007202881152460984, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.012004801920768308, | |
| "eval_loss": NaN, | |
| "eval_runtime": 14.4803, | |
| "eval_samples_per_second": 12.154, | |
| "eval_steps_per_second": 6.077, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.014405762304921969, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.021608643457382955, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.024009603841536616, | |
| "eval_loss": NaN, | |
| "eval_runtime": 14.5311, | |
| "eval_samples_per_second": 12.112, | |
| "eval_steps_per_second": 6.056, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.028811524609843937, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03601440576230492, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03601440576230492, | |
| "eval_loss": NaN, | |
| "eval_runtime": 14.5802, | |
| "eval_samples_per_second": 12.071, | |
| "eval_steps_per_second": 6.036, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04321728691476591, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04801920768307323, | |
| "eval_loss": NaN, | |
| "eval_runtime": 14.5775, | |
| "eval_samples_per_second": 12.073, | |
| "eval_steps_per_second": 6.037, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05042016806722689, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.057623049219687875, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.060024009603841535, | |
| "eval_loss": NaN, | |
| "eval_runtime": 14.565, | |
| "eval_samples_per_second": 12.084, | |
| "eval_steps_per_second": 6.042, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06482593037214886, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07202881152460984, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07202881152460984, | |
| "eval_loss": NaN, | |
| "eval_runtime": 14.586, | |
| "eval_samples_per_second": 12.066, | |
| "eval_steps_per_second": 6.033, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 15, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1129465925009408e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |