| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0015617679212868967, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00015617679212868969, | |
| "grad_norm": 5.404446601867676, | |
| "learning_rate": 2e-05, | |
| "loss": 5.986, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00015617679212868969, | |
| "eval_loss": 6.0940141677856445, | |
| "eval_runtime": 57.7493, | |
| "eval_samples_per_second": 46.702, | |
| "eval_steps_per_second": 23.36, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00031235358425737937, | |
| "grad_norm": 5.888598442077637, | |
| "learning_rate": 4e-05, | |
| "loss": 6.4665, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00046853037638606906, | |
| "grad_norm": 5.328481674194336, | |
| "learning_rate": 6e-05, | |
| "loss": 6.5356, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00046853037638606906, | |
| "eval_loss": 6.080668926239014, | |
| "eval_runtime": 56.5732, | |
| "eval_samples_per_second": 47.673, | |
| "eval_steps_per_second": 23.845, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006247071685147587, | |
| "grad_norm": 5.292506217956543, | |
| "learning_rate": 8e-05, | |
| "loss": 5.9008, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0007808839606434484, | |
| "grad_norm": 5.258495807647705, | |
| "learning_rate": 0.0001, | |
| "loss": 6.1166, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0009370607527721381, | |
| "grad_norm": 5.323895454406738, | |
| "learning_rate": 0.00012, | |
| "loss": 6.7297, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0009370607527721381, | |
| "eval_loss": 5.9072957038879395, | |
| "eval_runtime": 56.5863, | |
| "eval_samples_per_second": 47.662, | |
| "eval_steps_per_second": 23.84, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0010932375449008277, | |
| "grad_norm": 5.162273406982422, | |
| "learning_rate": 0.00014, | |
| "loss": 5.2246, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0012494143370295175, | |
| "grad_norm": 6.320584774017334, | |
| "learning_rate": 0.00016, | |
| "loss": 5.386, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.001405591129158207, | |
| "grad_norm": 5.657876491546631, | |
| "learning_rate": 0.00018, | |
| "loss": 5.5206, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.001405591129158207, | |
| "eval_loss": 5.303591251373291, | |
| "eval_runtime": 56.6066, | |
| "eval_samples_per_second": 47.645, | |
| "eval_steps_per_second": 23.831, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0015617679212868967, | |
| "grad_norm": 5.907142162322998, | |
| "learning_rate": 0.0002, | |
| "loss": 4.4764, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 240545515438080.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |