| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00909194226616661, | |
| "eval_steps": 8, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004545971133083305, | |
| "eval_loss": 3.4812397956848145, | |
| "eval_runtime": 13.4112, | |
| "eval_samples_per_second": 69.121, | |
| "eval_steps_per_second": 34.598, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013637913399249914, | |
| "grad_norm": 36.62466812133789, | |
| "learning_rate": 6e-05, | |
| "loss": 14.3869, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002727582679849983, | |
| "grad_norm": 30.937101364135742, | |
| "learning_rate": 0.00012, | |
| "loss": 13.3207, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003636776906466644, | |
| "eval_loss": 2.706923246383667, | |
| "eval_runtime": 12.3718, | |
| "eval_samples_per_second": 74.929, | |
| "eval_steps_per_second": 37.505, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004091374019774974, | |
| "grad_norm": 33.398101806640625, | |
| "learning_rate": 0.00018, | |
| "loss": 11.7831, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005455165359699966, | |
| "grad_norm": 56.49053192138672, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 8.7552, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006818956699624957, | |
| "grad_norm": 72.0090103149414, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 7.7473, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007273553812933288, | |
| "eval_loss": 1.5220115184783936, | |
| "eval_runtime": 12.9876, | |
| "eval_samples_per_second": 71.376, | |
| "eval_steps_per_second": 35.726, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.008182748039549948, | |
| "grad_norm": 106.22815704345703, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 6.378, | |
| "step": 18 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 354006639575040.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |