| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03350083752093802, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0033500837520938024, | |
| "grad_norm": 2.395430326461792, | |
| "learning_rate": 2e-05, | |
| "loss": 6.1427, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0033500837520938024, | |
| "eval_loss": 1.1585458517074585, | |
| "eval_runtime": 3.6182, | |
| "eval_samples_per_second": 34.824, | |
| "eval_steps_per_second": 17.412, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006700167504187605, | |
| "grad_norm": 2.3884027004241943, | |
| "learning_rate": 4e-05, | |
| "loss": 4.8958, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.010050251256281407, | |
| "grad_norm": 2.4061315059661865, | |
| "learning_rate": 6e-05, | |
| "loss": 2.8, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010050251256281407, | |
| "eval_loss": 1.1527312994003296, | |
| "eval_runtime": 2.5096, | |
| "eval_samples_per_second": 50.207, | |
| "eval_steps_per_second": 25.104, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01340033500837521, | |
| "grad_norm": 2.643523931503296, | |
| "learning_rate": 8e-05, | |
| "loss": 3.8858, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01675041876046901, | |
| "grad_norm": 2.8617804050445557, | |
| "learning_rate": 0.0001, | |
| "loss": 5.1144, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.020100502512562814, | |
| "grad_norm": 5.240389347076416, | |
| "learning_rate": 0.00012, | |
| "loss": 3.7216, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.020100502512562814, | |
| "eval_loss": 1.1134865283966064, | |
| "eval_runtime": 2.4448, | |
| "eval_samples_per_second": 51.538, | |
| "eval_steps_per_second": 25.769, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.023450586264656615, | |
| "grad_norm": 2.288501024246216, | |
| "learning_rate": 0.00014, | |
| "loss": 3.8796, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02680067001675042, | |
| "grad_norm": 2.6295199394226074, | |
| "learning_rate": 0.00016, | |
| "loss": 4.7079, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03015075376884422, | |
| "grad_norm": 2.4342594146728516, | |
| "learning_rate": 0.00018, | |
| "loss": 6.0453, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03015075376884422, | |
| "eval_loss": 1.0322495698928833, | |
| "eval_runtime": 2.4292, | |
| "eval_samples_per_second": 51.869, | |
| "eval_steps_per_second": 25.934, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03350083752093802, | |
| "grad_norm": 8.440423011779785, | |
| "learning_rate": 0.0002, | |
| "loss": 6.299, | |
| "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": 685596789964800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |