| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00034581733928139156, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.4581733928139156e-05, | |
| "grad_norm": 0.14639905095100403, | |
| "learning_rate": 2e-05, | |
| "loss": 0.489, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.4581733928139156e-05, | |
| "eval_loss": 0.3979541063308716, | |
| "eval_runtime": 626.7825, | |
| "eval_samples_per_second": 19.426, | |
| "eval_steps_per_second": 9.713, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.916346785627831e-05, | |
| "grad_norm": 0.14317984879016876, | |
| "learning_rate": 4e-05, | |
| "loss": 0.4193, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00010374520178441747, | |
| "grad_norm": 0.11532880365848541, | |
| "learning_rate": 6e-05, | |
| "loss": 0.3421, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00010374520178441747, | |
| "eval_loss": 0.39726510643959045, | |
| "eval_runtime": 626.4893, | |
| "eval_samples_per_second": 19.435, | |
| "eval_steps_per_second": 9.718, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00013832693571255662, | |
| "grad_norm": 0.12160821259021759, | |
| "learning_rate": 8e-05, | |
| "loss": 0.3099, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00017290866964069578, | |
| "grad_norm": 0.1576390117406845, | |
| "learning_rate": 0.0001, | |
| "loss": 0.438, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00020749040356883493, | |
| "grad_norm": 0.14320649206638336, | |
| "learning_rate": 0.00012, | |
| "loss": 0.2759, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00020749040356883493, | |
| "eval_loss": 0.3893989622592926, | |
| "eval_runtime": 626.4853, | |
| "eval_samples_per_second": 19.435, | |
| "eval_steps_per_second": 9.718, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002420721374969741, | |
| "grad_norm": 0.16904571652412415, | |
| "learning_rate": 0.00014, | |
| "loss": 0.4141, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00027665387142511324, | |
| "grad_norm": 0.1876726597547531, | |
| "learning_rate": 0.00016, | |
| "loss": 0.4954, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0003112356053532524, | |
| "grad_norm": 0.15570510923862457, | |
| "learning_rate": 0.00018, | |
| "loss": 0.322, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0003112356053532524, | |
| "eval_loss": 0.3594510853290558, | |
| "eval_runtime": 626.3708, | |
| "eval_samples_per_second": 19.439, | |
| "eval_steps_per_second": 9.719, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00034581733928139156, | |
| "grad_norm": 0.18487077951431274, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4807, | |
| "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": 3257466271825920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |