| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.14109347442680775, | |
| "eval_steps": 8, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007054673721340388, | |
| "eval_loss": 4.875167369842529, | |
| "eval_runtime": 1.7994, | |
| "eval_samples_per_second": 33.345, | |
| "eval_steps_per_second": 16.672, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.021164021164021163, | |
| "grad_norm": 2.9136528968811035, | |
| "learning_rate": 6e-05, | |
| "loss": 4.8761, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.042328042328042326, | |
| "grad_norm": 3.0984208583831787, | |
| "learning_rate": 0.00012, | |
| "loss": 4.9452, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0564373897707231, | |
| "eval_loss": 4.590116024017334, | |
| "eval_runtime": 1.4109, | |
| "eval_samples_per_second": 42.527, | |
| "eval_steps_per_second": 21.264, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06349206349206349, | |
| "grad_norm": 3.0312323570251465, | |
| "learning_rate": 0.00018, | |
| "loss": 4.6371, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08465608465608465, | |
| "grad_norm": 3.1206839084625244, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 4.444, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.10582010582010581, | |
| "grad_norm": 3.172377109527588, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 3.8552, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1128747795414462, | |
| "eval_loss": 3.4600846767425537, | |
| "eval_runtime": 1.4217, | |
| "eval_samples_per_second": 42.202, | |
| "eval_steps_per_second": 21.101, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.12698412698412698, | |
| "grad_norm": 2.4773268699645996, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 3.3272, | |
| "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": 1029368772034560.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |