| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.004018485031143259, |
| "eval_steps": 3, |
| "global_step": 10, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0004018485031143259, |
| "grad_norm": 1.4341641664505005, |
| "learning_rate": 2e-05, |
| "loss": 10.5636, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0008036970062286518, |
| "grad_norm": 1.5223380327224731, |
| "learning_rate": 4e-05, |
| "loss": 10.5317, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.0012055455093429777, |
| "grad_norm": 1.3711552619934082, |
| "learning_rate": 6e-05, |
| "loss": 10.5889, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.0012055455093429777, |
| "eval_loss": 10.556982040405273, |
| "eval_runtime": 26.1104, |
| "eval_samples_per_second": 40.137, |
| "eval_steps_per_second": 20.069, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.0016073940124573037, |
| "grad_norm": 1.3337384462356567, |
| "learning_rate": 8e-05, |
| "loss": 10.5303, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.0020092425155716293, |
| "grad_norm": 1.5682196617126465, |
| "learning_rate": 0.0001, |
| "loss": 10.5688, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.0024110910186859553, |
| "grad_norm": 1.5745059251785278, |
| "learning_rate": 0.00012, |
| "loss": 10.5141, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.0024110910186859553, |
| "eval_loss": 10.452882766723633, |
| "eval_runtime": 32.1563, |
| "eval_samples_per_second": 32.591, |
| "eval_steps_per_second": 16.295, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.0028129395218002813, |
| "grad_norm": 1.7966845035552979, |
| "learning_rate": 0.00014, |
| "loss": 10.3906, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.0032147880249146074, |
| "grad_norm": 2.097661018371582, |
| "learning_rate": 0.00016, |
| "loss": 10.352, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.003616636528028933, |
| "grad_norm": 2.159353017807007, |
| "learning_rate": 0.00018, |
| "loss": 10.2928, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.003616636528028933, |
| "eval_loss": 10.150440216064453, |
| "eval_runtime": 32.8812, |
| "eval_samples_per_second": 31.872, |
| "eval_steps_per_second": 15.936, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.004018485031143259, |
| "grad_norm": 2.4751334190368652, |
| "learning_rate": 0.0002, |
| "loss": 10.1359, |
| "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": 77002547134464.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
