| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.018769551616266946, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0020855057351407717, | |
| "grad_norm": 0.7125914692878723, | |
| "learning_rate": 2e-05, | |
| "loss": 1.9033, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0020855057351407717, | |
| "eval_loss": 2.006241798400879, | |
| "eval_runtime": 6.2744, | |
| "eval_samples_per_second": 32.195, | |
| "eval_steps_per_second": 16.097, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004171011470281543, | |
| "grad_norm": 0.7530663013458252, | |
| "learning_rate": 4e-05, | |
| "loss": 2.062, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006256517205422315, | |
| "grad_norm": 0.6641163229942322, | |
| "learning_rate": 6e-05, | |
| "loss": 1.5411, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006256517205422315, | |
| "eval_loss": 2.005281925201416, | |
| "eval_runtime": 6.2399, | |
| "eval_samples_per_second": 32.372, | |
| "eval_steps_per_second": 16.186, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008342022940563087, | |
| "grad_norm": 0.7793768644332886, | |
| "learning_rate": 8e-05, | |
| "loss": 2.1512, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.010427528675703858, | |
| "grad_norm": 0.7216593623161316, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6963, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01251303441084463, | |
| "grad_norm": 0.6446533799171448, | |
| "learning_rate": 0.00012, | |
| "loss": 1.6763, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01251303441084463, | |
| "eval_loss": 1.991089940071106, | |
| "eval_runtime": 6.3373, | |
| "eval_samples_per_second": 31.875, | |
| "eval_steps_per_second": 15.937, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.014598540145985401, | |
| "grad_norm": 0.8114572763442993, | |
| "learning_rate": 0.00014, | |
| "loss": 1.7647, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.016684045881126174, | |
| "grad_norm": 0.6929518580436707, | |
| "learning_rate": 0.00016, | |
| "loss": 1.4965, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.018769551616266946, | |
| "grad_norm": 0.7459466457366943, | |
| "learning_rate": 0.00018, | |
| "loss": 1.8414, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.018769551616266946, | |
| "eval_loss": 1.9566819667816162, | |
| "eval_runtime": 6.3571, | |
| "eval_samples_per_second": 31.775, | |
| "eval_steps_per_second": 15.888, | |
| "step": 9 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 487594897440768.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |