| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0001332462790976562, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.332462790976562e-05, | |
| "grad_norm": 3.859285593032837, | |
| "learning_rate": 2e-05, | |
| "loss": 6.9983, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.332462790976562e-05, | |
| "eval_loss": 11.747756958007812, | |
| "eval_runtime": 982.3561, | |
| "eval_samples_per_second": 32.168, | |
| "eval_steps_per_second": 16.084, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.664925581953124e-05, | |
| "grad_norm": 5.559948444366455, | |
| "learning_rate": 4e-05, | |
| "loss": 11.2571, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 3.997388372929686e-05, | |
| "grad_norm": 3.377122640609741, | |
| "learning_rate": 6e-05, | |
| "loss": 6.1369, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 3.997388372929686e-05, | |
| "eval_loss": 11.708137512207031, | |
| "eval_runtime": 982.2424, | |
| "eval_samples_per_second": 32.171, | |
| "eval_steps_per_second": 16.086, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 5.329851163906248e-05, | |
| "grad_norm": 6.9697370529174805, | |
| "learning_rate": 8e-05, | |
| "loss": 9.4804, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 6.66231395488281e-05, | |
| "grad_norm": 6.502429008483887, | |
| "learning_rate": 0.0001, | |
| "loss": 10.7664, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 7.994776745859372e-05, | |
| "grad_norm": 8.073918342590332, | |
| "learning_rate": 0.00012, | |
| "loss": 10.8971, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 7.994776745859372e-05, | |
| "eval_loss": 10.742100715637207, | |
| "eval_runtime": 981.7601, | |
| "eval_samples_per_second": 32.187, | |
| "eval_steps_per_second": 16.094, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 9.327239536835933e-05, | |
| "grad_norm": 6.771646022796631, | |
| "learning_rate": 0.00014, | |
| "loss": 7.8575, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00010659702327812496, | |
| "grad_norm": 10.480707168579102, | |
| "learning_rate": 0.00016, | |
| "loss": 9.7917, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00011992165118789058, | |
| "grad_norm": 13.705483436584473, | |
| "learning_rate": 0.00018, | |
| "loss": 9.9592, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00011992165118789058, | |
| "eval_loss": 7.728565216064453, | |
| "eval_runtime": 982.2098, | |
| "eval_samples_per_second": 32.172, | |
| "eval_steps_per_second": 16.086, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0001332462790976562, | |
| "grad_norm": 8.87639331817627, | |
| "learning_rate": 0.0002, | |
| "loss": 6.1856, | |
| "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": 1849564248145920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |