| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0035816618911174787, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00011938872970391595, | |
| "eval_loss": 5.59450101852417, | |
| "eval_runtime": 205.8742, | |
| "eval_samples_per_second": 17.132, | |
| "eval_steps_per_second": 8.568, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00035816618911174784, | |
| "grad_norm": 14.525588035583496, | |
| "learning_rate": 6e-05, | |
| "loss": 5.7848, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0007163323782234957, | |
| "grad_norm": 9.061497688293457, | |
| "learning_rate": 0.00012, | |
| "loss": 3.8537, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0009551098376313276, | |
| "eval_loss": 1.2870450019836426, | |
| "eval_runtime": 204.3938, | |
| "eval_samples_per_second": 17.256, | |
| "eval_steps_per_second": 8.63, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0010744985673352436, | |
| "grad_norm": 5.725028991699219, | |
| "learning_rate": 0.00018, | |
| "loss": 1.6249, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0014326647564469914, | |
| "grad_norm": 5.267549514770508, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.0863, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0017908309455587394, | |
| "grad_norm": 3.9862494468688965, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.9606, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0019102196752626551, | |
| "eval_loss": 0.8825110197067261, | |
| "eval_runtime": 204.4853, | |
| "eval_samples_per_second": 17.248, | |
| "eval_steps_per_second": 8.627, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.002148997134670487, | |
| "grad_norm": 2.57089900970459, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.8719, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.002507163323782235, | |
| "grad_norm": 3.1137900352478027, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.7725, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0028653295128939827, | |
| "grad_norm": 3.288762092590332, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.912, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0028653295128939827, | |
| "eval_loss": 0.8639681339263916, | |
| "eval_runtime": 204.5208, | |
| "eval_samples_per_second": 17.245, | |
| "eval_steps_per_second": 8.625, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0032234957020057307, | |
| "grad_norm": 3.853311061859131, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 1.0914, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0035816618911174787, | |
| "grad_norm": 2.4475674629211426, | |
| "learning_rate": 0.0, | |
| "loss": 0.8377, | |
| "step": 30 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1221045163851776e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |