| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.002319468068656255, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.731560228854182e-05, | |
| "eval_loss": 0.7148739695549011, | |
| "eval_runtime": 494.7064, | |
| "eval_samples_per_second": 11.009, | |
| "eval_steps_per_second": 5.504, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002319468068656255, | |
| "grad_norm": 4.81842041015625, | |
| "learning_rate": 6e-05, | |
| "loss": 11.6946, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000463893613731251, | |
| "grad_norm": 6.081270217895508, | |
| "learning_rate": 0.00012, | |
| "loss": 9.5971, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0006185248183083346, | |
| "eval_loss": 0.7004389762878418, | |
| "eval_runtime": 497.7994, | |
| "eval_samples_per_second": 10.94, | |
| "eval_steps_per_second": 5.47, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006958404205968764, | |
| "grad_norm": 10.870305061340332, | |
| "learning_rate": 0.00018, | |
| "loss": 8.6051, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.000927787227462502, | |
| "grad_norm": 9.37214183807373, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 7.6237, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0011597340343281275, | |
| "grad_norm": 13.013519287109375, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 6.9112, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0012370496366166692, | |
| "eval_loss": 0.7165130376815796, | |
| "eval_runtime": 498.1829, | |
| "eval_samples_per_second": 10.932, | |
| "eval_steps_per_second": 5.466, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0013916808411937528, | |
| "grad_norm": 63.50639724731445, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 6.4336, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0016236276480593784, | |
| "grad_norm": 4.184946537017822, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 4.8627, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.001855574454925004, | |
| "grad_norm": 5.131363391876221, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 5.2544, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.001855574454925004, | |
| "eval_loss": 0.645858108997345, | |
| "eval_runtime": 498.1385, | |
| "eval_samples_per_second": 10.933, | |
| "eval_steps_per_second": 5.466, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0020875212617906293, | |
| "grad_norm": 4.872713565826416, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 5.5263, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.002319468068656255, | |
| "grad_norm": 3.9103922843933105, | |
| "learning_rate": 0.0, | |
| "loss": 4.5022, | |
| "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": 5957676102057984.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |