| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0017720285296593276, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00017720285296593275, | |
| "grad_norm": 68.23906707763672, | |
| "learning_rate": 2e-05, | |
| "loss": 20.6003, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00017720285296593275, | |
| "eval_loss": 4.623178482055664, | |
| "eval_runtime": 34.268, | |
| "eval_samples_per_second": 69.365, | |
| "eval_steps_per_second": 34.697, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003544057059318655, | |
| "grad_norm": 47.974525451660156, | |
| "learning_rate": 4e-05, | |
| "loss": 18.135, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005316085588977983, | |
| "grad_norm": 67.08570861816406, | |
| "learning_rate": 6e-05, | |
| "loss": 18.75, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005316085588977983, | |
| "eval_loss": 4.618465423583984, | |
| "eval_runtime": 32.7311, | |
| "eval_samples_per_second": 72.622, | |
| "eval_steps_per_second": 36.326, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000708811411863731, | |
| "grad_norm": 59.070701599121094, | |
| "learning_rate": 8e-05, | |
| "loss": 17.0189, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008860142648296638, | |
| "grad_norm": 53.60502624511719, | |
| "learning_rate": 0.0001, | |
| "loss": 18.4737, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0010632171177955966, | |
| "grad_norm": 62.920711517333984, | |
| "learning_rate": 0.00012, | |
| "loss": 18.7371, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0010632171177955966, | |
| "eval_loss": 4.5854315757751465, | |
| "eval_runtime": 32.4984, | |
| "eval_samples_per_second": 73.142, | |
| "eval_steps_per_second": 36.586, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0012404199707615293, | |
| "grad_norm": 96.0009765625, | |
| "learning_rate": 0.00014, | |
| "loss": 21.3063, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.001417622823727462, | |
| "grad_norm": 56.73752975463867, | |
| "learning_rate": 0.00016, | |
| "loss": 16.3515, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0015948256766933947, | |
| "grad_norm": 55.107513427734375, | |
| "learning_rate": 0.00018, | |
| "loss": 19.0825, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0015948256766933947, | |
| "eval_loss": 4.481025218963623, | |
| "eval_runtime": 32.4589, | |
| "eval_samples_per_second": 73.231, | |
| "eval_steps_per_second": 36.631, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0017720285296593276, | |
| "grad_norm": 64.37794494628906, | |
| "learning_rate": 0.0002, | |
| "loss": 18.2627, | |
| "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": 122819992092672.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |