| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0011228385358185494, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00011228385358185493, | |
| "grad_norm": 1.0996258424711414e-05, | |
| "learning_rate": 2e-05, | |
| "loss": 46.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00011228385358185493, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 21.154, | |
| "eval_samples_per_second": 177.271, | |
| "eval_steps_per_second": 88.636, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00022456770716370987, | |
| "grad_norm": 5.615591362584382e-06, | |
| "learning_rate": 4e-05, | |
| "loss": 46.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00033685156074556477, | |
| "grad_norm": 8.00515499577159e-06, | |
| "learning_rate": 6e-05, | |
| "loss": 46.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00033685156074556477, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 21.028, | |
| "eval_samples_per_second": 178.334, | |
| "eval_steps_per_second": 89.167, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00044913541432741973, | |
| "grad_norm": 1.088977023755433e-05, | |
| "learning_rate": 8e-05, | |
| "loss": 46.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0005614192679092747, | |
| "grad_norm": 5.80341111344751e-06, | |
| "learning_rate": 0.0001, | |
| "loss": 46.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0006737031214911295, | |
| "grad_norm": 5.071321993455058e-06, | |
| "learning_rate": 0.00012, | |
| "loss": 46.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0006737031214911295, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 21.3045, | |
| "eval_samples_per_second": 176.019, | |
| "eval_steps_per_second": 88.01, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0007859869750729845, | |
| "grad_norm": 8.596444786235224e-06, | |
| "learning_rate": 0.00014, | |
| "loss": 46.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0008982708286548395, | |
| "grad_norm": 6.399572157533839e-06, | |
| "learning_rate": 0.00016, | |
| "loss": 46.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0010105546822366943, | |
| "grad_norm": 7.463736892532324e-06, | |
| "learning_rate": 0.00018, | |
| "loss": 46.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0010105546822366943, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 21.2508, | |
| "eval_samples_per_second": 176.464, | |
| "eval_steps_per_second": 88.232, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0011228385358185494, | |
| "grad_norm": 6.37277889836696e-06, | |
| "learning_rate": 0.0002, | |
| "loss": 46.0, | |
| "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": 328727494656.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |