Upload 2 files

config.json

@@ -0,0 +1,51 @@
+{
+  "accelerator_kwargs": {},
+  "adap_kl_ctrl": true,
+  "backward_batch_size": 1,
+  "batch_size": 64,
+  "cliprange": 0.2,
+  "cliprange_value": 0.2,
+  "compare_steps": 1,
+  "dataset_num_proc": null,
+  "early_stopping": true,
+  "exp_name": "rl_training",
+  "forward_batch_size": null,
+  "gamma": 1,
+  "global_backward_batch_size": 1,
+  "global_batch_size": 64,
+  "gradient_accumulation_steps": 1,
+  "gradient_checkpointing": false,
+  "horizon": 10000,
+  "init_kl_coef": 0.2,
+  "is_encoder_decoder": false,
+  "is_peft_model": true,
+  "kl_penalty": "kl",
+  "lam": 0.95,
+  "learning_rate": 1.4e-05,
+  "log_with": "mlflow",
+  "max_grad_norm": null,
+  "mini_batch_size": 1,
+  "model_name": "DLI-Lab/camel",
+  "optimize_cuda_cache": true,
+  "optimize_device_cache": false,
+  "ppo_epochs": 4,
+  "project_kwargs": {},
+  "push_to_hub_if_best_kwargs": {},
+  "query_dataset": "imdb",
+  "ratio_threshold": 10.0,
+  "remove_unused_columns": true,
+  "reward_model": "sentiment-analysis:lvwerra/distilbert-imdb",
+  "score_clip": null,
+  "seed": 0,
+  "steps": 10000,
+  "target": 6,
+  "target_kl": 0.1,
+  "task_name": null,
+  "tracker_kwargs": {},
+  "tracker_project_name": "trl",
+  "use_score_norm": false,
+  "use_score_scaling": false,
+  "vf_coef": 0.1,
+  "whiten_rewards": false,
+  "world_size": 1
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fae489432c27a7e85f40bdca42acd2f30e01ad9a447a4fae340354db5fdd3285
+size 17916