first commit

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<<": 32100,
+  ">>": 32101,
+  "[CLS]": 32102,
+  "[SEP]": 32103
+}

data_args.json

@@ -0,0 +1,15 @@
+{
+    "model_style": "enc",
+    "task": "multiarith",
+    "trajectory_path": "data/discriminator_data/sampled_trajectories/multiarith-clean/llama-7b/trajectories.jsonl",
+    "validation_split_percentage": 5,
+    "max_len": 512,
+    "n_examples": null,
+    "dev_is_train": false,
+    "invalid_prefix_prob": 0.0,
+    "max_alignment_cost": 2.0,
+    "step_aligner_model": "roscoe",
+    "step_delimiter": null,
+    "break_after_extra_step": false,
+    "use_correct_samples": false
+}

model_args.json

@@ -0,0 +1,4 @@
+{
+    "model": "google/flan-t5-large",
+    "pooling": "max"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e85613bfeea255b9b4a36fe6fbc9b97befe2317ec648adbba2f88169440e9e70
+size 3136877397

special_tokens_map.json

@@ -0,0 +1,109 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "cls_token": "[CLS]",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "sep_token": "[SEP]",
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

tokenizer_config.json

@@ -0,0 +1,112 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

train_args.json

@@ -0,0 +1,121 @@
+{
+    "output_dir": "ckpts/discrim/contrastive_models/gen.llama-7b/flan_t5_large_multiarith-clean_100K/",
+    "overwrite_output_dir": false,
+    "do_train": false,
+    "do_eval": true,
+    "do_predict": false,
+    "evaluation_strategy": "steps",
+    "prediction_loss_only": true,
+    "per_device_train_batch_size": 8,
+    "per_device_eval_batch_size": 8,
+    "per_gpu_train_batch_size": null,
+    "per_gpu_eval_batch_size": null,
+    "gradient_accumulation_steps": 2,
+    "eval_accumulation_steps": null,
+    "eval_delay": 0,
+    "learning_rate": 6e-05,
+    "weight_decay": 0.01,
+    "adam_beta1": 0.9,
+    "adam_beta2": 0.999,
+    "adam_epsilon": 1e-08,
+    "max_grad_norm": 1.0,
+    "num_train_epochs": 5.0,
+    "max_steps": -1,
+    "lr_scheduler_type": "cosine_with_restarts",
+    "warmup_ratio": 0.06,
+    "warmup_steps": 0,
+    "log_level": "passive",
+    "log_level_replica": "warning",
+    "log_on_each_node": true,
+    "logging_dir": "ckpts/discrim/contrastive_models/gen.llama-7b/flan_t5_large_multiarith-clean_100K/runs/May20_03-24-27_leibniz",
+    "logging_strategy": "steps",
+    "logging_first_step": false,
+    "logging_steps": 50,
+    "logging_nan_inf_filter": true,
+    "save_strategy": "steps",
+    "save_steps": 1000,
+    "save_total_limit": 2,
+    "save_safetensors": false,
+    "save_on_each_node": false,
+    "no_cuda": false,
+    "use_mps_device": false,
+    "seed": 7,
+    "data_seed": null,
+    "jit_mode_eval": false,
+    "use_ipex": false,
+    "bf16": true,
+    "fp16": false,
+    "fp16_opt_level": "O1",
+    "half_precision_backend": "cuda_amp",
+    "bf16_full_eval": false,
+    "fp16_full_eval": false,
+    "tf32": null,
+    "local_rank": 0,
+    "xpu_backend": null,
+    "tpu_num_cores": null,
+    "tpu_metrics_debug": false,
+    "debug": [],
+    "dataloader_drop_last": false,
+    "eval_steps": 1000,
+    "dataloader_num_workers": 0,
+    "past_index": -1,
+    "run_name": "ckpts/discrim/contrastive_models/gen.llama-7b/flan_t5_large_multiarith-clean_100K/",
+    "disable_tqdm": false,
+    "remove_unused_columns": true,
+    "label_names": null,
+    "load_best_model_at_end": true,
+    "metric_for_best_model": "loss",
+    "greater_is_better": false,
+    "ignore_data_skip": false,
+    "sharded_ddp": [],
+    "fsdp": [],
+    "fsdp_min_num_params": 0,
+    "fsdp_config": {
+        "fsdp_min_num_params": 0,
+        "xla": false,
+        "xla_fsdp_grad_ckpt": false
+    },
+    "fsdp_transformer_layer_cls_to_wrap": null,
+    "deepspeed": null,
+    "label_smoothing_factor": 0.0,
+    "optim": "adamw_hf",
+    "optim_args": null,
+    "adafactor": false,
+    "group_by_length": false,
+    "length_column_name": "length",
+    "report_to": [
+        "wandb"
+    ],
+    "ddp_find_unused_parameters": null,
+    "ddp_bucket_cap_mb": null,
+    "dataloader_pin_memory": true,
+    "skip_memory_metrics": true,
+    "use_legacy_prediction_loop": false,
+    "push_to_hub": false,
+    "resume_from_checkpoint": null,
+    "hub_model_id": null,
+    "hub_strategy": "every_save",
+    "hub_token": null,
+    "hub_private_repo": false,
+    "gradient_checkpointing": false,
+    "include_inputs_for_metrics": false,
+    "fp16_backend": "auto",
+    "push_to_hub_model_id": null,
+    "push_to_hub_organization": null,
+    "push_to_hub_token": null,
+    "_n_gpu": 1,
+    "mp_parameters": "",
+    "auto_find_batch_size": false,
+    "full_determinism": false,
+    "torchdynamo": null,
+    "ray_scope": "last",
+    "ddp_timeout": 1800,
+    "torch_compile": false,
+    "torch_compile_backend": null,
+    "torch_compile_mode": null,
+    "margin": 1.0,
+    "ckpt_dir": null,
+    "loss_type": "maxmargin",
+    "fix_tokenizer": false,
+    "dev_metric": "loss"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59c4852fc2e1d52afb34e43ff6e4a8de9233aac1b180bdae5a6a12162246233b
+size 3835