upload_3

.gitattributes

@@ -32,16 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.xz filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
-models/met_joint_f78b0fa9c1d7718b9ed703ddcf621ec9_lf_sd_train_gen_4/ filter=lfs diff=lfs merge=lfs -text
-models/met_joint_f78b0fa9c1d7718b9ed703ddcf621ec9_lf_sd_train_gen_4/best filter=lfs diff=lfs merge=lfs -text
-models/met_joint_f78b0fa9c1d7718b9ed703ddcf621ec9_lf_sd_train_gen_4/config.json filter=lfs diff=lfs merge=lfs -text
-models/met_joint_f78b0fa9c1d7718b9ed703ddcf621ec9_lf_sd_train_gen_4/best/model.pth filter=lfs diff=lfs merge=lfs -text
-models/met_joint_f78b0fa9c1d7718b9ed703ddcf621ec9_lf_sd_train_gen_4/best/doc_encoder/added_tokens.json filter=lfs diff=lfs merge=lfs -text
-models/met_joint_f78b0fa9c1d7718b9ed703ddcf621ec9_lf_sd_train_gen_4/best/doc_encoder/config.json filter=lfs diff=lfs merge=lfs -text
-models/met_joint_f78b0fa9c1d7718b9ed703ddcf621ec9_lf_sd_train_gen_4/best/doc_encoder/merges.txt filter=lfs diff=lfs merge=lfs -text
-models/met_joint_f78b0fa9c1d7718b9ed703ddcf621ec9_lf_sd_train_gen_4/best/doc_encoder/model.safetensors filter=lfs diff=lfs merge=lfs -text
-models/met_joint_f78b0fa9c1d7718b9ed703ddcf621ec9_lf_sd_train_gen_4/best/doc_encoder/special_tokens_map.json filter=lfs diff=lfs merge=lfs -text
-models/met_joint_f78b0fa9c1d7718b9ed703ddcf621ec9_lf_sd_train_gen_4/best/doc_encoder/tokenizer_config.json filter=lfs diff=lfs merge=lfs -text
-models/met_joint_f78b0fa9c1d7718b9ed703ddcf621ec9_lf_sd_train_gen_4/best/doc_encoder/tokenizer.json filter=lfs diff=lfs merge=lfs -text
-models/met_joint_f78b0fa9c1d7718b9ed703ddcf621ec9_lf_sd_train_gen_4/best/doc_encoder/vocab.json filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -1,5 +1,3 @@
-models/
-models_orig/
 baseline_src/wandb
 data/raw_data
 **/wandb/

models/met_joint_f78b0fa9c1d7718b9ed703ddcf621ec9_lf_sd_train_gen_4/best/doc_encoder/added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "[SPEAKER_END]": 50266,
+  "[SPEAKER_START]": 50265
+}

models/met_joint_f78b0fa9c1d7718b9ed703ddcf621ec9_lf_sd_train_gen_4/best/doc_encoder/config.json

@@ -0,0 +1,55 @@
+{
+  "_name_or_path": "allenai/longformer-large-4096",
+  "architectures": [
+    "LongformerModel"
+  ],
+  "attention_mode": "longformer",
+  "attention_probs_dropout_prob": 0.1,
+  "attention_window": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "ignore_attention_mask": false,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 4098,
+  "model_type": "longformer",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "onnx_export": false,
+  "pad_token_id": 1,
+  "sep_token_id": 2,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "type_vocab_size": 1,
+  "vocab_size": 50267
+}

models/met_joint_f78b0fa9c1d7718b9ed703ddcf621ec9_lf_sd_train_gen_4/best/doc_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ab82ffdba31413b7bbbb925d54ac5765bc8ff9e5ddf4e1e7c9b6a2ae8bb2ffd
+size 1734276256

models/met_joint_f78b0fa9c1d7718b9ed703ddcf621ec9_lf_sd_train_gen_4/best/doc_encoder/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "[SPEAKER_START]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[SPEAKER_END]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

models/met_joint_f78b0fa9c1d7718b9ed703ddcf621ec9_lf_sd_train_gen_4/best/doc_encoder/tokenizer_config.json

@@ -0,0 +1,77 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50265": {
+      "content": "[SPEAKER_START]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50266": {
+      "content": "[SPEAKER_END]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "[SPEAKER_START]",
+    "[SPEAKER_END]"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "LongformerTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

models/met_joint_f78b0fa9c1d7718b9ed703ddcf621ec9_lf_sd_train_gen_4/best/model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e71f84325c6264b91dc0f6f0db2e618b89207ab25e54eb7973b4527bce8f9b0
+size 149249711

models/met_joint_f78b0fa9c1d7718b9ed703ddcf621ec9_lf_sd_train_gen_4/config.json

@@ -0,0 +1,146 @@
+{
+    "datasets": {
+        "fantasy": {
+            "canonical_cluster_threshold": 0,
+            "cluster_threshold": 0,
+            "has_conll": true,
+            "name": "fantasy",
+            "num_dev_docs": 20,
+            "num_test_docs": 20,
+            "num_train_docs": 171,
+            "targeted_eval": false
+        },
+        "litbank": {
+            "canonical_cluster_threshold": 0,
+            "cluster_threshold": 0,
+            "cross_val_split": 0,
+            "has_conll": true,
+            "name": "LitBank",
+            "num_dev_docs": 10,
+            "num_test_docs": 10,
+            "num_train_docs": 80,
+            "targeted_eval": false
+        }
+    },
+    "desc": "Major Entity Tracking",
+    "device": "cuda:0",
+    "infra": {
+        "is_local": true,
+        "work_dir": "./"
+    },
+    "keep_singletons": true,
+    "key": "lf_sd_train_gen_4",
+    "log_vals": false,
+    "metrics": [
+        "MUC",
+        "Bcub",
+        "CEAFE"
+    ],
+    "model": {
+        "doc_encoder": {
+            "add_speaker_tokens": true,
+            "chunking": "independent",
+            "finetune": true,
+            "speaker_end": "[SPEAKER_END]",
+            "speaker_start": "[SPEAKER_START]",
+            "transformer": {
+                "max_encoder_segment_len": 4096,
+                "max_segment_len": 4096,
+                "model_size": "large",
+                "model_str": "allenai/longformer-large-4096",
+                "name": "longformer"
+            }
+        },
+        "memory": {
+            "batch_size": 64,
+            "emb_size": 20,
+            "entity_rep": "wt_avg",
+            "mem_type": {
+                "eval_max_ents": null,
+                "max_ents": null,
+                "name": "unbounded"
+            },
+            "mlp_depth": 1,
+            "mlp_size": 3000,
+            "num_embeds": 10,
+            "num_feats": 2,
+            "pivot": false,
+            "pseudo_dist": true,
+            "rep_pos": "learned",
+            "sim_func": "hadamard",
+            "thresh": 0.0,
+            "type": "hybrid"
+        },
+        "mention_params": {
+            "emb_size": 20,
+            "ext_ment": false,
+            "ignore_non_gold": true,
+            "max_span_width": 20,
+            "ment_emb": "attn",
+            "ment_emb_to_size_factor": {
+                "attn": 3,
+                "endpoint": 2,
+                "max": 1
+            },
+            "mlp_depth": 1,
+            "mlp_size": 3000,
+            "top_span_ratio": 0.4,
+            "use_gold_ments": false,
+            "use_topk": false
+        },
+        "metadata_params": {
+            "default_genre": "nw",
+            "genres": [
+                "bc",
+                "bn",
+                "mz",
+                "nw",
+                "pt",
+                "tc",
+                "wb"
+            ],
+            "use_genre_feature": false
+        }
+    },
+    "optimizer": {
+        "fine_tune_lr": 1e-05,
+        "init_lr": 0.0003,
+        "lr_decay": "linear",
+        "max_gradient_norm": 1.0
+    },
+    "override_encoder": false,
+    "override_memory": false,
+    "paths": {
+        "base_data_dir": "${paths.resource_dir}/raw_data",
+        "base_model_dir": "${infra.work_dir}/../models",
+        "best_model_dir": ".//../models/met_joint_f78b0fa9c1d7718b9ed703ddcf621ec9_lf_sd_train_gen_4/best",
+        "best_model_path": "/home/admin/coref_research/gpt-coref-met-1/models/met_joint_f78b0fa9c1d7718b9ed703ddcf621ec9_lf_sd_train_gen_4/best/model.pth",
+        "conll_scorer": "${paths.resource_dir}/reference-coreference-scorers/scorer.pl",
+        "doc_encoder_dirname": "doc_encoder",
+        "model_dir": ".//../models/met_joint_f78b0fa9c1d7718b9ed703ddcf621ec9_lf_sd_train_gen_4",
+        "model_filename": "model.pth",
+        "model_name": null,
+        "model_name_prefix": "met_",
+        "model_path": "/home/admin/coref_research/gpt-coref-met-1/models/met_joint_f78b0fa9c1d7718b9ed703ddcf621ec9_lf_sd_train_gen_4/model.pth",
+        "resource_dir": "../data/"
+    },
+    "seed": 4,
+    "train": true,
+    "trainer": {
+        "dropout_rate": 0.3,
+        "eval_per_k_steps": null,
+        "eval_type": "full",
+        "generalise": true,
+        "label_smoothing_wt": 0.1,
+        "log_frequency": 500,
+        "max_evals": 25,
+        "max_training_segments": 1,
+        "ment_loss_incl": true,
+        "ment_loss_mode": "all",
+        "normalize_loss": false,
+        "num_training_steps": null,
+        "patience": 10,
+        "to_save_model": false
+    },
+    "use_wandb": true
+}

models/mod_checkpts.ipynb

@@ -0,0 +1,109 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/tmp/ipykernel_2893037/1660114035.py:11: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.\n",
+      "  checkpoint = torch.load(model_path)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "met_joint_f78b0fa9c1d7718b9ed703ddcf621ec9_lf_sd_train_gen_4\n",
+      "hybrid\n",
+      "False\n",
+      "met_joint_ffbdebf78d7907df10c789e0d8cc8992_lf_sd_train_final_runs_1\n",
+      "hybrid\n",
+      "False\n",
+      "met_joint_aa985942ad294012e11cbc13fccf7de9_lf_sd_train_runs_5\n",
+      "hybrid\n",
+      "False\n",
+      "met_joint_aa985942ad294012e11cbc13fccf7de9_lf_sd_train_runs_2\n",
+      "hybrid\n",
+      "False\n",
+      "met_joint_b9386d26e9d1192471fa4b95de7b44ef_lf_sd_train_final_runs_2\n",
+      "hybrid\n",
+      "False\n",
+      "met_joint_aa985942ad294012e11cbc13fccf7de9_lf_sd_train_runs_3\n",
+      "hybrid\n",
+      "False\n",
+      "met_joint_aa985942ad294012e11cbc13fccf7de9_lf_sd_train_runs_1\n",
+      "hybrid\n",
+      "False\n",
+      "met_joint_aa985942ad294012e11cbc13fccf7de9_lf_sd_train_runs_4\n",
+      "hybrid\n",
+      "False\n",
+      "met_joint_abfff0992d2512e1fa18eb3444686071_lf_sd_train_gen_5\n",
+      "hybrid\n",
+      "False\n",
+      "met_joint_fc741fbf5d3d3874c10921ddad5dca5b_lf_sd_train_final_runs_3\n",
+      "hybrid\n",
+      "False\n",
+      "met_joint_d2df7853437ea532c03908843d3348b6_lf_sd_train_final_runs_5\n",
+      "hybrid\n",
+      "False\n",
+      "met_joint_6d2fa90c72a23c2c9c4ebcf439b39d15_lf_sd_train_final_runs_4\n",
+      "hybrid\n",
+      "False\n"
+     ]
+    }
+   ],
+   "source": [
+    "import torch\n",
+    "import os\n",
+    "\n",
+    "models_par = os.listdir('models_7_6_24')\n",
+    "for model_dir in models_par:\n",
+    "    # if model_dir.startswith(\"met\"):\n",
+    "    #     print(model_dir)\n",
+    "    model_path_folders = [\"models_7_6_24\", model_dir, \"best\", \"model.pth\"]\n",
+    "    model_path = os.path.join(*model_path_folders)\n",
+    "    if os.path.exists(model_path):\n",
+    "        checkpoint = torch.load(model_path)\n",
+    "        if 'type' in checkpoint['config']['model']['memory'] and checkpoint['config']['model']['memory']['type'] == 'hybrid':\n",
+    "            print(model_dir)\n",
+    "            print(checkpoint['config']['model']['memory']['type'])\n",
+    "            print(checkpoint['config']['model']['memory']['pivot'])\n",
+    "            # checkpoint['config']['model']['memory']['type'] = 'hybrid'\n",
+    "            # checkpoint['config']['model']['memory']['type'] = 'static'\n",
+    "            # torch.save(checkpoint, model_path)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "myenv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}