Upload 12 files

deberta-qqp/checkpoint-11372/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "/ibex/user/anb/Model_merging/EMR_Merging-main/merge_lm/ckpts/deberta/deberta-base",
+  "architectures": [
+    "DebertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "c2p",
+    "p2c"
+  ],
+  "position_biased_input": false,
+  "relative_attention": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.1",
+  "type_vocab_size": 0,
+  "vocab_size": 50265
+}

deberta-qqp/checkpoint-11372/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fec1def4cc671d4abe1cd3d0799afc0ba0737e3391f5c6ebd000e82ecf5a0cd7
+size 556799560

deberta-qqp/checkpoint-11372/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d829f9c39255e31846c3452a3d9504a2829626bb40d7d5a3b8cb0d8f593bea2a
+size 1113718138

deberta-qqp/checkpoint-11372/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b15e0024c9c8a9fa93123e91e814d8633969775eb8da219dc7415031539202e1
+size 14244

deberta-qqp/checkpoint-11372/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcb02368389a2944db4d46f009be72e3b09193ed8d718a7d39478b8665393be8
+size 1064

deberta-qqp/checkpoint-11372/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

deberta-qqp/checkpoint-11372/tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "errors": "replace",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "DebertaTokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "gpt2"
+}

deberta-qqp/checkpoint-11372/trainer_state.json

@@ -0,0 +1,231 @@
+{
+  "best_metric": 0.9007096582669913,
+  "best_model_checkpoint": "./deberta/deberta-qqp/checkpoint-11372",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 11372,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17587055926837847,
+      "grad_norm": 3.8531415462493896,
+      "learning_rate": 1.9433227063407724e-05,
+      "loss": 0.4045,
+      "step": 500
+    },
+    {
+      "epoch": 0.35174111853675694,
+      "grad_norm": 2.7262914180755615,
+      "learning_rate": 1.8724760892667377e-05,
+      "loss": 0.2962,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5276116778051354,
+      "grad_norm": 3.3588902950286865,
+      "learning_rate": 1.801629472192703e-05,
+      "loss": 0.2733,
+      "step": 1500
+    },
+    {
+      "epoch": 0.7034822370735139,
+      "grad_norm": 3.294558525085449,
+      "learning_rate": 1.7307828551186684e-05,
+      "loss": 0.26,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8793527963418923,
+      "grad_norm": 2.744117498397827,
+      "learning_rate": 1.6599362380446334e-05,
+      "loss": 0.2518,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8997773930249815,
+      "eval_averaged_scores": 0.8820205469747713,
+      "eval_f1": 0.8642637009245612,
+      "eval_loss": 0.23822057247161865,
+      "eval_runtime": 29.0289,
+      "eval_samples_per_second": 1392.749,
+      "eval_steps_per_second": 10.886,
+      "step": 2843
+    },
+    {
+      "epoch": 1.0552233556102708,
+      "grad_norm": 2.7211148738861084,
+      "learning_rate": 1.5890896209705987e-05,
+      "loss": 0.2339,
+      "step": 3000
+    },
+    {
+      "epoch": 1.2310939148786493,
+      "grad_norm": 2.3029513359069824,
+      "learning_rate": 1.5182430038965641e-05,
+      "loss": 0.2013,
+      "step": 3500
+    },
+    {
+      "epoch": 1.4069644741470277,
+      "grad_norm": 2.8892529010772705,
+      "learning_rate": 1.4473963868225294e-05,
+      "loss": 0.1995,
+      "step": 4000
+    },
+    {
+      "epoch": 1.5828350334154062,
+      "grad_norm": 3.092597246170044,
+      "learning_rate": 1.3765497697484946e-05,
+      "loss": 0.1962,
+      "step": 4500
+    },
+    {
+      "epoch": 1.7587055926837847,
+      "grad_norm": 3.066741943359375,
+      "learning_rate": 1.30570315267446e-05,
+      "loss": 0.1956,
+      "step": 5000
+    },
+    {
+      "epoch": 1.9345761519521631,
+      "grad_norm": 2.238586664199829,
+      "learning_rate": 1.2348565356004251e-05,
+      "loss": 0.1924,
+      "step": 5500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9083848627256987,
+      "eval_averaged_scores": 0.8931025778201656,
+      "eval_f1": 0.8778202929146325,
+      "eval_loss": 0.22309303283691406,
+      "eval_runtime": 28.5349,
+      "eval_samples_per_second": 1416.859,
+      "eval_steps_per_second": 11.074,
+      "step": 5686
+    },
+    {
+      "epoch": 2.1104467112205416,
+      "grad_norm": 3.8230233192443848,
+      "learning_rate": 1.1640099185263905e-05,
+      "loss": 0.1664,
+      "step": 6000
+    },
+    {
+      "epoch": 2.28631727048892,
+      "grad_norm": 2.2658090591430664,
+      "learning_rate": 1.0931633014523556e-05,
+      "loss": 0.1512,
+      "step": 6500
+    },
+    {
+      "epoch": 2.4621878297572986,
+      "grad_norm": 3.0441300868988037,
+      "learning_rate": 1.022316684378321e-05,
+      "loss": 0.1482,
+      "step": 7000
+    },
+    {
+      "epoch": 2.638058389025677,
+      "grad_norm": 3.4634249210357666,
+      "learning_rate": 9.514700673042863e-06,
+      "loss": 0.1475,
+      "step": 7500
+    },
+    {
+      "epoch": 2.8139289482940555,
+      "grad_norm": 3.0935544967651367,
+      "learning_rate": 8.806234502302515e-06,
+      "loss": 0.1504,
+      "step": 8000
+    },
+    {
+      "epoch": 2.989799507562434,
+      "grad_norm": 3.8666305541992188,
+      "learning_rate": 8.097768331562168e-06,
+      "loss": 0.1422,
+      "step": 8500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9121444471926787,
+      "eval_averaged_scores": 0.8981692502004082,
+      "eval_f1": 0.8841940532081377,
+      "eval_loss": 0.22350537776947021,
+      "eval_runtime": 29.7406,
+      "eval_samples_per_second": 1359.42,
+      "eval_steps_per_second": 10.625,
+      "step": 8529
+    },
+    {
+      "epoch": 3.1656700668308124,
+      "grad_norm": 4.540077209472656,
+      "learning_rate": 7.389302160821822e-06,
+      "loss": 0.1134,
+      "step": 9000
+    },
+    {
+      "epoch": 3.341540626099191,
+      "grad_norm": 3.0426108837127686,
+      "learning_rate": 6.680835990081474e-06,
+      "loss": 0.1136,
+      "step": 9500
+    },
+    {
+      "epoch": 3.5174111853675694,
+      "grad_norm": 3.1100268363952637,
+      "learning_rate": 5.972369819341127e-06,
+      "loss": 0.1127,
+      "step": 10000
+    },
+    {
+      "epoch": 3.693281744635948,
+      "grad_norm": 2.454662561416626,
+      "learning_rate": 5.26390364860078e-06,
+      "loss": 0.1114,
+      "step": 10500
+    },
+    {
+      "epoch": 3.8691523039043263,
+      "grad_norm": 4.162189960479736,
+      "learning_rate": 4.555437477860433e-06,
+      "loss": 0.1116,
+      "step": 11000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9150136037595845,
+      "eval_averaged_scores": 0.9007096582669913,
+      "eval_f1": 0.8864057127743983,
+      "eval_loss": 0.24532988667488098,
+      "eval_runtime": 29.8322,
+      "eval_samples_per_second": 1355.245,
+      "eval_steps_per_second": 10.593,
+      "step": 11372
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 14215,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.47443196957658e+16,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": null
+}

deberta-qqp/checkpoint-11372/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faeb4d2b1daeec0bf53de26aedda3a621755a1068034a81aed5f53aa74540b46
+size 5176