Upload 12 files

deberta-rte/checkpoint-195/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-rte/checkpoint-195/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3d9c0fcb565b5ec7f327bc236e07de35feef7ea10cb23556c8d2229e10edaaf
+size 556799560

deberta-rte/checkpoint-195/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92b32713fc6413a81f3f4aa575e187fb2f4196a9683037c81e9ce6fa9b14e6bd
+size 1113718138

deberta-rte/checkpoint-195/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a5a6da8a6d802e5ecb11066a1fbc248bceacac8f7bc901121114e3f9630a6ba
+size 14244

deberta-rte/checkpoint-195/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6341ae854532c35d5eb7c85e22f5fd447dd3009c5c76f080cb88f0f539b9815b
+size 1064

deberta-rte/checkpoint-195/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-rte/checkpoint-195/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-rte/checkpoint-195/trainer_state.json

@@ -0,0 +1,78 @@
+{
+  "best_metric": 0.6931407942238267,
+  "best_model_checkpoint": "./deberta/deberta-rte/checkpoint-195",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 195,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.6933599710464478,
+      "eval_runtime": 0.5548,
+      "eval_samples_per_second": 499.265,
+      "eval_steps_per_second": 9.012,
+      "step": 39
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6921877264976501,
+      "eval_runtime": 0.5556,
+      "eval_samples_per_second": 498.571,
+      "eval_steps_per_second": 8.999,
+      "step": 78
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.48014440433212996,
+      "eval_loss": 0.6923734545707703,
+      "eval_runtime": 0.5554,
+      "eval_samples_per_second": 498.763,
+      "eval_steps_per_second": 9.003,
+      "step": 117
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6606498194945848,
+      "eval_loss": 0.6229077577590942,
+      "eval_runtime": 0.5584,
+      "eval_samples_per_second": 496.1,
+      "eval_steps_per_second": 8.955,
+      "step": 156
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6931407942238267,
+      "eval_loss": 0.6258442401885986,
+      "eval_runtime": 0.5562,
+      "eval_samples_per_second": 497.991,
+      "eval_steps_per_second": 8.989,
+      "step": 195
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 195,
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1464296959816440.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

deberta-rte/checkpoint-195/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6983fbdbe5c9200279b56f1b2ecd7a0282a9a86ea9f2d5a3b96b37fdec8455d
+size 5176