Upload 12 files

deberta-sst2/checkpoint-4212/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-sst2/checkpoint-4212/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:737ce4851825587c9e0463b1fc6857b3f47e0424391a4414f1b7c25c6fd38fa0
+size 556799560

deberta-sst2/checkpoint-4212/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:687b06f92ce580bfa9002bf15527783d34118de4f4f45557dbe30069a6cef5bb
+size 1113718138

deberta-sst2/checkpoint-4212/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94a3ca709ce130b9dd7e786e66f15df196746d68d1d3d36a97d34728a4c5ae31
+size 14244

deberta-sst2/checkpoint-4212/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d5b2038593b7881ef14e6df5b8dae5b35e4860f7def205ab0f1ef88062b017d
+size 1064

deberta-sst2/checkpoint-4212/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-sst2/checkpoint-4212/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-sst2/checkpoint-4212/trainer_state.json

@@ -0,0 +1,125 @@
+{
+  "best_metric": 0.9506880733944955,
+  "best_model_checkpoint": "./deberta/deberta-sst2/checkpoint-4212",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 4212,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4748338081671415,
+      "grad_norm": 7.512232780456543,
+      "learning_rate": 1.845111326234269e-05,
+      "loss": 0.3521,
+      "step": 500
+    },
+    {
+      "epoch": 0.949667616334283,
+      "grad_norm": 3.8770008087158203,
+      "learning_rate": 1.6515004840271057e-05,
+      "loss": 0.19,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9472477064220184,
+      "eval_loss": 0.174738809466362,
+      "eval_runtime": 0.6354,
+      "eval_samples_per_second": 1372.414,
+      "eval_steps_per_second": 22.034,
+      "step": 1053
+    },
+    {
+      "epoch": 1.4245014245014245,
+      "grad_norm": 2.0795986652374268,
+      "learning_rate": 1.457889641819942e-05,
+      "loss": 0.1376,
+      "step": 1500
+    },
+    {
+      "epoch": 1.899335232668566,
+      "grad_norm": 2.3676655292510986,
+      "learning_rate": 1.2642787996127783e-05,
+      "loss": 0.1272,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.948394495412844,
+      "eval_loss": 0.17961029708385468,
+      "eval_runtime": 0.6356,
+      "eval_samples_per_second": 1372.017,
+      "eval_steps_per_second": 22.028,
+      "step": 2106
+    },
+    {
+      "epoch": 2.3741690408357075,
+      "grad_norm": 3.6499791145324707,
+      "learning_rate": 1.0706679574056149e-05,
+      "loss": 0.0975,
+      "step": 2500
+    },
+    {
+      "epoch": 2.849002849002849,
+      "grad_norm": 0.41007331013679504,
+      "learning_rate": 8.770571151984512e-06,
+      "loss": 0.0888,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9472477064220184,
+      "eval_loss": 0.16663160920143127,
+      "eval_runtime": 0.6347,
+      "eval_samples_per_second": 1373.947,
+      "eval_steps_per_second": 22.059,
+      "step": 3159
+    },
+    {
+      "epoch": 3.3238366571699904,
+      "grad_norm": 6.5026469230651855,
+      "learning_rate": 6.8344627299128755e-06,
+      "loss": 0.0692,
+      "step": 3500
+    },
+    {
+      "epoch": 3.798670465337132,
+      "grad_norm": 2.6195755004882812,
+      "learning_rate": 4.898354307841239e-06,
+      "loss": 0.0622,
+      "step": 4000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9506880733944955,
+      "eval_loss": 0.19045796990394592,
+      "eval_runtime": 0.6182,
+      "eval_samples_per_second": 1410.452,
+      "eval_steps_per_second": 22.645,
+      "step": 4212
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5265,
+  "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": 7307969952955116.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

deberta-sst2/checkpoint-4212/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a375f0d3dfa6fdbd9bc88fca0c7b38e43bfc555acab95a924a16cdf2c11ca57
+size 5176