Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 250101
+}

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "deberta-large",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "classification"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "classification": 0
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "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": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "problem_type": "multi_label_classification",
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.0.dev0",
+  "type_vocab_size": 0,
+  "vocab_size": 251000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:255a6359f066f9346e94f029c91d6c43ff8b71b458fe585ec6f7babc64207d43
+size 1115265124

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71e061024c578ca3c541cbfd93684a3b1756774a115fcd7a6c421f02afd95e5f
+size 2230649850

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5d9b3a71b33691150034399232a67fc24ea63d0158b95bc660fc1bd39d642fa
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfe876355c3ad8ea4874b0caf7fc5563ff8f1a4c8ddc26a911f599c6afa82741
+size 1064

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13c8d666d62a7bc4ac8f040aab68e942c861f93303156cc28f5c7e885d86d6e3
+size 4305025

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f42839ec04c3025630c31f069df13d750b5a3c969345d768ca8e0da9119600c7
+size 16331661

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250101": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

trainer_state.json

@@ -0,0 +1,126 @@
+{
+  "best_metric": 0.8532171581769437,
+  "best_model_checkpoint": "deberta-classification-chatrag/checkpoint-4228",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 6342,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.24,
+      "learning_rate": 9.211605171870073e-06,
+      "loss": 0.4251,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 8.423210343740146e-06,
+      "loss": 0.3842,
+      "step": 1000
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 7.634815515610218e-06,
+      "loss": 0.3502,
+      "step": 1500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 6.846420687480291e-06,
+      "loss": 0.334,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8458445040214477,
+      "eval_f1": 0.8458445040214477,
+      "eval_loss": 0.37406206130981445,
+      "eval_roc_auc": 0.846812946081549,
+      "eval_runtime": 22.7345,
+      "eval_samples_per_second": 65.627,
+      "eval_steps_per_second": 8.225,
+      "step": 2114
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 6.058025859350363e-06,
+      "loss": 0.3267,
+      "step": 2500
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 5.269631031220436e-06,
+      "loss": 0.3134,
+      "step": 3000
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 4.4812362030905085e-06,
+      "loss": 0.3171,
+      "step": 3500
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 3.6928413749605807e-06,
+      "loss": 0.3197,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8532171581769437,
+      "eval_f1": 0.8532171581769437,
+      "eval_loss": 0.42327263951301575,
+      "eval_roc_auc": 0.8199641368101195,
+      "eval_runtime": 22.432,
+      "eval_samples_per_second": 66.512,
+      "eval_steps_per_second": 8.336,
+      "step": 4228
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 2.904446546830653e-06,
+      "loss": 0.3166,
+      "step": 4500
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 2.1160517187007253e-06,
+      "loss": 0.2854,
+      "step": 5000
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 1.3276568905707978e-06,
+      "loss": 0.29,
+      "step": 5500
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 5.392620624408705e-07,
+      "loss": 0.2915,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8525469168900804,
+      "eval_f1": 0.8525469168900803,
+      "eval_loss": 0.4641505181789398,
+      "eval_roc_auc": 0.8244735354391916,
+      "eval_runtime": 22.4686,
+      "eval_samples_per_second": 66.404,
+      "eval_steps_per_second": 8.323,
+      "step": 6342
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6342,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 1.3345375348952064e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b18c4d3e38493cfa685ef07cffd2a926b11b29f521eb55401590d3a3427fd5e
+size 4792