Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-base",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "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-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,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22b202821370d59aea2ad4b2179043beab0f4331581c2e2c9055de33aab53d21
+size 737719272

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b7d14c98326f86746911545c16d9cd3d1d50a9f515f68d78e06e3b49c811b9d
+size 14244

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:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

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
+    },
+    "128000": {
+      "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 +1,85 @@
+{
+  "best_metric": 0.16614657640457153,
+  "best_model_checkpoint": "/home/paperspace/microsoft_deberta-v3-base_cpt_f89a5abe/checkpoint-3744",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 3744,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.27,
+      "learning_rate": 9.109686609686609e-07,
+      "loss": 0.4669,
+      "step": 500
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 8.219373219373219e-07,
+      "loss": 0.2923,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 7.329059829059828e-07,
+      "loss": 0.2644,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9365846057961982,
+      "eval_f1": 0.9374518233030922,
+      "eval_loss": 0.20392829179763794,
+      "eval_precision": 0.9391690915156866,
+      "eval_recall": 0.9365846057961982,
+      "eval_runtime": 9.474,
+      "eval_samples_per_second": 677.432,
+      "eval_steps_per_second": 42.432,
+      "step": 1872
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 6.438746438746438e-07,
+      "loss": 0.2187,
+      "step": 2000
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 5.548433048433048e-07,
+      "loss": 0.207,
+      "step": 2500
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 4.658119658119658e-07,
+      "loss": 0.2034,
+      "step": 3000
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 3.767806267806268e-07,
+      "loss": 0.1867,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.946712371455282,
+      "eval_f1": 0.9475582315535889,
+      "eval_loss": 0.16614657640457153,
+      "eval_precision": 0.9495886957118708,
+      "eval_recall": 0.946712371455282,
+      "eval_runtime": 9.3971,
+      "eval_samples_per_second": 682.974,
+      "eval_steps_per_second": 42.779,
+      "step": 3744
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5616,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 2005789101411648.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b39992d215a68c4a96e0f63c16cc14cc15b589cf310328d9de08a6f3a63d03e
+size 4664