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 sha256:34d8467f81801f2ddf8c2cb1d97ac532d7fce64bf18d4c2e7c653699916ffc63
+size 737719272

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:553f734d315ce4b397000d04d1617ecd9c29d02f6eb29ee8973931c32bddcd0f
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a6bd38f765e71367a684587431dace6d068128f9bce8b6ee5462f5937bb3135
+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: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 +1,181 @@
+{
+  "best_metric": 0.15075480937957764,
+  "best_model_checkpoint": "/home/paperspace/microsoft_deberta-v3-base_cpt_64aa255e/checkpoint-9820",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 9820,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "learning_rate": 9.709048588885654e-07,
+      "loss": 0.5526,
+      "step": 500
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 9.418097177771311e-07,
+      "loss": 0.2449,
+      "step": 1000
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 9.127145766656967e-07,
+      "loss": 0.1637,
+      "step": 1500
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 8.836194355542625e-07,
+      "loss": 0.1627,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9574516238542492,
+      "eval_f1": 0.9576402605174089,
+      "eval_loss": 0.15390127897262573,
+      "eval_precision": 0.9583932523988209,
+      "eval_recall": 0.9574516238542492,
+      "eval_runtime": 11.3772,
+      "eval_samples_per_second": 776.73,
+      "eval_steps_per_second": 48.606,
+      "step": 2455
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 8.54524294442828e-07,
+      "loss": 0.1536,
+      "step": 2500
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 8.254291533313936e-07,
+      "loss": 0.1497,
+      "step": 3000
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 7.963340122199592e-07,
+      "loss": 0.1478,
+      "step": 3500
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 7.672388711085248e-07,
+      "loss": 0.1452,
+      "step": 4000
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 7.381437299970904e-07,
+      "loss": 0.149,
+      "step": 4500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9596016747765078,
+      "eval_f1": 0.9597684084567597,
+      "eval_loss": 0.15375804901123047,
+      "eval_precision": 0.9604205146694305,
+      "eval_recall": 0.9596016747765078,
+      "eval_runtime": 11.4943,
+      "eval_samples_per_second": 768.813,
+      "eval_steps_per_second": 48.111,
+      "step": 4910
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 7.090485888856561e-07,
+      "loss": 0.1415,
+      "step": 5000
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 6.799534477742217e-07,
+      "loss": 0.1358,
+      "step": 5500
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 6.508583066627873e-07,
+      "loss": 0.1382,
+      "step": 6000
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 6.217631655513529e-07,
+      "loss": 0.1289,
+      "step": 6500
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 5.926680244399185e-07,
+      "loss": 0.1329,
+      "step": 7000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9591490324770849,
+      "eval_f1": 0.9593624018161547,
+      "eval_loss": 0.16056260466575623,
+      "eval_precision": 0.9603821831580927,
+      "eval_recall": 0.9591490324770849,
+      "eval_runtime": 11.3768,
+      "eval_samples_per_second": 776.759,
+      "eval_steps_per_second": 48.608,
+      "step": 7365
+    },
+    {
+      "epoch": 3.05,
+      "learning_rate": 5.63572883328484e-07,
+      "loss": 0.1321,
+      "step": 7500
+    },
+    {
+      "epoch": 3.26,
+      "learning_rate": 5.344777422170497e-07,
+      "loss": 0.1324,
+      "step": 8000
+    },
+    {
+      "epoch": 3.46,
+      "learning_rate": 5.053826011056153e-07,
+      "loss": 0.1299,
+      "step": 8500
+    },
+    {
+      "epoch": 3.67,
+      "learning_rate": 4.7628745999418097e-07,
+      "loss": 0.136,
+      "step": 9000
+    },
+    {
+      "epoch": 3.87,
+      "learning_rate": 4.4719231888274657e-07,
+      "loss": 0.1308,
+      "step": 9500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9608464410999208,
+      "eval_f1": 0.9610329418449746,
+      "eval_loss": 0.15075480937957764,
+      "eval_precision": 0.9618808519987467,
+      "eval_recall": 0.9608464410999208,
+      "eval_runtime": 11.2225,
+      "eval_samples_per_second": 787.436,
+      "eval_steps_per_second": 49.276,
+      "step": 9820
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 17185,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 3808161445168620.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e70840e0cfcf8fb576d1fc12469df9415b94e472002c13a74d5f660c5fc0120f
+size 4664