Upload model files

added_tokens.json

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

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-base",
+  "architectures": [
+    "DebertaV2ForMaskedLM"
+  ],
+  "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": "4.27.2",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aea3aebd91d5a168e50bb2851280f5bea6ab06a79e552bd857423bc701fda675
+size 1476531925

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bfef5dedca4bb93288ef5e32ac6cd376b7a90eae03b8b7f7dae8c5a4b1f91b2
+size 738280041

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db0f530bb41e080ee20485c77310c156d3c424ce8736a9dc85e2ad9481eaf442
+size 15523

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b072947d6060f3e5dee244bf1ee02569b1b9c88c546adf49ac035ef8c58db5a
+size 559

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f363455e2051801ced6bf76a7d26ab76a727b7efc8f14b95241961df0c01139
+size 623

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "bos_token": "[CLS]",
+  "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": {},
+  "special_tokens_map_file": null,
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

trainer_state.json

@@ -0,0 +1,156 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 25150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.900198807157058e-05,
+      "loss": 3.4819,
+      "step": 2515
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.2373175621032715,
+      "eval_runtime": 310.738,
+      "eval_samples_per_second": 28.777,
+      "eval_steps_per_second": 1.799,
+      "step": 2515
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.8002385685884693e-05,
+      "loss": 2.1965,
+      "step": 5030
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.8015460968017578,
+      "eval_runtime": 310.6652,
+      "eval_samples_per_second": 28.783,
+      "eval_steps_per_second": 1.799,
+      "step": 5030
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.700278330019881e-05,
+      "loss": 1.8805,
+      "step": 7545
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.5936048030853271,
+      "eval_runtime": 310.3586,
+      "eval_samples_per_second": 28.812,
+      "eval_steps_per_second": 1.801,
+      "step": 7545
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.6003180914512923e-05,
+      "loss": 1.6926,
+      "step": 10060
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.451478362083435,
+      "eval_runtime": 310.2705,
+      "eval_samples_per_second": 28.82,
+      "eval_steps_per_second": 1.802,
+      "step": 10060
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 1.500357852882704e-05,
+      "loss": 1.5731,
+      "step": 12575
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.3821080923080444,
+      "eval_runtime": 310.2193,
+      "eval_samples_per_second": 28.825,
+      "eval_steps_per_second": 1.802,
+      "step": 12575
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 1.4003976143141154e-05,
+      "loss": 1.4862,
+      "step": 15090
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.3046475648880005,
+      "eval_runtime": 310.6594,
+      "eval_samples_per_second": 28.784,
+      "eval_steps_per_second": 1.799,
+      "step": 15090
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 1.3003976143141155e-05,
+      "loss": 1.4197,
+      "step": 17605
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 1.253291368484497,
+      "eval_runtime": 310.6843,
+      "eval_samples_per_second": 28.782,
+      "eval_steps_per_second": 1.799,
+      "step": 17605
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 1.20051689860835e-05,
+      "loss": 1.368,
+      "step": 20120
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 1.221903920173645,
+      "eval_runtime": 310.6521,
+      "eval_samples_per_second": 28.785,
+      "eval_steps_per_second": 1.799,
+      "step": 20120
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 1.10051689860835e-05,
+      "loss": 1.3235,
+      "step": 22635
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 1.1836310625076294,
+      "eval_runtime": 310.7209,
+      "eval_samples_per_second": 28.778,
+      "eval_steps_per_second": 1.799,
+      "step": 22635
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 1.00051689860835e-05,
+      "loss": 1.2855,
+      "step": 25150
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 1.1522128582000732,
+      "eval_runtime": 310.7087,
+      "eval_samples_per_second": 28.779,
+      "eval_steps_per_second": 1.799,
+      "step": 25150
+    }
+  ],
+  "max_steps": 50300,
+  "num_train_epochs": 20,
+  "total_flos": 5.301609303112704e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:965f2458e95501df384851bc0579397655cb22b29b447f3dfe9b3d8dca645256
+size 3695