upload checkpoint 48000 steps

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": 0.25,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.3,
+  "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": "4.20.1",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ab8d8c4f1ac24c46ff7b28ed49f06271b705b4b1264da145ef2e6ab703218ad
+size 1475506521

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2103cf57482805ddf3a71c9fae901c1bfa4422fee27d44184dea8cd95d816ad1
+size 737766955

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d32f824d6a96da7a56ccf37010a3986e327a3127f41890263700c8915582dab
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:299e28ab337cd8e77d6eba5a00148d9a0aeb1c4e6eda68ad43ef442a0931585d
+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]",
+  "name_or_path": "microsoft/deberta-v3-base",
+  "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 +1,52 @@
+{
+  "best_metric": 0.026952052488923073,
+  "best_model_checkpoint": "/kaggle/working/checkpoint-48000",
+  "epoch": 1.8262060569167553,
+  "global_step": 48000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.0868969715416225e-05,
+      "loss": 0.052,
+      "step": 24000
+    },
+    {
+      "epoch": 0.91,
+      "eval_accuracy": 0.988260534944281,
+      "eval_f1": 0.9937665318461085,
+      "eval_loss": 0.07157213985919952,
+      "eval_precision": 0.9997522006273829,
+      "eval_recall": 0.9878521107166308,
+      "eval_runtime": 2387.3537,
+      "eval_samples_per_second": 79.461,
+      "eval_steps_per_second": 9.933,
+      "step": 24000
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1.7379394308324458e-06,
+      "loss": 0.0151,
+      "step": 48000
+    },
+    {
+      "epoch": 1.83,
+      "eval_accuracy": 0.9959251879263266,
+      "eval_f1": 0.9978455183716244,
+      "eval_loss": 0.026952052488923073,
+      "eval_precision": 0.999564452634224,
+      "eval_recall": 0.9961324860046076,
+      "eval_runtime": 2388.0426,
+      "eval_samples_per_second": 79.438,
+      "eval_steps_per_second": 9.93,
+      "step": 48000
+    }
+  ],
+  "max_steps": 52568,
+  "num_train_epochs": 2,
+  "total_flos": 7.954978277974467e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0881c70fe9f953fe4a73b44dd918fb11a0143b59a2c46b1fc5c2d9a88e466361
+size 3311