End of training

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 2728127034966060.0,
+    "train_loss": 0.3373028761675569,
+    "train_runtime": 308.4038,
+    "train_samples_per_second": 243.168,
+    "train_steps_per_second": 1.907
+}

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "kkmkorea/checkpoint25000",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_head_size": 64,
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "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,
+  "padding_idx": 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": "4.31.0",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc6e27682800db4bb99f80fa651672533b3dbc957f4f4d95aa0d7c70fdd69269
+size 737765613

runs/Jul28_14-21-57_deeplatform/events.out.tfevents.1690521762.deeplatform.2373781.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8bdc74b6691df28402ec0598365052ffc423a0c767c95ebc41fe98e73d3ac8f
+size 4845

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 2728127034966060.0,
+    "train_loss": 0.3373028761675569,
+    "train_runtime": 308.4038,
+    "train_samples_per_second": 243.168,
+    "train_steps_per_second": 1.907
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea60a15a7887799b76e5f99b8fe125de9db20a1bf02c29430f2367e2a5d2e65a
+size 3951