Training in progress, epoch 1

Browse files

Files changed (13) hide show

.gitignore +1 -0
config.json +42 -0
merges.txt +0 -0
pytorch_model.bin +3 -0
runs/Nov01_20-50-45_teesta/1667316057.8131225/events.out.tfevents.1667316057.teesta.40651.3 +3 -0
runs/Nov01_20-50-45_teesta/events.out.tfevents.1667316057.teesta.40651.2 +3 -0
runs/Nov01_20-52-22_teesta/1667316152.5477555/events.out.tfevents.1667316152.teesta.40651.5 +3 -0
runs/Nov01_20-52-22_teesta/events.out.tfevents.1667316152.teesta.40651.4 +3 -0
special_tokens_map.json +51 -0
tokenizer.json +0 -0
tokenizer_config.json +67 -0
training_args.bin +3 -0
vocab.json +0 -0

.gitignore ADDED Viewed

	@@ -0,0 +1 @@


1	+ checkpoint-*/

config.json ADDED Viewed

	@@ -0,0 +1,42 @@

+{
+  "_name_or_path": "microsoft/deberta-base-mnli",
+  "architectures": [
+    "DebertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "0",
+    "1": "1",
+    "2": "2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": "0",
+    "1": "1",
+    "2": "2"
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta",
+  "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": [
+    "c2p",
+    "p2c"
+  ],
+  "position_biased_input": false,
+  "relative_attention": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0.dev0",
+  "type_vocab_size": 0,
+  "vocab_size": 50265
+}

merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

pytorch_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ba72de2d67f5f2f3f6a9782911eebddb9dc364d98fecd018dd88f715d4380d7c
+size 556849903

runs/Nov01_20-50-45_teesta/1667316057.8131225/events.out.tfevents.1667316057.teesta.40651.3 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:1c20b58c475ead8e1356df6caca69b4975026e89b7589d03efac18e8df2c795c
+size 5613

runs/Nov01_20-50-45_teesta/events.out.tfevents.1667316057.teesta.40651.2 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:751f0214b7d3ba2a7b0ebca5f1c49941671596696113ca73e1b1bc8b90460603
+size 4098

runs/Nov01_20-52-22_teesta/1667316152.5477555/events.out.tfevents.1667316152.teesta.40651.5 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:1ae8e7a5a62232b0ab4e3469fd24e455d41c9080fb0e5f98de2c7d9f6736792e
+size 5613

runs/Nov01_20-52-22_teesta/events.out.tfevents.1667316152.teesta.40651.4 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:74ef908a62d131e8f2b3bb709ad6e06673c8379d435c398288bea033f008760c
+size 5040

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,51 @@

+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,67 @@

+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "__type": "AddedToken",
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "do_lower_case": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "name_or_path": "microsoft/deberta-base-mnli",
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "__type": "AddedToken",
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "special_tokens_map_file": null,
+  "tokenizer_class": "DebertaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "vocab_type": "gpt2"
+}

training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ccb2095fdf88f0edfda38284d26a806151551d1a170021c895ea6c89ac615696
+size 3503

vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff