Training in progress, epoch 1

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "Ayus077BCT014Bhandari/vartat5-using-100K-plus-with-pruned-data-plus-2",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 1024,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 8,
+  "num_heads": 6,
+  "num_layers": 8,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0",
+  "use_cache": true,
+  "vocab_size": 128128
+}

logs/events.out.tfevents.1709031001.8c1bce108dd1.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:569edc9e0fe3b52e1455fa58c0d1bc9ffd4322e8423d22b432f646104aa8e9c8
+size 25070

logs/events.out.tfevents.1709039324.9be0f1da2c2a.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5126d6f789077a3bca189ccd609f5987da9295e8c87baca9eea6775cf7de80e
+size 25070

logs/events.out.tfevents.1709049687.9be0f1da2c2a.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b68de32f7987bd56449698895b089084c398a9b35076de05b806b6cca0f695be
+size 4184

logs/events.out.tfevents.1709050144.facfc0273a4e.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dfa9cb9f08071932b0004f23c7398ce40a2b3b323f0f5596890af8f6be68230
+size 25070

logs/events.out.tfevents.1709089260.1b4d3e130c3e.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb019476d8cc2f6a1c372c25c5fec29404a5a65c39e39a793181c0648d4b6e33
+size 25070

logs/events.out.tfevents.1709119240.ce1503d66798.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:363142ef4f0a97a8a5630a0beb31e051255038da7e9c7d0f355d324ea7c42c69
+size 4184

logs/events.out.tfevents.1709119393.ce1503d66798.252.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75c751f0e72a048eef4d7b70780a5995aeb37b173674c89e071f433440874edd
+size 7806

logs/events.out.tfevents.1709120187.ce1503d66798.452.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5a09c735f27da0bf47b4138ea75afa5f12f17317320b7d430da4f99d17652a2
+size 7827

logs/events.out.tfevents.1709121167.ce1503d66798.656.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf8d9deb5282f83e23818c9f3ef8d4f3280616ef20b064f94b99033eb39f23e1
+size 7831

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38b1c494ca51cc064c7b64f143611bfb992789bc60a3c71093cbb6f699659669
+size 701083048

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8fa9326187aa3c8e2c333d3d5d8c697072004914262b697bddef8202ce6424b
+size 4920