Training in progress, step 500

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "cointegrated/rut5-base-multitask",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "gradient_checkpointing": false,
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "use_cache": true,
+  "vocab_size": 30000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72332e4a2a28e0124791370f9a303d35ca08fd46cf74a5e11473c78d7478e173
+size 977270632

runs/May08_11-08-11_7515d5f82dbe/events.out.tfevents.1715166564.7515d5f82dbe.1603.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44d9757cbc341dd2334847adeebe150b1992f49fad9eeea3a22766726c6ed9a1
+size 5066

runs/May08_11-21-28_7515d5f82dbe/events.out.tfevents.1715167317.7515d5f82dbe.1603.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5566b39bf5648ab7d14e7986cba67b5e9ec81e53b6001fc724367a835d034a44
+size 5066

runs/May08_11-24-18_7515d5f82dbe/events.out.tfevents.1715167476.7515d5f82dbe.1603.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2cefb570391456140da7328ace3041f8773afa1ed75a03dbe10830b2184ca50
+size 5066

runs/May08_11-29-10_7515d5f82dbe/events.out.tfevents.1715167768.7515d5f82dbe.1603.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5e5b8d259996baddebb7f17e6062b38ffba4444c0ca975590d9383bc05a9c86
+size 5066

runs/May08_12-00-42_7515d5f82dbe/events.out.tfevents.1715169680.7515d5f82dbe.1603.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30291108d2f972e8dd431bb937a15e16c2f39ce8df6be7e8262522388d7ca62d
+size 5066

runs/May08_12-00-42_7515d5f82dbe/events.out.tfevents.1715169903.7515d5f82dbe.1603.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ee6238785c3766f46ef78dc78bdeb49aaaec95cdc710425b000e8b270052b91
+size 5066

runs/May08_12-00-42_7515d5f82dbe/events.out.tfevents.1715170034.7515d5f82dbe.1603.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8745299ac5a3035701e52537e1f550fd1be1a7849eaeb1bf2b567426d677248
+size 5819

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76927654c70c667e967c8caca165a3bb1311b415316b6aed8037ed5ede86b10e
+size 827566

tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a396ec53dc642d57d9464a1a140abd0205e3b4881f24054f407be66574d8f611
+size 5176