Training in progress, step 500

config.json

@@ -0,0 +1,62 @@
+{
+  "_name_or_path": "ai-forever/ruT5-base",
+  "_num_labels": 2,
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 2,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "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,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0",
+  "use_cache": true,
+  "vocab_size": 32128
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e93a633c6f5a90e33992faad0d23d31533a91c2f7c24e6e6f62b563d9116f07
+size 891644712

runs/Nov20_02-47-37_2da49c505a12/events.out.tfevents.1700448462.2da49c505a12.47.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27383d6052049532ea1f0dbb504161abe26387bde0a9d92a71f8d8db384ecf74
+size 5196

runs/Nov20_02-50-19_2da49c505a12/events.out.tfevents.1700448620.2da49c505a12.47.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a67acd53cd192c2d0bc83243c20fd51deebf9196ad36ac44ce1aaad46dd5c743
+size 5196

runs/Nov20_03-14-56_2da49c505a12/events.out.tfevents.1700450097.2da49c505a12.47.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b45fb62415b7f3d0cdb9a125bf0dfaff3f6075e1cc07b282ac309a9414c1b5e
+size 5624

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cebdb4b7094b2281e1d7fec1c4e6e5b074420c50cf3e05e3086427d46c91fcc5
+size 4219