Training in progress, step 5000

.gitignore

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

config.json

@@ -0,0 +1,62 @@
+{
+  "_name_or_path": "sberbank-ai/ruT5-base",
+  "_num_labels": 2,
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "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,
+  "max_length": 256,
+  "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": "4.26.0",
+  "use_cache": true,
+  "vocab_size": 32100
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5caf0c7f419b3fad4399c50c916b89360fda056edeec22bd0628398b1389a4b0
+size 891616913

runs/Feb02_15-55-17_1d950ccfaa28/1675353324.2909386/events.out.tfevents.1675353324.1d950ccfaa28.1815.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e3c593f22fddc82524d6357e170ea78833cc5075d5f88a5a0f580609ad1d331
+size 5894

runs/Feb02_15-55-17_1d950ccfaa28/events.out.tfevents.1675353324.1d950ccfaa28.1815.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2091082334fd4f67738483fc0aeda36d7a07f11043bdbcca342087cc5536a53a
+size 15320

runs/Feb02_16-01-58_1d950ccfaa28/1675353725.7573538/events.out.tfevents.1675353725.1d950ccfaa28.1815.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51aa9dd732c9209b915b0d97a8df4c95b5ea125bfcbbd89e59cbee7a6026381a
+size 5894

runs/Feb02_16-01-58_1d950ccfaa28/events.out.tfevents.1675353725.1d950ccfaa28.1815.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0aa52462292d2f0afa03861723a8c3dcccff06a2faafccb0ff9865ed10e16b10
+size 88497

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54158d9e8a798ffcf864090d3b47c320b75067ecb38b819475b709063b6d85fd
+size 3579