Training in progress, step 5000

.gitignore

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

config.json

@@ -0,0 +1,62 @@
+{
+  "_name_or_path": "UrukHan/t5-russian-spell",
+  "_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:d0e7cac39bb6b55d2f65d24b2ff225950aaf7aa68a4b5fe603665edd370fc2bc
+size 891616913

runs/Jan31_13-19-41_1ce20600a79e/1675171238.2109883/events.out.tfevents.1675171238.1ce20600a79e.183.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dba48635dae41ccec9668f298e35c8a4fb0a002456a68423a81f571bcb9d0d2f
+size 5915

runs/Jan31_13-19-41_1ce20600a79e/events.out.tfevents.1675171238.1ce20600a79e.183.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f99544f56f5e2a6bd8ee90bf8223627f86b083675ce468eb65ed71d9fbad82ec
+size 10390

runs/Jan31_13-33-55_1ce20600a79e/1675172047.6750045/events.out.tfevents.1675172047.1ce20600a79e.183.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:657499bca0d12bd602a88bbf03c23a466efff8dafedf2bd598d983da3594e748
+size 5915

runs/Jan31_13-33-55_1ce20600a79e/events.out.tfevents.1675172047.1ce20600a79e.183.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a18df24620cfa24bba4727be0ea760b67e458e4bc1faedfc1aca70b2ae308e
+size 9032

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44df1aa3e68add3f353c2fdc6b522040c7cda1bb6b8c1813fa513d76e88f82e4
+size 3643