Training in progress, step 500

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "google/mt5-small",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "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": "mt5",
+  "num_decoder_layers": 8,
+  "num_heads": 6,
+  "num_layers": 8,
+  "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": "4.35.0",
+  "use_cache": true,
+  "vocab_size": 250112
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1133e120bcec3c18ebda88e16ee2816ad75dcea5e2768524efdc396075449a0c
+size 1200729512

runs/Mar09_13-11-57_1502905a1f9e/events.out.tfevents.1709990000.1502905a1f9e.47.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04e61e7cf6c49daa675c69045e3d345c571c4fa908b7fd234b5e58230dd172bd
+size 4652

runs/Mar09_13-18-03_1502905a1f9e/events.out.tfevents.1709990284.1502905a1f9e.47.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d89db5d21552bd459884c739ce883060160190cfb9b852785fab400df3e5584
+size 9798

runs/Mar09_13-18-03_1502905a1f9e/events.out.tfevents.1709990291.1502905a1f9e.47.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64668d9839609646e1c8707a01649ec83baf0c93d02b7677ab55063d749c316f
+size 553

runs/Mar09_14-03-58_1502905a1f9e/events.out.tfevents.1709993040.1502905a1f9e.1257.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1913508e62a79c959186b878545e119719a476f7cbcec852614614ff96dd6113
+size 9798

runs/Mar09_14-03-58_1502905a1f9e/events.out.tfevents.1709993082.1502905a1f9e.1257.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:637a897b44a09cd6bd3d93d8e82de4dbf20a2235734c7eb1f173079789152513
+size 553

runs/Mar09_14-10-44_1502905a1f9e/events.out.tfevents.1709993532.1502905a1f9e.1257.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4b52273328c485c31a4a54c6cda029f24653dbc19f0232fdf5a36fa1a41733b
+size 4974

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:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
+size 4309802

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d07d197bb675754e0839f9bc8888740d94b9d89f6050a848d16110b3dcdc6907
+size 16330494

tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "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 sha256:2f72cd8d4be9f779df23712c5e8d7a959aab7b474320b14c4d8273581bd5dce7
+size 4283