Training in progress, step 125

.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 +1,35 @@
+{
+  "_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,
+  "length_penalty": 0.6,
+  "model_type": "mt5",
+  "no_repeat_ngram_size": 2,
+  "num_beams": 15,
+  "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": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 250112
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e0d6090ed6b9c92bca225c5ca6a7dc98ac5fcfea370ecb668cdb368bdb0365e
+size 1200729512

runs/Jan01_13-01-34_3e61f83ba140/events.out.tfevents.1704114101.3e61f83ba140.344.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ad935bf557008493cb08f4901c7c4a13876fc65cd9dc44a2a3585bb5745b559
+size 18600

runs/Jan01_13-10-41_3e61f83ba140/events.out.tfevents.1704114647.3e61f83ba140.344.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fb9d2cc817588f8b5a603b33c9e29e061513f7af8f1303cd8213312b814fedb
+size 10416

runs/Jan01_13-29-07_3e61f83ba140/events.out.tfevents.1704115753.3e61f83ba140.344.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa05080c0d1b71a2335657309a0af89ff8116250bc5330b04581d88023689de2
+size 4713

runs/Jan01_13-30-20_3e61f83ba140/events.out.tfevents.1704115828.3e61f83ba140.344.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88c2429129cc1bf9b91c7ca1b459c7dbd3293427259a6d84aff2308d41ce4842
+size 9028

runs/Jan01_13-57-59_3e61f83ba140/events.out.tfevents.1704117486.3e61f83ba140.344.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c2929c8327f9598e4b69320fc96b16983c3d75493b1e48dcd49ed6093ae2812
+size 5328

runs/Jan01_14-02-30_3e61f83ba140/events.out.tfevents.1704117760.3e61f83ba140.19494.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5351f0b364c2898bdc09a8f83ddb180bea0c8366141694494a0b872688ce026
+size 9496

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 sha256:3c9b5296bb1bdbcc33ccb40be1c81db3a36335a1c2b080a5368b48fb7a9eaa66
+size 16330461

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:b857d82ce94e4862ba753a1e0647bd6afaceeeda8ab7dfca38d18a6b5154f0be
+size 4664