Training in progress, step 500

.gitattributes

@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

.gitignore

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

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "google/mt5-small",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "d_ff": 1024,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": 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_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.16.1",
+  "use_cache": true,
+  "vocab_size": 250112
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4c88f0a7be12e7aa97eb2ed09467798b5504e49fc351e903e004cdb5456b990
+size 1200792197

runs/Jan29_18-21-54_c6bc7118b50f/1643480536.3165722/events.out.tfevents.1643480536.c6bc7118b50f.76.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6da55bffa6c260a01163f38a7bfd387c838ac6e10961f17bc761b0b079e7f216
+size 5021

runs/Jan29_18-21-54_c6bc7118b50f/events.out.tfevents.1643480536.c6bc7118b50f.76.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b306efe9175ac80c8db943a2c01740e54f02e6021483182854321a6d0db14202
+size 3453

runs/Jan29_18-29-17_c6bc7118b50f/1643480981.6201138/events.out.tfevents.1643480981.c6bc7118b50f.909.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da98486603a61307f9599ae4e8a74b99eaeaa5c8e441b947a6eba8aacd0e0d2f
+size 5021

runs/Jan29_18-29-17_c6bc7118b50f/events.out.tfevents.1643480981.c6bc7118b50f.909.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd55f95cad7dd6b17ce838921d795ad5f422e1b1801de5705646481b400b68d8
+size 3611

special_tokens_map.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}

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:d15b59d404d29e41d3eddebcd213b00395e140bf9493419c646b0c74647efbea
+size 16330467

tokenizer_config.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": null, "special_tokens_map_file": "/root/.cache/huggingface/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276", "name_or_path": "google/mt5-small", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cb19a3bd32b03fe53cc5c44fbe6a05858d28e9241f28e7a28386a372efff30a
+size 3183