Training in progress, step 4000

.gitattributes

@@ -32,3 +32,4 @@ 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

.gitignore

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

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "google/mt5-xl",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "d_ff": 5120,
+  "d_kv": 64,
+  "d_model": 2048,
+  "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": 24,
+  "num_heads": 32,
+  "num_layers": 24,
+  "output_past": true,
+  "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": "4.31.0.dev0",
+  "use_cache": true,
+  "vocab_size": 250112
+}

runs/Jun08_16-24-12_209-20-157-96/events.out.tfevents.1686241506.209-20-157-96.159083.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17bc4d8819f3a2cbfd05800800f2ccd1b9848dd139f32ba41b6d2b92b7efff94
+size 4295

runs/Jun08_16-25-37_209-20-157-96/events.out.tfevents.1686241586.209-20-157-96.159668.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0608cb9ce165166f29f9f4480679a15d1b79414e04b88f2387993f7817e042a2
+size 4295

runs/Jun08_16-27-02_209-20-157-96/events.out.tfevents.1686241670.209-20-157-96.160233.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e6cae2c869fef05d240ac05e66d34c4aff0e4203eb569d4a38d7a4bfb8d53aa
+size 4136

runs/Jun08_16-29-09_209-20-157-96/events.out.tfevents.1686241795.209-20-157-96.160989.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:784401c0cdc0d05707bdef7ae22c1774f753ecf75c5c5a35ce49a48cb7b74f93
+size 4136

runs/Jun08_16-33-34_209-20-157-96/events.out.tfevents.1686242065.209-20-157-96.162471.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d6fe595dd16289182ac22bfd692edf41d13da5e6fcf9f9aad9719f82da73481
+size 4136

runs/Jun08_16-55-29_209-20-157-96/events.out.tfevents.1686243379.209-20-157-96.169899.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af5689f2e80038627df0245e5fb240fabe464d5d496eba665abb7322b0a5ff6e
+size 5558

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

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 sha256:93c3578052e1605d8332eb961bc08d72e246071974e4cc54aa6991826b802aa5
+size 16330369

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": null,
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "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:ca716116da0d23bcc27c08d906377cfb9b88f98d1af84585fd603583095331ba
+size 4155