Training in progress, step 45000

.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-large",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "d_ff": 2816,
+  "d_kv": 64,
+  "d_model": 1024,
+  "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": 16,
+  "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": "4.29.2",
+  "use_cache": true,
+  "vocab_size": 250112
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9efc7d4f63a35ea526d46193ca77adef9eef5e36cbd3851dec1b960e68f631ab
+size 4918519065

runs/May29_11-43-32_relela-04/1685375346.8160613/events.out.tfevents.1685375346.relela-04.1810797.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3e5fcf38db87d8739945f3316b50251f42a9d5229e473eb782c11a29ebf5587
+size 6345

runs/May29_11-43-32_relela-04/events.out.tfevents.1685375346.relela-04.1810797.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f64e2c8ce1a891274ad95a667a9fd424025e68dd5f6d8abd84b3f2368eb3529a
+size 4445

runs/May29_15-09-27_relela-04/1685387387.358516/events.out.tfevents.1685387387.relela-04.1812940.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33a20ceabc6a0214fce00a6825a003038f75aa93742d553397ccee981666b594
+size 6345

runs/May29_15-09-27_relela-04/events.out.tfevents.1685387387.relela-04.1812940.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a90428ef5ff9cfe23bbb298694596702ebb4289caec6043c35a7c163a1fd1dcf
+size 4445

runs/May29_15-29-18_relela-04/1685388576.50919/events.out.tfevents.1685388576.relela-04.1813766.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:204b774ab83f3b1ca98f39d390558ae8c5b8788e3737ffecf7b16f87e703f6fc
+size 6345

runs/May29_15-29-18_relela-04/events.out.tfevents.1685388576.relela-04.1813766.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:636d1dfbd2bdac47746cb46cd4c17a048b84d3f32c4f4f6a4c0d955ce84ec79d
+size 18749

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:a222b61de3d842e93a524233ea7fccf3d8dc1458bf2d84ff4a57d730012a812e
+size 4219