Training in progress, epoch 1

.gitattributes

@@ -29,3 +29,4 @@ 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 +1,31 @@
+{
+  "_name_or_path": "google/mt5-small",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "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": "t5",
+  "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": "4.20.1",
+  "use_cache": true,
+  "vocab_size": 250112
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc4055e449b5550cfc53abc4ed8c0fc8dc7d41f461b48458aa73fd56340ddb10
+size 1200770885

runs/Aug30_23-45-58_ac4cc68cb2d6/events.out.tfevents.1661903270.ac4cc68cb2d6.17.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a28d3aab3d66709b9c77516e53f688b1b64ac5f42e9a516ad881b403a178781
+size 1071

runs/Aug30_23-49-09_ac4cc68cb2d6/events.out.tfevents.1661903409.ac4cc68cb2d6.17.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f3b7598e35bbebc03446287c74681e50161d995ed58f94fc226851f79c3fc8e
+size 1209

runs/Aug30_23-51-29_ac4cc68cb2d6/events.out.tfevents.1661903553.ac4cc68cb2d6.17.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:721b18dc7d5855092c841ac073d36d21e687c38778da9b250e3f8b160d588737
+size 1209

runs/Aug30_23-55-33_ac4cc68cb2d6/1661903831.843871/events.out.tfevents.1661903831.ac4cc68cb2d6.17.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02953b35ece9783a142faa5f8dcbcf4059240beed6ce436dc71081a035b835d0
+size 5591

runs/Aug30_23-55-33_ac4cc68cb2d6/events.out.tfevents.1661903791.ac4cc68cb2d6.17.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:627eedc3caa836a30f4d6a428fb4c3bc2350c1be071f14bdea92ed758ecf5b8f
+size 11073

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 sha256:93e420fed0afb3269cb4d73650d5ac4feb6bdcc95c0087ac545847351eca14b5
+size 16330632

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": null,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "name_or_path": "google/mt5-small",
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/root/.cache/huggingface/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5a576a1c5c2a0a78fefb6cdb2d8fe7feab212e783bc2c733a5a8697aa500406
+size 3439