Training in progress, epoch 1

.gitignore

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

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "google/mt5-small",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "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": "mt5",
+  "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": "4.23.1",
+  "use_cache": true,
+  "vocab_size": 250112
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5dd2bc4e132b5a8c5fc2b5eb50d32a45af110a440001262a5c94c2de7cd7caa
+size 1200770757

runs/Oct15_14-15-53_7dc1d8ea61d0/1665843366.128989/events.out.tfevents.1665843366.7dc1d8ea61d0.69.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27b409318eea3eb4af85b7ded7a016b5fff19b2e5f7645abc17b17e36c188ade
+size 5769

runs/Oct15_14-15-53_7dc1d8ea61d0/events.out.tfevents.1665843366.7dc1d8ea61d0.69.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abf9b6b3bf057556b0c151cf80742f5303380edbc2ec826ed5aeba4a248859c1
+size 12013

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_config.json

@@ -0,0 +1,12 @@
+{
+  "additional_special_tokens": null,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "name_or_path": "google/mt5-small",
+  "pad_token": "<pad>",
+  "return_tensors": "pt",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--google--mt5-small/snapshots/f03a52d3eaa650878b6f52e443bc4d5b385e786e/special_tokens_map.json",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f074b7138fb24698ccf51cbad2892d6f377feeaa0eca088ffc443fa9fbc80f7d
+size 3567