Training in progress, epoch 1

tmp-checkpoint-2586/config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "/home/tong/text_to_sql/content/ALL_mt5-base_15_wikiSQL_no_sch",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "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": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "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": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 250112
+}

tmp-checkpoint-2586/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.38.2"
+}

tmp-checkpoint-2586/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d3b8d666a880d98693607ebd8555e6bb73f0b9cd157633271524e4b12945b1a
+size 2329638768

tmp-checkpoint-2586/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22e86d4e88f853fc592faa099c2741e64a946f4f909819191fb72c848751b0f0
+size 1317290112

tmp-checkpoint-2586/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e588c608c02d115ba592a7271c0e5a4b9e4dfda809458dda90fd4e0530f1b8a0
+size 5176

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e588c608c02d115ba592a7271c0e5a4b9e4dfda809458dda90fd4e0530f1b8a0
+oid sha256:7266836b9924a49ad93cd2ca57534bf1fd533fded681a2e8dc2963cf998da542
 size 5176