Training in progress, epoch 1

.gitignore

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

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "google/mt5-base",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "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": "mt5",
+  "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": "4.26.1",
+  "use_cache": true,
+  "vocab_size": 250112
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:978327e58a907867258efc669394c1f520eaaa1c5fd30fd79fa84b80d3ae9271
+size 2329702453

runs/Jan23_00-49-57_munich/1705946264.2089508/events.out.tfevents.1705946264.munich.530136.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b474e833ef741dfcbf2bc729ecbfbcdf2e6f7906c58b5602bd65493853ecbe2c
+size 6059

runs/Jan23_00-49-57_munich/events.out.tfevents.1705946263.munich.530136.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b0ddb0b962c92e8e64dbff27aba12cae3521fc3a00d5e86b8a8fc92c5a62b96
+size 4598

runs/Jan23_01-11-19_munich/1705947501.8041177/events.out.tfevents.1705947501.munich.535516.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a7ad924a3cb24d6eb8e06f1c877d9db92465baf95b88c7f0aca87f29ec620ce
+size 6059

runs/Jan23_01-11-19_munich/events.out.tfevents.1705947501.munich.535516.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:558550a2b58b8a997d4035ebafffa98e7cc9edd4d7976589d4be3a754398a712
+size 6301

runs/Jan23_10-58-10_munich/1705982689.1571157/events.out.tfevents.1705982689.munich.678730.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8bd75ee88cbd01fc4d34fbdf9687e29df9d7bb16f3376b459caa42f48c5870b
+size 6059

runs/Jan23_10-58-10_munich/events.out.tfevents.1705982688.munich.678730.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72da5f6b3c18e3654ed47613f78d0e638716a8307090503c23e0b1d7658b1d36
+size 6301

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22e4de7f1d3bf4525b0cfdf671e61084621c221c9ea54a92ab4391939b1c9714
+size 3707