Training in progress, epoch 0

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "bigscience/mt0-base",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "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": "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": "4.44.0",
+  "use_cache": true,
+  "vocab_size": 250112
+}

logs/events.out.tfevents.1735442561.94236d6c1ccc.70.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d746c45366cccbae1f1b443f917b3d5220d13fb90e4d1e8a78127bc45fae724
+size 7098

logs/events.out.tfevents.1735447998.94236d6c1ccc.116.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df00cd4e3c68cb9f1fcaace4d955eeb521064c9e2bfe3662ccf8634d87c0b291
+size 7304

logs/events.out.tfevents.1735457063.94236d6c1ccc.165.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a132273e4f4ddf5f1297bedbf8c72aaeb90a131911760ee65822ac478488984
+size 5055

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feee651007568a2feca46ddef626d242daa7c60b4497fbbc53fbe2c009c9cf13
+size 2329638768

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a490796752f58190639c97e7afbd21ceb4b28ffde5a533375eef9fed9665d88e
+size 5176