Training in progress, epoch 1

.gitattributes

@@ -33,3 +33,4 @@ 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

config.json

@@ -0,0 +1,33 @@
+{
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "bos_token_id": null,
+  "classifier_dropout": 0.0,
+  "d_ff": 1024,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "dtype": "float32",
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_decoder": false,
+  "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": true,
+  "tokenizer_class": "T5Tokenizer",
+  "transformers_version": "5.4.0",
+  "use_cache": false,
+  "vocab_size": 250112
+}

generation_config.json

@@ -0,0 +1,37 @@
+{
+  "_from_model_config": false,
+  "assistant_confidence_threshold": 0.4,
+  "assistant_lookbehind": 10,
+  "decoder_start_token_id": 0,
+  "diversity_penalty": 0.0,
+  "do_sample": false,
+  "early_stopping": false,
+  "encoder_no_repeat_ngram_size": 0,
+  "encoder_repetition_penalty": 1.0,
+  "eos_token_id": [
+    1
+  ],
+  "epsilon_cutoff": 0.0,
+  "eta_cutoff": 0.0,
+  "length_penalty": 1.0,
+  "max_length": 20,
+  "min_length": 0,
+  "no_repeat_ngram_size": 0,
+  "num_assistant_tokens": 20,
+  "num_assistant_tokens_schedule": "constant",
+  "num_beam_groups": 1,
+  "num_beams": 1,
+  "num_return_sequences": 1,
+  "output_scores": false,
+  "pad_token_id": 0,
+  "remove_invalid_values": false,
+  "repetition_penalty": 1.0,
+  "return_dict_in_generate": false,
+  "target_lookbehind": 10,
+  "temperature": 1.0,
+  "top_k": 50,
+  "top_p": 1.0,
+  "transformers_version": "5.4.0",
+  "typical_p": 1.0,
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3000aee8d618670e7095d6ad5d223437cb645b0bd2c1fe8eb49f25d127608bc
+size 1200729512

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:652432621fdf83a8c9719c2d11e3a2a5232667623e35030ce78e7c70390b0890
+size 16350027

tokenizer_config.json

@@ -0,0 +1,115 @@
+{
+  "backend": "tokenizers",
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "extra_special_tokens": [
+    "<pad>",
+    "</s>",
+    "▁<extra_id_99>",
+    "▁<extra_id_98>",
+    "▁<extra_id_97>",
+    "▁<extra_id_96>",
+    "▁<extra_id_95>",
+    "▁<extra_id_94>",
+    "▁<extra_id_93>",
+    "▁<extra_id_92>",
+    "▁<extra_id_91>",
+    "▁<extra_id_90>",
+    "▁<extra_id_89>",
+    "▁<extra_id_88>",
+    "▁<extra_id_87>",
+    "▁<extra_id_86>",
+    "▁<extra_id_85>",
+    "▁<extra_id_84>",
+    "▁<extra_id_83>",
+    "▁<extra_id_82>",
+    "▁<extra_id_81>",
+    "▁<extra_id_80>",
+    "▁<extra_id_79>",
+    "▁<extra_id_78>",
+    "▁<extra_id_77>",
+    "▁<extra_id_76>",
+    "▁<extra_id_75>",
+    "▁<extra_id_74>",
+    "▁<extra_id_73>",
+    "▁<extra_id_72>",
+    "▁<extra_id_71>",
+    "▁<extra_id_70>",
+    "▁<extra_id_69>",
+    "▁<extra_id_68>",
+    "▁<extra_id_67>",
+    "▁<extra_id_66>",
+    "▁<extra_id_65>",
+    "▁<extra_id_64>",
+    "▁<extra_id_63>",
+    "▁<extra_id_62>",
+    "▁<extra_id_61>",
+    "▁<extra_id_60>",
+    "▁<extra_id_59>",
+    "▁<extra_id_58>",
+    "▁<extra_id_57>",
+    "▁<extra_id_56>",
+    "▁<extra_id_55>",
+    "▁<extra_id_54>",
+    "▁<extra_id_53>",
+    "▁<extra_id_52>",
+    "▁<extra_id_51>",
+    "▁<extra_id_50>",
+    "▁<extra_id_49>",
+    "▁<extra_id_48>",
+    "▁<extra_id_47>",
+    "▁<extra_id_46>",
+    "▁<extra_id_45>",
+    "▁<extra_id_44>",
+    "▁<extra_id_43>",
+    "▁<extra_id_42>",
+    "▁<extra_id_41>",
+    "▁<extra_id_40>",
+    "▁<extra_id_39>",
+    "▁<extra_id_38>",
+    "▁<extra_id_37>",
+    "▁<extra_id_36>",
+    "▁<extra_id_35>",
+    "▁<extra_id_34>",
+    "▁<extra_id_33>",
+    "▁<extra_id_32>",
+    "▁<extra_id_31>",
+    "▁<extra_id_30>",
+    "▁<extra_id_29>",
+    "▁<extra_id_28>",
+    "▁<extra_id_27>",
+    "▁<extra_id_26>",
+    "▁<extra_id_25>",
+    "▁<extra_id_24>",
+    "▁<extra_id_23>",
+    "▁<extra_id_22>",
+    "▁<extra_id_21>",
+    "▁<extra_id_20>",
+    "▁<extra_id_19>",
+    "▁<extra_id_18>",
+    "▁<extra_id_17>",
+    "▁<extra_id_16>",
+    "▁<extra_id_15>",
+    "▁<extra_id_14>",
+    "▁<extra_id_13>",
+    "▁<extra_id_12>",
+    "▁<extra_id_11>",
+    "▁<extra_id_10>",
+    "▁<extra_id_9>",
+    "▁<extra_id_8>",
+    "▁<extra_id_7>",
+    "▁<extra_id_6>",
+    "▁<extra_id_5>",
+    "▁<extra_id_4>",
+    "▁<extra_id_3>",
+    "▁<extra_id_2>",
+    "▁<extra_id_1>",
+    "▁<extra_id_0>"
+  ],
+  "is_local": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_id": 2,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc4599fdabd6ae8ab4bf23673aa89620fd2b814224779bbaa44d35ef76d48d69
+size 5393