Training in progress, step 1000

added_tokens.json

@@ -0,0 +1,9 @@
+{
+  "</s>": 3,
+  "<s>": 2,
+  "[CLS]": 4,
+  "[MASK]": 6,
+  "[PAD]": 0,
+  "[SEP]": 5,
+  "[UNK]": 1
+}

config.json

@@ -0,0 +1,38 @@
+{
+  "activation_dropout": 0.0,
+  "activation_fn": "swish",
+  "architectures": [
+    "RetNetForCausalLM"
+  ],
+  "decoder_embed_dim": 1280,
+  "decoder_ffn_embed_dim": 2560,
+  "decoder_layers": 12,
+  "decoder_normalize_before": true,
+  "decoder_retention_heads": 8,
+  "decoder_value_embed_dim": 2560,
+  "deepnorm": false,
+  "drop_path_rate": 0.0,
+  "dropout": 0.0,
+  "eos_token_id": 50256,
+  "forward_impl": "parallel",
+  "initializer_range": 0.02,
+  "is_decoder": true,
+  "layernorm_embedding": true,
+  "layernorm_eps": 1e-06,
+  "model_type": "retnet",
+  "no_scale_embedding": false,
+  "output_retentions": false,
+  "pad_token_id": 50256,
+  "recurrent_chunk_size": 512,
+  "subln": true,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.0",
+  "unk_token_id": 50256,
+  "use_cache": true,
+  "use_ffn_rms_norm": false,
+  "use_glu": true,
+  "use_lm_decay": false,
+  "vocab_size": 50257,
+  "z_loss_coeff": 0.0
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:056916394d5842d7848ab46eaf76f5a15e0a344a90c65c22789939ff8edccf2d
+size 1615784368

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "[CLS]",
+  "eos_token": "</s>",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d78ab344146700112cd41628ac7ce54b79c0868fe0c7c201750d8237b54dbb4
+size 786216

tokenizer_config.json

@@ -0,0 +1,75 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "</s>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "legacy": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99b4305a08962dafa0e9bc5a994af4d018463ff14053809ec77928b08913d838
+size 4027