Training in progress, step 100

config.json

@@ -0,0 +1,43 @@
+{
+  "_block_types": [
+    "recurrent",
+    "recurrent",
+    "attention"
+  ],
+  "_name_or_path": "silu-griffin-1024-c3t-8layer",
+  "architectures": [
+    "RecurrentGemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attention_window_size": 2048,
+  "block_types": [
+    "recurrent",
+    "recurrent",
+    "attention"
+  ],
+  "bos_token_id": 0,
+  "conv1d_width": 4,
+  "embeddings_scale_by_sqrt_dim": true,
+  "eos_token_id": 0,
+  "final_w_init_variance_scale": 0.25,
+  "head_dim": 128,
+  "hidden_activation": "silu",
+  "hidden_size": 1024,
+  "intermediate_size": 6144,
+  "logits_soft_cap": 30.0,
+  "lru_width": 1024,
+  "model_type": "recurrent_gemma",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "num_key_value_heads": 2,
+  "pad_token_id": 0,
+  "partial_rotary_factor": 0.5,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "use_cache": true,
+  "vocab_size": 65024,
+  "w_init_variance_scale": 0.01
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:635fbbdb8f708c1180e0aa6e3d423bee1f2fe2ae095cfb4979d2afd1f979b12e
+size 671684224

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<EOT>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<EOT>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<EOT>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,51 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<EOT>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<META>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<META_START>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<META_END>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<SOS>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<EOT>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<EOT>",
+  "model_max_length": 200000,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<EOT>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a6e28c74a2f33aaaec19dc2973a4c2f6c3705e61acf9c5c8b35870263eb8bc4
+size 5176