Training in progress, step 1000

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "facebook/opt-1.3b",
+  "_remove_final_layer_norm": false,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 8192,
+  "hidden_size": 2048,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "opt",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "prefix": "</s>",
+  "torch_dtype": "float16",
+  "transformers_version": "4.45.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 2048
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e223479e99f1c544f30630d4d5312ae84a5c3fc332a25697eba4ed1c8d704175
+size 2631561680

model.safetensors.index.json

@@ -0,0 +1,395 @@
+{
+  "metadata": {
+    "total_size": 5263032320
+  },
+  "weight_map": {
+    "model.decoder.embed_positions.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.21.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.21.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.21.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.21.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.21.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.21.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.22.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.22.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.22.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.23.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.3.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -1,23 +1,23 @@
 {
   "bos_token": {
-    "content": "<s>",
+    "content": "</s>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
     "content": "</s>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": "</s>",
   "unk_token": {
-    "content": "<unk>",
+    "content": "</s>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   }

tokenizer_config.json

@@ -1,20 +1,11 @@
 {
   "add_bos_token": true,
-  "add_eos_token": false,
-  "add_prefix_space": true,
+  "add_prefix_space": false,
   "added_tokens_decoder": {
-    "0": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
     "1": {
-      "content": "<s>",
+      "content": "<pad>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -22,23 +13,18 @@
     "2": {
       "content": "</s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "bos_token": "<s>",
-  "clean_up_tokenization_spaces": false,
+  "bos_token": "</s>",
+  "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
-  "legacy": false,
-  "model_max_length": 512,
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "</s>",
-  "padding_side": "left",
-  "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
-  "tokenizer_class": "LlamaTokenizer",
-  "truncation_side": "left",
-  "unk_token": "<unk>",
-  "use_default_system_prompt": false
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "</s>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6b4637004ec81ab6ab4a30c2e68589f3b1e1bf728f5e3b87de3fb55ecf460f2
+oid sha256:12ce0084039c16842dc0d61d373d380626060de9b7b1727dd4154a35dc970e76
 size 5368