feat: ✨ Uploaded artifacts

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/content/drive/MyDrive/Projects/nitic-nlp-team/webnavix/checkpoints/webnavix/nitic-nlp-team/webnavix-llama-base/checkpoint-1500/",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 6912,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 20,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.44.2"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5057ad469c520bf8e2d1a41573aa24b24df659fa0fb73d0b53a87393fe3f7f72
+size 4974521464

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdb084116fb34a7029eec45e9e1e54055c2b13ca5cd6fd9b43f463635125b658
+size 428632856

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 5403120640
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b168ac6245fea4b38962c3af9cc8b722aa3b4a483acd143f295dd693934efee
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12a10f8dacd0a239ef69a06243af2064bce46a49875aa3f51647ac2196d57341
+size 1064

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "max_length": 4096,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "stride": 0,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,470 @@
+{
+  "best_metric": 0.5988770127296448,
+  "best_model_checkpoint": "/content/drive/MyDrive/Projects/nitic-nlp-team/webnavix/checkpoints/webnavix/nitic-nlp-team/webnavix-llama-ai-tools/checkpoint-100",
+  "epoch": 2.873563218390805,
+  "eval_steps": 50,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005747126436781609,
+      "grad_norm": 1.1171875,
+      "learning_rate": 4.9942528735632185e-05,
+      "loss": 0.3466,
+      "step": 1
+    },
+    {
+      "epoch": 0.05747126436781609,
+      "grad_norm": 0.5625,
+      "learning_rate": 4.9425287356321845e-05,
+      "loss": 0.4403,
+      "step": 10
+    },
+    {
+      "epoch": 0.11494252873563218,
+      "grad_norm": 0.494140625,
+      "learning_rate": 4.885057471264368e-05,
+      "loss": 0.3798,
+      "step": 20
+    },
+    {
+      "epoch": 0.1724137931034483,
+      "grad_norm": 0.5625,
+      "learning_rate": 4.827586206896552e-05,
+      "loss": 0.3666,
+      "step": 30
+    },
+    {
+      "epoch": 0.22988505747126436,
+      "grad_norm": 0.59765625,
+      "learning_rate": 4.770114942528736e-05,
+      "loss": 0.3313,
+      "step": 40
+    },
+    {
+      "epoch": 0.28735632183908044,
+      "grad_norm": 0.5859375,
+      "learning_rate": 4.7126436781609195e-05,
+      "loss": 0.3662,
+      "step": 50
+    },
+    {
+      "epoch": 0.28735632183908044,
+      "eval_loss": 0.6048163175582886,
+      "eval_runtime": 15.3039,
+      "eval_samples_per_second": 12.48,
+      "eval_steps_per_second": 0.784,
+      "step": 50
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "grad_norm": 0.5625,
+      "learning_rate": 4.655172413793104e-05,
+      "loss": 0.3606,
+      "step": 60
+    },
+    {
+      "epoch": 0.40229885057471265,
+      "grad_norm": 0.56640625,
+      "learning_rate": 4.597701149425287e-05,
+      "loss": 0.3232,
+      "step": 70
+    },
+    {
+      "epoch": 0.45977011494252873,
+      "grad_norm": 0.53515625,
+      "learning_rate": 4.5402298850574716e-05,
+      "loss": 0.2805,
+      "step": 80
+    },
+    {
+      "epoch": 0.5172413793103449,
+      "grad_norm": 0.62890625,
+      "learning_rate": 4.482758620689655e-05,
+      "loss": 0.3106,
+      "step": 90
+    },
+    {
+      "epoch": 0.5747126436781609,
+      "grad_norm": 0.5859375,
+      "learning_rate": 4.4252873563218394e-05,
+      "loss": 0.357,
+      "step": 100
+    },
+    {
+      "epoch": 0.5747126436781609,
+      "eval_loss": 0.5988770127296448,
+      "eval_runtime": 15.2078,
+      "eval_samples_per_second": 12.559,
+      "eval_steps_per_second": 0.789,
+      "step": 100
+    },
+    {
+      "epoch": 0.632183908045977,
+      "grad_norm": 0.625,
+      "learning_rate": 4.367816091954024e-05,
+      "loss": 0.3058,
+      "step": 110
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 0.578125,
+      "learning_rate": 4.3103448275862066e-05,
+      "loss": 0.2477,
+      "step": 120
+    },
+    {
+      "epoch": 0.7471264367816092,
+      "grad_norm": 0.8203125,
+      "learning_rate": 4.252873563218391e-05,
+      "loss": 0.2842,
+      "step": 130
+    },
+    {
+      "epoch": 0.8045977011494253,
+      "grad_norm": 0.60546875,
+      "learning_rate": 4.195402298850575e-05,
+      "loss": 0.3173,
+      "step": 140
+    },
+    {
+      "epoch": 0.8620689655172413,
+      "grad_norm": 0.64453125,
+      "learning_rate": 4.1379310344827587e-05,
+      "loss": 0.2785,
+      "step": 150
+    },
+    {
+      "epoch": 0.8620689655172413,
+      "eval_loss": 0.60736083984375,
+      "eval_runtime": 15.21,
+      "eval_samples_per_second": 12.558,
+      "eval_steps_per_second": 0.789,
+      "step": 150
+    },
+    {
+      "epoch": 0.9195402298850575,
+      "grad_norm": 0.68359375,
+      "learning_rate": 4.080459770114943e-05,
+      "loss": 0.2478,
+      "step": 160
+    },
+    {
+      "epoch": 0.9770114942528736,
+      "grad_norm": 0.66015625,
+      "learning_rate": 4.0229885057471265e-05,
+      "loss": 0.2232,
+      "step": 170
+    },
+    {
+      "epoch": 1.0344827586206897,
+      "grad_norm": 0.8671875,
+      "learning_rate": 3.965517241379311e-05,
+      "loss": 0.2507,
+      "step": 180
+    },
+    {
+      "epoch": 1.0919540229885056,
+      "grad_norm": 0.65625,
+      "learning_rate": 3.908045977011495e-05,
+      "loss": 0.2459,
+      "step": 190
+    },
+    {
+      "epoch": 1.1494252873563218,
+      "grad_norm": 0.66796875,
+      "learning_rate": 3.850574712643678e-05,
+      "loss": 0.2052,
+      "step": 200
+    },
+    {
+      "epoch": 1.1494252873563218,
+      "eval_loss": 0.630184531211853,
+      "eval_runtime": 14.8723,
+      "eval_samples_per_second": 12.843,
+      "eval_steps_per_second": 0.807,
+      "step": 200
+    },
+    {
+      "epoch": 1.206896551724138,
+      "grad_norm": 0.65234375,
+      "learning_rate": 3.793103448275862e-05,
+      "loss": 0.1732,
+      "step": 210
+    },
+    {
+      "epoch": 1.264367816091954,
+      "grad_norm": 0.80078125,
+      "learning_rate": 3.735632183908046e-05,
+      "loss": 0.1942,
+      "step": 220
+    },
+    {
+      "epoch": 1.3218390804597702,
+      "grad_norm": 0.69140625,
+      "learning_rate": 3.67816091954023e-05,
+      "loss": 0.2293,
+      "step": 230
+    },
+    {
+      "epoch": 1.3793103448275863,
+      "grad_norm": 0.6640625,
+      "learning_rate": 3.620689655172414e-05,
+      "loss": 0.2122,
+      "step": 240
+    },
+    {
+      "epoch": 1.4367816091954024,
+      "grad_norm": 0.671875,
+      "learning_rate": 3.563218390804598e-05,
+      "loss": 0.1795,
+      "step": 250
+    },
+    {
+      "epoch": 1.4367816091954024,
+      "eval_loss": 0.6453364491462708,
+      "eval_runtime": 15.2489,
+      "eval_samples_per_second": 12.525,
+      "eval_steps_per_second": 0.787,
+      "step": 250
+    },
+    {
+      "epoch": 1.4942528735632183,
+      "grad_norm": 0.8359375,
+      "learning_rate": 3.505747126436782e-05,
+      "loss": 0.166,
+      "step": 260
+    },
+    {
+      "epoch": 1.5517241379310345,
+      "grad_norm": 0.6328125,
+      "learning_rate": 3.4482758620689657e-05,
+      "loss": 0.227,
+      "step": 270
+    },
+    {
+      "epoch": 1.6091954022988506,
+      "grad_norm": 0.75,
+      "learning_rate": 3.390804597701149e-05,
+      "loss": 0.2018,
+      "step": 280
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.58984375,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.1623,
+      "step": 290
+    },
+    {
+      "epoch": 1.7241379310344827,
+      "grad_norm": 0.58984375,
+      "learning_rate": 3.275862068965517e-05,
+      "loss": 0.1336,
+      "step": 300
+    },
+    {
+      "epoch": 1.7241379310344827,
+      "eval_loss": 0.6576523780822754,
+      "eval_runtime": 15.2413,
+      "eval_samples_per_second": 12.532,
+      "eval_steps_per_second": 0.787,
+      "step": 300
+    },
+    {
+      "epoch": 1.7816091954022988,
+      "grad_norm": 0.80078125,
+      "learning_rate": 3.218390804597701e-05,
+      "loss": 0.2007,
+      "step": 310
+    },
+    {
+      "epoch": 1.839080459770115,
+      "grad_norm": 0.61328125,
+      "learning_rate": 3.160919540229885e-05,
+      "loss": 0.1948,
+      "step": 320
+    },
+    {
+      "epoch": 1.896551724137931,
+      "grad_norm": 0.72265625,
+      "learning_rate": 3.103448275862069e-05,
+      "loss": 0.1634,
+      "step": 330
+    },
+    {
+      "epoch": 1.9540229885057472,
+      "grad_norm": 0.578125,
+      "learning_rate": 3.045977011494253e-05,
+      "loss": 0.1416,
+      "step": 340
+    },
+    {
+      "epoch": 2.0114942528735633,
+      "grad_norm": 0.63671875,
+      "learning_rate": 2.988505747126437e-05,
+      "loss": 0.151,
+      "step": 350
+    },
+    {
+      "epoch": 2.0114942528735633,
+      "eval_loss": 0.6700878739356995,
+      "eval_runtime": 14.8872,
+      "eval_samples_per_second": 12.83,
+      "eval_steps_per_second": 0.806,
+      "step": 350
+    },
+    {
+      "epoch": 2.0689655172413794,
+      "grad_norm": 0.66015625,
+      "learning_rate": 2.9310344827586206e-05,
+      "loss": 0.1591,
+      "step": 360
+    },
+    {
+      "epoch": 2.1264367816091956,
+      "grad_norm": 0.53125,
+      "learning_rate": 2.8735632183908045e-05,
+      "loss": 0.1404,
+      "step": 370
+    },
+    {
+      "epoch": 2.1839080459770113,
+      "grad_norm": 0.58203125,
+      "learning_rate": 2.8160919540229884e-05,
+      "loss": 0.1173,
+      "step": 380
+    },
+    {
+      "epoch": 2.2413793103448274,
+      "grad_norm": 0.6171875,
+      "learning_rate": 2.7586206896551727e-05,
+      "loss": 0.1067,
+      "step": 390
+    },
+    {
+      "epoch": 2.2988505747126435,
+      "grad_norm": 0.703125,
+      "learning_rate": 2.7011494252873566e-05,
+      "loss": 0.1504,
+      "step": 400
+    },
+    {
+      "epoch": 2.2988505747126435,
+      "eval_loss": 0.7032656073570251,
+      "eval_runtime": 15.2246,
+      "eval_samples_per_second": 12.545,
+      "eval_steps_per_second": 0.788,
+      "step": 400
+    },
+    {
+      "epoch": 2.3563218390804597,
+      "grad_norm": 0.6015625,
+      "learning_rate": 2.6436781609195405e-05,
+      "loss": 0.1334,
+      "step": 410
+    },
+    {
+      "epoch": 2.413793103448276,
+      "grad_norm": 0.66796875,
+      "learning_rate": 2.5862068965517244e-05,
+      "loss": 0.1166,
+      "step": 420
+    },
+    {
+      "epoch": 2.471264367816092,
+      "grad_norm": 0.63671875,
+      "learning_rate": 2.5287356321839083e-05,
+      "loss": 0.0998,
+      "step": 430
+    },
+    {
+      "epoch": 2.528735632183908,
+      "grad_norm": 0.734375,
+      "learning_rate": 2.4712643678160922e-05,
+      "loss": 0.1299,
+      "step": 440
+    },
+    {
+      "epoch": 2.586206896551724,
+      "grad_norm": 0.6328125,
+      "learning_rate": 2.413793103448276e-05,
+      "loss": 0.1443,
+      "step": 450
+    },
+    {
+      "epoch": 2.586206896551724,
+      "eval_loss": 0.7000734210014343,
+      "eval_runtime": 15.3232,
+      "eval_samples_per_second": 12.465,
+      "eval_steps_per_second": 0.783,
+      "step": 450
+    },
+    {
+      "epoch": 2.6436781609195403,
+      "grad_norm": 0.6484375,
+      "learning_rate": 2.3563218390804597e-05,
+      "loss": 0.1129,
+      "step": 460
+    },
+    {
+      "epoch": 2.7011494252873565,
+      "grad_norm": 0.6015625,
+      "learning_rate": 2.2988505747126437e-05,
+      "loss": 0.0966,
+      "step": 470
+    },
+    {
+      "epoch": 2.7586206896551726,
+      "grad_norm": 0.69921875,
+      "learning_rate": 2.2413793103448276e-05,
+      "loss": 0.1044,
+      "step": 480
+    },
+    {
+      "epoch": 2.8160919540229887,
+      "grad_norm": 0.6953125,
+      "learning_rate": 2.183908045977012e-05,
+      "loss": 0.1447,
+      "step": 490
+    },
+    {
+      "epoch": 2.873563218390805,
+      "grad_norm": 0.64453125,
+      "learning_rate": 2.1264367816091954e-05,
+      "loss": 0.1156,
+      "step": 500
+    },
+    {
+      "epoch": 2.873563218390805,
+      "eval_loss": 0.7145028710365295,
+      "eval_runtime": 15.3052,
+      "eval_samples_per_second": 12.479,
+      "eval_steps_per_second": 0.784,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 870,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.5051522405612032e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2f426026b577c9a01d510963a11b9739a0fe05aae18ca70ff554e19c7eea3aa
+size 5688