Training in progress, epoch 0

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.3",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "vocab_size": 32768
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:817261c1ff95c592d6134b9eaf8f5716e82fe67c4286e5ccd31425c3efdd6c94
+size 4949453792

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15c8b53916bc2ab51f97e211964485128c91a7f8fe6802234be93b112fe355b0
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0720febbd5566d54a11d02b88b6214274de00a2b83f9a8ead117588b1385d00e
+size 4546807800

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14496047104
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

trainer_log.jsonl

@@ -0,0 +1,68 @@
+{"current_steps": 10, "total_steps": 2001, "loss": 0.902, "lr": 1.6611295681063126e-07, "epoch": 0.014989694584972832, "percentage": 0.5, "elapsed_time": "0:05:21", "remaining_time": "17:46:33"}
+{"current_steps": 20, "total_steps": 2001, "loss": 0.8565, "lr": 3.322259136212625e-07, "epoch": 0.029979389169945664, "percentage": 1.0, "elapsed_time": "0:10:36", "remaining_time": "17:30:12"}
+{"current_steps": 30, "total_steps": 2001, "loss": 0.7765, "lr": 4.983388704318938e-07, "epoch": 0.044969083754918496, "percentage": 1.5, "elapsed_time": "0:15:50", "remaining_time": "17:20:46"}
+{"current_steps": 40, "total_steps": 2001, "loss": 0.7102, "lr": 6.64451827242525e-07, "epoch": 0.05995877833989133, "percentage": 2.0, "elapsed_time": "0:21:04", "remaining_time": "17:13:32"}
+{"current_steps": 50, "total_steps": 2001, "loss": 0.6762, "lr": 8.305647840531563e-07, "epoch": 0.07494847292486416, "percentage": 2.5, "elapsed_time": "0:26:19", "remaining_time": "17:07:15"}
+{"current_steps": 60, "total_steps": 2001, "loss": 0.6471, "lr": 9.966777408637875e-07, "epoch": 0.08993816750983699, "percentage": 3.0, "elapsed_time": "0:31:32", "remaining_time": "17:00:24"}
+{"current_steps": 70, "total_steps": 2001, "loss": 0.6264, "lr": 1.1627906976744188e-06, "epoch": 0.10492786209480982, "percentage": 3.5, "elapsed_time": "0:36:43", "remaining_time": "16:53:16"}
+{"current_steps": 80, "total_steps": 2001, "loss": 0.6131, "lr": 1.32890365448505e-06, "epoch": 0.11991755667978266, "percentage": 4.0, "elapsed_time": "0:41:58", "remaining_time": "16:48:02"}
+{"current_steps": 90, "total_steps": 2001, "loss": 0.6011, "lr": 1.4950166112956813e-06, "epoch": 0.13490725126475547, "percentage": 4.5, "elapsed_time": "0:47:12", "remaining_time": "16:42:25"}
+{"current_steps": 100, "total_steps": 2001, "loss": 0.5888, "lr": 1.6611295681063126e-06, "epoch": 0.14989694584972832, "percentage": 5.0, "elapsed_time": "0:52:26", "remaining_time": "16:36:58"}
+{"current_steps": 110, "total_steps": 2001, "loss": 0.5836, "lr": 1.8272425249169438e-06, "epoch": 0.16488664043470114, "percentage": 5.5, "elapsed_time": "0:57:41", "remaining_time": "16:31:52"}
+{"current_steps": 120, "total_steps": 2001, "loss": 0.5767, "lr": 1.993355481727575e-06, "epoch": 0.17987633501967398, "percentage": 6.0, "elapsed_time": "1:02:54", "remaining_time": "16:26:06"}
+{"current_steps": 130, "total_steps": 2001, "loss": 0.5689, "lr": 2.1594684385382063e-06, "epoch": 0.1948660296046468, "percentage": 6.5, "elapsed_time": "1:08:08", "remaining_time": "16:20:48"}
+{"current_steps": 140, "total_steps": 2001, "loss": 0.5694, "lr": 2.3255813953488376e-06, "epoch": 0.20985572418961965, "percentage": 7.0, "elapsed_time": "1:13:25", "remaining_time": "16:16:03"}
+{"current_steps": 150, "total_steps": 2001, "loss": 0.5576, "lr": 2.4916943521594684e-06, "epoch": 0.22484541877459246, "percentage": 7.5, "elapsed_time": "1:18:40", "remaining_time": "16:10:51"}
+{"current_steps": 160, "total_steps": 2001, "loss": 0.5556, "lr": 2.6578073089701e-06, "epoch": 0.2398351133595653, "percentage": 8.0, "elapsed_time": "1:23:56", "remaining_time": "16:05:47"}
+{"current_steps": 170, "total_steps": 2001, "loss": 0.5521, "lr": 2.8239202657807313e-06, "epoch": 0.25482480794453816, "percentage": 8.5, "elapsed_time": "1:29:10", "remaining_time": "16:00:26"}
+{"current_steps": 180, "total_steps": 2001, "loss": 0.5471, "lr": 2.9900332225913626e-06, "epoch": 0.26981450252951095, "percentage": 9.0, "elapsed_time": "1:34:24", "remaining_time": "15:55:00"}
+{"current_steps": 190, "total_steps": 2001, "loss": 0.5444, "lr": 3.156146179401994e-06, "epoch": 0.2848041971144838, "percentage": 9.5, "elapsed_time": "1:39:39", "remaining_time": "15:49:51"}
+{"current_steps": 200, "total_steps": 2001, "loss": 0.5385, "lr": 3.322259136212625e-06, "epoch": 0.29979389169945664, "percentage": 10.0, "elapsed_time": "1:44:52", "remaining_time": "15:44:26"}
+{"current_steps": 210, "total_steps": 2001, "loss": 0.5351, "lr": 3.4883720930232564e-06, "epoch": 0.31478358628442943, "percentage": 10.49, "elapsed_time": "1:50:05", "remaining_time": "15:38:58"}
+{"current_steps": 220, "total_steps": 2001, "loss": 0.5363, "lr": 3.6544850498338876e-06, "epoch": 0.3297732808694023, "percentage": 10.99, "elapsed_time": "1:55:20", "remaining_time": "15:33:41"}
+{"current_steps": 230, "total_steps": 2001, "loss": 0.5334, "lr": 3.8205980066445185e-06, "epoch": 0.3447629754543751, "percentage": 11.49, "elapsed_time": "2:00:36", "remaining_time": "15:28:37"}
+{"current_steps": 240, "total_steps": 2001, "loss": 0.5316, "lr": 3.98671096345515e-06, "epoch": 0.35975267003934797, "percentage": 11.99, "elapsed_time": "2:05:52", "remaining_time": "15:23:36"}
+{"current_steps": 250, "total_steps": 2001, "loss": 0.5268, "lr": 4.152823920265781e-06, "epoch": 0.37474236462432076, "percentage": 12.49, "elapsed_time": "2:11:07", "remaining_time": "15:18:25"}
+{"current_steps": 260, "total_steps": 2001, "loss": 0.5289, "lr": 4.318936877076413e-06, "epoch": 0.3897320592092936, "percentage": 12.99, "elapsed_time": "2:16:23", "remaining_time": "15:13:18"}
+{"current_steps": 270, "total_steps": 2001, "loss": 0.5235, "lr": 4.4850498338870435e-06, "epoch": 0.40472175379426645, "percentage": 13.49, "elapsed_time": "2:21:39", "remaining_time": "15:08:09"}
+{"current_steps": 280, "total_steps": 2001, "loss": 0.5265, "lr": 4.651162790697675e-06, "epoch": 0.4197114483792393, "percentage": 13.99, "elapsed_time": "2:26:52", "remaining_time": "15:02:44"}
+{"current_steps": 290, "total_steps": 2001, "loss": 0.5193, "lr": 4.817275747508306e-06, "epoch": 0.4347011429642121, "percentage": 14.49, "elapsed_time": "2:32:07", "remaining_time": "14:57:31"}
+{"current_steps": 300, "total_steps": 2001, "loss": 0.5156, "lr": 4.983388704318937e-06, "epoch": 0.44969083754918493, "percentage": 14.99, "elapsed_time": "2:37:23", "remaining_time": "14:52:26"}
+{"current_steps": 310, "total_steps": 2001, "loss": 0.5177, "lr": 4.999654230307899e-06, "epoch": 0.4646805321341578, "percentage": 15.49, "elapsed_time": "2:42:39", "remaining_time": "14:47:15"}
+{"current_steps": 320, "total_steps": 2001, "loss": 0.512, "lr": 4.998459099844914e-06, "epoch": 0.4796702267191306, "percentage": 15.99, "elapsed_time": "2:47:55", "remaining_time": "14:42:06"}
+{"current_steps": 330, "total_steps": 2001, "loss": 0.5104, "lr": 4.996410747888184e-06, "epoch": 0.4946599213041034, "percentage": 16.49, "elapsed_time": "2:53:10", "remaining_time": "14:36:53"}
+{"current_steps": 340, "total_steps": 2001, "loss": 0.5083, "lr": 4.993509873948025e-06, "epoch": 0.5096496158890763, "percentage": 16.99, "elapsed_time": "2:58:24", "remaining_time": "14:31:34"}
+{"current_steps": 350, "total_steps": 2001, "loss": 0.5049, "lr": 4.989757468670231e-06, "epoch": 0.5246393104740491, "percentage": 17.49, "elapsed_time": "3:03:40", "remaining_time": "14:26:27"}
+{"current_steps": 360, "total_steps": 2001, "loss": 0.5093, "lr": 4.985154813497765e-06, "epoch": 0.5396290050590219, "percentage": 17.99, "elapsed_time": "3:08:58", "remaining_time": "14:21:22"}
+{"current_steps": 370, "total_steps": 2001, "loss": 0.5034, "lr": 4.979703480233156e-06, "epoch": 0.5546186996439948, "percentage": 18.49, "elapsed_time": "3:14:14", "remaining_time": "14:16:12"}
+{"current_steps": 380, "total_steps": 2001, "loss": 0.5023, "lr": 4.973405330501715e-06, "epoch": 0.5696083942289676, "percentage": 18.99, "elapsed_time": "3:19:30", "remaining_time": "14:11:04"}
+{"current_steps": 390, "total_steps": 2001, "loss": 0.4999, "lr": 4.966262515115808e-06, "epoch": 0.5845980888139404, "percentage": 19.49, "elapsed_time": "3:24:46", "remaining_time": "14:05:51"}
+{"current_steps": 400, "total_steps": 2001, "loss": 0.5043, "lr": 4.958277473340345e-06, "epoch": 0.5995877833989133, "percentage": 19.99, "elapsed_time": "3:30:01", "remaining_time": "14:00:37"}
+{"current_steps": 410, "total_steps": 2001, "loss": 0.5012, "lr": 4.949452932059777e-06, "epoch": 0.6145774779838861, "percentage": 20.49, "elapsed_time": "3:35:18", "remaining_time": "13:55:28"}
+{"current_steps": 420, "total_steps": 2001, "loss": 0.4969, "lr": 4.939791904846869e-06, "epoch": 0.6295671725688589, "percentage": 20.99, "elapsed_time": "3:40:33", "remaining_time": "13:50:15"}
+{"current_steps": 430, "total_steps": 2001, "loss": 0.4976, "lr": 4.929297690933561e-06, "epoch": 0.6445568671538318, "percentage": 21.49, "elapsed_time": "3:45:49", "remaining_time": "13:45:03"}
+{"current_steps": 440, "total_steps": 2001, "loss": 0.494, "lr": 4.917973874084293e-06, "epoch": 0.6595465617388045, "percentage": 21.99, "elapsed_time": "3:51:05", "remaining_time": "13:39:51"}
+{"current_steps": 450, "total_steps": 2001, "loss": 0.4946, "lr": 4.905824321372143e-06, "epoch": 0.6745362563237775, "percentage": 22.49, "elapsed_time": "3:56:21", "remaining_time": "13:34:40"}
+{"current_steps": 460, "total_steps": 2001, "loss": 0.4883, "lr": 4.892853181858234e-06, "epoch": 0.6895259509087502, "percentage": 22.99, "elapsed_time": "4:01:37", "remaining_time": "13:29:27"}
+{"current_steps": 470, "total_steps": 2001, "loss": 0.4873, "lr": 4.879064885174825e-06, "epoch": 0.704515645493723, "percentage": 23.49, "elapsed_time": "4:06:53", "remaining_time": "13:24:15"}
+{"current_steps": 480, "total_steps": 2001, "loss": 0.4922, "lr": 4.8644641400126035e-06, "epoch": 0.7195053400786959, "percentage": 23.99, "elapsed_time": "4:12:07", "remaining_time": "13:18:55"}
+{"current_steps": 490, "total_steps": 2001, "loss": 0.4911, "lr": 4.849055932512666e-06, "epoch": 0.7344950346636687, "percentage": 24.49, "elapsed_time": "4:17:23", "remaining_time": "13:13:41"}
+{"current_steps": 500, "total_steps": 2001, "loss": 0.4884, "lr": 4.832845524563758e-06, "epoch": 0.7494847292486415, "percentage": 24.99, "elapsed_time": "4:22:36", "remaining_time": "13:08:22"}
+{"current_steps": 510, "total_steps": 2001, "loss": 0.4941, "lr": 4.815838452005344e-06, "epoch": 0.7644744238336144, "percentage": 25.49, "elapsed_time": "4:27:52", "remaining_time": "13:03:07"}
+{"current_steps": 520, "total_steps": 2001, "loss": 0.4873, "lr": 4.798040522737122e-06, "epoch": 0.7794641184185872, "percentage": 25.99, "elapsed_time": "4:33:08", "remaining_time": "12:57:55"}
+{"current_steps": 530, "total_steps": 2001, "loss": 0.4841, "lr": 4.779457814735632e-06, "epoch": 0.7944538130035601, "percentage": 26.49, "elapsed_time": "4:38:23", "remaining_time": "12:52:39"}
+{"current_steps": 540, "total_steps": 2001, "loss": 0.4824, "lr": 4.760096673978634e-06, "epoch": 0.8094435075885329, "percentage": 26.99, "elapsed_time": "4:43:37", "remaining_time": "12:47:21"}
+{"current_steps": 550, "total_steps": 2001, "loss": 0.4872, "lr": 4.73996371227796e-06, "epoch": 0.8244332021735057, "percentage": 27.49, "elapsed_time": "4:48:53", "remaining_time": "12:42:08"}
+{"current_steps": 560, "total_steps": 2001, "loss": 0.4839, "lr": 4.719065805021584e-06, "epoch": 0.8394228967584786, "percentage": 27.99, "elapsed_time": "4:54:09", "remaining_time": "12:36:54"}
+{"current_steps": 570, "total_steps": 2001, "loss": 0.4832, "lr": 4.697410088825692e-06, "epoch": 0.8544125913434514, "percentage": 28.49, "elapsed_time": "4:59:25", "remaining_time": "12:31:41"}
+{"current_steps": 580, "total_steps": 2001, "loss": 0.4767, "lr": 4.675003959097525e-06, "epoch": 0.8694022859284242, "percentage": 28.99, "elapsed_time": "5:04:40", "remaining_time": "12:26:27"}
+{"current_steps": 590, "total_steps": 2001, "loss": 0.4782, "lr": 4.65185506750986e-06, "epoch": 0.8843919805133971, "percentage": 29.49, "elapsed_time": "5:09:54", "remaining_time": "12:21:10"}
+{"current_steps": 600, "total_steps": 2001, "loss": 0.4795, "lr": 4.627971319387965e-06, "epoch": 0.8993816750983699, "percentage": 29.99, "elapsed_time": "5:15:10", "remaining_time": "12:15:56"}
+{"current_steps": 610, "total_steps": 2001, "loss": 0.4774, "lr": 4.603360871009946e-06, "epoch": 0.9143713696833426, "percentage": 30.48, "elapsed_time": "5:20:26", "remaining_time": "12:10:42"}
+{"current_steps": 620, "total_steps": 2001, "loss": 0.4771, "lr": 4.578032126821377e-06, "epoch": 0.9293610642683156, "percentage": 30.98, "elapsed_time": "5:25:41", "remaining_time": "12:05:27"}
+{"current_steps": 630, "total_steps": 2001, "loss": 0.4785, "lr": 4.5519937365651945e-06, "epoch": 0.9443507588532883, "percentage": 31.48, "elapsed_time": "5:30:57", "remaining_time": "12:00:13"}
+{"current_steps": 640, "total_steps": 2001, "loss": 0.4712, "lr": 4.525254592327817e-06, "epoch": 0.9593404534382612, "percentage": 31.98, "elapsed_time": "5:36:13", "remaining_time": "11:54:59"}
+{"current_steps": 650, "total_steps": 2001, "loss": 0.4746, "lr": 4.497823825502507e-06, "epoch": 0.974330148023234, "percentage": 32.48, "elapsed_time": "5:41:29", "remaining_time": "11:49:45"}
+{"current_steps": 660, "total_steps": 2001, "loss": 0.4707, "lr": 4.469710803671004e-06, "epoch": 0.9893198426082068, "percentage": 32.98, "elapsed_time": "5:46:45", "remaining_time": "11:44:32"}
+{"current_steps": 667, "total_steps": 2001, "eval_loss": 0.058926939964294434, "epoch": 0.9998126288176878, "percentage": 33.33, "elapsed_time": "5:58:05", "remaining_time": "11:56:11"}
+{"current_steps": 670, "total_steps": 2001, "loss": 0.4526, "lr": 4.440925127404512e-06, "epoch": 1.0043095371931796, "percentage": 33.48, "elapsed_time": "6:00:42", "remaining_time": "11:56:34"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aac63a446b98cd237dbc2d8a5aed044282a0aec3fb24be71278804e899a09a6
+size 7288