Training in progress, epoch 1

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 sha256:2e49bd18f507a432e122a528c7dc5d52697cf7c4d683e1180e8d0ff7c17469aa
+size 4949453792

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c186933dfc1c0acc8c22caab7d420cd53d62131d7253c5ffc81f1db6ce4ccc8
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9c9ca1704090a92ad1a671537c23eb4a7282ac021c8d62108f5e181ddf5c7bd
+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 +1,67 @@
+{"current_steps": 10, "total_steps": 1920, "loss": 0.8468, "lr": 5.208333333333334e-07, "epoch": 0.015625, "percentage": 0.52, "elapsed_time": "0:01:00", "remaining_time": "3:11:25"}
+{"current_steps": 20, "total_steps": 1920, "loss": 0.7571, "lr": 1.0416666666666667e-06, "epoch": 0.03125, "percentage": 1.04, "elapsed_time": "0:01:59", "remaining_time": "3:08:38"}
+{"current_steps": 30, "total_steps": 1920, "loss": 0.6887, "lr": 1.5625e-06, "epoch": 0.046875, "percentage": 1.56, "elapsed_time": "0:02:59", "remaining_time": "3:08:35"}
+{"current_steps": 40, "total_steps": 1920, "loss": 0.6419, "lr": 2.0833333333333334e-06, "epoch": 0.0625, "percentage": 2.08, "elapsed_time": "0:03:59", "remaining_time": "3:07:21"}
+{"current_steps": 50, "total_steps": 1920, "loss": 0.6117, "lr": 2.604166666666667e-06, "epoch": 0.078125, "percentage": 2.6, "elapsed_time": "0:04:58", "remaining_time": "3:06:02"}
+{"current_steps": 60, "total_steps": 1920, "loss": 0.5912, "lr": 3.125e-06, "epoch": 0.09375, "percentage": 3.12, "elapsed_time": "0:05:57", "remaining_time": "3:04:54"}
+{"current_steps": 70, "total_steps": 1920, "loss": 0.5743, "lr": 3.6458333333333333e-06, "epoch": 0.109375, "percentage": 3.65, "elapsed_time": "0:06:57", "remaining_time": "3:03:54"}
+{"current_steps": 80, "total_steps": 1920, "loss": 0.5807, "lr": 4.166666666666667e-06, "epoch": 0.125, "percentage": 4.17, "elapsed_time": "0:07:56", "remaining_time": "3:02:45"}
+{"current_steps": 90, "total_steps": 1920, "loss": 0.561, "lr": 4.6875000000000004e-06, "epoch": 0.140625, "percentage": 4.69, "elapsed_time": "0:08:55", "remaining_time": "3:01:37"}
+{"current_steps": 100, "total_steps": 1920, "loss": 0.5596, "lr": 4.999946602507342e-06, "epoch": 0.15625, "percentage": 5.21, "elapsed_time": "0:09:55", "remaining_time": "3:00:38"}
+{"current_steps": 110, "total_steps": 1920, "loss": 0.5426, "lr": 4.999345909821495e-06, "epoch": 0.171875, "percentage": 5.73, "elapsed_time": "0:10:55", "remaining_time": "2:59:40"}
+{"current_steps": 120, "total_steps": 1920, "loss": 0.5514, "lr": 4.998077956371428e-06, "epoch": 0.1875, "percentage": 6.25, "elapsed_time": "0:11:54", "remaining_time": "2:58:38"}
+{"current_steps": 130, "total_steps": 1920, "loss": 0.5499, "lr": 4.996143118291191e-06, "epoch": 0.203125, "percentage": 6.77, "elapsed_time": "0:12:53", "remaining_time": "2:57:33"}
+{"current_steps": 140, "total_steps": 1920, "loss": 0.535, "lr": 4.993541969543877e-06, "epoch": 0.21875, "percentage": 7.29, "elapsed_time": "0:13:53", "remaining_time": "2:56:31"}
+{"current_steps": 150, "total_steps": 1920, "loss": 0.5295, "lr": 4.990275281751359e-06, "epoch": 0.234375, "percentage": 7.81, "elapsed_time": "0:14:52", "remaining_time": "2:55:32"}
+{"current_steps": 160, "total_steps": 1920, "loss": 0.5394, "lr": 4.9863440239653865e-06, "epoch": 0.25, "percentage": 8.33, "elapsed_time": "0:15:52", "remaining_time": "2:54:33"}
+{"current_steps": 170, "total_steps": 1920, "loss": 0.5318, "lr": 4.981749362380126e-06, "epoch": 0.265625, "percentage": 8.85, "elapsed_time": "0:16:51", "remaining_time": "2:53:33"}
+{"current_steps": 180, "total_steps": 1920, "loss": 0.5273, "lr": 4.976492659986207e-06, "epoch": 0.28125, "percentage": 9.38, "elapsed_time": "0:17:50", "remaining_time": "2:52:31"}
+{"current_steps": 190, "total_steps": 1920, "loss": 0.5262, "lr": 4.9705754761663995e-06, "epoch": 0.296875, "percentage": 9.9, "elapsed_time": "0:18:50", "remaining_time": "2:51:33"}
+{"current_steps": 200, "total_steps": 1920, "loss": 0.5156, "lr": 4.9639995662330295e-06, "epoch": 0.3125, "percentage": 10.42, "elapsed_time": "0:19:50", "remaining_time": "2:50:35"}
+{"current_steps": 210, "total_steps": 1920, "loss": 0.5138, "lr": 4.956766880907269e-06, "epoch": 0.328125, "percentage": 10.94, "elapsed_time": "0:20:49", "remaining_time": "2:49:36"}
+{"current_steps": 220, "total_steps": 1920, "loss": 0.5117, "lr": 4.948879565740459e-06, "epoch": 0.34375, "percentage": 11.46, "elapsed_time": "0:21:49", "remaining_time": "2:48:38"}
+{"current_steps": 230, "total_steps": 1920, "loss": 0.5158, "lr": 4.940339960477644e-06, "epoch": 0.359375, "percentage": 11.98, "elapsed_time": "0:22:49", "remaining_time": "2:47:39"}
+{"current_steps": 240, "total_steps": 1920, "loss": 0.5056, "lr": 4.931150598363494e-06, "epoch": 0.375, "percentage": 12.5, "elapsed_time": "0:23:48", "remaining_time": "2:46:40"}
+{"current_steps": 250, "total_steps": 1920, "loss": 0.5059, "lr": 4.921314205390822e-06, "epoch": 0.390625, "percentage": 13.02, "elapsed_time": "0:24:48", "remaining_time": "2:45:40"}
+{"current_steps": 260, "total_steps": 1920, "loss": 0.4997, "lr": 4.910833699491932e-06, "epoch": 0.40625, "percentage": 13.54, "elapsed_time": "0:25:47", "remaining_time": "2:44:39"}
+{"current_steps": 270, "total_steps": 1920, "loss": 0.5034, "lr": 4.899712189673023e-06, "epoch": 0.421875, "percentage": 14.06, "elapsed_time": "0:26:46", "remaining_time": "2:43:39"}
+{"current_steps": 280, "total_steps": 1920, "loss": 0.5035, "lr": 4.8879529750919105e-06, "epoch": 0.4375, "percentage": 14.58, "elapsed_time": "0:27:46", "remaining_time": "2:42:40"}
+{"current_steps": 290, "total_steps": 1920, "loss": 0.5024, "lr": 4.875559544079348e-06, "epoch": 0.453125, "percentage": 15.1, "elapsed_time": "0:28:45", "remaining_time": "2:41:39"}
+{"current_steps": 300, "total_steps": 1920, "loss": 0.49, "lr": 4.862535573104217e-06, "epoch": 0.46875, "percentage": 15.62, "elapsed_time": "0:29:45", "remaining_time": "2:40:40"}
+{"current_steps": 310, "total_steps": 1920, "loss": 0.494, "lr": 4.848884925682926e-06, "epoch": 0.484375, "percentage": 16.15, "elapsed_time": "0:30:45", "remaining_time": "2:39:46"}
+{"current_steps": 320, "total_steps": 1920, "loss": 0.4978, "lr": 4.8346116512333045e-06, "epoch": 0.5, "percentage": 16.67, "elapsed_time": "0:31:47", "remaining_time": "2:38:55"}
+{"current_steps": 330, "total_steps": 1920, "loss": 0.4959, "lr": 4.819719983873357e-06, "epoch": 0.515625, "percentage": 17.19, "elapsed_time": "0:32:46", "remaining_time": "2:37:54"}
+{"current_steps": 340, "total_steps": 1920, "loss": 0.4933, "lr": 4.804214341165228e-06, "epoch": 0.53125, "percentage": 17.71, "elapsed_time": "0:33:45", "remaining_time": "2:36:52"}
+{"current_steps": 350, "total_steps": 1920, "loss": 0.4835, "lr": 4.788099322804749e-06, "epoch": 0.546875, "percentage": 18.23, "elapsed_time": "0:34:44", "remaining_time": "2:35:51"}
+{"current_steps": 360, "total_steps": 1920, "loss": 0.4899, "lr": 4.771379709256953e-06, "epoch": 0.5625, "percentage": 18.75, "elapsed_time": "0:35:43", "remaining_time": "2:34:50"}
+{"current_steps": 370, "total_steps": 1920, "loss": 0.4904, "lr": 4.754060460337963e-06, "epoch": 0.578125, "percentage": 19.27, "elapsed_time": "0:36:43", "remaining_time": "2:33:49"}
+{"current_steps": 380, "total_steps": 1920, "loss": 0.4909, "lr": 4.7361467137436846e-06, "epoch": 0.59375, "percentage": 19.79, "elapsed_time": "0:37:42", "remaining_time": "2:32:48"}
+{"current_steps": 390, "total_steps": 1920, "loss": 0.4878, "lr": 4.7176437835257225e-06, "epoch": 0.609375, "percentage": 20.31, "elapsed_time": "0:38:41", "remaining_time": "2:31:47"}
+{"current_steps": 400, "total_steps": 1920, "loss": 0.5006, "lr": 4.698557158514988e-06, "epoch": 0.625, "percentage": 20.83, "elapsed_time": "0:39:40", "remaining_time": "2:30:46"}
+{"current_steps": 410, "total_steps": 1920, "loss": 0.493, "lr": 4.678892500693451e-06, "epoch": 0.640625, "percentage": 21.35, "elapsed_time": "0:40:39", "remaining_time": "2:29:44"}
+{"current_steps": 420, "total_steps": 1920, "loss": 0.4815, "lr": 4.6586556435145404e-06, "epoch": 0.65625, "percentage": 21.88, "elapsed_time": "0:41:40", "remaining_time": "2:28:50"}
+{"current_steps": 430, "total_steps": 1920, "loss": 0.4936, "lr": 4.637852590172665e-06, "epoch": 0.671875, "percentage": 22.4, "elapsed_time": "0:42:43", "remaining_time": "2:28:01"}
+{"current_steps": 440, "total_steps": 1920, "loss": 0.4885, "lr": 4.616489511822384e-06, "epoch": 0.6875, "percentage": 22.92, "elapsed_time": "0:43:44", "remaining_time": "2:27:08"}
+{"current_steps": 450, "total_steps": 1920, "loss": 0.4937, "lr": 4.59457274574776e-06, "epoch": 0.703125, "percentage": 23.44, "elapsed_time": "0:44:44", "remaining_time": "2:26:07"}
+{"current_steps": 460, "total_steps": 1920, "loss": 0.4834, "lr": 4.572108793482425e-06, "epoch": 0.71875, "percentage": 23.96, "elapsed_time": "0:45:43", "remaining_time": "2:25:06"}
+{"current_steps": 470, "total_steps": 1920, "loss": 0.4955, "lr": 4.549104318880919e-06, "epoch": 0.734375, "percentage": 24.48, "elapsed_time": "0:46:42", "remaining_time": "2:24:06"}
+{"current_steps": 480, "total_steps": 1920, "loss": 0.4839, "lr": 4.525566146141886e-06, "epoch": 0.75, "percentage": 25.0, "elapsed_time": "0:47:41", "remaining_time": "2:23:05"}
+{"current_steps": 490, "total_steps": 1920, "loss": 0.482, "lr": 4.501501257783692e-06, "epoch": 0.765625, "percentage": 25.52, "elapsed_time": "0:48:41", "remaining_time": "2:22:04"}
+{"current_steps": 500, "total_steps": 1920, "loss": 0.4758, "lr": 4.47691679257309e-06, "epoch": 0.78125, "percentage": 26.04, "elapsed_time": "0:49:40", "remaining_time": "2:21:03"}
+{"current_steps": 510, "total_steps": 1920, "loss": 0.4788, "lr": 4.451820043407527e-06, "epoch": 0.796875, "percentage": 26.56, "elapsed_time": "0:50:39", "remaining_time": "2:20:02"}
+{"current_steps": 520, "total_steps": 1920, "loss": 0.4722, "lr": 4.426218455151733e-06, "epoch": 0.8125, "percentage": 27.08, "elapsed_time": "0:51:38", "remaining_time": "2:19:02"}
+{"current_steps": 530, "total_steps": 1920, "loss": 0.4792, "lr": 4.400119622429226e-06, "epoch": 0.828125, "percentage": 27.6, "elapsed_time": "0:52:37", "remaining_time": "2:18:01"}
+{"current_steps": 540, "total_steps": 1920, "loss": 0.4836, "lr": 4.3735312873693905e-06, "epoch": 0.84375, "percentage": 28.12, "elapsed_time": "0:53:37", "remaining_time": "2:17:01"}
+{"current_steps": 550, "total_steps": 1920, "loss": 0.4827, "lr": 4.346461337310805e-06, "epoch": 0.859375, "percentage": 28.65, "elapsed_time": "0:54:36", "remaining_time": "2:16:00"}
+{"current_steps": 560, "total_steps": 1920, "loss": 0.4798, "lr": 4.31891780246149e-06, "epoch": 0.875, "percentage": 29.17, "elapsed_time": "0:55:35", "remaining_time": "2:15:00"}
+{"current_steps": 570, "total_steps": 1920, "loss": 0.4764, "lr": 4.290908853516771e-06, "epoch": 0.890625, "percentage": 29.69, "elapsed_time": "0:56:34", "remaining_time": "2:13:59"}
+{"current_steps": 580, "total_steps": 1920, "loss": 0.4698, "lr": 4.262442799235474e-06, "epoch": 0.90625, "percentage": 30.21, "elapsed_time": "0:57:33", "remaining_time": "2:12:59"}
+{"current_steps": 590, "total_steps": 1920, "loss": 0.4702, "lr": 4.233528083975155e-06, "epoch": 0.921875, "percentage": 30.73, "elapsed_time": "0:58:33", "remaining_time": "2:11:59"}
+{"current_steps": 600, "total_steps": 1920, "loss": 0.466, "lr": 4.204173285187117e-06, "epoch": 0.9375, "percentage": 31.25, "elapsed_time": "0:59:32", "remaining_time": "2:10:59"}
+{"current_steps": 610, "total_steps": 1920, "loss": 0.4696, "lr": 4.1743871108719334e-06, "epoch": 0.953125, "percentage": 31.77, "elapsed_time": "1:00:31", "remaining_time": "2:09:59"}
+{"current_steps": 620, "total_steps": 1920, "loss": 0.4708, "lr": 4.1441783969962506e-06, "epoch": 0.96875, "percentage": 32.29, "elapsed_time": "1:01:30", "remaining_time": "2:08:58"}
+{"current_steps": 630, "total_steps": 1920, "loss": 0.4684, "lr": 4.113556104871631e-06, "epoch": 0.984375, "percentage": 32.81, "elapsed_time": "1:02:29", "remaining_time": "2:07:57"}
+{"current_steps": 640, "total_steps": 1920, "loss": 0.4706, "lr": 4.082529318496206e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "1:03:26", "remaining_time": "2:06:53"}
+{"current_steps": 640, "total_steps": 1920, "eval_loss": 0.4656927287578583, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "1:04:26", "remaining_time": "2:08:52"}
+{"current_steps": 650, "total_steps": 1920, "loss": 0.3837, "lr": 4.051107241859944e-06, "epoch": 1.015625, "percentage": 33.85, "elapsed_time": "1:06:24", "remaining_time": "2:09:44"}
+{"current_steps": 660, "total_steps": 1920, "loss": 0.3803, "lr": 4.019299196214315e-06, "epoch": 1.03125, "percentage": 34.38, "elapsed_time": "1:07:23", "remaining_time": "2:08:39"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:125fdddf538d3b4add78d6d7075d103cc1bb3010885f078edd0e79f9df47f7be
+size 7352