Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "models/Qwen2-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.4",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.43.4"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98e6ac4417db9e5bfb3c82854083e6dea87fd94fe0358d7c650867b1a84a52c4
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:295569238818682fc40bf6dee882765c49649234fe9164aaea4ed2324738f097
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cbdcbe59f9b436c3825ed1dfbb262640c88a2de4d3da39dd9b687a8d7a2907a
+size 4991478896

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d608765577e2da8da8c2219f9a97e7e78c4c8466ee4a89892f6d08a4b21b274
+size 1361612328

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 16163464192
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ab35f68dc4adbfd1f953529be90c00be38f87c3c438e8ef126a85f0d97eb370
+size 3728945366

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9a464a4bb38035d01b7923033ab69172fd427cd42378211d983f2134560d0fd
+size 14768

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dee9722ed4cef759c7e050a49c3e0abafeb0721fb1e496eb3d7b18db99e2ebca
+size 14768

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1370bac436b97343955d07682100afbd58f36b1a30915ccfa26c44d5d654ce8b
+size 14768

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4917025009c4f3a7ceaa77f145cceff9ff5bb46e49309065737036bc21c6b05
+size 1064

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,878 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 19.51219512195122,
+  "eval_steps": 100,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1951219512195122,
+      "grad_norm": 3.5239181518554688,
+      "learning_rate": 4.999451708687114e-05,
+      "loss": 1.1522,
+      "num_input_tokens_seen": 2231104,
+      "step": 5
+    },
+    {
+      "epoch": 0.3902439024390244,
+      "grad_norm": 1.2978184223175049,
+      "learning_rate": 4.997807075247146e-05,
+      "loss": 0.8861,
+      "num_input_tokens_seen": 4468608,
+      "step": 10
+    },
+    {
+      "epoch": 0.5853658536585366,
+      "grad_norm": 1.0176712274551392,
+      "learning_rate": 4.995066821070679e-05,
+      "loss": 0.8351,
+      "num_input_tokens_seen": 6779584,
+      "step": 15
+    },
+    {
+      "epoch": 0.7804878048780488,
+      "grad_norm": 0.6517723798751831,
+      "learning_rate": 4.991232148123761e-05,
+      "loss": 0.7797,
+      "num_input_tokens_seen": 9106880,
+      "step": 20
+    },
+    {
+      "epoch": 0.975609756097561,
+      "grad_norm": 0.6675965785980225,
+      "learning_rate": 4.9863047384206835e-05,
+      "loss": 0.7575,
+      "num_input_tokens_seen": 11435136,
+      "step": 25
+    },
+    {
+      "epoch": 1.170731707317073,
+      "grad_norm": 1.225784182548523,
+      "learning_rate": 4.980286753286195e-05,
+      "loss": 0.7345,
+      "num_input_tokens_seen": 13738880,
+      "step": 30
+    },
+    {
+      "epoch": 1.3658536585365852,
+      "grad_norm": 0.4991011321544647,
+      "learning_rate": 4.9731808324074717e-05,
+      "loss": 0.7443,
+      "num_input_tokens_seen": 16001920,
+      "step": 35
+    },
+    {
+      "epoch": 1.5609756097560976,
+      "grad_norm": 0.7908358573913574,
+      "learning_rate": 4.964990092676263e-05,
+      "loss": 0.7211,
+      "num_input_tokens_seen": 18282944,
+      "step": 40
+    },
+    {
+      "epoch": 1.7560975609756098,
+      "grad_norm": 0.9223726391792297,
+      "learning_rate": 4.9557181268217227e-05,
+      "loss": 0.7306,
+      "num_input_tokens_seen": 20575296,
+      "step": 45
+    },
+    {
+      "epoch": 1.951219512195122,
+      "grad_norm": 0.8891558051109314,
+      "learning_rate": 4.9453690018345144e-05,
+      "loss": 0.7039,
+      "num_input_tokens_seen": 22849856,
+      "step": 50
+    },
+    {
+      "epoch": 2.1463414634146343,
+      "grad_norm": 1.3324096202850342,
+      "learning_rate": 4.933947257182901e-05,
+      "loss": 0.7044,
+      "num_input_tokens_seen": 25176896,
+      "step": 55
+    },
+    {
+      "epoch": 2.341463414634146,
+      "grad_norm": 1.0357320308685303,
+      "learning_rate": 4.9214579028215776e-05,
+      "loss": 0.6768,
+      "num_input_tokens_seen": 27457472,
+      "step": 60
+    },
+    {
+      "epoch": 2.5365853658536586,
+      "grad_norm": 0.6939280033111572,
+      "learning_rate": 4.907906416994146e-05,
+      "loss": 0.6906,
+      "num_input_tokens_seen": 29772544,
+      "step": 65
+    },
+    {
+      "epoch": 2.7317073170731705,
+      "grad_norm": 0.7578678727149963,
+      "learning_rate": 4.893298743830168e-05,
+      "loss": 0.6595,
+      "num_input_tokens_seen": 32013760,
+      "step": 70
+    },
+    {
+      "epoch": 2.926829268292683,
+      "grad_norm": 0.548279345035553,
+      "learning_rate": 4.877641290737884e-05,
+      "loss": 0.6514,
+      "num_input_tokens_seen": 34342848,
+      "step": 75
+    },
+    {
+      "epoch": 3.1219512195121952,
+      "grad_norm": 1.1982917785644531,
+      "learning_rate": 4.860940925593703e-05,
+      "loss": 0.6498,
+      "num_input_tokens_seen": 36592000,
+      "step": 80
+    },
+    {
+      "epoch": 3.317073170731707,
+      "grad_norm": 1.0446078777313232,
+      "learning_rate": 4.843204973729729e-05,
+      "loss": 0.6537,
+      "num_input_tokens_seen": 38878528,
+      "step": 85
+    },
+    {
+      "epoch": 3.5121951219512195,
+      "grad_norm": 0.7469108700752258,
+      "learning_rate": 4.8244412147206284e-05,
+      "loss": 0.5996,
+      "num_input_tokens_seen": 41156672,
+      "step": 90
+    },
+    {
+      "epoch": 3.7073170731707314,
+      "grad_norm": 0.7562854886054993,
+      "learning_rate": 4.8046578789712515e-05,
+      "loss": 0.6289,
+      "num_input_tokens_seen": 43475456,
+      "step": 95
+    },
+    {
+      "epoch": 3.902439024390244,
+      "grad_norm": 0.7673454880714417,
+      "learning_rate": 4.783863644106502e-05,
+      "loss": 0.6607,
+      "num_input_tokens_seen": 45798272,
+      "step": 100
+    },
+    {
+      "epoch": 3.902439024390244,
+      "eval_loss": 0.6353042125701904,
+      "eval_runtime": 174.6543,
+      "eval_samples_per_second": 12.07,
+      "eval_steps_per_second": 0.504,
+      "num_input_tokens_seen": 45798272,
+      "step": 100
+    },
+    {
+      "epoch": 4.097560975609756,
+      "grad_norm": 0.6962050199508667,
+      "learning_rate": 4.762067631165049e-05,
+      "loss": 0.5924,
+      "num_input_tokens_seen": 48035456,
+      "step": 105
+    },
+    {
+      "epoch": 4.2926829268292686,
+      "grad_norm": 1.080012559890747,
+      "learning_rate": 4.7392794005985326e-05,
+      "loss": 0.6107,
+      "num_input_tokens_seen": 50295680,
+      "step": 110
+    },
+    {
+      "epoch": 4.487804878048781,
+      "grad_norm": 0.6142390966415405,
+      "learning_rate": 4.715508948078037e-05,
+      "loss": 0.6016,
+      "num_input_tokens_seen": 52611072,
+      "step": 115
+    },
+    {
+      "epoch": 4.682926829268292,
+      "grad_norm": 0.7695103883743286,
+      "learning_rate": 4.690766700109659e-05,
+      "loss": 0.5946,
+      "num_input_tokens_seen": 54817920,
+      "step": 120
+    },
+    {
+      "epoch": 4.878048780487805,
+      "grad_norm": 0.7141166925430298,
+      "learning_rate": 4.665063509461097e-05,
+      "loss": 0.5926,
+      "num_input_tokens_seen": 57135552,
+      "step": 125
+    },
+    {
+      "epoch": 5.073170731707317,
+      "grad_norm": 0.9515812993049622,
+      "learning_rate": 4.638410650401267e-05,
+      "loss": 0.5986,
+      "num_input_tokens_seen": 59455680,
+      "step": 130
+    },
+    {
+      "epoch": 5.2682926829268295,
+      "grad_norm": 1.5192577838897705,
+      "learning_rate": 4.610819813755038e-05,
+      "loss": 0.5619,
+      "num_input_tokens_seen": 61782208,
+      "step": 135
+    },
+    {
+      "epoch": 5.463414634146342,
+      "grad_norm": 1.0420284271240234,
+      "learning_rate": 4.5823031017752485e-05,
+      "loss": 0.5739,
+      "num_input_tokens_seen": 64051520,
+      "step": 140
+    },
+    {
+      "epoch": 5.658536585365853,
+      "grad_norm": 0.6723448038101196,
+      "learning_rate": 4.5528730228342605e-05,
+      "loss": 0.5673,
+      "num_input_tokens_seen": 66320192,
+      "step": 145
+    },
+    {
+      "epoch": 5.853658536585366,
+      "grad_norm": 0.8727495074272156,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 0.5607,
+      "num_input_tokens_seen": 68535424,
+      "step": 150
+    },
+    {
+      "epoch": 6.048780487804878,
+      "grad_norm": 1.1162189245224,
+      "learning_rate": 4.491324795060491e-05,
+      "loss": 0.5711,
+      "num_input_tokens_seen": 70861632,
+      "step": 155
+    },
+    {
+      "epoch": 6.2439024390243905,
+      "grad_norm": 1.0553621053695679,
+      "learning_rate": 4.4592336433146e-05,
+      "loss": 0.5437,
+      "num_input_tokens_seen": 73124480,
+      "step": 160
+    },
+    {
+      "epoch": 6.439024390243903,
+      "grad_norm": 1.105603575706482,
+      "learning_rate": 4.426283106939474e-05,
+      "loss": 0.5437,
+      "num_input_tokens_seen": 75439232,
+      "step": 165
+    },
+    {
+      "epoch": 6.634146341463414,
+      "grad_norm": 0.9295886158943176,
+      "learning_rate": 4.3924876391293915e-05,
+      "loss": 0.5321,
+      "num_input_tokens_seen": 77689536,
+      "step": 170
+    },
+    {
+      "epoch": 6.829268292682927,
+      "grad_norm": 0.9514282941818237,
+      "learning_rate": 4.357862063693486e-05,
+      "loss": 0.5075,
+      "num_input_tokens_seen": 80000000,
+      "step": 175
+    },
+    {
+      "epoch": 7.024390243902439,
+      "grad_norm": 0.641543447971344,
+      "learning_rate": 4.3224215685535294e-05,
+      "loss": 0.5246,
+      "num_input_tokens_seen": 82294336,
+      "step": 180
+    },
+    {
+      "epoch": 7.219512195121951,
+      "grad_norm": 0.6666741967201233,
+      "learning_rate": 4.2861816990820084e-05,
+      "loss": 0.5021,
+      "num_input_tokens_seen": 84609856,
+      "step": 185
+    },
+    {
+      "epoch": 7.414634146341464,
+      "grad_norm": 0.9410921931266785,
+      "learning_rate": 4.249158351283414e-05,
+      "loss": 0.4766,
+      "num_input_tokens_seen": 86956608,
+      "step": 190
+    },
+    {
+      "epoch": 7.609756097560975,
+      "grad_norm": 0.9510065913200378,
+      "learning_rate": 4.211367764821722e-05,
+      "loss": 0.4922,
+      "num_input_tokens_seen": 89199040,
+      "step": 195
+    },
+    {
+      "epoch": 7.804878048780488,
+      "grad_norm": 0.9778364896774292,
+      "learning_rate": 4.172826515897146e-05,
+      "loss": 0.5149,
+      "num_input_tokens_seen": 91464512,
+      "step": 200
+    },
+    {
+      "epoch": 7.804878048780488,
+      "eval_loss": 0.6269230246543884,
+      "eval_runtime": 173.5455,
+      "eval_samples_per_second": 12.147,
+      "eval_steps_per_second": 0.507,
+      "num_input_tokens_seen": 91464512,
+      "step": 200
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 1.1030495166778564,
+      "learning_rate": 4.133551509975264e-05,
+      "loss": 0.5019,
+      "num_input_tokens_seen": 93698368,
+      "step": 205
+    },
+    {
+      "epoch": 8.195121951219512,
+      "grad_norm": 0.8688378930091858,
+      "learning_rate": 4.093559974371725e-05,
+      "loss": 0.4275,
+      "num_input_tokens_seen": 96008256,
+      "step": 210
+    },
+    {
+      "epoch": 8.390243902439025,
+      "grad_norm": 0.9601365327835083,
+      "learning_rate": 4.052869450695776e-05,
+      "loss": 0.4545,
+      "num_input_tokens_seen": 98232832,
+      "step": 215
+    },
+    {
+      "epoch": 8.585365853658537,
+      "grad_norm": 0.9640222191810608,
+      "learning_rate": 4.011497787155938e-05,
+      "loss": 0.4577,
+      "num_input_tokens_seen": 100520128,
+      "step": 220
+    },
+    {
+      "epoch": 8.78048780487805,
+      "grad_norm": 0.7299013137817383,
+      "learning_rate": 3.969463130731183e-05,
+      "loss": 0.4589,
+      "num_input_tokens_seen": 102814976,
+      "step": 225
+    },
+    {
+      "epoch": 8.975609756097562,
+      "grad_norm": 0.6459980607032776,
+      "learning_rate": 3.92678391921108e-05,
+      "loss": 0.4482,
+      "num_input_tokens_seen": 105142528,
+      "step": 230
+    },
+    {
+      "epoch": 9.170731707317072,
+      "grad_norm": 0.8188865184783936,
+      "learning_rate": 3.883478873108361e-05,
+      "loss": 0.4301,
+      "num_input_tokens_seen": 107394880,
+      "step": 235
+    },
+    {
+      "epoch": 9.365853658536585,
+      "grad_norm": 0.7741889953613281,
+      "learning_rate": 3.8395669874474915e-05,
+      "loss": 0.3852,
+      "num_input_tokens_seen": 109706560,
+      "step": 240
+    },
+    {
+      "epoch": 9.560975609756097,
+      "grad_norm": 0.7010043263435364,
+      "learning_rate": 3.795067523432826e-05,
+      "loss": 0.3886,
+      "num_input_tokens_seen": 111993664,
+      "step": 245
+    },
+    {
+      "epoch": 9.75609756097561,
+      "grad_norm": 0.5523029565811157,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.4028,
+      "num_input_tokens_seen": 114255232,
+      "step": 250
+    },
+    {
+      "epoch": 9.951219512195122,
+      "grad_norm": 0.5837187170982361,
+      "learning_rate": 3.704384185254288e-05,
+      "loss": 0.3847,
+      "num_input_tokens_seen": 116578560,
+      "step": 255
+    },
+    {
+      "epoch": 10.146341463414634,
+      "grad_norm": 0.7814375162124634,
+      "learning_rate": 3.6582400877996546e-05,
+      "loss": 0.3516,
+      "num_input_tokens_seen": 118836800,
+      "step": 260
+    },
+    {
+      "epoch": 10.341463414634147,
+      "grad_norm": 0.9329513907432556,
+      "learning_rate": 3.611587947962319e-05,
+      "loss": 0.3504,
+      "num_input_tokens_seen": 121148608,
+      "step": 265
+    },
+    {
+      "epoch": 10.536585365853659,
+      "grad_norm": 0.5801968574523926,
+      "learning_rate": 3.564448228912682e-05,
+      "loss": 0.3303,
+      "num_input_tokens_seen": 123490176,
+      "step": 270
+    },
+    {
+      "epoch": 10.731707317073171,
+      "grad_norm": 0.5544772744178772,
+      "learning_rate": 3.516841607689501e-05,
+      "loss": 0.336,
+      "num_input_tokens_seen": 125741376,
+      "step": 275
+    },
+    {
+      "epoch": 10.926829268292684,
+      "grad_norm": 0.5629393458366394,
+      "learning_rate": 3.4687889661302576e-05,
+      "loss": 0.337,
+      "num_input_tokens_seen": 127996480,
+      "step": 280
+    },
+    {
+      "epoch": 11.121951219512194,
+      "grad_norm": 0.6132429242134094,
+      "learning_rate": 3.4203113817116957e-05,
+      "loss": 0.3102,
+      "num_input_tokens_seen": 130286208,
+      "step": 285
+    },
+    {
+      "epoch": 11.317073170731707,
+      "grad_norm": 0.6265811920166016,
+      "learning_rate": 3.3714301183045385e-05,
+      "loss": 0.2777,
+      "num_input_tokens_seen": 132600256,
+      "step": 290
+    },
+    {
+      "epoch": 11.512195121951219,
+      "grad_norm": 0.7565940618515015,
+      "learning_rate": 3.322166616846458e-05,
+      "loss": 0.2875,
+      "num_input_tokens_seen": 134908928,
+      "step": 295
+    },
+    {
+      "epoch": 11.707317073170731,
+      "grad_norm": 0.8063022494316101,
+      "learning_rate": 3.272542485937369e-05,
+      "loss": 0.2768,
+      "num_input_tokens_seen": 137181248,
+      "step": 300
+    },
+    {
+      "epoch": 11.707317073170731,
+      "eval_loss": 0.718697726726532,
+      "eval_runtime": 173.4793,
+      "eval_samples_per_second": 12.151,
+      "eval_steps_per_second": 0.507,
+      "num_input_tokens_seen": 137181248,
+      "step": 300
+    },
+    {
+      "epoch": 11.902439024390244,
+      "grad_norm": 0.7160292267799377,
+      "learning_rate": 3.222579492361179e-05,
+      "loss": 0.2823,
+      "num_input_tokens_seen": 139385728,
+      "step": 305
+    },
+    {
+      "epoch": 12.097560975609756,
+      "grad_norm": 0.6414353251457214,
+      "learning_rate": 3.172299551538164e-05,
+      "loss": 0.27,
+      "num_input_tokens_seen": 141670400,
+      "step": 310
+    },
+    {
+      "epoch": 12.292682926829269,
+      "grad_norm": 0.6131883859634399,
+      "learning_rate": 3.121724717912138e-05,
+      "loss": 0.2308,
+      "num_input_tokens_seen": 143944512,
+      "step": 315
+    },
+    {
+      "epoch": 12.487804878048781,
+      "grad_norm": 0.46672749519348145,
+      "learning_rate": 3.0708771752766394e-05,
+      "loss": 0.2236,
+      "num_input_tokens_seen": 146200128,
+      "step": 320
+    },
+    {
+      "epoch": 12.682926829268293,
+      "grad_norm": 0.48453348875045776,
+      "learning_rate": 3.0197792270443982e-05,
+      "loss": 0.2227,
+      "num_input_tokens_seen": 148494912,
+      "step": 325
+    },
+    {
+      "epoch": 12.878048780487806,
+      "grad_norm": 0.5639292597770691,
+      "learning_rate": 2.9684532864643122e-05,
+      "loss": 0.2236,
+      "num_input_tokens_seen": 150765632,
+      "step": 330
+    },
+    {
+      "epoch": 13.073170731707316,
+      "grad_norm": 0.45188578963279724,
+      "learning_rate": 2.916921866790256e-05,
+      "loss": 0.2193,
+      "num_input_tokens_seen": 153025984,
+      "step": 335
+    },
+    {
+      "epoch": 13.268292682926829,
+      "grad_norm": 0.5362280011177063,
+      "learning_rate": 2.8652075714060295e-05,
+      "loss": 0.1804,
+      "num_input_tokens_seen": 155359744,
+      "step": 340
+    },
+    {
+      "epoch": 13.463414634146341,
+      "grad_norm": 0.46796223521232605,
+      "learning_rate": 2.8133330839107608e-05,
+      "loss": 0.1763,
+      "num_input_tokens_seen": 157653760,
+      "step": 345
+    },
+    {
+      "epoch": 13.658536585365853,
+      "grad_norm": 0.6022464036941528,
+      "learning_rate": 2.761321158169134e-05,
+      "loss": 0.1785,
+      "num_input_tokens_seen": 159970112,
+      "step": 350
+    },
+    {
+      "epoch": 13.853658536585366,
+      "grad_norm": 0.6007694005966187,
+      "learning_rate": 2.7091946083307896e-05,
+      "loss": 0.1847,
+      "num_input_tokens_seen": 162266048,
+      "step": 355
+    },
+    {
+      "epoch": 14.048780487804878,
+      "grad_norm": 0.5330171585083008,
+      "learning_rate": 2.656976298823284e-05,
+      "loss": 0.1765,
+      "num_input_tokens_seen": 164502784,
+      "step": 360
+    },
+    {
+      "epoch": 14.24390243902439,
+      "grad_norm": 0.4508293569087982,
+      "learning_rate": 2.604689134322999e-05,
+      "loss": 0.1433,
+      "num_input_tokens_seen": 166793792,
+      "step": 365
+    },
+    {
+      "epoch": 14.439024390243903,
+      "grad_norm": 0.4898134469985962,
+      "learning_rate": 2.5523560497083926e-05,
+      "loss": 0.1436,
+      "num_input_tokens_seen": 169105536,
+      "step": 370
+    },
+    {
+      "epoch": 14.634146341463415,
+      "grad_norm": 0.5252612829208374,
+      "learning_rate": 2.5e-05,
+      "loss": 0.1456,
+      "num_input_tokens_seen": 171380160,
+      "step": 375
+    },
+    {
+      "epoch": 14.829268292682928,
+      "grad_norm": 0.45608317852020264,
+      "learning_rate": 2.447643950291608e-05,
+      "loss": 0.1361,
+      "num_input_tokens_seen": 173636544,
+      "step": 380
+    },
+    {
+      "epoch": 15.024390243902438,
+      "grad_norm": 0.5009132623672485,
+      "learning_rate": 2.3953108656770016e-05,
+      "loss": 0.1381,
+      "num_input_tokens_seen": 175912832,
+      "step": 385
+    },
+    {
+      "epoch": 15.21951219512195,
+      "grad_norm": 0.4505337178707123,
+      "learning_rate": 2.3430237011767167e-05,
+      "loss": 0.1121,
+      "num_input_tokens_seen": 178157824,
+      "step": 390
+    },
+    {
+      "epoch": 15.414634146341463,
+      "grad_norm": 0.43384668231010437,
+      "learning_rate": 2.2908053916692117e-05,
+      "loss": 0.1103,
+      "num_input_tokens_seen": 180468736,
+      "step": 395
+    },
+    {
+      "epoch": 15.609756097560975,
+      "grad_norm": 0.4433673620223999,
+      "learning_rate": 2.238678841830867e-05,
+      "loss": 0.1126,
+      "num_input_tokens_seen": 182788736,
+      "step": 400
+    },
+    {
+      "epoch": 15.609756097560975,
+      "eval_loss": 0.8370733261108398,
+      "eval_runtime": 173.2462,
+      "eval_samples_per_second": 12.168,
+      "eval_steps_per_second": 0.508,
+      "num_input_tokens_seen": 182788736,
+      "step": 400
+    },
+    {
+      "epoch": 15.804878048780488,
+      "grad_norm": 0.39896300435066223,
+      "learning_rate": 2.186666916089239e-05,
+      "loss": 0.1114,
+      "num_input_tokens_seen": 185050944,
+      "step": 405
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 0.3975840210914612,
+      "learning_rate": 2.1347924285939714e-05,
+      "loss": 0.1135,
+      "num_input_tokens_seen": 187289920,
+      "step": 410
+    },
+    {
+      "epoch": 16.195121951219512,
+      "grad_norm": 0.3381832242012024,
+      "learning_rate": 2.0830781332097446e-05,
+      "loss": 0.0935,
+      "num_input_tokens_seen": 189562944,
+      "step": 415
+    },
+    {
+      "epoch": 16.390243902439025,
+      "grad_norm": 0.3201667070388794,
+      "learning_rate": 2.031546713535688e-05,
+      "loss": 0.0851,
+      "num_input_tokens_seen": 191813696,
+      "step": 420
+    },
+    {
+      "epoch": 16.585365853658537,
+      "grad_norm": 0.38780859112739563,
+      "learning_rate": 1.980220772955602e-05,
+      "loss": 0.0897,
+      "num_input_tokens_seen": 194094144,
+      "step": 425
+    },
+    {
+      "epoch": 16.78048780487805,
+      "grad_norm": 0.31540414690971375,
+      "learning_rate": 1.9291228247233605e-05,
+      "loss": 0.0886,
+      "num_input_tokens_seen": 196385984,
+      "step": 430
+    },
+    {
+      "epoch": 16.975609756097562,
+      "grad_norm": 0.5678117275238037,
+      "learning_rate": 1.8782752820878634e-05,
+      "loss": 0.0899,
+      "num_input_tokens_seen": 198700032,
+      "step": 435
+    },
+    {
+      "epoch": 17.170731707317074,
+      "grad_norm": 0.4425772726535797,
+      "learning_rate": 1.827700448461836e-05,
+      "loss": 0.0753,
+      "num_input_tokens_seen": 201036480,
+      "step": 440
+    },
+    {
+      "epoch": 17.365853658536587,
+      "grad_norm": 0.32113131880760193,
+      "learning_rate": 1.7774205076388206e-05,
+      "loss": 0.0724,
+      "num_input_tokens_seen": 203331520,
+      "step": 445
+    },
+    {
+      "epoch": 17.5609756097561,
+      "grad_norm": 0.2662774920463562,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 0.0711,
+      "num_input_tokens_seen": 205627072,
+      "step": 450
+    },
+    {
+      "epoch": 17.75609756097561,
+      "grad_norm": 0.27264896035194397,
+      "learning_rate": 1.677833383153542e-05,
+      "loss": 0.0719,
+      "num_input_tokens_seen": 207845568,
+      "step": 455
+    },
+    {
+      "epoch": 17.951219512195124,
+      "grad_norm": 0.29512110352516174,
+      "learning_rate": 1.6285698816954624e-05,
+      "loss": 0.0704,
+      "num_input_tokens_seen": 210180736,
+      "step": 460
+    },
+    {
+      "epoch": 18.146341463414632,
+      "grad_norm": 0.252193421125412,
+      "learning_rate": 1.5796886182883053e-05,
+      "loss": 0.0666,
+      "num_input_tokens_seen": 212454016,
+      "step": 465
+    },
+    {
+      "epoch": 18.341463414634145,
+      "grad_norm": 0.23161688446998596,
+      "learning_rate": 1.5312110338697426e-05,
+      "loss": 0.0564,
+      "num_input_tokens_seen": 214714240,
+      "step": 470
+    },
+    {
+      "epoch": 18.536585365853657,
+      "grad_norm": 0.25446033477783203,
+      "learning_rate": 1.4831583923104999e-05,
+      "loss": 0.0617,
+      "num_input_tokens_seen": 217009664,
+      "step": 475
+    },
+    {
+      "epoch": 18.73170731707317,
+      "grad_norm": 0.2264089584350586,
+      "learning_rate": 1.4355517710873184e-05,
+      "loss": 0.0587,
+      "num_input_tokens_seen": 219270336,
+      "step": 480
+    },
+    {
+      "epoch": 18.926829268292682,
+      "grad_norm": 0.21758581697940826,
+      "learning_rate": 1.388412052037682e-05,
+      "loss": 0.0573,
+      "num_input_tokens_seen": 221604736,
+      "step": 485
+    },
+    {
+      "epoch": 19.121951219512194,
+      "grad_norm": 0.21286001801490784,
+      "learning_rate": 1.3417599122003464e-05,
+      "loss": 0.0537,
+      "num_input_tokens_seen": 223843968,
+      "step": 490
+    },
+    {
+      "epoch": 19.317073170731707,
+      "grad_norm": 0.19537770748138428,
+      "learning_rate": 1.2956158147457115e-05,
+      "loss": 0.0505,
+      "num_input_tokens_seen": 226198144,
+      "step": 495
+    },
+    {
+      "epoch": 19.51219512195122,
+      "grad_norm": 0.18156716227531433,
+      "learning_rate": 1.2500000000000006e-05,
+      "loss": 0.0494,
+      "num_input_tokens_seen": 228521280,
+      "step": 500
+    },
+    {
+      "epoch": 19.51219512195122,
+      "eval_loss": 0.9114091396331787,
+      "eval_runtime": 173.5404,
+      "eval_samples_per_second": 12.147,
+      "eval_steps_per_second": 0.507,
+      "num_input_tokens_seen": 228521280,
+      "step": 500
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 750,
+  "num_input_tokens_seen": 228521280,
+  "num_train_epochs": 30,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.694721607846593e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73adf469b5cb14fcdec30e8fe22975b18d955ed0f43b280349b22b74f932a2cf
+size 5368