Upload folder using huggingface_hub

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/home/sigma/klyang/deepseek-math-7b-base/",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 100000,
+  "eos_token_id": 100001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_cache": false,
+  "vocab_size": 102400
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 100000,
+  "eos_token_id": 100001,
+  "transformers_version": "4.44.2"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2767b53d1003e262d702687b10ba94c873ca5c490dfa0ea3337f9dd2e2961961
+size 4982968608

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b220986783f847c9731c94c5030208b5faa5c8bb925b1cfa9a0da4bdbce245d
+size 4991424808

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efb95c76f5ec0a035e240d7bf6b961f657a7f44671ac7dbe05460c7b4986e3e7
+size 4924315880

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02b66aa4ecdd7da386d14c7b3386e6e1e695ddcb6a18cba9d93534c2115ea738
+size 4857206904

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0a815158cd1e33dc456e778ffb272d794e9a4d1e9e5ee3ce4adcb4f898c8427
+size 4857206904

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5ae46ced68a8d93858cb891bfc6d47732db48626549afd37f639b923385b65e
+size 3028371240

model.safetensors.index.json

@@ -0,0 +1,280 @@
+{
+  "metadata": {
+    "total_size": 27641462784
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbfb2ca81a2d76bd1d004fddefc862641c2d581b8c07352122a9c2a00bda3651
+size 15664

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5ef9243974408b2353ac5d3ff0dac5345ea50963b15cdb44c5d1a92c534fd11
+size 15664

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c42e80bc4c304973c38b70183a788f63650be7be26325b8dea24a08f8b5641f
+size 15664

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be1f7e127a7f1cf8f631a51e2fa07a5449a3afa892e09a9606262efed9e85e71
+size 15664

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40cb89072b4134cd9503286a15f1b1f19cc2e95daa800a64bd109649e842589d
+size 1064

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<｜end▁of▁sentence｜>"
+}

tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "100000": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100001": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ 'Assistant: ' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ message['content'] + '\n\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,1102 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9991503823279524,
+  "eval_steps": 29,
+  "global_step": 147,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006796941376380629,
+      "grad_norm": 4.598693370819092,
+      "learning_rate": 1.111111111111111e-06,
+      "loss": 0.5628,
+      "step": 1
+    },
+    {
+      "epoch": 0.013593882752761258,
+      "grad_norm": 3.3473575115203857,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 0.5195,
+      "step": 2
+    },
+    {
+      "epoch": 0.020390824129141887,
+      "grad_norm": 4.778041362762451,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.5557,
+      "step": 3
+    },
+    {
+      "epoch": 0.027187765505522515,
+      "grad_norm": 4.810835838317871,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 0.5973,
+      "step": 4
+    },
+    {
+      "epoch": 0.033984706881903144,
+      "grad_norm": 4.811781406402588,
+      "learning_rate": 5.555555555555557e-06,
+      "loss": 0.5647,
+      "step": 5
+    },
+    {
+      "epoch": 0.04078164825828377,
+      "grad_norm": 2.4056437015533447,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.5343,
+      "step": 6
+    },
+    {
+      "epoch": 0.0475785896346644,
+      "grad_norm": 1.500022530555725,
+      "learning_rate": 7.77777777777778e-06,
+      "loss": 0.4847,
+      "step": 7
+    },
+    {
+      "epoch": 0.05437553101104503,
+      "grad_norm": 1.5126186609268188,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 0.5285,
+      "step": 8
+    },
+    {
+      "epoch": 0.06117247238742566,
+      "grad_norm": 1.3590396642684937,
+      "learning_rate": 1e-05,
+      "loss": 0.4215,
+      "step": 9
+    },
+    {
+      "epoch": 0.06796941376380629,
+      "grad_norm": 1.0946522951126099,
+      "learning_rate": 1.1111111111111113e-05,
+      "loss": 0.4077,
+      "step": 10
+    },
+    {
+      "epoch": 0.07476635514018691,
+      "grad_norm": 1.035597801208496,
+      "learning_rate": 1.2222222222222224e-05,
+      "loss": 0.3961,
+      "step": 11
+    },
+    {
+      "epoch": 0.08156329651656755,
+      "grad_norm": 0.9033994078636169,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.3715,
+      "step": 12
+    },
+    {
+      "epoch": 0.08836023789294817,
+      "grad_norm": 1.1996865272521973,
+      "learning_rate": 1.4444444444444446e-05,
+      "loss": 0.3576,
+      "step": 13
+    },
+    {
+      "epoch": 0.0951571792693288,
+      "grad_norm": 0.9262693524360657,
+      "learning_rate": 1.555555555555556e-05,
+      "loss": 0.3483,
+      "step": 14
+    },
+    {
+      "epoch": 0.10195412064570943,
+      "grad_norm": 0.8593380451202393,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.3552,
+      "step": 15
+    },
+    {
+      "epoch": 0.10875106202209006,
+      "grad_norm": 0.9698188900947571,
+      "learning_rate": 1.7777777777777777e-05,
+      "loss": 0.329,
+      "step": 16
+    },
+    {
+      "epoch": 0.11554800339847068,
+      "grad_norm": 1.0091280937194824,
+      "learning_rate": 1.888888888888889e-05,
+      "loss": 0.3793,
+      "step": 17
+    },
+    {
+      "epoch": 0.12234494477485132,
+      "grad_norm": 0.8758748173713684,
+      "learning_rate": 2e-05,
+      "loss": 0.3134,
+      "step": 18
+    },
+    {
+      "epoch": 0.12914188615123195,
+      "grad_norm": 0.7287446856498718,
+      "learning_rate": 1.9999724204599748e-05,
+      "loss": 0.3261,
+      "step": 19
+    },
+    {
+      "epoch": 0.13593882752761258,
+      "grad_norm": 0.9394727349281311,
+      "learning_rate": 1.9998896833611603e-05,
+      "loss": 0.3553,
+      "step": 20
+    },
+    {
+      "epoch": 0.1427357689039932,
+      "grad_norm": 0.8428260684013367,
+      "learning_rate": 1.9997517932672592e-05,
+      "loss": 0.3411,
+      "step": 21
+    },
+    {
+      "epoch": 0.14953271028037382,
+      "grad_norm": 0.8483632802963257,
+      "learning_rate": 1.999558757784162e-05,
+      "loss": 0.351,
+      "step": 22
+    },
+    {
+      "epoch": 0.15632965165675447,
+      "grad_norm": 0.7444515228271484,
+      "learning_rate": 1.999310587559529e-05,
+      "loss": 0.3487,
+      "step": 23
+    },
+    {
+      "epoch": 0.1631265930331351,
+      "grad_norm": 0.8404412865638733,
+      "learning_rate": 1.999007296282201e-05,
+      "loss": 0.3439,
+      "step": 24
+    },
+    {
+      "epoch": 0.16992353440951571,
+      "grad_norm": 0.7445095181465149,
+      "learning_rate": 1.9986489006814454e-05,
+      "loss": 0.2972,
+      "step": 25
+    },
+    {
+      "epoch": 0.17672047578589634,
+      "grad_norm": 0.7440016269683838,
+      "learning_rate": 1.9982354205260347e-05,
+      "loss": 0.3391,
+      "step": 26
+    },
+    {
+      "epoch": 0.18351741716227699,
+      "grad_norm": 0.6863638162612915,
+      "learning_rate": 1.9977668786231536e-05,
+      "loss": 0.2993,
+      "step": 27
+    },
+    {
+      "epoch": 0.1903143585386576,
+      "grad_norm": 0.7364312410354614,
+      "learning_rate": 1.9972433008171417e-05,
+      "loss": 0.3169,
+      "step": 28
+    },
+    {
+      "epoch": 0.19711129991503823,
+      "grad_norm": 0.7718295454978943,
+      "learning_rate": 1.9966647159880703e-05,
+      "loss": 0.3291,
+      "step": 29
+    },
+    {
+      "epoch": 0.19711129991503823,
+      "eval_loss": 0.3171866536140442,
+      "eval_runtime": 25.1652,
+      "eval_samples_per_second": 19.869,
+      "eval_steps_per_second": 0.636,
+      "step": 29
+    },
+    {
+      "epoch": 0.20390824129141885,
+      "grad_norm": 0.7047903537750244,
+      "learning_rate": 1.9960311560501457e-05,
+      "loss": 0.3326,
+      "step": 30
+    },
+    {
+      "epoch": 0.2107051826677995,
+      "grad_norm": 0.7129018902778625,
+      "learning_rate": 1.9953426559499508e-05,
+      "loss": 0.3404,
+      "step": 31
+    },
+    {
+      "epoch": 0.21750212404418012,
+      "grad_norm": 0.740166187286377,
+      "learning_rate": 1.9945992536645188e-05,
+      "loss": 0.3283,
+      "step": 32
+    },
+    {
+      "epoch": 0.22429906542056074,
+      "grad_norm": 0.6873639225959778,
+      "learning_rate": 1.993800990199235e-05,
+      "loss": 0.3064,
+      "step": 33
+    },
+    {
+      "epoch": 0.23109600679694137,
+      "grad_norm": 0.7272984981536865,
+      "learning_rate": 1.9929479095855783e-05,
+      "loss": 0.3305,
+      "step": 34
+    },
+    {
+      "epoch": 0.23789294817332202,
+      "grad_norm": 0.7347909808158875,
+      "learning_rate": 1.99204005887869e-05,
+      "loss": 0.323,
+      "step": 35
+    },
+    {
+      "epoch": 0.24468988954970264,
+      "grad_norm": 0.7388918399810791,
+      "learning_rate": 1.9910774881547803e-05,
+      "loss": 0.3013,
+      "step": 36
+    },
+    {
+      "epoch": 0.25148683092608326,
+      "grad_norm": 0.702777087688446,
+      "learning_rate": 1.990060250508365e-05,
+      "loss": 0.3274,
+      "step": 37
+    },
+    {
+      "epoch": 0.2582837723024639,
+      "grad_norm": 0.7246643900871277,
+      "learning_rate": 1.9889884020493363e-05,
+      "loss": 0.3362,
+      "step": 38
+    },
+    {
+      "epoch": 0.2650807136788445,
+      "grad_norm": 0.6060255765914917,
+      "learning_rate": 1.9878620018998696e-05,
+      "loss": 0.287,
+      "step": 39
+    },
+    {
+      "epoch": 0.27187765505522515,
+      "grad_norm": 0.6417918801307678,
+      "learning_rate": 1.986681112191161e-05,
+      "loss": 0.2818,
+      "step": 40
+    },
+    {
+      "epoch": 0.2786745964316058,
+      "grad_norm": 0.7274541258811951,
+      "learning_rate": 1.98544579806e-05,
+      "loss": 0.3222,
+      "step": 41
+    },
+    {
+      "epoch": 0.2854715378079864,
+      "grad_norm": 0.7122014164924622,
+      "learning_rate": 1.984156127645178e-05,
+      "loss": 0.3392,
+      "step": 42
+    },
+    {
+      "epoch": 0.29226847918436705,
+      "grad_norm": 0.6548435688018799,
+      "learning_rate": 1.9828121720837288e-05,
+      "loss": 0.3056,
+      "step": 43
+    },
+    {
+      "epoch": 0.29906542056074764,
+      "grad_norm": 0.6896780133247375,
+      "learning_rate": 1.9814140055070044e-05,
+      "loss": 0.3107,
+      "step": 44
+    },
+    {
+      "epoch": 0.3058623619371283,
+      "grad_norm": 0.7305508255958557,
+      "learning_rate": 1.979961705036587e-05,
+      "loss": 0.3077,
+      "step": 45
+    },
+    {
+      "epoch": 0.31265930331350894,
+      "grad_norm": 0.6713555455207825,
+      "learning_rate": 1.9784553507800346e-05,
+      "loss": 0.2747,
+      "step": 46
+    },
+    {
+      "epoch": 0.31945624468988953,
+      "grad_norm": 0.7295777797698975,
+      "learning_rate": 1.9768950258264625e-05,
+      "loss": 0.3126,
+      "step": 47
+    },
+    {
+      "epoch": 0.3262531860662702,
+      "grad_norm": 0.6292139291763306,
+      "learning_rate": 1.975280816241959e-05,
+      "loss": 0.2966,
+      "step": 48
+    },
+    {
+      "epoch": 0.33305012744265083,
+      "grad_norm": 0.6628125309944153,
+      "learning_rate": 1.9736128110648407e-05,
+      "loss": 0.3266,
+      "step": 49
+    },
+    {
+      "epoch": 0.33984706881903143,
+      "grad_norm": 0.6593727469444275,
+      "learning_rate": 1.9718911023007382e-05,
+      "loss": 0.3055,
+      "step": 50
+    },
+    {
+      "epoch": 0.3466440101954121,
+      "grad_norm": 0.737305760383606,
+      "learning_rate": 1.970115784917523e-05,
+      "loss": 0.3038,
+      "step": 51
+    },
+    {
+      "epoch": 0.35344095157179267,
+      "grad_norm": 0.6167359948158264,
+      "learning_rate": 1.9682869568400683e-05,
+      "loss": 0.3112,
+      "step": 52
+    },
+    {
+      "epoch": 0.3602378929481733,
+      "grad_norm": 0.6573403477668762,
+      "learning_rate": 1.9664047189448496e-05,
+      "loss": 0.2971,
+      "step": 53
+    },
+    {
+      "epoch": 0.36703483432455397,
+      "grad_norm": 0.7991875410079956,
+      "learning_rate": 1.964469175054377e-05,
+      "loss": 0.3504,
+      "step": 54
+    },
+    {
+      "epoch": 0.37383177570093457,
+      "grad_norm": 0.6709067225456238,
+      "learning_rate": 1.9624804319314704e-05,
+      "loss": 0.3307,
+      "step": 55
+    },
+    {
+      "epoch": 0.3806287170773152,
+      "grad_norm": 0.5573310852050781,
+      "learning_rate": 1.9604385992733718e-05,
+      "loss": 0.2759,
+      "step": 56
+    },
+    {
+      "epoch": 0.3874256584536958,
+      "grad_norm": 0.6823217868804932,
+      "learning_rate": 1.9583437897056915e-05,
+      "loss": 0.2965,
+      "step": 57
+    },
+    {
+      "epoch": 0.39422259983007646,
+      "grad_norm": 0.6070125699043274,
+      "learning_rate": 1.9561961187761987e-05,
+      "loss": 0.2893,
+      "step": 58
+    },
+    {
+      "epoch": 0.39422259983007646,
+      "eval_loss": 0.29359060525894165,
+      "eval_runtime": 24.6748,
+      "eval_samples_per_second": 20.264,
+      "eval_steps_per_second": 0.648,
+      "step": 58
+    },
+    {
+      "epoch": 0.4010195412064571,
+      "grad_norm": 0.6562219858169556,
+      "learning_rate": 1.953995704948446e-05,
+      "loss": 0.2821,
+      "step": 59
+    },
+    {
+      "epoch": 0.4078164825828377,
+      "grad_norm": 0.6055108904838562,
+      "learning_rate": 1.9517426695952358e-05,
+      "loss": 0.297,
+      "step": 60
+    },
+    {
+      "epoch": 0.41461342395921835,
+      "grad_norm": 0.7652341723442078,
+      "learning_rate": 1.9494371369919253e-05,
+      "loss": 0.3092,
+      "step": 61
+    },
+    {
+      "epoch": 0.421410365335599,
+      "grad_norm": 0.612332284450531,
+      "learning_rate": 1.9470792343095718e-05,
+      "loss": 0.291,
+      "step": 62
+    },
+    {
+      "epoch": 0.4282073067119796,
+      "grad_norm": 0.5866986513137817,
+      "learning_rate": 1.944669091607919e-05,
+      "loss": 0.2586,
+      "step": 63
+    },
+    {
+      "epoch": 0.43500424808836025,
+      "grad_norm": 0.847610592842102,
+      "learning_rate": 1.9422068418282204e-05,
+      "loss": 0.3567,
+      "step": 64
+    },
+    {
+      "epoch": 0.44180118946474084,
+      "grad_norm": 0.6735373139381409,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 0.3018,
+      "step": 65
+    },
+    {
+      "epoch": 0.4485981308411215,
+      "grad_norm": 0.7430619597434998,
+      "learning_rate": 1.9371265671631038e-05,
+      "loss": 0.3245,
+      "step": 66
+    },
+    {
+      "epoch": 0.45539507221750214,
+      "grad_norm": 0.7295202016830444,
+      "learning_rate": 1.9345088225009626e-05,
+      "loss": 0.3464,
+      "step": 67
+    },
+    {
+      "epoch": 0.46219201359388273,
+      "grad_norm": 0.6956584453582764,
+      "learning_rate": 1.931839531191873e-05,
+      "loss": 0.3116,
+      "step": 68
+    },
+    {
+      "epoch": 0.4689889549702634,
+      "grad_norm": 0.7618936896324158,
+      "learning_rate": 1.9291188404714876e-05,
+      "loss": 0.2802,
+      "step": 69
+    },
+    {
+      "epoch": 0.47578589634664403,
+      "grad_norm": 0.6563156843185425,
+      "learning_rate": 1.926346900410604e-05,
+      "loss": 0.3162,
+      "step": 70
+    },
+    {
+      "epoch": 0.4825828377230246,
+      "grad_norm": 0.6584069728851318,
+      "learning_rate": 1.9235238639068855e-05,
+      "loss": 0.3147,
+      "step": 71
+    },
+    {
+      "epoch": 0.4893797790994053,
+      "grad_norm": 0.7286915183067322,
+      "learning_rate": 1.920649886676429e-05,
+      "loss": 0.3232,
+      "step": 72
+    },
+    {
+      "epoch": 0.49617672047578587,
+      "grad_norm": 0.6320315599441528,
+      "learning_rate": 1.9177251272451742e-05,
+      "loss": 0.2946,
+      "step": 73
+    },
+    {
+      "epoch": 0.5029736618521665,
+      "grad_norm": 0.7056065797805786,
+      "learning_rate": 1.914749746940161e-05,
+      "loss": 0.3148,
+      "step": 74
+    },
+    {
+      "epoch": 0.5097706032285472,
+      "grad_norm": 0.6424931287765503,
+      "learning_rate": 1.9117239098806296e-05,
+      "loss": 0.2757,
+      "step": 75
+    },
+    {
+      "epoch": 0.5165675446049278,
+      "grad_norm": 0.6416671872138977,
+      "learning_rate": 1.9086477829689688e-05,
+      "loss": 0.2962,
+      "step": 76
+    },
+    {
+      "epoch": 0.5233644859813084,
+      "grad_norm": 0.7531472444534302,
+      "learning_rate": 1.905521535881509e-05,
+      "loss": 0.3129,
+      "step": 77
+    },
+    {
+      "epoch": 0.530161427357689,
+      "grad_norm": 0.631662130355835,
+      "learning_rate": 1.902345341059164e-05,
+      "loss": 0.3076,
+      "step": 78
+    },
+    {
+      "epoch": 0.5369583687340697,
+      "grad_norm": 0.6587047576904297,
+      "learning_rate": 1.8991193736979176e-05,
+      "loss": 0.3031,
+      "step": 79
+    },
+    {
+      "epoch": 0.5437553101104503,
+      "grad_norm": 0.6439694762229919,
+      "learning_rate": 1.895843811739162e-05,
+      "loss": 0.2765,
+      "step": 80
+    },
+    {
+      "epoch": 0.550552251486831,
+      "grad_norm": 0.584459662437439,
+      "learning_rate": 1.8925188358598815e-05,
+      "loss": 0.2602,
+      "step": 81
+    },
+    {
+      "epoch": 0.5573491928632116,
+      "grad_norm": 0.6689626574516296,
+      "learning_rate": 1.8891446294626868e-05,
+      "loss": 0.2842,
+      "step": 82
+    },
+    {
+      "epoch": 0.5641461342395921,
+      "grad_norm": 0.664592981338501,
+      "learning_rate": 1.8857213786656986e-05,
+      "loss": 0.2827,
+      "step": 83
+    },
+    {
+      "epoch": 0.5709430756159728,
+      "grad_norm": 0.5949574708938599,
+      "learning_rate": 1.882249272292282e-05,
+      "loss": 0.2781,
+      "step": 84
+    },
+    {
+      "epoch": 0.5777400169923534,
+      "grad_norm": 0.6539214253425598,
+      "learning_rate": 1.87872850186063e-05,
+      "loss": 0.2772,
+      "step": 85
+    },
+    {
+      "epoch": 0.5845369583687341,
+      "grad_norm": 0.6778468489646912,
+      "learning_rate": 1.8751592615732007e-05,
+      "loss": 0.2938,
+      "step": 86
+    },
+    {
+      "epoch": 0.5913338997451147,
+      "grad_norm": 0.7007662057876587,
+      "learning_rate": 1.871541748306005e-05,
+      "loss": 0.2962,
+      "step": 87
+    },
+    {
+      "epoch": 0.5913338997451147,
+      "eval_loss": 0.288781076669693,
+      "eval_runtime": 24.6643,
+      "eval_samples_per_second": 20.272,
+      "eval_steps_per_second": 0.649,
+      "step": 87
+    },
+    {
+      "epoch": 0.5981308411214953,
+      "grad_norm": 0.6959559321403503,
+      "learning_rate": 1.867876161597747e-05,
+      "loss": 0.2944,
+      "step": 88
+    },
+    {
+      "epoch": 0.6049277824978759,
+      "grad_norm": 0.6510220766067505,
+      "learning_rate": 1.8641627036388168e-05,
+      "loss": 0.2974,
+      "step": 89
+    },
+    {
+      "epoch": 0.6117247238742566,
+      "grad_norm": 0.6992867588996887,
+      "learning_rate": 1.8604015792601395e-05,
+      "loss": 0.2915,
+      "step": 90
+    },
+    {
+      "epoch": 0.6185216652506372,
+      "grad_norm": 0.6997932195663452,
+      "learning_rate": 1.856592995921876e-05,
+      "loss": 0.2795,
+      "step": 91
+    },
+    {
+      "epoch": 0.6253186066270179,
+      "grad_norm": 0.747304379940033,
+      "learning_rate": 1.852737163701979e-05,
+      "loss": 0.2991,
+      "step": 92
+    },
+    {
+      "epoch": 0.6321155480033984,
+      "grad_norm": 0.6337850093841553,
+      "learning_rate": 1.8488342952846074e-05,
+      "loss": 0.2816,
+      "step": 93
+    },
+    {
+      "epoch": 0.6389124893797791,
+      "grad_norm": 0.6768142580986023,
+      "learning_rate": 1.844884605948392e-05,
+      "loss": 0.2882,
+      "step": 94
+    },
+    {
+      "epoch": 0.6457094307561597,
+      "grad_norm": 0.6271469593048096,
+      "learning_rate": 1.8408883135545634e-05,
+      "loss": 0.2767,
+      "step": 95
+    },
+    {
+      "epoch": 0.6525063721325404,
+      "grad_norm": 0.751917839050293,
+      "learning_rate": 1.8368456385349333e-05,
+      "loss": 0.3126,
+      "step": 96
+    },
+    {
+      "epoch": 0.659303313508921,
+      "grad_norm": 0.6843672394752502,
+      "learning_rate": 1.832756803879737e-05,
+      "loss": 0.3092,
+      "step": 97
+    },
+    {
+      "epoch": 0.6661002548853017,
+      "grad_norm": 0.6191291213035583,
+      "learning_rate": 1.8286220351253324e-05,
+      "loss": 0.27,
+      "step": 98
+    },
+    {
+      "epoch": 0.6728971962616822,
+      "grad_norm": 0.7665583491325378,
+      "learning_rate": 1.8244415603417603e-05,
+      "loss": 0.3247,
+      "step": 99
+    },
+    {
+      "epoch": 0.6796941376380629,
+      "grad_norm": 0.5895417332649231,
+      "learning_rate": 1.8202156101201646e-05,
+      "loss": 0.2967,
+      "step": 100
+    },
+    {
+      "epoch": 0.6864910790144435,
+      "grad_norm": 0.697557270526886,
+      "learning_rate": 1.8159444175600706e-05,
+      "loss": 0.3319,
+      "step": 101
+    },
+    {
+      "epoch": 0.6932880203908242,
+      "grad_norm": 0.6296725273132324,
+      "learning_rate": 1.8116282182565313e-05,
+      "loss": 0.3177,
+      "step": 102
+    },
+    {
+      "epoch": 0.7000849617672048,
+      "grad_norm": 0.5775023102760315,
+      "learning_rate": 1.8072672502871295e-05,
+      "loss": 0.2712,
+      "step": 103
+    },
+    {
+      "epoch": 0.7068819031435853,
+      "grad_norm": 0.5521108508110046,
+      "learning_rate": 1.802861754198847e-05,
+      "loss": 0.2724,
+      "step": 104
+    },
+    {
+      "epoch": 0.713678844519966,
+      "grad_norm": 0.7251706719398499,
+      "learning_rate": 1.7984119729947944e-05,
+      "loss": 0.3194,
+      "step": 105
+    },
+    {
+      "epoch": 0.7204757858963466,
+      "grad_norm": 0.6509170532226562,
+      "learning_rate": 1.79391815212081e-05,
+      "loss": 0.2859,
+      "step": 106
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 0.7021235227584839,
+      "learning_rate": 1.7893805394519187e-05,
+      "loss": 0.3059,
+      "step": 107
+    },
+    {
+      "epoch": 0.7340696686491079,
+      "grad_norm": 0.6381179690361023,
+      "learning_rate": 1.7847993852786612e-05,
+      "loss": 0.2556,
+      "step": 108
+    },
+    {
+      "epoch": 0.7408666100254885,
+      "grad_norm": 0.6494466662406921,
+      "learning_rate": 1.780174942293287e-05,
+      "loss": 0.2933,
+      "step": 109
+    },
+    {
+      "epoch": 0.7476635514018691,
+      "grad_norm": 0.7242010831832886,
+      "learning_rate": 1.7755074655758174e-05,
+      "loss": 0.3111,
+      "step": 110
+    },
+    {
+      "epoch": 0.7544604927782498,
+      "grad_norm": 0.6928083896636963,
+      "learning_rate": 1.7707972125799738e-05,
+      "loss": 0.2913,
+      "step": 111
+    },
+    {
+      "epoch": 0.7612574341546304,
+      "grad_norm": 0.6862010955810547,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 0.2961,
+      "step": 112
+    },
+    {
+      "epoch": 0.7680543755310111,
+      "grad_norm": 0.622751772403717,
+      "learning_rate": 1.761249419351222e-05,
+      "loss": 0.2581,
+      "step": 113
+    },
+    {
+      "epoch": 0.7748513169073916,
+      "grad_norm": 0.6430375576019287,
+      "learning_rate": 1.7564124057658057e-05,
+      "loss": 0.2817,
+      "step": 114
+    },
+    {
+      "epoch": 0.7816482582837723,
+      "grad_norm": 0.5642279386520386,
+      "learning_rate": 1.7515336691679478e-05,
+      "loss": 0.2759,
+      "step": 115
+    },
+    {
+      "epoch": 0.7884451996601529,
+      "grad_norm": 0.5759322047233582,
+      "learning_rate": 1.746613478664271e-05,
+      "loss": 0.2708,
+      "step": 116
+    },
+    {
+      "epoch": 0.7884451996601529,
+      "eval_loss": 0.28095486760139465,
+      "eval_runtime": 24.6484,
+      "eval_samples_per_second": 20.285,
+      "eval_steps_per_second": 0.649,
+      "step": 116
+    },
+    {
+      "epoch": 0.7952421410365336,
+      "grad_norm": 0.6173487305641174,
+      "learning_rate": 1.7416521056479577e-05,
+      "loss": 0.3005,
+      "step": 117
+    },
+    {
+      "epoch": 0.8020390824129142,
+      "grad_norm": 0.6516419649124146,
+      "learning_rate": 1.736649823783779e-05,
+      "loss": 0.2788,
+      "step": 118
+    },
+    {
+      "epoch": 0.8088360237892949,
+      "grad_norm": 0.6238332986831665,
+      "learning_rate": 1.7316069089930007e-05,
+      "loss": 0.2789,
+      "step": 119
+    },
+    {
+      "epoch": 0.8156329651656754,
+      "grad_norm": 0.5984514355659485,
+      "learning_rate": 1.7265236394381634e-05,
+      "loss": 0.3,
+      "step": 120
+    },
+    {
+      "epoch": 0.822429906542056,
+      "grad_norm": 0.6230698823928833,
+      "learning_rate": 1.7214002955077394e-05,
+      "loss": 0.2579,
+      "step": 121
+    },
+    {
+      "epoch": 0.8292268479184367,
+      "grad_norm": 0.6018764972686768,
+      "learning_rate": 1.7162371598006668e-05,
+      "loss": 0.3065,
+      "step": 122
+    },
+    {
+      "epoch": 0.8360237892948174,
+      "grad_norm": 0.6184946298599243,
+      "learning_rate": 1.711034517110761e-05,
+      "loss": 0.2699,
+      "step": 123
+    },
+    {
+      "epoch": 0.842820730671198,
+      "grad_norm": 0.5912549495697021,
+      "learning_rate": 1.705792654411007e-05,
+      "loss": 0.2656,
+      "step": 124
+    },
+    {
+      "epoch": 0.8496176720475785,
+      "grad_norm": 0.6374722123146057,
+      "learning_rate": 1.7005118608377288e-05,
+      "loss": 0.3074,
+      "step": 125
+    },
+    {
+      "epoch": 0.8564146134239592,
+      "grad_norm": 0.6522223353385925,
+      "learning_rate": 1.6951924276746425e-05,
+      "loss": 0.2842,
+      "step": 126
+    },
+    {
+      "epoch": 0.8632115548003398,
+      "grad_norm": 0.6337326765060425,
+      "learning_rate": 1.689834648336787e-05,
+      "loss": 0.3009,
+      "step": 127
+    },
+    {
+      "epoch": 0.8700084961767205,
+      "grad_norm": 0.6591935753822327,
+      "learning_rate": 1.6844388183543418e-05,
+      "loss": 0.2758,
+      "step": 128
+    },
+    {
+      "epoch": 0.8768054375531011,
+      "grad_norm": 0.71869957447052,
+      "learning_rate": 1.6790052353563254e-05,
+      "loss": 0.3036,
+      "step": 129
+    },
+    {
+      "epoch": 0.8836023789294817,
+      "grad_norm": 0.6463243961334229,
+      "learning_rate": 1.6735341990541766e-05,
+      "loss": 0.2749,
+      "step": 130
+    },
+    {
+      "epoch": 0.8903993203058623,
+      "grad_norm": 0.5988742709159851,
+      "learning_rate": 1.6680260112252253e-05,
+      "loss": 0.2857,
+      "step": 131
+    },
+    {
+      "epoch": 0.897196261682243,
+      "grad_norm": 0.5640173554420471,
+      "learning_rate": 1.6624809756960445e-05,
+      "loss": 0.265,
+      "step": 132
+    },
+    {
+      "epoch": 0.9039932030586236,
+      "grad_norm": 0.6231476068496704,
+      "learning_rate": 1.656899398325693e-05,
+      "loss": 0.2837,
+      "step": 133
+    },
+    {
+      "epoch": 0.9107901444350043,
+      "grad_norm": 0.644237220287323,
+      "learning_rate": 1.651281586988844e-05,
+      "loss": 0.2911,
+      "step": 134
+    },
+    {
+      "epoch": 0.9175870858113849,
+      "grad_norm": 0.6296971440315247,
+      "learning_rate": 1.6456278515588023e-05,
+      "loss": 0.3025,
+      "step": 135
+    },
+    {
+      "epoch": 0.9243840271877655,
+      "grad_norm": 0.6154587864875793,
+      "learning_rate": 1.639938503890414e-05,
+      "loss": 0.2427,
+      "step": 136
+    },
+    {
+      "epoch": 0.9311809685641461,
+      "grad_norm": 0.6521453261375427,
+      "learning_rate": 1.6342138578028613e-05,
+      "loss": 0.2742,
+      "step": 137
+    },
+    {
+      "epoch": 0.9379779099405268,
+      "grad_norm": 0.7209259271621704,
+      "learning_rate": 1.6284542290623568e-05,
+      "loss": 0.3017,
+      "step": 138
+    },
+    {
+      "epoch": 0.9447748513169074,
+      "grad_norm": 0.6163744330406189,
+      "learning_rate": 1.622659935364723e-05,
+      "loss": 0.2779,
+      "step": 139
+    },
+    {
+      "epoch": 0.9515717926932881,
+      "grad_norm": 0.622027575969696,
+      "learning_rate": 1.61683129631787e-05,
+      "loss": 0.2767,
+      "step": 140
+    },
+    {
+      "epoch": 0.9583687340696686,
+      "grad_norm": 0.6272425055503845,
+      "learning_rate": 1.6109686334241655e-05,
+      "loss": 0.2644,
+      "step": 141
+    },
+    {
+      "epoch": 0.9651656754460493,
+      "grad_norm": 0.5646295547485352,
+      "learning_rate": 1.605072270062701e-05,
+      "loss": 0.2589,
+      "step": 142
+    },
+    {
+      "epoch": 0.9719626168224299,
+      "grad_norm": 0.6147757768630981,
+      "learning_rate": 1.599142531471456e-05,
+      "loss": 0.29,
+      "step": 143
+    },
+    {
+      "epoch": 0.9787595581988106,
+      "grad_norm": 0.610895574092865,
+      "learning_rate": 1.5931797447293553e-05,
+      "loss": 0.262,
+      "step": 144
+    },
+    {
+      "epoch": 0.9855564995751912,
+      "grad_norm": 0.5855327248573303,
+      "learning_rate": 1.5871842387382307e-05,
+      "loss": 0.2435,
+      "step": 145
+    },
+    {
+      "epoch": 0.9855564995751912,
+      "eval_loss": 0.27577897906303406,
+      "eval_runtime": 24.6998,
+      "eval_samples_per_second": 20.243,
+      "eval_steps_per_second": 0.648,
+      "step": 145
+    },
+    {
+      "epoch": 0.9923534409515717,
+      "grad_norm": 0.6426906585693359,
+      "learning_rate": 1.5811563442046768e-05,
+      "loss": 0.2755,
+      "step": 146
+    },
+    {
+      "epoch": 0.9991503823279524,
+      "grad_norm": 0.5879192352294922,
+      "learning_rate": 1.5750963936218104e-05,
+      "loss": 0.2515,
+      "step": 147
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 441,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 10.0,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.877564828072018e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d96649993ae58241d55f4fcca8533f14664d1d7ba60a6aee7a0172ed606b1a60
+size 5432