Upload folder using huggingface_hub

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "../deepseek-math-7b-rl/",
+  "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,
+  "model_type": "llama",
+  "moe_intermediate_size": 11008,
+  "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,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "use_cache": true,
+  "vocab_size": 100003
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 100000,
+  "eos_token_id": 100001,
+  "transformers_version": "4.39.3"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7fb8aabfeba72010bc4889428c8f62f298ae17bfe19f5ce8548b92b463c7850
+size 4943696160

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1493dbcf1445e15c9e3292708098085ce31e4393d14f1e2f117c521ed9aa2ad
+size 4991424808

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:478a8b8039191baca0eb0d54844d0dfb49280d06cd081bc2e85118f0c676d860
+size 4924315880

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:983d1467958221ce5d871703ea0c59bd0520439837c844d8cea27988795c2040
+size 4857206904

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab13ff259a7ef592863f4e442441007541961d19fd021f1ab50060cb4802f5ab
+size 4857206904

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74b1145c4ebaaaae0fbc21a514ca7669250974025e7385d051c9c1ef7d9393bd
+size 2989098792

model.safetensors.index.json

@@ -0,0 +1,280 @@
+{
+  "metadata": {
+    "total_size": 27562917888
+  },
+  "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"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "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": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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
+    },
+    "100002": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "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": 512,
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,891 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.946107784431138,
+  "eval_steps": 500,
+  "global_step": 123,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 3.5533928871154785,
+      "learning_rate": 5e-06,
+      "loss": 0.9102,
+      "step": 1
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 3.562413454055786,
+      "learning_rate": 1e-05,
+      "loss": 0.8938,
+      "step": 2
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 3.4130544662475586,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.8939,
+      "step": 3
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.9644792079925537,
+      "learning_rate": 2e-05,
+      "loss": 0.8619,
+      "step": 4
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.8332546949386597,
+      "learning_rate": 1.9996515418688493e-05,
+      "loss": 0.7327,
+      "step": 5
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 1.0436848402023315,
+      "learning_rate": 1.998606410321534e-05,
+      "loss": 0.5738,
+      "step": 6
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 1.0107005834579468,
+      "learning_rate": 1.9968653337272262e-05,
+      "loss": 0.5469,
+      "step": 7
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.7438812851905823,
+      "learning_rate": 1.9944295254705187e-05,
+      "loss": 0.4875,
+      "step": 8
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.5902363061904907,
+      "learning_rate": 1.9913006831057967e-05,
+      "loss": 0.4739,
+      "step": 9
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.46615442633628845,
+      "learning_rate": 1.9874809871741877e-05,
+      "loss": 0.4424,
+      "step": 10
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.5380907654762268,
+      "learning_rate": 1.982973099683902e-05,
+      "loss": 0.4509,
+      "step": 11
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.47004133462905884,
+      "learning_rate": 1.977780162255041e-05,
+      "loss": 0.4342,
+      "step": 12
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.40097948908805847,
+      "learning_rate": 1.9719057939301477e-05,
+      "loss": 0.4242,
+      "step": 13
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.34752586483955383,
+      "learning_rate": 1.9653540886520387e-05,
+      "loss": 0.3988,
+      "step": 14
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.3399445712566376,
+      "learning_rate": 1.9581296124106682e-05,
+      "loss": 0.3897,
+      "step": 15
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.33792683482170105,
+      "learning_rate": 1.9502374000610152e-05,
+      "loss": 0.4071,
+      "step": 16
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.3393308222293854,
+      "learning_rate": 1.941682951814212e-05,
+      "loss": 0.4146,
+      "step": 17
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.317430704832077,
+      "learning_rate": 1.932472229404356e-05,
+      "loss": 0.3902,
+      "step": 18
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.31500697135925293,
+      "learning_rate": 1.922611651933683e-05,
+      "loss": 0.3921,
+      "step": 19
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.2933339476585388,
+      "learning_rate": 1.912108091398988e-05,
+      "loss": 0.3684,
+      "step": 20
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.2962222695350647,
+      "learning_rate": 1.900968867902419e-05,
+      "loss": 0.3622,
+      "step": 21
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.28932732343673706,
+      "learning_rate": 1.8892017445499812e-05,
+      "loss": 0.3745,
+      "step": 22
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.29461416602134705,
+      "learning_rate": 1.876814922041299e-05,
+      "loss": 0.3853,
+      "step": 23
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.28936246037483215,
+      "learning_rate": 1.8638170329544164e-05,
+      "loss": 0.3924,
+      "step": 24
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.2772411108016968,
+      "learning_rate": 1.8502171357296144e-05,
+      "loss": 0.3611,
+      "step": 25
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.42885950207710266,
+      "learning_rate": 1.8360247083564343e-05,
+      "loss": 0.3865,
+      "step": 26
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.26259008049964905,
+      "learning_rate": 1.8212496417683135e-05,
+      "loss": 0.3817,
+      "step": 27
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.27198928594589233,
+      "learning_rate": 1.805902232949435e-05,
+      "loss": 0.3696,
+      "step": 28
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.288399338722229,
+      "learning_rate": 1.789993177758588e-05,
+      "loss": 0.364,
+      "step": 29
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.26658785343170166,
+      "learning_rate": 1.773533563475053e-05,
+      "loss": 0.3552,
+      "step": 30
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.29077863693237305,
+      "learning_rate": 1.7565348610716963e-05,
+      "loss": 0.3662,
+      "step": 31
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.27203258872032166,
+      "learning_rate": 1.7390089172206594e-05,
+      "loss": 0.3743,
+      "step": 32
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.28761982917785645,
+      "learning_rate": 1.720967946037225e-05,
+      "loss": 0.3666,
+      "step": 33
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.2662566304206848,
+      "learning_rate": 1.7024245205675986e-05,
+      "loss": 0.3663,
+      "step": 34
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.2690587341785431,
+      "learning_rate": 1.6833915640265485e-05,
+      "loss": 0.3469,
+      "step": 35
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.2774984836578369,
+      "learning_rate": 1.6638823407910085e-05,
+      "loss": 0.3595,
+      "step": 36
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.2686326801776886,
+      "learning_rate": 1.6439104471559157e-05,
+      "loss": 0.3503,
+      "step": 37
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.26562628149986267,
+      "learning_rate": 1.6234898018587336e-05,
+      "loss": 0.3634,
+      "step": 38
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.2668813467025757,
+      "learning_rate": 1.6026346363792565e-05,
+      "loss": 0.3594,
+      "step": 39
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.265369713306427,
+      "learning_rate": 1.58135948502146e-05,
+      "loss": 0.3506,
+      "step": 40
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.2864444851875305,
+      "learning_rate": 1.5596791747843083e-05,
+      "loss": 0.3611,
+      "step": 41
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 0.2715173065662384,
+      "learning_rate": 1.5376088150285777e-05,
+      "loss": 0.3526,
+      "step": 42
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 0.2655029892921448,
+      "learning_rate": 1.515163786946896e-05,
+      "loss": 0.3097,
+      "step": 43
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 0.2665596604347229,
+      "learning_rate": 1.4923597328443423e-05,
+      "loss": 0.3064,
+      "step": 44
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.26131537556648254,
+      "learning_rate": 1.4692125452370664e-05,
+      "loss": 0.2972,
+      "step": 45
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.2644971013069153,
+      "learning_rate": 1.4457383557765385e-05,
+      "loss": 0.2917,
+      "step": 46
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 0.26761534810066223,
+      "learning_rate": 1.4219535240071378e-05,
+      "loss": 0.3019,
+      "step": 47
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 0.24523305892944336,
+      "learning_rate": 1.397874625964921e-05,
+      "loss": 0.2933,
+      "step": 48
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 0.26386815309524536,
+      "learning_rate": 1.3735184426255117e-05,
+      "loss": 0.299,
+      "step": 49
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.26587986946105957,
+      "learning_rate": 1.348901948209167e-05,
+      "loss": 0.304,
+      "step": 50
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 0.2641456723213196,
+      "learning_rate": 1.324042298351166e-05,
+      "loss": 0.3009,
+      "step": 51
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.30507728457450867,
+      "learning_rate": 1.2989568181457704e-05,
+      "loss": 0.297,
+      "step": 52
+    },
+    {
+      "epoch": 1.27,
+      "grad_norm": 0.29200825095176697,
+      "learning_rate": 1.2736629900720832e-05,
+      "loss": 0.2976,
+      "step": 53
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 0.2573084235191345,
+      "learning_rate": 1.248178441810224e-05,
+      "loss": 0.286,
+      "step": 54
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.2846490144729614,
+      "learning_rate": 1.2225209339563144e-05,
+      "loss": 0.2859,
+      "step": 55
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 0.29042041301727295,
+      "learning_rate": 1.1967083476448282e-05,
+      "loss": 0.2852,
+      "step": 56
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 0.2833590805530548,
+      "learning_rate": 1.1707586720869375e-05,
+      "loss": 0.2949,
+      "step": 57
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 0.2739700675010681,
+      "learning_rate": 1.1446899920335407e-05,
+      "loss": 0.2878,
+      "step": 58
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 0.26602038741111755,
+      "learning_rate": 1.118520475171703e-05,
+      "loss": 0.2812,
+      "step": 59
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.2630026042461395,
+      "learning_rate": 1.092268359463302e-05,
+      "loss": 0.2766,
+      "step": 60
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 0.2863544225692749,
+      "learning_rate": 1.0659519404346955e-05,
+      "loss": 0.2794,
+      "step": 61
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 0.3084492087364197,
+      "learning_rate": 1.0395895584262696e-05,
+      "loss": 0.2816,
+      "step": 62
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 0.27484026551246643,
+      "learning_rate": 1.013199585810759e-05,
+      "loss": 0.2805,
+      "step": 63
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 0.2850649952888489,
+      "learning_rate": 9.868004141892412e-06,
+      "loss": 0.2842,
+      "step": 64
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.27223044633865356,
+      "learning_rate": 9.604104415737309e-06,
+      "loss": 0.2728,
+      "step": 65
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 0.28590163588523865,
+      "learning_rate": 9.340480595653047e-06,
+      "loss": 0.291,
+      "step": 66
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.41988322138786316,
+      "learning_rate": 9.07731640536698e-06,
+      "loss": 0.2809,
+      "step": 67
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 0.33170831203460693,
+      "learning_rate": 8.814795248282974e-06,
+      "loss": 0.3017,
+      "step": 68
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 0.27779626846313477,
+      "learning_rate": 8.553100079664598e-06,
+      "loss": 0.272,
+      "step": 69
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 0.2752010226249695,
+      "learning_rate": 8.292413279130625e-06,
+      "loss": 0.2926,
+      "step": 70
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.28389397263526917,
+      "learning_rate": 8.03291652355172e-06,
+      "loss": 0.2984,
+      "step": 71
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.2841671407222748,
+      "learning_rate": 7.774790660436857e-06,
+      "loss": 0.2966,
+      "step": 72
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.2771681249141693,
+      "learning_rate": 7.518215581897763e-06,
+      "loss": 0.2879,
+      "step": 73
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 0.2740575075149536,
+      "learning_rate": 7.263370099279173e-06,
+      "loss": 0.2868,
+      "step": 74
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.2688918709754944,
+      "learning_rate": 7.010431818542298e-06,
+      "loss": 0.2799,
+      "step": 75
+    },
+    {
+      "epoch": 1.82,
+      "grad_norm": 0.28831538558006287,
+      "learning_rate": 6.759577016488343e-06,
+      "loss": 0.2852,
+      "step": 76
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 0.28444015979766846,
+      "learning_rate": 6.510980517908334e-06,
+      "loss": 0.296,
+      "step": 77
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 0.2855989634990692,
+      "learning_rate": 6.264815573744884e-06,
+      "loss": 0.3021,
+      "step": 78
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 0.3444156348705292,
+      "learning_rate": 6.021253740350793e-06,
+      "loss": 0.2756,
+      "step": 79
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.292364239692688,
+      "learning_rate": 5.780464759928623e-06,
+      "loss": 0.2872,
+      "step": 80
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 0.28317102789878845,
+      "learning_rate": 5.542616442234618e-06,
+      "loss": 0.2889,
+      "step": 81
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.28034478425979614,
+      "learning_rate": 5.307874547629339e-06,
+      "loss": 0.2829,
+      "step": 82
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 0.27621331810951233,
+      "learning_rate": 5.076402671556578e-06,
+      "loss": 0.2806,
+      "step": 83
+    },
+    {
+      "epoch": 2.01,
+      "grad_norm": 0.26098138093948364,
+      "learning_rate": 4.848362130531039e-06,
+      "loss": 0.2667,
+      "step": 84
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 0.2581479549407959,
+      "learning_rate": 4.623911849714226e-06,
+      "loss": 0.2336,
+      "step": 85
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 0.2613183856010437,
+      "learning_rate": 4.403208252156921e-06,
+      "loss": 0.2484,
+      "step": 86
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.26595166325569153,
+      "learning_rate": 4.186405149785403e-06,
+      "loss": 0.2485,
+      "step": 87
+    },
+    {
+      "epoch": 2.11,
+      "grad_norm": 0.2694242596626282,
+      "learning_rate": 3.973653636207437e-06,
+      "loss": 0.2327,
+      "step": 88
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 0.27296847105026245,
+      "learning_rate": 3.7651019814126656e-06,
+      "loss": 0.2476,
+      "step": 89
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 0.27051979303359985,
+      "learning_rate": 3.560895528440844e-06,
+      "loss": 0.247,
+      "step": 90
+    },
+    {
+      "epoch": 2.18,
+      "grad_norm": 0.2605610191822052,
+      "learning_rate": 3.361176592089919e-06,
+      "loss": 0.2512,
+      "step": 91
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.2650965750217438,
+      "learning_rate": 3.1660843597345137e-06,
+      "loss": 0.2497,
+      "step": 92
+    },
+    {
+      "epoch": 2.23,
+      "grad_norm": 0.2880423963069916,
+      "learning_rate": 2.975754794324015e-06,
+      "loss": 0.2342,
+      "step": 93
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.2823397219181061,
+      "learning_rate": 2.7903205396277546e-06,
+      "loss": 0.2507,
+      "step": 94
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 0.28528815507888794,
+      "learning_rate": 2.6099108277934105e-06,
+      "loss": 0.262,
+      "step": 95
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 0.27001848816871643,
+      "learning_rate": 2.4346513892830427e-06,
+      "loss": 0.247,
+      "step": 96
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 0.2607811689376831,
+      "learning_rate": 2.2646643652494693e-06,
+      "loss": 0.2348,
+      "step": 97
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 0.26551198959350586,
+      "learning_rate": 2.100068222414121e-06,
+      "loss": 0.2413,
+      "step": 98
+    },
+    {
+      "epoch": 2.37,
+      "grad_norm": 0.277545690536499,
+      "learning_rate": 1.9409776705056514e-06,
+      "loss": 0.2557,
+      "step": 99
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.26287129521369934,
+      "learning_rate": 1.7875035823168641e-06,
+      "loss": 0.2422,
+      "step": 100
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 0.2761671245098114,
+      "learning_rate": 1.6397529164356606e-06,
+      "loss": 0.2465,
+      "step": 101
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 0.2713651657104492,
+      "learning_rate": 1.4978286427038602e-06,
+      "loss": 0.2394,
+      "step": 102
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 0.25854483246803284,
+      "learning_rate": 1.3618296704558364e-06,
+      "loss": 0.2301,
+      "step": 103
+    },
+    {
+      "epoch": 2.49,
+      "grad_norm": 0.2666904330253601,
+      "learning_rate": 1.2318507795870138e-06,
+      "loss": 0.2445,
+      "step": 104
+    },
+    {
+      "epoch": 2.51,
+      "grad_norm": 0.29085126519203186,
+      "learning_rate": 1.1079825545001887e-06,
+      "loss": 0.2379,
+      "step": 105
+    },
+    {
+      "epoch": 2.54,
+      "grad_norm": 0.27726316452026367,
+      "learning_rate": 9.903113209758098e-07,
+      "loss": 0.2473,
+      "step": 106
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.2835868000984192,
+      "learning_rate": 8.789190860101226e-07,
+      "loss": 0.2472,
+      "step": 107
+    },
+    {
+      "epoch": 2.59,
+      "grad_norm": 0.26035404205322266,
+      "learning_rate": 7.738834806631712e-07,
+      "loss": 0.2296,
+      "step": 108
+    },
+    {
+      "epoch": 2.61,
+      "grad_norm": 0.30347537994384766,
+      "learning_rate": 6.752777059564431e-07,
+      "loss": 0.2668,
+      "step": 109
+    },
+    {
+      "epoch": 2.63,
+      "grad_norm": 0.6443763971328735,
+      "learning_rate": 5.831704818578842e-07,
+      "loss": 0.2407,
+      "step": 110
+    },
+    {
+      "epoch": 2.66,
+      "grad_norm": 0.2779424488544464,
+      "learning_rate": 4.976259993898503e-07,
+      "loss": 0.2385,
+      "step": 111
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 0.26803234219551086,
+      "learning_rate": 4.187038758933204e-07,
+      "loss": 0.243,
+      "step": 112
+    },
+    {
+      "epoch": 2.71,
+      "grad_norm": 0.2761984169483185,
+      "learning_rate": 3.4645911347961357e-07,
+      "loss": 0.2367,
+      "step": 113
+    },
+    {
+      "epoch": 2.73,
+      "grad_norm": 0.2672320306301117,
+      "learning_rate": 2.809420606985236e-07,
+      "loss": 0.2425,
+      "step": 114
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.25563764572143555,
+      "learning_rate": 2.2219837744959284e-07,
+      "loss": 0.2351,
+      "step": 115
+    },
+    {
+      "epoch": 2.78,
+      "grad_norm": 0.2778139114379883,
+      "learning_rate": 1.7026900316098217e-07,
+      "loss": 0.2384,
+      "step": 116
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.31073540449142456,
+      "learning_rate": 1.2519012825812804e-07,
+      "loss": 0.2444,
+      "step": 117
+    },
+    {
+      "epoch": 2.83,
+      "grad_norm": 0.2570035457611084,
+      "learning_rate": 8.699316894203225e-08,
+      "loss": 0.237,
+      "step": 118
+    },
+    {
+      "epoch": 2.85,
+      "grad_norm": 0.3120572865009308,
+      "learning_rate": 5.5704745294815624e-08,
+      "loss": 0.2413,
+      "step": 119
+    },
+    {
+      "epoch": 2.87,
+      "grad_norm": 0.2754634618759155,
+      "learning_rate": 3.134666272774034e-08,
+      "loss": 0.235,
+      "step": 120
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 0.2690906524658203,
+      "learning_rate": 1.3935896784663671e-08,
+      "loss": 0.2361,
+      "step": 121
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 0.26298609375953674,
+      "learning_rate": 3.4845813115114147e-09,
+      "loss": 0.2336,
+      "step": 122
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 0.2775000333786011,
+      "learning_rate": 0.0,
+      "loss": 0.2431,
+      "step": 123
+    },
+    {
+      "epoch": 2.95,
+      "step": 123,
+      "total_flos": 3.803134263348429e+16,
+      "train_loss": 0.3296439991733892,
+      "train_runtime": 519.019,
+      "train_samples_per_second": 30.797,
+      "train_steps_per_second": 0.237
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 123,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "total_flos": 3.803134263348429e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7fb574de093b2f59af48ca718dea6d7bb275531ce63c21dfab6712da9ad0314
+size 5112