417

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/lustre/fast/fast/wliu/longhui/ckpt/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 sha256:7fb6c7c2dd374fe480a4d305f716b1c5d4c61d5c20d1a2a57f86cfd695d8e8ef
+size 4943696160

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53816e76c3022434d3b16b7b501ca8a2ec49fa2a618e336602ff0da7c172d809
+size 4991424808

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3e8b46c886fa5c8ae34bca69f60515e601608bcf1c67ce4eb88d5195b051222
+size 4924315880

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e01c3424fa9e0046121f565697e1edecb6ec5945650225a5e7ef394b4d1d092
+size 4857206904

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5f14150ec0bd2daeb57d6925425e78d2543688d31310f40be1ecce6a045554b
+size 4857206904

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9960b398ca7b53998f6b202481d30c0999316b2cb5f189a87179412178e215e
+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 +1,660 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.926829268292683,
+  "eval_steps": 500,
+  "global_step": 90,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "grad_norm": 8.280744552612305,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.565,
+      "step": 1
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 8.70754337310791,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.6161,
+      "step": 2
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 8.472146987915039,
+      "learning_rate": 2e-05,
+      "loss": 1.5893,
+      "step": 3
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 5.23038911819458,
+      "learning_rate": 1.999348095389677e-05,
+      "loss": 1.3983,
+      "step": 4
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.8397700786590576,
+      "learning_rate": 1.9973932315179502e-05,
+      "loss": 1.2206,
+      "step": 5
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 2.181596040725708,
+      "learning_rate": 1.9941379571543597e-05,
+      "loss": 1.1032,
+      "step": 6
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 1.1165341138839722,
+      "learning_rate": 1.9895865165556375e-05,
+      "loss": 1.065,
+      "step": 7
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.8952399492263794,
+      "learning_rate": 1.9837448439320027e-05,
+      "loss": 1.035,
+      "step": 8
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.7685825824737549,
+      "learning_rate": 1.976620555710087e-05,
+      "loss": 0.9635,
+      "step": 9
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.7761624455451965,
+      "learning_rate": 1.9682229406025635e-05,
+      "loss": 0.9618,
+      "step": 10
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.7371810078620911,
+      "learning_rate": 1.9585629474974413e-05,
+      "loss": 0.9613,
+      "step": 11
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.6214499473571777,
+      "learning_rate": 1.9476531711828027e-05,
+      "loss": 0.9501,
+      "step": 12
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.5390974879264832,
+      "learning_rate": 1.935507835925601e-05,
+      "loss": 0.964,
+      "step": 13
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.5018035769462585,
+      "learning_rate": 1.9221427769259333e-05,
+      "loss": 0.9304,
+      "step": 14
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.526158332824707,
+      "learning_rate": 1.9075754196709574e-05,
+      "loss": 0.9554,
+      "step": 15
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.5072513222694397,
+      "learning_rate": 1.8918247572153822e-05,
+      "loss": 0.9078,
+      "step": 16
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.4988534450531006,
+      "learning_rate": 1.8749113254181498e-05,
+      "loss": 0.9291,
+      "step": 17
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.4912777841091156,
+      "learning_rate": 1.8568571761675893e-05,
+      "loss": 0.9626,
+      "step": 18
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.5130652785301208,
+      "learning_rate": 1.837685848629965e-05,
+      "loss": 0.9074,
+      "step": 19
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.4877808690071106,
+      "learning_rate": 1.817422338558892e-05,
+      "loss": 0.8972,
+      "step": 20
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.48035475611686707,
+      "learning_rate": 1.796093065705644e-05,
+      "loss": 0.9162,
+      "step": 21
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.45466920733451843,
+      "learning_rate": 1.7737258393728363e-05,
+      "loss": 0.9067,
+      "step": 22
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.49428102374076843,
+      "learning_rate": 1.7503498221564026e-05,
+      "loss": 0.9073,
+      "step": 23
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.49855947494506836,
+      "learning_rate": 1.725995491923131e-05,
+      "loss": 0.941,
+      "step": 24
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.4245299696922302,
+      "learning_rate": 1.7006946020733426e-05,
+      "loss": 0.8765,
+      "step": 25
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.45259377360343933,
+      "learning_rate": 1.6744801401405138e-05,
+      "loss": 0.8845,
+      "step": 26
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.45279204845428467,
+      "learning_rate": 1.647386284781828e-05,
+      "loss": 0.9069,
+      "step": 27
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.4377584159374237,
+      "learning_rate": 1.6194483612157232e-05,
+      "loss": 0.8889,
+      "step": 28
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.44903799891471863,
+      "learning_rate": 1.590702795164551e-05,
+      "loss": 0.8981,
+      "step": 29
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.44891077280044556,
+      "learning_rate": 1.5611870653623826e-05,
+      "loss": 0.8773,
+      "step": 30
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 0.49123069643974304,
+      "learning_rate": 1.530939654689887e-05,
+      "loss": 0.8863,
+      "step": 31
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.49654659628868103,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.7918,
+      "step": 32
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 0.4908214807510376,
+      "learning_rate": 1.4684084406997903e-05,
+      "loss": 0.761,
+      "step": 33
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 0.45682042837142944,
+      "learning_rate": 1.4362061661555675e-05,
+      "loss": 0.781,
+      "step": 34
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 0.466132253408432,
+      "learning_rate": 1.4034351619898088e-05,
+      "loss": 0.7392,
+      "step": 35
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 0.4905536472797394,
+      "learning_rate": 1.3701381553399147e-05,
+      "loss": 0.763,
+      "step": 36
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.48623326420783997,
+      "learning_rate": 1.3363585591501751e-05,
+      "loss": 0.7628,
+      "step": 37
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.48992201685905457,
+      "learning_rate": 1.3021404155695728e-05,
+      "loss": 0.7798,
+      "step": 38
+    },
+    {
+      "epoch": 1.27,
+      "grad_norm": 0.45171797275543213,
+      "learning_rate": 1.2675283385292212e-05,
+      "loss": 0.7196,
+      "step": 39
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.48216456174850464,
+      "learning_rate": 1.2325674555743106e-05,
+      "loss": 0.7346,
+      "step": 40
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 0.44965651631355286,
+      "learning_rate": 1.1973033490264e-05,
+      "loss": 0.7058,
+      "step": 41
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 0.5034527778625488,
+      "learning_rate": 1.161781996552765e-05,
+      "loss": 0.7719,
+      "step": 42
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.5173734426498413,
+      "learning_rate": 1.1260497112202895e-05,
+      "loss": 0.745,
+      "step": 43
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 0.49784746766090393,
+      "learning_rate": 1.0901530811120655e-05,
+      "loss": 0.7376,
+      "step": 44
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 0.4722931385040283,
+      "learning_rate": 1.0541389085854177e-05,
+      "loss": 0.7419,
+      "step": 45
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.4892752170562744,
+      "learning_rate": 1.0180541492505605e-05,
+      "loss": 0.6948,
+      "step": 46
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 0.4865082800388336,
+      "learning_rate": 9.819458507494395e-06,
+      "loss": 0.634,
+      "step": 47
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.5185601711273193,
+      "learning_rate": 9.458610914145826e-06,
+      "loss": 0.6824,
+      "step": 48
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 0.47616997361183167,
+      "learning_rate": 9.098469188879348e-06,
+      "loss": 0.7001,
+      "step": 49
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 0.49744558334350586,
+      "learning_rate": 8.739502887797108e-06,
+      "loss": 0.7358,
+      "step": 50
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 0.5162651538848877,
+      "learning_rate": 8.382180034472353e-06,
+      "loss": 0.7079,
+      "step": 51
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 0.5150533318519592,
+      "learning_rate": 8.026966509736001e-06,
+      "loss": 0.6997,
+      "step": 52
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 1.0735119581222534,
+      "learning_rate": 7.674325444256899e-06,
+      "loss": 0.7211,
+      "step": 53
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.4927270710468292,
+      "learning_rate": 7.324716614707794e-06,
+      "loss": 0.7257,
+      "step": 54
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 0.49033042788505554,
+      "learning_rate": 6.978595844304272e-06,
+      "loss": 0.728,
+      "step": 55
+    },
+    {
+      "epoch": 1.82,
+      "grad_norm": 0.5927804112434387,
+      "learning_rate": 6.636414408498249e-06,
+      "loss": 0.6914,
+      "step": 56
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 0.5300837159156799,
+      "learning_rate": 6.298618446600856e-06,
+      "loss": 0.7206,
+      "step": 57
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 0.4967361092567444,
+      "learning_rate": 5.965648380101916e-06,
+      "loss": 0.6897,
+      "step": 58
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.5123832821846008,
+      "learning_rate": 5.637938338444325e-06,
+      "loss": 0.7064,
+      "step": 59
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 0.5195019245147705,
+      "learning_rate": 5.3159155930021e-06,
+      "loss": 0.6979,
+      "step": 60
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 0.5248487591743469,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.6823,
+      "step": 61
+    },
+    {
+      "epoch": 2.02,
+      "grad_norm": 0.5308733582496643,
+      "learning_rate": 4.690603453101134e-06,
+      "loss": 0.6827,
+      "step": 62
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 0.5279427766799927,
+      "learning_rate": 4.388129346376177e-06,
+      "loss": 0.6421,
+      "step": 63
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.4864795207977295,
+      "learning_rate": 4.092972048354491e-06,
+      "loss": 0.5883,
+      "step": 64
+    },
+    {
+      "epoch": 2.11,
+      "grad_norm": 0.4978441894054413,
+      "learning_rate": 3.8055163878427703e-06,
+      "loss": 0.5958,
+      "step": 65
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 0.5329935550689697,
+      "learning_rate": 3.5261371521817247e-06,
+      "loss": 0.6346,
+      "step": 66
+    },
+    {
+      "epoch": 2.18,
+      "grad_norm": 0.4853770434856415,
+      "learning_rate": 3.255198598594862e-06,
+      "loss": 0.5986,
+      "step": 67
+    },
+    {
+      "epoch": 2.21,
+      "grad_norm": 0.5128601789474487,
+      "learning_rate": 2.9930539792665767e-06,
+      "loss": 0.6008,
+      "step": 68
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.5175537467002869,
+      "learning_rate": 2.740045080768694e-06,
+      "loss": 0.5825,
+      "step": 69
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 0.5446229577064514,
+      "learning_rate": 2.496501778435977e-06,
+      "loss": 0.6201,
+      "step": 70
+    },
+    {
+      "epoch": 2.31,
+      "grad_norm": 0.5520351529121399,
+      "learning_rate": 2.2627416062716366e-06,
+      "loss": 0.6502,
+      "step": 71
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 0.5046796202659607,
+      "learning_rate": 2.0390693429435626e-06,
+      "loss": 0.5877,
+      "step": 72
+    },
+    {
+      "epoch": 2.37,
+      "grad_norm": 0.5116910338401794,
+      "learning_rate": 1.8257766144110823e-06,
+      "loss": 0.5992,
+      "step": 73
+    },
+    {
+      "epoch": 2.41,
+      "grad_norm": 0.5164862871170044,
+      "learning_rate": 1.6231415137003536e-06,
+      "loss": 0.5826,
+      "step": 74
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 0.5107815265655518,
+      "learning_rate": 1.4314282383241097e-06,
+      "loss": 0.5679,
+      "step": 75
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 0.5102241039276123,
+      "learning_rate": 1.2508867458185037e-06,
+      "loss": 0.5972,
+      "step": 76
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.5415460467338562,
+      "learning_rate": 1.0817524278461777e-06,
+      "loss": 0.5738,
+      "step": 77
+    },
+    {
+      "epoch": 2.54,
+      "grad_norm": 0.525007426738739,
+      "learning_rate": 9.242458032904311e-07,
+      "loss": 0.592,
+      "step": 78
+    },
+    {
+      "epoch": 2.57,
+      "grad_norm": 0.48747336864471436,
+      "learning_rate": 7.785722307406685e-07,
+      "loss": 0.5858,
+      "step": 79
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.5466867089271545,
+      "learning_rate": 6.449216407439906e-07,
+      "loss": 0.6307,
+      "step": 80
+    },
+    {
+      "epoch": 2.63,
+      "grad_norm": 0.529702365398407,
+      "learning_rate": 5.234682881719766e-07,
+      "loss": 0.6177,
+      "step": 81
+    },
+    {
+      "epoch": 2.67,
+      "grad_norm": 0.550619900226593,
+      "learning_rate": 4.1437052502558693e-07,
+      "loss": 0.6064,
+      "step": 82
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 0.5231672525405884,
+      "learning_rate": 3.1777059397436693e-07,
+      "loss": 0.6194,
+      "step": 83
+    },
+    {
+      "epoch": 2.73,
+      "grad_norm": 0.506498396396637,
+      "learning_rate": 2.3379444289913344e-07,
+      "loss": 0.6191,
+      "step": 84
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 0.5445461273193359,
+      "learning_rate": 1.6255156067997325e-07,
+      "loss": 0.5635,
+      "step": 85
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.5693822503089905,
+      "learning_rate": 1.041348344436277e-07,
+      "loss": 0.6426,
+      "step": 86
+    },
+    {
+      "epoch": 2.83,
+      "grad_norm": 0.5474693775177002,
+      "learning_rate": 5.862042845640403e-08,
+      "loss": 0.6243,
+      "step": 87
+    },
+    {
+      "epoch": 2.86,
+      "grad_norm": 0.5175514221191406,
+      "learning_rate": 2.606768482050215e-08,
+      "loss": 0.5747,
+      "step": 88
+    },
+    {
+      "epoch": 2.89,
+      "grad_norm": 0.5419387221336365,
+      "learning_rate": 6.5190461032305085e-09,
+      "loss": 0.6008,
+      "step": 89
+    },
+    {
+      "epoch": 2.93,
+      "grad_norm": 0.4993443787097931,
+      "learning_rate": 0.0,
+      "loss": 0.6343,
+      "step": 90
+    },
+    {
+      "epoch": 2.93,
+      "step": 90,
+      "total_flos": 2.582894619708621e+16,
+      "train_loss": 0.7904547598626879,
+      "train_runtime": 253.8743,
+      "train_samples_per_second": 46.381,
+      "train_steps_per_second": 0.355
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 90,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "total_flos": 2.582894619708621e+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 sha256:94f58500a790cf7f63d130398989aa53d1f6701a5feb223dea56db61b6e23361
+size 5176