add

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "./llama-7b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_sequence_length": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32001
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.28.0.dev0"
+}

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd45660a9665b24706948105917b1e85074cd300fe1fad05503fe65d4eadc0a6
+size 9878005970

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:150c461c7a60ad064d2f7c98f153c515ca2a2ed4b2099323b6d991ad62349536
+size 9894801014

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6d14ef493c9950f6757b8bbc22f2c59b21b8a1cecb04c74d0e163948353f4e4
+size 7181007033

pytorch_model.bin.index.json

@@ -0,0 +1,330 @@
+{
+  "metadata": {
+    "total_size": 26953703424
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00003-of-00003.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.norm.weight": "pytorch_model-00003-of-00003.bin"
+  }
+}

runs/Mar22_02-17-27_nv23u9o4yt/._events.out.tfevents.1679451514.nv23u9o4yt.4106.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4960ba34fc8876aa52d1c648d53a68eac8f3117f5424ced728fed2470e075ece
+size 4096

runs/Mar22_02-17-27_nv23u9o4yt/1679451514.250914/._events.out.tfevents.1679451514.nv23u9o4yt.4106.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4960ba34fc8876aa52d1c648d53a68eac8f3117f5424ced728fed2470e075ece
+size 4096

runs/Mar22_02-17-27_nv23u9o4yt/1679451514.250914/events.out.tfevents.1679451514.nv23u9o4yt.4106.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bad93f8069ea680c5fee1551ebc7a12772b84b07150300eb441a013c5b4bccec
+size 5980

runs/Mar22_02-17-27_nv23u9o4yt/events.out.tfevents.1679451514.nv23u9o4yt.4106.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fddd411558161a24b403ad3d2c02d470ee43f6c8ad94ac6b18be1bcf8186da0
+size 3996

runs/Mar23_16-08-14_nrs4s3eo1s/._events.out.tfevents.1679587783.nrs4s3eo1s.396.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4960ba34fc8876aa52d1c648d53a68eac8f3117f5424ced728fed2470e075ece
+size 4096

runs/Mar23_16-08-14_nrs4s3eo1s/1679587783.9238882/._events.out.tfevents.1679587783.nrs4s3eo1s.396.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4960ba34fc8876aa52d1c648d53a68eac8f3117f5424ced728fed2470e075ece
+size 4096

runs/Mar23_16-08-14_nrs4s3eo1s/1679587783.9238882/events.out.tfevents.1679587783.nrs4s3eo1s.396.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bc9829e74b0b5dd4a5d65023b471c26a90d08f0d32ff989d1203c5f720e6f33
+size 5989

runs/Mar23_16-08-14_nrs4s3eo1s/events.out.tfevents.1679587783.nrs4s3eo1s.396.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3f6b4cb86efbc7cc6311e98ec99d15ec7fce740b9a675567a3ddc766e6249ec
+size 4009

runs/Mar23_16-15-05_nrs4s3eo1s/._events.out.tfevents.1679588175.nrs4s3eo1s.577.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4960ba34fc8876aa52d1c648d53a68eac8f3117f5424ced728fed2470e075ece
+size 4096

runs/Mar23_16-15-05_nrs4s3eo1s/1679588175.7056534/._events.out.tfevents.1679588175.nrs4s3eo1s.577.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4960ba34fc8876aa52d1c648d53a68eac8f3117f5424ced728fed2470e075ece
+size 4096

runs/Mar23_16-15-05_nrs4s3eo1s/1679588175.7056534/events.out.tfevents.1679588175.nrs4s3eo1s.577.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b1bac4cefdb7f3d371b638b4970751af65f4b18d247442f5e596eccc86936f6
+size 5980

runs/Mar23_16-15-05_nrs4s3eo1s/events.out.tfevents.1679588175.nrs4s3eo1s.577.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3229d1863c6b696a2ccee96b4739039f0840e8cd9ec97b8d9094c3d588aa978
+size 5730

runs/Mar23_17-20-31_nrs4s3eo1s/._events.out.tfevents.1679592100.nrs4s3eo1s.698.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4960ba34fc8876aa52d1c648d53a68eac8f3117f5424ced728fed2470e075ece
+size 4096

runs/Mar23_17-20-31_nrs4s3eo1s/1679592100.584624/._events.out.tfevents.1679592100.nrs4s3eo1s.698.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4960ba34fc8876aa52d1c648d53a68eac8f3117f5424ced728fed2470e075ece
+size 4096

runs/Mar23_17-20-31_nrs4s3eo1s/1679592100.584624/events.out.tfevents.1679592100.nrs4s3eo1s.698.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b8af7fd691dd8fcd8c2ff42e8e9b2aff50dd1118812912398fe13f3a887085b
+size 5980

runs/Mar23_17-20-31_nrs4s3eo1s/events.out.tfevents.1679592100.nrs4s3eo1s.698.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1857bf6b90257dd22186a160a9cfe769a18fbfa30c5d4dea78d75eadbaa4ee00
+size 3997

runs/Mar23_17-38-14_nrs4s3eo1s/._events.out.tfevents.1679593162.nrs4s3eo1s.1035.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4960ba34fc8876aa52d1c648d53a68eac8f3117f5424ced728fed2470e075ece
+size 4096

runs/Mar23_17-38-14_nrs4s3eo1s/1679593162.7529712/._events.out.tfevents.1679593162.nrs4s3eo1s.1035.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4960ba34fc8876aa52d1c648d53a68eac8f3117f5424ced728fed2470e075ece
+size 4096

runs/Mar23_17-38-14_nrs4s3eo1s/1679593162.7529712/events.out.tfevents.1679593162.nrs4s3eo1s.1035.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01215bc2654f2d58587dab2ccb7a33efdd7b3535f1f5ec668d764096d37bbeda
+size 5980

runs/Mar23_17-38-14_nrs4s3eo1s/events.out.tfevents.1679593162.nrs4s3eo1s.1035.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f19124613eed5c0019d9908c391791e028b8819c01b2531f2df4e86230fc1918
+size 18205

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "</s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "</s>"
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "",
+  "eos_token": "",
+  "model_max_length": 512,
+  "padding_side": "right",
+  "special_tokens_map_file": "./llama-7b/special_tokens_map.json",
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": ""
+}

trainer_state.json

@@ -0,0 +1,565 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 27.692307692307693,
+  "global_step": 90,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.31,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 3.768,
+      "step": 1
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 12.368,
+      "step": 2
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2e-05,
+      "loss": 11.537,
+      "step": 3
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.999348095389677e-05,
+      "loss": 7.8117,
+      "step": 4
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.9973932315179502e-05,
+      "loss": 5.6659,
+      "step": 5
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 1.9941379571543597e-05,
+      "loss": 4.2924,
+      "step": 6
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 1.9895865165556375e-05,
+      "loss": 2.1566,
+      "step": 7
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 1.9837448439320027e-05,
+      "loss": 2.607,
+      "step": 8
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 1.976620555710087e-05,
+      "loss": 2.6508,
+      "step": 9
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 1.9682229406025635e-05,
+      "loss": 3.4377,
+      "step": 10
+    },
+    {
+      "epoch": 3.38,
+      "learning_rate": 1.9585629474974413e-05,
+      "loss": 2.3918,
+      "step": 11
+    },
+    {
+      "epoch": 3.69,
+      "learning_rate": 1.9476531711828027e-05,
+      "loss": 0.9541,
+      "step": 12
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.935507835925601e-05,
+      "loss": 0.2939,
+      "step": 13
+    },
+    {
+      "epoch": 4.31,
+      "learning_rate": 1.9221427769259333e-05,
+      "loss": 0.717,
+      "step": 14
+    },
+    {
+      "epoch": 4.62,
+      "learning_rate": 1.9075754196709574e-05,
+      "loss": 0.3357,
+      "step": 15
+    },
+    {
+      "epoch": 4.92,
+      "learning_rate": 1.8918247572153822e-05,
+      "loss": 0.2568,
+      "step": 16
+    },
+    {
+      "epoch": 5.23,
+      "learning_rate": 1.8749113254181498e-05,
+      "loss": 0.1306,
+      "step": 17
+    },
+    {
+      "epoch": 5.54,
+      "learning_rate": 1.8568571761675893e-05,
+      "loss": 0.3485,
+      "step": 18
+    },
+    {
+      "epoch": 5.85,
+      "learning_rate": 1.837685848629965e-05,
+      "loss": 0.1659,
+      "step": 19
+    },
+    {
+      "epoch": 6.15,
+      "learning_rate": 1.817422338558892e-05,
+      "loss": 0.6525,
+      "step": 20
+    },
+    {
+      "epoch": 6.46,
+      "learning_rate": 1.796093065705644e-05,
+      "loss": 0.1003,
+      "step": 21
+    },
+    {
+      "epoch": 6.77,
+      "learning_rate": 1.7737258393728363e-05,
+      "loss": 0.3485,
+      "step": 22
+    },
+    {
+      "epoch": 7.08,
+      "learning_rate": 1.7503498221564026e-05,
+      "loss": 0.2097,
+      "step": 23
+    },
+    {
+      "epoch": 7.38,
+      "learning_rate": 1.725995491923131e-05,
+      "loss": 0.1424,
+      "step": 24
+    },
+    {
+      "epoch": 7.69,
+      "learning_rate": 1.7006946020733426e-05,
+      "loss": 0.1512,
+      "step": 25
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 1.6744801401405138e-05,
+      "loss": 0.0815,
+      "step": 26
+    },
+    {
+      "epoch": 8.31,
+      "learning_rate": 1.647386284781828e-05,
+      "loss": 0.0202,
+      "step": 27
+    },
+    {
+      "epoch": 8.62,
+      "learning_rate": 1.6194483612157232e-05,
+      "loss": 0.0909,
+      "step": 28
+    },
+    {
+      "epoch": 8.92,
+      "learning_rate": 1.590702795164551e-05,
+      "loss": 0.1048,
+      "step": 29
+    },
+    {
+      "epoch": 9.23,
+      "learning_rate": 1.5611870653623826e-05,
+      "loss": 0.1186,
+      "step": 30
+    },
+    {
+      "epoch": 9.54,
+      "learning_rate": 1.530939654689887e-05,
+      "loss": 0.0219,
+      "step": 31
+    },
+    {
+      "epoch": 9.85,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.0718,
+      "step": 32
+    },
+    {
+      "epoch": 10.15,
+      "learning_rate": 1.4684084406997903e-05,
+      "loss": 0.0788,
+      "step": 33
+    },
+    {
+      "epoch": 10.46,
+      "learning_rate": 1.4362061661555675e-05,
+      "loss": 0.0534,
+      "step": 34
+    },
+    {
+      "epoch": 10.77,
+      "learning_rate": 1.4034351619898088e-05,
+      "loss": 0.0225,
+      "step": 35
+    },
+    {
+      "epoch": 11.08,
+      "learning_rate": 1.3701381553399147e-05,
+      "loss": 0.0345,
+      "step": 36
+    },
+    {
+      "epoch": 11.38,
+      "learning_rate": 1.3363585591501751e-05,
+      "loss": 0.0125,
+      "step": 37
+    },
+    {
+      "epoch": 11.69,
+      "learning_rate": 1.3021404155695728e-05,
+      "loss": 0.0211,
+      "step": 38
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 1.2675283385292212e-05,
+      "loss": 0.0998,
+      "step": 39
+    },
+    {
+      "epoch": 12.31,
+      "learning_rate": 1.2325674555743106e-05,
+      "loss": 0.0139,
+      "step": 40
+    },
+    {
+      "epoch": 12.62,
+      "learning_rate": 1.1973033490264e-05,
+      "loss": 0.0052,
+      "step": 41
+    },
+    {
+      "epoch": 12.92,
+      "learning_rate": 1.161781996552765e-05,
+      "loss": 0.0069,
+      "step": 42
+    },
+    {
+      "epoch": 13.23,
+      "learning_rate": 1.1260497112202895e-05,
+      "loss": 0.1117,
+      "step": 43
+    },
+    {
+      "epoch": 13.54,
+      "learning_rate": 1.0901530811120655e-05,
+      "loss": 0.0081,
+      "step": 44
+    },
+    {
+      "epoch": 13.85,
+      "learning_rate": 1.0541389085854177e-05,
+      "loss": 0.009,
+      "step": 45
+    },
+    {
+      "epoch": 14.15,
+      "learning_rate": 1.0180541492505605e-05,
+      "loss": 0.0019,
+      "step": 46
+    },
+    {
+      "epoch": 14.46,
+      "learning_rate": 9.819458507494395e-06,
+      "loss": 0.0309,
+      "step": 47
+    },
+    {
+      "epoch": 14.77,
+      "learning_rate": 9.458610914145826e-06,
+      "loss": 0.0016,
+      "step": 48
+    },
+    {
+      "epoch": 15.08,
+      "learning_rate": 9.098469188879348e-06,
+      "loss": 0.0158,
+      "step": 49
+    },
+    {
+      "epoch": 15.38,
+      "learning_rate": 8.739502887797108e-06,
+      "loss": 0.0013,
+      "step": 50
+    },
+    {
+      "epoch": 15.69,
+      "learning_rate": 8.382180034472353e-06,
+      "loss": 0.0056,
+      "step": 51
+    },
+    {
+      "epoch": 16.0,
+      "learning_rate": 8.026966509736001e-06,
+      "loss": 0.0311,
+      "step": 52
+    },
+    {
+      "epoch": 16.31,
+      "learning_rate": 7.674325444256899e-06,
+      "loss": 0.0198,
+      "step": 53
+    },
+    {
+      "epoch": 16.62,
+      "learning_rate": 7.324716614707794e-06,
+      "loss": 0.0032,
+      "step": 54
+    },
+    {
+      "epoch": 16.92,
+      "learning_rate": 6.978595844304272e-06,
+      "loss": 0.0011,
+      "step": 55
+    },
+    {
+      "epoch": 17.23,
+      "learning_rate": 6.636414408498249e-06,
+      "loss": 0.0038,
+      "step": 56
+    },
+    {
+      "epoch": 17.54,
+      "learning_rate": 6.298618446600856e-06,
+      "loss": 0.011,
+      "step": 57
+    },
+    {
+      "epoch": 17.85,
+      "learning_rate": 5.965648380101916e-06,
+      "loss": 0.023,
+      "step": 58
+    },
+    {
+      "epoch": 18.15,
+      "learning_rate": 5.637938338444325e-06,
+      "loss": 0.0005,
+      "step": 59
+    },
+    {
+      "epoch": 18.46,
+      "learning_rate": 5.3159155930021e-06,
+      "loss": 0.0007,
+      "step": 60
+    },
+    {
+      "epoch": 18.77,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.0063,
+      "step": 61
+    },
+    {
+      "epoch": 19.08,
+      "learning_rate": 4.690603453101134e-06,
+      "loss": 0.0009,
+      "step": 62
+    },
+    {
+      "epoch": 19.38,
+      "learning_rate": 4.388129346376177e-06,
+      "loss": 0.0021,
+      "step": 63
+    },
+    {
+      "epoch": 19.69,
+      "learning_rate": 4.092972048354491e-06,
+      "loss": 0.02,
+      "step": 64
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 3.8055163878427703e-06,
+      "loss": 0.001,
+      "step": 65
+    },
+    {
+      "epoch": 20.31,
+      "learning_rate": 3.5261371521817247e-06,
+      "loss": 0.0008,
+      "step": 66
+    },
+    {
+      "epoch": 20.62,
+      "learning_rate": 3.255198598594862e-06,
+      "loss": 0.0098,
+      "step": 67
+    },
+    {
+      "epoch": 20.92,
+      "learning_rate": 2.9930539792665767e-06,
+      "loss": 0.0014,
+      "step": 68
+    },
+    {
+      "epoch": 21.23,
+      "learning_rate": 2.740045080768694e-06,
+      "loss": 0.0015,
+      "step": 69
+    },
+    {
+      "epoch": 21.54,
+      "learning_rate": 2.496501778435977e-06,
+      "loss": 0.0006,
+      "step": 70
+    },
+    {
+      "epoch": 21.85,
+      "learning_rate": 2.2627416062716366e-06,
+      "loss": 0.0064,
+      "step": 71
+    },
+    {
+      "epoch": 22.15,
+      "learning_rate": 2.0390693429435626e-06,
+      "loss": 0.0007,
+      "step": 72
+    },
+    {
+      "epoch": 22.46,
+      "learning_rate": 1.8257766144110823e-06,
+      "loss": 0.0015,
+      "step": 73
+    },
+    {
+      "epoch": 22.77,
+      "learning_rate": 1.6231415137003536e-06,
+      "loss": 0.0089,
+      "step": 74
+    },
+    {
+      "epoch": 23.08,
+      "learning_rate": 1.4314282383241097e-06,
+      "loss": 0.0022,
+      "step": 75
+    },
+    {
+      "epoch": 23.38,
+      "learning_rate": 1.2508867458185037e-06,
+      "loss": 0.0076,
+      "step": 76
+    },
+    {
+      "epoch": 23.69,
+      "learning_rate": 1.0817524278461777e-06,
+      "loss": 0.0004,
+      "step": 77
+    },
+    {
+      "epoch": 24.0,
+      "learning_rate": 9.242458032904311e-07,
+      "loss": 0.0005,
+      "step": 78
+    },
+    {
+      "epoch": 24.31,
+      "learning_rate": 7.785722307406685e-07,
+      "loss": 0.0004,
+      "step": 79
+    },
+    {
+      "epoch": 24.62,
+      "learning_rate": 6.449216407439906e-07,
+      "loss": 0.0049,
+      "step": 80
+    },
+    {
+      "epoch": 24.92,
+      "learning_rate": 5.234682881719766e-07,
+      "loss": 0.004,
+      "step": 81
+    },
+    {
+      "epoch": 25.23,
+      "learning_rate": 4.1437052502558693e-07,
+      "loss": 0.0037,
+      "step": 82
+    },
+    {
+      "epoch": 25.54,
+      "learning_rate": 3.1777059397436693e-07,
+      "loss": 0.0099,
+      "step": 83
+    },
+    {
+      "epoch": 25.85,
+      "learning_rate": 2.3379444289913344e-07,
+      "loss": 0.001,
+      "step": 84
+    },
+    {
+      "epoch": 26.15,
+      "learning_rate": 1.6255156067997325e-07,
+      "loss": 0.0004,
+      "step": 85
+    },
+    {
+      "epoch": 26.46,
+      "learning_rate": 1.041348344436277e-07,
+      "loss": 0.0021,
+      "step": 86
+    },
+    {
+      "epoch": 26.77,
+      "learning_rate": 5.862042845640403e-08,
+      "loss": 0.0052,
+      "step": 87
+    },
+    {
+      "epoch": 27.08,
+      "learning_rate": 2.606768482050215e-08,
+      "loss": 0.0047,
+      "step": 88
+    },
+    {
+      "epoch": 27.38,
+      "learning_rate": 6.5190461032305085e-09,
+      "loss": 0.0004,
+      "step": 89
+    },
+    {
+      "epoch": 27.69,
+      "learning_rate": 0.0,
+      "loss": 0.0003,
+      "step": 90
+    },
+    {
+      "epoch": 27.69,
+      "step": 90,
+      "total_flos": 9963642317438976.0,
+      "train_loss": 0.7193527906240585,
+      "train_runtime": 2724.9841,
+      "train_samples_per_second": 1.134,
+      "train_steps_per_second": 0.033
+    }
+  ],
+  "max_steps": 90,
+  "num_train_epochs": 30,
+  "total_flos": 9963642317438976.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:759b49e67f15f9362339e98a862e0285b6eaa8da92381955d099480520c8c022
+size 3707