Upload folder using huggingface_hub

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/workspace/airoboros-13b-gpt4",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 2048,
+  "max_seq_len": 4096,
+  "max_sequence_length": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "pad_token_id": -1,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.2",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.29.2"
+}

pytorch_model-00001-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1da4566a32f37bc0cbde77925aa701ac2702439a968a051de7a88cf9cdca285
+size 9956543883

pytorch_model-00002-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffb59fbf7a23b7c0b50aed2f0c05dcd84505af43cbe73feac66a9827dc2fa072
+size 9940856385

pytorch_model-00003-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d518dd4cecbe69d2ac1feb9f1264325bedc8a6a34eeaa9d993fe3b62c0be6712
+size 9940856943

pytorch_model-00004-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abc7ff33c05a5d3c184df78d5d9c48c20ca5adf671e5addcb4d0a3230617cb74
+size 9867415289

pytorch_model-00005-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fe8132cd353517b6a8a4039aeb66c3952e1765f01b09af996080a1052415e9c
+size 9867456961

pytorch_model-00006-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8bce38825ac82721bb81962ec76efdd21470fb9eb31aa498d3e1948687fe5ad
+size 2490476207

pytorch_model.bin.index.json

@@ -0,0 +1,410 @@
+{
+  "metadata": {
+    "total_size": 52063467520
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00006-of-00006.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.norm.weight": "pytorch_model-00006-of-00006.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 4096,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,817 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 132,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.1628,
+      "step": 1
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.2466,
+      "step": 2
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1e-05,
+      "loss": 0.1574,
+      "step": 3
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.2579,
+      "step": 4
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.1541,
+      "step": 5
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2e-05,
+      "loss": 0.1936,
+      "step": 6
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9996891820008165e-05,
+      "loss": 0.2,
+      "step": 7
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9987569212189224e-05,
+      "loss": 0.1831,
+      "step": 8
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9972037971811802e-05,
+      "loss": 0.2248,
+      "step": 9
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9950307753654016e-05,
+      "loss": 0.1665,
+      "step": 10
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9922392066001724e-05,
+      "loss": 0.2094,
+      "step": 11
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9888308262251286e-05,
+      "loss": 0.2001,
+      "step": 12
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9848077530122083e-05,
+      "loss": 0.1172,
+      "step": 13
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9801724878485438e-05,
+      "loss": 0.2056,
+      "step": 14
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9749279121818235e-05,
+      "loss": 0.2014,
+      "step": 15
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.969077286229078e-05,
+      "loss": 0.1684,
+      "step": 16
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.962624246950012e-05,
+      "loss": 0.1373,
+      "step": 17
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.955572805786141e-05,
+      "loss": 0.1828,
+      "step": 18
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.947927346167132e-05,
+      "loss": 0.2026,
+      "step": 19
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 0.2229,
+      "step": 20
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9308737486442045e-05,
+      "loss": 0.223,
+      "step": 21
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.921476211870408e-05,
+      "loss": 0.1184,
+      "step": 22
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9115058523116734e-05,
+      "loss": 0.1451,
+      "step": 23
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.900968867902419e-05,
+      "loss": 0.1882,
+      "step": 24
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8898718088114688e-05,
+      "loss": 0.1531,
+      "step": 25
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8782215733702286e-05,
+      "loss": 0.1562,
+      "step": 26
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.866025403784439e-05,
+      "loss": 0.1659,
+      "step": 27
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8532908816321557e-05,
+      "loss": 0.1937,
+      "step": 28
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8400259231507716e-05,
+      "loss": 0.1737,
+      "step": 29
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.826238774315995e-05,
+      "loss": 0.1417,
+      "step": 30
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.811938005715857e-05,
+      "loss": 0.1761,
+      "step": 31
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7971325072229227e-05,
+      "loss": 0.13,
+      "step": 32
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.78183148246803e-05,
+      "loss": 0.1835,
+      "step": 33
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 0.1799,
+      "step": 34
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7497812029677344e-05,
+      "loss": 0.1744,
+      "step": 35
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7330518718298263e-05,
+      "loss": 0.1656,
+      "step": 36
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.7158668492597186e-05,
+      "loss": 0.1198,
+      "step": 37
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.698236818086073e-05,
+      "loss": 0.218,
+      "step": 38
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6801727377709195e-05,
+      "loss": 0.1288,
+      "step": 39
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6616858375968596e-05,
+      "loss": 0.183,
+      "step": 40
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6427876096865394e-05,
+      "loss": 0.1998,
+      "step": 41
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.6234898018587336e-05,
+      "loss": 0.2144,
+      "step": 42
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.6038044103254775e-05,
+      "loss": 0.2268,
+      "step": 43
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5837436722347902e-05,
+      "loss": 0.1978,
+      "step": 44
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.563320058063622e-05,
+      "loss": 0.2205,
+      "step": 45
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5425462638657597e-05,
+      "loss": 0.1178,
+      "step": 46
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.5214352033794981e-05,
+      "loss": 0.1766,
+      "step": 47
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.1925,
+      "step": 48
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4782539786213184e-05,
+      "loss": 0.1857,
+      "step": 49
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4562106573531632e-05,
+      "loss": 0.1898,
+      "step": 50
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.4338837391175582e-05,
+      "loss": 0.2147,
+      "step": 51
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.4112871031306118e-05,
+      "loss": 0.0981,
+      "step": 52
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3884347962746949e-05,
+      "loss": 0.12,
+      "step": 53
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3653410243663953e-05,
+      "loss": 0.1628,
+      "step": 54
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.342020143325669e-05,
+      "loss": 0.1212,
+      "step": 55
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3184866502516846e-05,
+      "loss": 0.1532,
+      "step": 56
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2947551744109044e-05,
+      "loss": 0.2227,
+      "step": 57
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2708404681430054e-05,
+      "loss": 0.1514,
+      "step": 58
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2467573976902936e-05,
+      "loss": 0.1682,
+      "step": 59
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2225209339563144e-05,
+      "loss": 0.1198,
+      "step": 60
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1981461431993978e-05,
+      "loss": 0.1467,
+      "step": 61
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.1495,
+      "step": 62
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1490422661761744e-05,
+      "loss": 0.184,
+      "step": 63
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1243437046474854e-05,
+      "loss": 0.1868,
+      "step": 64
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0995678465958168e-05,
+      "loss": 0.1448,
+      "step": 65
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0747300935864245e-05,
+      "loss": 0.1522,
+      "step": 66
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0498458856606972e-05,
+      "loss": 0.1626,
+      "step": 67
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.0249306917380731e-05,
+      "loss": 0.1445,
+      "step": 68
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1e-05,
+      "loss": 0.1869,
+      "step": 69
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.750693082619274e-06,
+      "loss": 0.1127,
+      "step": 70
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.501541143393028e-06,
+      "loss": 0.1223,
+      "step": 71
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.252699064135759e-06,
+      "loss": 0.13,
+      "step": 72
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.004321534041836e-06,
+      "loss": 0.147,
+      "step": 73
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.756562953525151e-06,
+      "loss": 0.2119,
+      "step": 74
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.509577338238255e-06,
+      "loss": 0.1632,
+      "step": 75
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 0.1092,
+      "step": 76
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.018538568006027e-06,
+      "loss": 0.1726,
+      "step": 77
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.774790660436857e-06,
+      "loss": 0.2059,
+      "step": 78
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.532426023097063e-06,
+      "loss": 0.1428,
+      "step": 79
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.291595318569951e-06,
+      "loss": 0.2208,
+      "step": 80
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.052448255890958e-06,
+      "loss": 0.1072,
+      "step": 81
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.815133497483157e-06,
+      "loss": 0.1428,
+      "step": 82
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.579798566743314e-06,
+      "loss": 0.1458,
+      "step": 83
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.34658975633605e-06,
+      "loss": 0.1575,
+      "step": 84
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.115652037253054e-06,
+      "loss": 0.1377,
+      "step": 85
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.887128968693887e-06,
+      "loss": 0.1238,
+      "step": 86
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.66116260882442e-06,
+      "loss": 0.189,
+      "step": 87
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.43789342646837e-06,
+      "loss": 0.1362,
+      "step": 88
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.217460213786822e-06,
+      "loss": 0.1111,
+      "step": 89
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.1703,
+      "step": 90
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.78564796620502e-06,
+      "loss": 0.2067,
+      "step": 91
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.5745373613424075e-06,
+      "loss": 0.1176,
+      "step": 92
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.3667994193637794e-06,
+      "loss": 0.0989,
+      "step": 93
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.162563277652104e-06,
+      "loss": 0.1806,
+      "step": 94
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.961955896745224e-06,
+      "loss": 0.1268,
+      "step": 95
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.7651019814126656e-06,
+      "loss": 0.0781,
+      "step": 96
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.5721239031346067e-06,
+      "loss": 0.0953,
+      "step": 97
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.3831416240314085e-06,
+      "loss": 0.1347,
+      "step": 98
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.1982726222908046e-06,
+      "loss": 0.0712,
+      "step": 99
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.017631819139273e-06,
+      "loss": 0.1236,
+      "step": 100
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.8413315074028157e-06,
+      "loss": 0.1177,
+      "step": 101
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.669481281701739e-06,
+      "loss": 0.1223,
+      "step": 102
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.502187970322657e-06,
+      "loss": 0.1171,
+      "step": 103
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 0.1337,
+      "step": 104
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.1816851753197023e-06,
+      "loss": 0.1113,
+      "step": 105
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.0286749277707783e-06,
+      "loss": 0.111,
+      "step": 106
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.880619942841435e-06,
+      "loss": 0.1522,
+      "step": 107
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7376122568400533e-06,
+      "loss": 0.1428,
+      "step": 108
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.599740768492286e-06,
+      "loss": 0.1221,
+      "step": 109
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.467091183678444e-06,
+      "loss": 0.1171,
+      "step": 110
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.339745962155613e-06,
+      "loss": 0.1237,
+      "step": 111
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.2177842662977136e-06,
+      "loss": 0.1008,
+      "step": 112
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.1012819118853147e-06,
+      "loss": 0.1522,
+      "step": 113
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.903113209758098e-07,
+      "loss": 0.0842,
+      "step": 114
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.849414768832687e-07,
+      "loss": 0.1417,
+      "step": 115
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.852378812959227e-07,
+      "loss": 0.1132,
+      "step": 116
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.912625135579587e-07,
+      "loss": 0.1316,
+      "step": 117
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 0.1119,
+      "step": 118
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.207265383286831e-07,
+      "loss": 0.114,
+      "step": 119
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.4427194213859216e-07,
+      "loss": 0.1215,
+      "step": 120
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.7375753049987974e-07,
+      "loss": 0.1544,
+      "step": 121
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.0922713770922155e-07,
+      "loss": 0.1228,
+      "step": 122
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.507208781817638e-07,
+      "loss": 0.1326,
+      "step": 123
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.9827512151456175e-07,
+      "loss": 0.0861,
+      "step": 124
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.519224698779198e-07,
+      "loss": 0.1173,
+      "step": 125
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.1169173774871478e-07,
+      "loss": 0.1554,
+      "step": 126
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 7.760793399827937e-08,
+      "loss": 0.2177,
+      "step": 127
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.9692246345985905e-08,
+      "loss": 0.1132,
+      "step": 128
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.796202818819871e-08,
+      "loss": 0.1256,
+      "step": 129
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.2430787810776556e-08,
+      "loss": 0.1504,
+      "step": 130
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 3.1081799918375454e-09,
+      "loss": 0.1139,
+      "step": 131
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 0.1595,
+      "step": 132
+    },
+    {
+      "epoch": 1.0,
+      "step": 132,
+      "total_flos": 5.0444743239899546e+17,
+      "train_loss": 0.1553735863417387,
+      "train_runtime": 4037.8946,
+      "train_samples_per_second": 3.124,
+      "train_steps_per_second": 0.033
+    }
+  ],
+  "max_steps": 132,
+  "num_train_epochs": 1,
+  "total_flos": 5.0444743239899546e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b360d54d17b37e6a0fa07b8dbabae6c6ea81daf84741915c8708c2ee4b18f843
+size 4091