Alpagasus-7B fine-tuned on Claud-filtered data

added_tokens.json

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

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "../models/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_position_embeddings": 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": "4.30.0.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": "4.30.0.dev0"
+}

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:190ebcdd0627452f4362dfc99fe76761435307fcd23f74a541ca57de1fc2a54b
+size 9878009874

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a71442c1411e53d5e5a704fb28ca5c594263bcad63dac6765c906ea332b13bc
+size 9894805046

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c569b75f4fb560ff5f3b1abbdb771d5d1a3c5c8d956f9c5c41f814ef32720b2c
+size 7181009913

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"
+  }
+}

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": "[PAD]",
+  "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": 512,
+  "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 +1,763 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.963855421686747,
+  "global_step": 123,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 5e-06,
+      "loss": 12.7599,
+      "step": 1
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1e-05,
+      "loss": 12.7749,
+      "step": 2
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 12.1365,
+      "step": 3
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2e-05,
+      "loss": 11.4632,
+      "step": 4
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9996515418688493e-05,
+      "loss": 10.9159,
+      "step": 5
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.998606410321534e-05,
+      "loss": 12.7472,
+      "step": 6
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9968653337272262e-05,
+      "loss": 10.7166,
+      "step": 7
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9944295254705187e-05,
+      "loss": 13.1637,
+      "step": 8
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9913006831057967e-05,
+      "loss": 11.1352,
+      "step": 9
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9874809871741877e-05,
+      "loss": 11.1739,
+      "step": 10
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.982973099683902e-05,
+      "loss": 10.5036,
+      "step": 11
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.977780162255041e-05,
+      "loss": 10.3354,
+      "step": 12
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9719057939301477e-05,
+      "loss": 9.8824,
+      "step": 13
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.9653540886520387e-05,
+      "loss": 10.1267,
+      "step": 14
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.9581296124106682e-05,
+      "loss": 9.2406,
+      "step": 15
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.9502374000610152e-05,
+      "loss": 9.5681,
+      "step": 16
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.941682951814212e-05,
+      "loss": 9.2435,
+      "step": 17
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.932472229404356e-05,
+      "loss": 9.0242,
+      "step": 18
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.922611651933683e-05,
+      "loss": 8.7959,
+      "step": 19
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.912108091398988e-05,
+      "loss": 8.5755,
+      "step": 20
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.900968867902419e-05,
+      "loss": 8.2596,
+      "step": 21
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.8892017445499812e-05,
+      "loss": 8.6343,
+      "step": 22
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.876814922041299e-05,
+      "loss": 8.8388,
+      "step": 23
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.8638170329544164e-05,
+      "loss": 8.5935,
+      "step": 24
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.8502171357296144e-05,
+      "loss": 8.3216,
+      "step": 25
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.8360247083564343e-05,
+      "loss": 8.045,
+      "step": 26
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.8212496417683135e-05,
+      "loss": 7.9973,
+      "step": 27
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.805902232949435e-05,
+      "loss": 8.1722,
+      "step": 28
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.789993177758588e-05,
+      "loss": 8.026,
+      "step": 29
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.773533563475053e-05,
+      "loss": 7.867,
+      "step": 30
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.7565348610716963e-05,
+      "loss": 7.8396,
+      "step": 31
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.7390089172206594e-05,
+      "loss": 7.7395,
+      "step": 32
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.720967946037225e-05,
+      "loss": 7.7482,
+      "step": 33
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7024245205675986e-05,
+      "loss": 7.7828,
+      "step": 34
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.6833915640265485e-05,
+      "loss": 7.4998,
+      "step": 35
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.6638823407910085e-05,
+      "loss": 7.5944,
+      "step": 36
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.6439104471559157e-05,
+      "loss": 7.6167,
+      "step": 37
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.6234898018587336e-05,
+      "loss": 7.7313,
+      "step": 38
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.6026346363792565e-05,
+      "loss": 7.4581,
+      "step": 39
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.58135948502146e-05,
+      "loss": 7.5363,
+      "step": 40
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.5596791747843083e-05,
+      "loss": 7.5225,
+      "step": 41
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.5376088150285777e-05,
+      "loss": 7.4017,
+      "step": 42
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.515163786946896e-05,
+      "loss": 7.4952,
+      "step": 43
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.4923597328443423e-05,
+      "loss": 7.3242,
+      "step": 44
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.4692125452370664e-05,
+      "loss": 7.3788,
+      "step": 45
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.4457383557765385e-05,
+      "loss": 7.3215,
+      "step": 46
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 1.4219535240071378e-05,
+      "loss": 7.2517,
+      "step": 47
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.397874625964921e-05,
+      "loss": 7.2527,
+      "step": 48
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.3735184426255117e-05,
+      "loss": 7.274,
+      "step": 49
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.348901948209167e-05,
+      "loss": 7.1363,
+      "step": 50
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.324042298351166e-05,
+      "loss": 7.1403,
+      "step": 51
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.2989568181457704e-05,
+      "loss": 7.3037,
+      "step": 52
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.2736629900720832e-05,
+      "loss": 7.2893,
+      "step": 53
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.248178441810224e-05,
+      "loss": 7.2115,
+      "step": 54
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.2225209339563144e-05,
+      "loss": 7.1864,
+      "step": 55
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.1967083476448282e-05,
+      "loss": 7.1604,
+      "step": 56
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.1707586720869375e-05,
+      "loss": 7.0975,
+      "step": 57
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.1446899920335407e-05,
+      "loss": 7.1251,
+      "step": 58
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.118520475171703e-05,
+      "loss": 7.2199,
+      "step": 59
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.092268359463302e-05,
+      "loss": 7.0316,
+      "step": 60
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.0659519404346955e-05,
+      "loss": 7.044,
+      "step": 61
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.0395895584262696e-05,
+      "loss": 7.0167,
+      "step": 62
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.013199585810759e-05,
+      "loss": 7.0915,
+      "step": 63
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 9.868004141892412e-06,
+      "loss": 7.0904,
+      "step": 64
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 9.604104415737309e-06,
+      "loss": 6.9912,
+      "step": 65
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 9.340480595653047e-06,
+      "loss": 6.9406,
+      "step": 66
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 9.07731640536698e-06,
+      "loss": 7.0428,
+      "step": 67
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 8.814795248282974e-06,
+      "loss": 6.882,
+      "step": 68
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 8.553100079664598e-06,
+      "loss": 7.0737,
+      "step": 69
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 8.292413279130625e-06,
+      "loss": 6.8735,
+      "step": 70
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 8.03291652355172e-06,
+      "loss": 6.8399,
+      "step": 71
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 7.774790660436857e-06,
+      "loss": 6.9917,
+      "step": 72
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 7.518215581897763e-06,
+      "loss": 6.9535,
+      "step": 73
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 7.263370099279173e-06,
+      "loss": 6.8895,
+      "step": 74
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 7.010431818542298e-06,
+      "loss": 6.8379,
+      "step": 75
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 6.759577016488343e-06,
+      "loss": 6.7974,
+      "step": 76
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 6.510980517908334e-06,
+      "loss": 6.748,
+      "step": 77
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 6.264815573744884e-06,
+      "loss": 6.7623,
+      "step": 78
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 6.021253740350793e-06,
+      "loss": 6.7696,
+      "step": 79
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 5.780464759928623e-06,
+      "loss": 6.6339,
+      "step": 80
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 5.542616442234618e-06,
+      "loss": 6.8452,
+      "step": 81
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 5.307874547629339e-06,
+      "loss": 6.727,
+      "step": 82
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 5.076402671556578e-06,
+      "loss": 6.6032,
+      "step": 83
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 4.848362130531039e-06,
+      "loss": 6.6008,
+      "step": 84
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 4.623911849714226e-06,
+      "loss": 6.6522,
+      "step": 85
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 4.403208252156921e-06,
+      "loss": 6.5143,
+      "step": 86
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 4.186405149785403e-06,
+      "loss": 6.5768,
+      "step": 87
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 3.973653636207437e-06,
+      "loss": 6.7096,
+      "step": 88
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 3.7651019814126656e-06,
+      "loss": 6.4894,
+      "step": 89
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 3.560895528440844e-06,
+      "loss": 6.5474,
+      "step": 90
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 3.361176592089919e-06,
+      "loss": 6.5607,
+      "step": 91
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 3.1660843597345137e-06,
+      "loss": 6.5093,
+      "step": 92
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 2.975754794324015e-06,
+      "loss": 6.5916,
+      "step": 93
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 2.7903205396277546e-06,
+      "loss": 6.56,
+      "step": 94
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 2.6099108277934105e-06,
+      "loss": 6.4986,
+      "step": 95
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 2.4346513892830427e-06,
+      "loss": 6.4452,
+      "step": 96
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 2.2646643652494693e-06,
+      "loss": 6.5954,
+      "step": 97
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 2.100068222414121e-06,
+      "loss": 6.4479,
+      "step": 98
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 1.9409776705056514e-06,
+      "loss": 6.3907,
+      "step": 99
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 1.7875035823168641e-06,
+      "loss": 6.4218,
+      "step": 100
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 1.6397529164356606e-06,
+      "loss": 6.3627,
+      "step": 101
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 1.4978286427038602e-06,
+      "loss": 6.5013,
+      "step": 102
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 1.3618296704558364e-06,
+      "loss": 6.4827,
+      "step": 103
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 1.2318507795870138e-06,
+      "loss": 6.5356,
+      "step": 104
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 1.1079825545001887e-06,
+      "loss": 6.5029,
+      "step": 105
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 9.903113209758098e-07,
+      "loss": 6.496,
+      "step": 106
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 8.789190860101226e-07,
+      "loss": 6.4866,
+      "step": 107
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 7.738834806631712e-07,
+      "loss": 6.3356,
+      "step": 108
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 6.752777059564431e-07,
+      "loss": 6.4111,
+      "step": 109
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 5.831704818578842e-07,
+      "loss": 6.4152,
+      "step": 110
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 4.976259993898503e-07,
+      "loss": 6.5019,
+      "step": 111
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 4.187038758933204e-07,
+      "loss": 6.4881,
+      "step": 112
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 3.4645911347961357e-07,
+      "loss": 6.3741,
+      "step": 113
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 2.809420606985236e-07,
+      "loss": 6.37,
+      "step": 114
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 2.2219837744959284e-07,
+      "loss": 6.326,
+      "step": 115
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 1.7026900316098217e-07,
+      "loss": 6.2528,
+      "step": 116
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 1.2519012825812804e-07,
+      "loss": 6.3813,
+      "step": 117
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 8.699316894203225e-08,
+      "loss": 6.3577,
+      "step": 118
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 5.5704745294815624e-08,
+      "loss": 6.4415,
+      "step": 119
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 3.134666272774034e-08,
+      "loss": 6.3013,
+      "step": 120
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 1.3935896784663671e-08,
+      "loss": 6.49,
+      "step": 121
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 3.4845813115114147e-09,
+      "loss": 6.4333,
+      "step": 122
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 0.0,
+      "loss": 6.3852,
+      "step": 123
+    },
+    {
+      "epoch": 2.96,
+      "step": 123,
+      "total_flos": 2.5449308383870976e+16,
+      "train_loss": 7.608938182272563,
+      "train_runtime": 1311.0928,
+      "train_samples_per_second": 12.139,
+      "train_steps_per_second": 0.094
+    }
+  ],
+  "max_steps": 123,
+  "num_train_epochs": 3,
+  "total_flos": 2.5449308383870976e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cd21a214d00f814d1ddda227abffe8d06937f730cefb76bd9c80b41966c047c
+size 4091