Initial commit to push model at path_local_hub_repo = /lfs/skampere1/0/brando9/data/maf_data/results_2023-m09-d29-t11h_23m_01s/hub-checkpoint-6000

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.34.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.34.0.dev0"
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b928ceb13238af6b2001350bcdfb55a9a74021b335a891e6827e6eb760045baf
+size 9943030860

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6791b1ddf7e382721303673174fc03fbc7aa28de05f873759d687484b791e7a2
+size 4540536863

pytorch_model.bin.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14483464192
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00002-of-00002.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.norm.weight": "pytorch_model-00002-of-00002.bin"
+  }
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:696b4cef517e79a03215d5c5fccde0c73d2d962fe70ebab1e472f650136142b2
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cf6010cf7b7365bcda49378b37a296245a0036fad4d900f5ac2b2c0a8c8bc4e
+size 627

trainer_state.json

@@ -0,0 +1,739 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 12.818800907998398,
+  "eval_steps": 500,
+  "global_step": 6000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 0.8267,
+      "step": 50
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.6077,
+      "step": 100
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 3e-06,
+      "loss": 0.3982,
+      "step": 150
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.3004,
+      "step": 200
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 5e-06,
+      "loss": 0.2925,
+      "step": 250
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6e-06,
+      "loss": 0.2492,
+      "step": 300
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7e-06,
+      "loss": 0.2615,
+      "step": 350
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.2496,
+      "step": 400
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 9e-06,
+      "loss": 0.2456,
+      "step": 450
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1e-05,
+      "loss": 0.2304,
+      "step": 500
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 9.998737209226261e-06,
+      "loss": 0.2353,
+      "step": 550
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 9.994949474761258e-06,
+      "loss": 0.2178,
+      "step": 600
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 9.988638709851444e-06,
+      "loss": 0.2347,
+      "step": 650
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 9.9798081021671e-06,
+      "loss": 0.233,
+      "step": 700
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 9.968462112192194e-06,
+      "loss": 0.2157,
+      "step": 750
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 9.954606470971309e-06,
+      "loss": 0.2296,
+      "step": 800
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 9.9382481772148e-06,
+      "loss": 0.2192,
+      "step": 850
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 9.919395493763642e-06,
+      "loss": 0.2181,
+      "step": 900
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 9.898057943415722e-06,
+      "loss": 0.2032,
+      "step": 950
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 9.874246304115728e-06,
+      "loss": 0.1536,
+      "step": 1000
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 9.847972603511025e-06,
+      "loss": 0.167,
+      "step": 1050
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 9.8192501128763e-06,
+      "loss": 0.1455,
+      "step": 1100
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 9.78809334041002e-06,
+      "loss": 0.1488,
+      "step": 1150
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 9.754518023906113e-06,
+      "loss": 0.1488,
+      "step": 1200
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 9.718541122804537e-06,
+      "loss": 0.1571,
+      "step": 1250
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 9.680180809624806e-06,
+      "loss": 0.1556,
+      "step": 1300
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 9.639456460786743e-06,
+      "loss": 0.1468,
+      "step": 1350
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 9.59638864682314e-06,
+      "loss": 0.1577,
+      "step": 1400
+    },
+    {
+      "epoch": 3.1,
+      "learning_rate": 9.550999121989246e-06,
+      "loss": 0.0985,
+      "step": 1450
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 9.503310813274334e-06,
+      "loss": 0.0786,
+      "step": 1500
+    },
+    {
+      "epoch": 3.31,
+      "learning_rate": 9.453347808820907e-06,
+      "loss": 0.088,
+      "step": 1550
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 9.401135345757387e-06,
+      "loss": 0.0828,
+      "step": 1600
+    },
+    {
+      "epoch": 3.53,
+      "learning_rate": 9.346699797450427e-06,
+      "loss": 0.086,
+      "step": 1650
+    },
+    {
+      "epoch": 3.63,
+      "learning_rate": 9.290068660183292e-06,
+      "loss": 0.0863,
+      "step": 1700
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 9.23127053926704e-06,
+      "loss": 0.0924,
+      "step": 1750
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 9.170335134591516e-06,
+      "loss": 0.0941,
+      "step": 1800
+    },
+    {
+      "epoch": 3.95,
+      "learning_rate": 9.107293225623445e-06,
+      "loss": 0.0897,
+      "step": 1850
+    },
+    {
+      "epoch": 4.06,
+      "learning_rate": 9.042176655859231e-06,
+      "loss": 0.0622,
+      "step": 1900
+    },
+    {
+      "epoch": 4.17,
+      "learning_rate": 8.975018316740278e-06,
+      "loss": 0.0388,
+      "step": 1950
+    },
+    {
+      "epoch": 4.27,
+      "learning_rate": 8.905852131038996e-06,
+      "loss": 0.0424,
+      "step": 2000
+    },
+    {
+      "epoch": 4.38,
+      "learning_rate": 8.834713035723846e-06,
+      "loss": 0.0463,
+      "step": 2050
+    },
+    {
+      "epoch": 4.49,
+      "learning_rate": 8.761636964312114e-06,
+      "loss": 0.0436,
+      "step": 2100
+    },
+    {
+      "epoch": 4.59,
+      "learning_rate": 8.686660828719309e-06,
+      "loss": 0.0449,
+      "step": 2150
+    },
+    {
+      "epoch": 4.7,
+      "learning_rate": 8.609822500614336e-06,
+      "loss": 0.0441,
+      "step": 2200
+    },
+    {
+      "epoch": 4.81,
+      "learning_rate": 8.531160792289917e-06,
+      "loss": 0.0438,
+      "step": 2250
+    },
+    {
+      "epoch": 4.91,
+      "learning_rate": 8.45071543705786e-06,
+      "loss": 0.0458,
+      "step": 2300
+    },
+    {
+      "epoch": 5.02,
+      "learning_rate": 8.368527069179117e-06,
+      "loss": 0.0399,
+      "step": 2350
+    },
+    {
+      "epoch": 5.13,
+      "learning_rate": 8.284637203338753e-06,
+      "loss": 0.0211,
+      "step": 2400
+    },
+    {
+      "epoch": 5.23,
+      "learning_rate": 8.199088213676205e-06,
+      "loss": 0.0215,
+      "step": 2450
+    },
+    {
+      "epoch": 5.34,
+      "learning_rate": 8.111923312381413e-06,
+      "loss": 0.0223,
+      "step": 2500
+    },
+    {
+      "epoch": 5.45,
+      "learning_rate": 8.023186527867637e-06,
+      "loss": 0.0217,
+      "step": 2550
+    },
+    {
+      "epoch": 5.55,
+      "learning_rate": 7.932922682531986e-06,
+      "loss": 0.0229,
+      "step": 2600
+    },
+    {
+      "epoch": 5.66,
+      "learning_rate": 7.841177370114898e-06,
+      "loss": 0.0223,
+      "step": 2650
+    },
+    {
+      "epoch": 5.77,
+      "learning_rate": 7.747996932669996e-06,
+      "loss": 0.0222,
+      "step": 2700
+    },
+    {
+      "epoch": 5.88,
+      "learning_rate": 7.653428437155956e-06,
+      "loss": 0.023,
+      "step": 2750
+    },
+    {
+      "epoch": 5.98,
+      "learning_rate": 7.557519651662229e-06,
+      "loss": 0.0218,
+      "step": 2800
+    },
+    {
+      "epoch": 6.09,
+      "learning_rate": 7.460319021280591e-06,
+      "loss": 0.0148,
+      "step": 2850
+    },
+    {
+      "epoch": 6.2,
+      "learning_rate": 7.3618756436347415e-06,
+      "loss": 0.013,
+      "step": 2900
+    },
+    {
+      "epoch": 6.3,
+      "learning_rate": 7.262239244080291e-06,
+      "loss": 0.013,
+      "step": 2950
+    },
+    {
+      "epoch": 6.41,
+      "learning_rate": 7.161460150587674e-06,
+      "loss": 0.0129,
+      "step": 3000
+    },
+    {
+      "epoch": 6.52,
+      "learning_rate": 7.05958926832067e-06,
+      "loss": 0.0129,
+      "step": 3050
+    },
+    {
+      "epoch": 6.62,
+      "learning_rate": 6.956678053923373e-06,
+      "loss": 0.0137,
+      "step": 3100
+    },
+    {
+      "epoch": 6.73,
+      "learning_rate": 6.852778489528608e-06,
+      "loss": 0.0133,
+      "step": 3150
+    },
+    {
+      "epoch": 6.84,
+      "learning_rate": 6.7479430565008986e-06,
+      "loss": 0.013,
+      "step": 3200
+    },
+    {
+      "epoch": 6.94,
+      "learning_rate": 6.642224708927281e-06,
+      "loss": 0.0141,
+      "step": 3250
+    },
+    {
+      "epoch": 7.05,
+      "learning_rate": 6.535676846869327e-06,
+      "loss": 0.0109,
+      "step": 3300
+    },
+    {
+      "epoch": 7.16,
+      "learning_rate": 6.428353289389902e-06,
+      "loss": 0.0076,
+      "step": 3350
+    },
+    {
+      "epoch": 7.26,
+      "learning_rate": 6.320308247368285e-06,
+      "loss": 0.0077,
+      "step": 3400
+    },
+    {
+      "epoch": 7.37,
+      "learning_rate": 6.2115962961173616e-06,
+      "loss": 0.0075,
+      "step": 3450
+    },
+    {
+      "epoch": 7.48,
+      "learning_rate": 6.1022723478167445e-06,
+      "loss": 0.0076,
+      "step": 3500
+    },
+    {
+      "epoch": 7.58,
+      "learning_rate": 5.992391623775738e-06,
+      "loss": 0.0081,
+      "step": 3550
+    },
+    {
+      "epoch": 7.69,
+      "learning_rate": 5.882009626540155e-06,
+      "loss": 0.0081,
+      "step": 3600
+    },
+    {
+      "epoch": 7.8,
+      "learning_rate": 5.771182111857075e-06,
+      "loss": 0.0076,
+      "step": 3650
+    },
+    {
+      "epoch": 7.9,
+      "learning_rate": 5.659965060511705e-06,
+      "loss": 0.0078,
+      "step": 3700
+    },
+    {
+      "epoch": 8.01,
+      "learning_rate": 5.5484146500505735e-06,
+      "loss": 0.0074,
+      "step": 3750
+    },
+    {
+      "epoch": 8.12,
+      "learning_rate": 5.436587226405333e-06,
+      "loss": 0.0047,
+      "step": 3800
+    },
+    {
+      "epoch": 8.23,
+      "learning_rate": 5.324539275431518e-06,
+      "loss": 0.0046,
+      "step": 3850
+    },
+    {
+      "epoch": 8.33,
+      "learning_rate": 5.212327394376612e-06,
+      "loss": 0.0045,
+      "step": 3900
+    },
+    {
+      "epoch": 8.44,
+      "learning_rate": 5.100008263291852e-06,
+      "loss": 0.0046,
+      "step": 3950
+    },
+    {
+      "epoch": 8.55,
+      "learning_rate": 4.987638616402219e-06,
+      "loss": 0.0046,
+      "step": 4000
+    },
+    {
+      "epoch": 8.65,
+      "learning_rate": 4.875275213449051e-06,
+      "loss": 0.0046,
+      "step": 4050
+    },
+    {
+      "epoch": 8.76,
+      "learning_rate": 4.762974811019766e-06,
+      "loss": 0.0045,
+      "step": 4100
+    },
+    {
+      "epoch": 8.87,
+      "learning_rate": 4.650794133879198e-06,
+      "loss": 0.0049,
+      "step": 4150
+    },
+    {
+      "epoch": 8.97,
+      "learning_rate": 4.538789846316977e-06,
+      "loss": 0.0047,
+      "step": 4200
+    },
+    {
+      "epoch": 9.08,
+      "learning_rate": 4.4270185235254904e-06,
+      "loss": 0.0037,
+      "step": 4250
+    },
+    {
+      "epoch": 9.19,
+      "learning_rate": 4.3155366230228055e-06,
+      "loss": 0.0034,
+      "step": 4300
+    },
+    {
+      "epoch": 9.29,
+      "learning_rate": 4.204400456135086e-06,
+      "loss": 0.0033,
+      "step": 4350
+    },
+    {
+      "epoch": 9.4,
+      "learning_rate": 4.093666159552802e-06,
+      "loss": 0.0032,
+      "step": 4400
+    },
+    {
+      "epoch": 9.51,
+      "learning_rate": 3.983389666975174e-06,
+      "loss": 0.0033,
+      "step": 4450
+    },
+    {
+      "epoch": 9.61,
+      "learning_rate": 3.873626680857161e-06,
+      "loss": 0.0033,
+      "step": 4500
+    },
+    {
+      "epoch": 9.72,
+      "learning_rate": 3.7644326442732255e-06,
+      "loss": 0.0033,
+      "step": 4550
+    },
+    {
+      "epoch": 9.83,
+      "learning_rate": 3.6558627129121506e-06,
+      "loss": 0.0033,
+      "step": 4600
+    },
+    {
+      "epoch": 9.93,
+      "learning_rate": 3.547971727216982e-06,
+      "loss": 0.0033,
+      "step": 4650
+    },
+    {
+      "epoch": 10.04,
+      "learning_rate": 3.4408141846842493e-06,
+      "loss": 0.0035,
+      "step": 4700
+    },
+    {
+      "epoch": 10.15,
+      "learning_rate": 3.334444212336364e-06,
+      "loss": 0.0029,
+      "step": 4750
+    },
+    {
+      "epoch": 10.26,
+      "learning_rate": 3.2289155393812045e-06,
+      "loss": 0.0033,
+      "step": 4800
+    },
+    {
+      "epoch": 10.36,
+      "learning_rate": 3.1242814700725977e-06,
+      "loss": 0.0029,
+      "step": 4850
+    },
+    {
+      "epoch": 10.47,
+      "learning_rate": 3.0205948567854815e-06,
+      "loss": 0.003,
+      "step": 4900
+    },
+    {
+      "epoch": 10.58,
+      "learning_rate": 2.917908073319302e-06,
+      "loss": 0.0031,
+      "step": 4950
+    },
+    {
+      "epoch": 10.68,
+      "learning_rate": 2.816272988443158e-06,
+      "loss": 0.003,
+      "step": 5000
+    },
+    {
+      "epoch": 10.79,
+      "learning_rate": 2.71574093969604e-06,
+      "loss": 0.003,
+      "step": 5050
+    },
+    {
+      "epoch": 10.9,
+      "learning_rate": 2.6163627074553954e-06,
+      "loss": 0.003,
+      "step": 5100
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 2.5181884892871378e-06,
+      "loss": 0.003,
+      "step": 5150
+    },
+    {
+      "epoch": 11.11,
+      "learning_rate": 2.4212678745900336e-06,
+      "loss": 0.0032,
+      "step": 5200
+    },
+    {
+      "epoch": 11.22,
+      "learning_rate": 2.3256498195472966e-06,
+      "loss": 0.0028,
+      "step": 5250
+    },
+    {
+      "epoch": 11.32,
+      "learning_rate": 2.231382622398008e-06,
+      "loss": 0.0028,
+      "step": 5300
+    },
+    {
+      "epoch": 11.43,
+      "learning_rate": 2.1385138990409037e-06,
+      "loss": 0.0029,
+      "step": 5350
+    },
+    {
+      "epoch": 11.54,
+      "learning_rate": 2.0470905589827853e-06,
+      "loss": 0.0029,
+      "step": 5400
+    },
+    {
+      "epoch": 11.64,
+      "learning_rate": 1.957158781643792e-06,
+      "loss": 0.0029,
+      "step": 5450
+    },
+    {
+      "epoch": 11.75,
+      "learning_rate": 1.8687639930313944e-06,
+      "loss": 0.0029,
+      "step": 5500
+    },
+    {
+      "epoch": 11.86,
+      "learning_rate": 1.781950842794999e-06,
+      "loss": 0.0029,
+      "step": 5550
+    },
+    {
+      "epoch": 11.96,
+      "learning_rate": 1.6967631816726676e-06,
+      "loss": 0.0029,
+      "step": 5600
+    },
+    {
+      "epoch": 12.07,
+      "learning_rate": 1.613244039341399e-06,
+      "loss": 0.0029,
+      "step": 5650
+    },
+    {
+      "epoch": 12.18,
+      "learning_rate": 1.5314356026821426e-06,
+      "loss": 0.0027,
+      "step": 5700
+    },
+    {
+      "epoch": 12.28,
+      "learning_rate": 1.451379194470507e-06,
+      "loss": 0.0028,
+      "step": 5750
+    },
+    {
+      "epoch": 12.39,
+      "learning_rate": 1.3731152525039627e-06,
+      "loss": 0.0028,
+      "step": 5800
+    },
+    {
+      "epoch": 12.5,
+      "learning_rate": 1.29668330917604e-06,
+      "loss": 0.0028,
+      "step": 5850
+    },
+    {
+      "epoch": 12.61,
+      "learning_rate": 1.2221219715078808e-06,
+      "loss": 0.0028,
+      "step": 5900
+    },
+    {
+      "epoch": 12.71,
+      "learning_rate": 1.1494689016471977e-06,
+      "loss": 0.0028,
+      "step": 5950
+    },
+    {
+      "epoch": 12.82,
+      "learning_rate": 1.0787607978445153e-06,
+      "loss": 0.003,
+      "step": 6000
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 7489,
+  "num_train_epochs": 17,
+  "save_steps": 2000,
+  "total_flos": 3.355230384370483e+19,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c21f11413ccb09f6f15733b35375d9cc91d5312f2e68bdc8148e4fb5da5fecc
+size 4091