Upload folder using huggingface_hub

stealthwriter/dsafsaf/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "</s>": 2,
+  "<s>": 1,
+  "<unk>": 0
+}

stealthwriter/dsafsaf/checkpoint-281/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": "float32",
+  "transformers_version": "4.35.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

stealthwriter/dsafsaf/checkpoint-281/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.35.0.dev0"
+}

stealthwriter/dsafsaf/checkpoint-281/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c5e4fe088c3db08141d06485c5651c8a6d2a526db32351b56df1b7f7ee1de63
+size 14512103111

stealthwriter/dsafsaf/checkpoint-281/pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d3b3719331884697a43230c825540b383f7e255c3dbe1a79c085eaab9b21f52
+size 9886732660

stealthwriter/dsafsaf/checkpoint-281/pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad55395888283422fec7d6a01e7ffcb216129677d55f0a8e4b93fb5b4b894fde
+size 5121655723

stealthwriter/dsafsaf/checkpoint-281/pytorch_model.bin.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 15008284672
+  },
+  "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-00002-of-00002.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-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-00002-of-00002.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-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-00002-of-00002.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-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"
+  }
+}

stealthwriter/dsafsaf/checkpoint-281/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62645c695530bea3f09200c274e27a94375cae128377db5b017b297143c54c49
+size 14575

stealthwriter/dsafsaf/checkpoint-281/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e95a08d27c9f75742ffb991b3013a8bfa25634154a8fe680dc21b98335c62d95
+size 627

stealthwriter/dsafsaf/checkpoint-281/trainer_state.json

@@ -0,0 +1,1817 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9991111111111111,
+  "eval_steps": 20,
+  "global_step": 281,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 2.1971,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.8696,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.5e-06,
+      "loss": 2.1836,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.4715,
+      "step": 4
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.5e-06,
+      "loss": 1.3989,
+      "step": 5
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3e-06,
+      "loss": 1.1159,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.5e-06,
+      "loss": 1.3961,
+      "step": 7
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.0953,
+      "step": 8
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.5e-06,
+      "loss": 1.1007,
+      "step": 9
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 5e-06,
+      "loss": 1.1095,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.999832016620967e-06,
+      "loss": 1.0528,
+      "step": 11
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.999328089058596e-06,
+      "loss": 1.0659,
+      "step": 12
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.998488285034055e-06,
+      "loss": 1.0704,
+      "step": 13
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.997312717405835e-06,
+      "loss": 0.877,
+      "step": 14
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.995801544154597e-06,
+      "loss": 1.0001,
+      "step": 15
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.99395496836193e-06,
+      "loss": 1.2647,
+      "step": 16
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.991773238183067e-06,
+      "loss": 0.9862,
+      "step": 17
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.989256646813534e-06,
+      "loss": 0.9529,
+      "step": 18
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.98640553244975e-06,
+      "loss": 0.8286,
+      "step": 19
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.9832202782435746e-06,
+      "loss": 1.1062,
+      "step": 20
+    },
+    {
+      "epoch": 0.07,
+      "eval_loss": 1.0378432273864746,
+      "eval_runtime": 1.0944,
+      "eval_samples_per_second": 49.343,
+      "eval_steps_per_second": 24.671,
+      "step": 20
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.979701312250818e-06,
+      "loss": 1.0919,
+      "step": 21
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.9758491073737205e-06,
+      "loss": 0.9304,
+      "step": 22
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.971664181297394e-06,
+      "loss": 0.9646,
+      "step": 23
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.967147096420259e-06,
+      "loss": 0.9302,
+      "step": 24
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.962298459778458e-06,
+      "loss": 0.9062,
+      "step": 25
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.957118922964287e-06,
+      "loss": 0.9465,
+      "step": 26
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.951609182038621e-06,
+      "loss": 1.0982,
+      "step": 27
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.945769977437379e-06,
+      "loss": 0.8274,
+      "step": 28
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.939602093872018e-06,
+      "loss": 1.144,
+      "step": 29
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.9331063602240746e-06,
+      "loss": 0.9,
+      "step": 30
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.926283649433778e-06,
+      "loss": 0.9576,
+      "step": 31
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.919134878382742e-06,
+      "loss": 1.0861,
+      "step": 32
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.911661007770737e-06,
+      "loss": 0.956,
+      "step": 33
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.903863041986596e-06,
+      "loss": 0.8711,
+      "step": 34
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.895742028973232e-06,
+      "loss": 0.9257,
+      "step": 35
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.887299060086813e-06,
+      "loss": 1.0093,
+      "step": 36
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.87853526995009e-06,
+      "loss": 0.8837,
+      "step": 37
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.869451836299929e-06,
+      "loss": 0.7972,
+      "step": 38
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.860049979829031e-06,
+      "loss": 0.9679,
+      "step": 39
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.850330964021893e-06,
+      "loss": 1.1033,
+      "step": 40
+    },
+    {
+      "epoch": 0.14,
+      "eval_loss": 1.0473524332046509,
+      "eval_runtime": 1.1155,
+      "eval_samples_per_second": 48.408,
+      "eval_steps_per_second": 24.204,
+      "step": 40
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.8402960949850075e-06,
+      "loss": 1.0729,
+      "step": 41
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.829946721271342e-06,
+      "loss": 1.1439,
+      "step": 42
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.819284233699108e-06,
+      "loss": 1.0476,
+      "step": 43
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.80831006516486e-06,
+      "loss": 0.9107,
+      "step": 44
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.79702569045093e-06,
+      "loss": 1.1481,
+      "step": 45
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.785432626027231e-06,
+      "loss": 1.2507,
+      "step": 46
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.773532429847472e-06,
+      "loss": 0.8986,
+      "step": 47
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.761326701139785e-06,
+      "loss": 0.9127,
+      "step": 48
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.7488170801918134e-06,
+      "loss": 0.787,
+      "step": 49
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.7360052481302724e-06,
+      "loss": 0.9466,
+      "step": 50
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.722892926695037e-06,
+      "loss": 1.1056,
+      "step": 51
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.7094818780077555e-06,
+      "loss": 0.8997,
+      "step": 52
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.695773904335048e-06,
+      "loss": 0.9316,
+      "step": 53
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.681770847846305e-06,
+      "loss": 0.9053,
+      "step": 54
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.6674745903661225e-06,
+      "loss": 0.9341,
+      "step": 55
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.652887053121412e-06,
+      "loss": 0.973,
+      "step": 56
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.638010196483212e-06,
+      "loss": 0.8249,
+      "step": 57
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.62284601970324e-06,
+      "loss": 0.8658,
+      "step": 58
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.607396560645221e-06,
+      "loss": 1.0389,
+      "step": 59
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.591663895511024e-06,
+      "loss": 0.9296,
+      "step": 60
+    },
+    {
+      "epoch": 0.21,
+      "eval_loss": 1.02631413936615,
+      "eval_runtime": 1.1188,
+      "eval_samples_per_second": 48.267,
+      "eval_steps_per_second": 24.133,
+      "step": 60
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.57565013856165e-06,
+      "loss": 1.0555,
+      "step": 61
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.559357441833102e-06,
+      "loss": 0.8764,
+      "step": 62
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.542787994847179e-06,
+      "loss": 1.0836,
+      "step": 63
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.525944024317236e-06,
+      "loss": 0.6844,
+      "step": 64
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.5088277938489424e-06,
+      "loss": 1.1778,
+      "step": 65
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.491441603636082e-06,
+      "loss": 1.0161,
+      "step": 66
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.4737877901514396e-06,
+      "loss": 0.8945,
+      "step": 67
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.455868725832808e-06,
+      "loss": 1.0666,
+      "step": 68
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.437686818764168e-06,
+      "loss": 0.9255,
+      "step": 69
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.4192445123520655e-06,
+      "loss": 0.9419,
+      "step": 70
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.400544284997262e-06,
+      "loss": 0.9248,
+      "step": 71
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.381588649761659e-06,
+      "loss": 0.8787,
+      "step": 72
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.362380154030586e-06,
+      "loss": 1.0428,
+      "step": 73
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.342921379170456e-06,
+      "loss": 0.9497,
+      "step": 74
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.323214940181873e-06,
+      "loss": 0.9041,
+      "step": 75
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.303263485348205e-06,
+      "loss": 0.9085,
+      "step": 76
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.283069695879689e-06,
+      "loss": 0.9847,
+      "step": 77
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.262636285553121e-06,
+      "loss": 0.9642,
+      "step": 78
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.241966000347148e-06,
+      "loss": 0.9225,
+      "step": 79
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.221061618073254e-06,
+      "loss": 0.9349,
+      "step": 80
+    },
+    {
+      "epoch": 0.28,
+      "eval_loss": 1.0077301263809204,
+      "eval_runtime": 1.1245,
+      "eval_samples_per_second": 48.023,
+      "eval_steps_per_second": 24.011,
+      "step": 80
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.199925948002457e-06,
+      "loss": 0.9573,
+      "step": 81
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.1785618304877766e-06,
+      "loss": 0.7771,
+      "step": 82
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.156972136582534e-06,
+      "loss": 0.7372,
+      "step": 83
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.135159767654518e-06,
+      "loss": 0.7984,
+      "step": 84
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.113127654996075e-06,
+      "loss": 1.0468,
+      "step": 85
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.0908787594301934e-06,
+      "loss": 1.065,
+      "step": 86
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.068416070912598e-06,
+      "loss": 1.0398,
+      "step": 87
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.045742608129943e-06,
+      "loss": 0.8079,
+      "step": 88
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.022861418094145e-06,
+      "loss": 0.6808,
+      "step": 89
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 3.999775575732896e-06,
+      "loss": 1.2168,
+      "step": 90
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 3.976488183476444e-06,
+      "loss": 0.839,
+      "step": 91
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 3.953002370840661e-06,
+      "loss": 1.0509,
+      "step": 92
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 3.929321294006478e-06,
+      "loss": 0.9867,
+      "step": 93
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 3.905448135395742e-06,
+      "loss": 0.884,
+      "step": 94
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.881386103243533e-06,
+      "loss": 0.8762,
+      "step": 95
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.857138431167026e-06,
+      "loss": 0.8968,
+      "step": 96
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.83270837773093e-06,
+      "loss": 0.9443,
+      "step": 97
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 3.808099226009588e-06,
+      "loss": 1.0523,
+      "step": 98
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 3.7833142831457685e-06,
+      "loss": 1.1171,
+      "step": 99
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 3.7583568799062323e-06,
+      "loss": 0.8586,
+      "step": 100
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 1.0145351886749268,
+      "eval_runtime": 1.1232,
+      "eval_samples_per_second": 48.077,
+      "eval_steps_per_second": 24.039,
+      "step": 100
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 3.733230370234123e-06,
+      "loss": 0.9599,
+      "step": 101
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 3.7079381307982372e-06,
+      "loss": 1.0458,
+      "step": 102
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 3.6824835605392512e-06,
+      "loss": 0.9745,
+      "step": 103
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 3.6568700802129436e-06,
+      "loss": 0.8301,
+      "step": 104
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 3.6311011319304943e-06,
+      "loss": 0.8636,
+      "step": 105
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.605180178695909e-06,
+      "loss": 1.0519,
+      "step": 106
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.5791107039406357e-06,
+      "loss": 0.8668,
+      "step": 107
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.5528962110554428e-06,
+      "loss": 0.879,
+      "step": 108
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 3.5265402229196055e-06,
+      "loss": 1.0228,
+      "step": 109
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 3.5000462814274798e-06,
+      "loss": 0.8075,
+      "step": 110
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 3.4734179470125184e-06,
+      "loss": 0.9479,
+      "step": 111
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3.446658798168796e-06,
+      "loss": 0.9812,
+      "step": 112
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3.419772430970107e-06,
+      "loss": 0.8175,
+      "step": 113
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 3.3927624585867e-06,
+      "loss": 0.7484,
+      "step": 114
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 3.3656325107997185e-06,
+      "loss": 0.8793,
+      "step": 115
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 3.3383862335134045e-06,
+      "loss": 0.8877,
+      "step": 116
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.3110272882651374e-06,
+      "loss": 0.8975,
+      "step": 117
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.2835593517333732e-06,
+      "loss": 0.8904,
+      "step": 118
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.2559861152435457e-06,
+      "loss": 0.8961,
+      "step": 119
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 3.228311284272006e-06,
+      "loss": 0.87,
+      "step": 120
+    },
+    {
+      "epoch": 0.43,
+      "eval_loss": 1.009682536125183,
+      "eval_runtime": 1.1421,
+      "eval_samples_per_second": 47.28,
+      "eval_steps_per_second": 23.64,
+      "step": 120
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 3.200538577948049e-06,
+      "loss": 1.0088,
+      "step": 121
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 3.172671728554119e-06,
+      "loss": 1.1713,
+      "step": 122
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 3.1447144810242337e-06,
+      "loss": 0.936,
+      "step": 123
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 3.1166705924407208e-06,
+      "loss": 1.1882,
+      "step": 124
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 3.088543831529313e-06,
+      "loss": 0.8949,
+      "step": 125
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 3.0603379781526816e-06,
+      "loss": 0.8646,
+      "step": 126
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 3.0320568228024727e-06,
+      "loss": 1.0794,
+      "step": 127
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 3.003704166089918e-06,
+      "loss": 1.0737,
+      "step": 128
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2.97528381823508e-06,
+      "loss": 0.8349,
+      "step": 129
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2.9467995985548124e-06,
+      "loss": 1.1471,
+      "step": 130
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.918255334949492e-06,
+      "loss": 0.9503,
+      "step": 131
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.8896548633886e-06,
+      "loss": 0.9196,
+      "step": 132
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.861002027395221e-06,
+      "loss": 0.9517,
+      "step": 133
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.832300677529522e-06,
+      "loss": 0.7699,
+      "step": 134
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.8035546708712897e-06,
+      "loss": 0.8816,
+      "step": 135
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.7747678705015903e-06,
+      "loss": 0.7005,
+      "step": 136
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.7459441449836207e-06,
+      "loss": 0.9879,
+      "step": 137
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.717087367842829e-06,
+      "loss": 0.9621,
+      "step": 138
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.6882014170463606e-06,
+      "loss": 0.9198,
+      "step": 139
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.659290174481913e-06,
+      "loss": 0.845,
+      "step": 140
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 1.0057734251022339,
+      "eval_runtime": 1.132,
+      "eval_samples_per_second": 47.703,
+      "eval_steps_per_second": 23.851,
+      "step": 140
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.6303575254360596e-06,
+      "loss": 0.7492,
+      "step": 141
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.6014073580721223e-06,
+      "loss": 0.8781,
+      "step": 142
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2.5724435629076504e-06,
+      "loss": 0.9511,
+      "step": 143
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2.5434700322915894e-06,
+      "loss": 0.9554,
+      "step": 144
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 2.5144906598811996e-06,
+      "loss": 0.9193,
+      "step": 145
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 2.485509340118801e-06,
+      "loss": 1.0948,
+      "step": 146
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 2.456529967708411e-06,
+      "loss": 0.9276,
+      "step": 147
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.4275564370923504e-06,
+      "loss": 1.2539,
+      "step": 148
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.398592641927878e-06,
+      "loss": 1.0415,
+      "step": 149
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.3696424745639413e-06,
+      "loss": 1.0589,
+      "step": 150
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.3407098255180884e-06,
+      "loss": 0.9404,
+      "step": 151
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.3117985829536403e-06,
+      "loss": 0.966,
+      "step": 152
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.282912632157172e-06,
+      "loss": 0.9222,
+      "step": 153
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.2540558550163797e-06,
+      "loss": 1.0793,
+      "step": 154
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.225232129498411e-06,
+      "loss": 0.9236,
+      "step": 155
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.1964453291287103e-06,
+      "loss": 1.0245,
+      "step": 156
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 2.167699322470479e-06,
+      "loss": 0.6727,
+      "step": 157
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 2.138997972604779e-06,
+      "loss": 0.9867,
+      "step": 158
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2.110345136611401e-06,
+      "loss": 0.9262,
+      "step": 159
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2.0817446650505086e-06,
+      "loss": 0.9251,
+      "step": 160
+    },
+    {
+      "epoch": 0.57,
+      "eval_loss": 0.9886958599090576,
+      "eval_runtime": 1.1221,
+      "eval_samples_per_second": 48.122,
+      "eval_steps_per_second": 24.061,
+      "step": 160
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2.0532004014451884e-06,
+      "loss": 0.8896,
+      "step": 161
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 2.024716181764921e-06,
+      "loss": 0.8962,
+      "step": 162
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.996295833910083e-06,
+      "loss": 1.0207,
+      "step": 163
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.9679431771975286e-06,
+      "loss": 0.9865,
+      "step": 164
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.9396620218473193e-06,
+      "loss": 0.7606,
+      "step": 165
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.9114561684706874e-06,
+      "loss": 0.9108,
+      "step": 166
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.8833294075592792e-06,
+      "loss": 0.8081,
+      "step": 167
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.8552855189757667e-06,
+      "loss": 1.0495,
+      "step": 168
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.8273282714458811e-06,
+      "loss": 0.8476,
+      "step": 169
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.7994614220519512e-06,
+      "loss": 0.8754,
+      "step": 170
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.7716887157279955e-06,
+      "loss": 0.7188,
+      "step": 171
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.7440138847564548e-06,
+      "loss": 0.7527,
+      "step": 172
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.7164406482666285e-06,
+      "loss": 0.6502,
+      "step": 173
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.6889727117348634e-06,
+      "loss": 1.0657,
+      "step": 174
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.6616137664865966e-06,
+      "loss": 0.8579,
+      "step": 175
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.634367489200282e-06,
+      "loss": 1.1399,
+      "step": 176
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.607237541413301e-06,
+      "loss": 0.9598,
+      "step": 177
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.580227569029894e-06,
+      "loss": 0.7723,
+      "step": 178
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.5533412018312043e-06,
+      "loss": 1.0247,
+      "step": 179
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.526582052987482e-06,
+      "loss": 1.0108,
+      "step": 180
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 0.981923520565033,
+      "eval_runtime": 1.1233,
+      "eval_samples_per_second": 48.071,
+      "eval_steps_per_second": 24.036,
+      "step": 180
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.499953718572521e-06,
+      "loss": 1.0422,
+      "step": 181
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.473459777080396e-06,
+      "loss": 0.9422,
+      "step": 182
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.4471037889445576e-06,
+      "loss": 0.9185,
+      "step": 183
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.420889296059365e-06,
+      "loss": 0.9711,
+      "step": 184
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.3948198213040922e-06,
+      "loss": 0.9289,
+      "step": 185
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.3688988680695059e-06,
+      "loss": 0.7391,
+      "step": 186
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.3431299197870568e-06,
+      "loss": 0.9233,
+      "step": 187
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.31751643946075e-06,
+      "loss": 1.0112,
+      "step": 188
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.2920618692017634e-06,
+      "loss": 0.8613,
+      "step": 189
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.2667696297658784e-06,
+      "loss": 0.7893,
+      "step": 190
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.241643120093769e-06,
+      "loss": 0.8409,
+      "step": 191
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.2166857168542325e-06,
+      "loss": 1.0121,
+      "step": 192
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.191900773990413e-06,
+      "loss": 0.8271,
+      "step": 193
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.1672916222690707e-06,
+      "loss": 1.0269,
+      "step": 194
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.1428615688329758e-06,
+      "loss": 0.9023,
+      "step": 195
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.1186138967564675e-06,
+      "loss": 0.9995,
+      "step": 196
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.0945518646042589e-06,
+      "loss": 0.9171,
+      "step": 197
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.070678705993522e-06,
+      "loss": 0.9004,
+      "step": 198
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.0469976291593403e-06,
+      "loss": 0.8427,
+      "step": 199
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.0235118165235563e-06,
+      "loss": 0.6899,
+      "step": 200
+    },
+    {
+      "epoch": 0.71,
+      "eval_loss": 0.9773601293563843,
+      "eval_runtime": 1.1227,
+      "eval_samples_per_second": 48.1,
+      "eval_steps_per_second": 24.05,
+      "step": 200
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.0002244242671045e-06,
+      "loss": 0.8198,
+      "step": 201
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 9.771385819058562e-07,
+      "loss": 0.9696,
+      "step": 202
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 9.54257391870057e-07,
+      "loss": 0.8043,
+      "step": 203
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 9.315839290874029e-07,
+      "loss": 0.8259,
+      "step": 204
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 9.091212405698066e-07,
+      "loss": 0.8619,
+      "step": 205
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 8.868723450039251e-07,
+      "loss": 1.0856,
+      "step": 206
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 8.648402323454827e-07,
+      "loss": 0.9383,
+      "step": 207
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 8.43027863417466e-07,
+      "loss": 1.105,
+      "step": 208
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 8.214381695122231e-07,
+      "loss": 0.9021,
+      "step": 209
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 8.000740519975436e-07,
+      "loss": 0.8687,
+      "step": 210
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.789383819267465e-07,
+      "loss": 0.9884,
+      "step": 211
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.580339996528524e-07,
+      "loss": 0.9178,
+      "step": 212
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 7.373637144468799e-07,
+      "loss": 1.1743,
+      "step": 213
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 7.169303041203116e-07,
+      "loss": 0.853,
+      "step": 214
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 6.967365146517968e-07,
+      "loss": 0.8146,
+      "step": 215
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.767850598181275e-07,
+      "loss": 0.821,
+      "step": 216
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.570786208295446e-07,
+      "loss": 1.1706,
+      "step": 217
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 6.376198459694146e-07,
+      "loss": 1.0696,
+      "step": 218
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 6.184113502383415e-07,
+      "loss": 0.8113,
+      "step": 219
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 5.994557150027391e-07,
+      "loss": 0.8889,
+      "step": 220
+    },
+    {
+      "epoch": 0.78,
+      "eval_loss": 0.9770259857177734,
+      "eval_runtime": 1.1234,
+      "eval_samples_per_second": 48.07,
+      "eval_steps_per_second": 24.035,
+      "step": 220
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 5.807554876479357e-07,
+      "loss": 0.8209,
+      "step": 221
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 5.62313181235834e-07,
+      "loss": 0.8947,
+      "step": 222
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 5.441312741671923e-07,
+      "loss": 1.0871,
+      "step": 223
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 5.262122098485614e-07,
+      "loss": 0.857,
+      "step": 224
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 5.085583963639184e-07,
+      "loss": 0.9359,
+      "step": 225
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.911722061510585e-07,
+      "loss": 1.0515,
+      "step": 226
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.740559756827645e-07,
+      "loss": 0.9827,
+      "step": 227
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.5721200515282197e-07,
+      "loss": 1.1047,
+      "step": 228
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.406425581668988e-07,
+      "loss": 0.8075,
+      "step": 229
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 4.2434986143835065e-07,
+      "loss": 0.7395,
+      "step": 230
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 4.0833610448897694e-07,
+      "loss": 0.7539,
+      "step": 231
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.9260343935478006e-07,
+      "loss": 0.8704,
+      "step": 232
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.771539802967611e-07,
+      "loss": 0.9078,
+      "step": 233
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.619898035167887e-07,
+      "loss": 0.7626,
+      "step": 234
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.471129468785886e-07,
+      "loss": 0.7827,
+      "step": 235
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.325254096338773e-07,
+      "loss": 0.8929,
+      "step": 236
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.182291521536951e-07,
+      "loss": 1.0776,
+      "step": 237
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.042260956649515e-07,
+      "loss": 0.6496,
+      "step": 238
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2.9051812199224483e-07,
+      "loss": 0.6905,
+      "step": 239
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2.7710707330496357e-07,
+      "loss": 0.8297,
+      "step": 240
+    },
+    {
+      "epoch": 0.85,
+      "eval_loss": 0.9769445657730103,
+      "eval_runtime": 1.1266,
+      "eval_samples_per_second": 47.932,
+      "eval_steps_per_second": 23.966,
+      "step": 240
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.6399475186972835e-07,
+      "loss": 0.7985,
+      "step": 241
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.511829198081875e-07,
+      "loss": 0.7916,
+      "step": 242
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.3867329886021554e-07,
+      "loss": 0.7736,
+      "step": 243
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.264675701525293e-07,
+      "loss": 0.8849,
+      "step": 244
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.1456737397277022e-07,
+      "loss": 1.0649,
+      "step": 245
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.0297430954907133e-07,
+      "loss": 1.0071,
+      "step": 246
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.9168993483514004e-07,
+      "loss": 1.0899,
+      "step": 247
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.8071576630089293e-07,
+      "loss": 0.9516,
+      "step": 248
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.7005327872865935e-07,
+      "loss": 0.8072,
+      "step": 249
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.5970390501499316e-07,
+      "loss": 0.9805,
+      "step": 250
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.4966903597810723e-07,
+      "loss": 0.7793,
+      "step": 251
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.3995002017096915e-07,
+      "loss": 1.0237,
+      "step": 252
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.305481637000719e-07,
+      "loss": 0.8881,
+      "step": 253
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.2146473004991082e-07,
+      "loss": 0.7652,
+      "step": 254
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.1270093991318814e-07,
+      "loss": 0.8863,
+      "step": 255
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.0425797102676772e-07,
+      "loss": 0.9421,
+      "step": 256
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 9.613695801340444e-08,
+      "loss": 0.8833,
+      "step": 257
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 8.833899222926351e-08,
+      "loss": 1.1955,
+      "step": 258
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 8.086512161725874e-08,
+      "loss": 0.9213,
+      "step": 259
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 7.371635056622139e-08,
+      "loss": 0.8395,
+      "step": 260
+    },
+    {
+      "epoch": 0.92,
+      "eval_loss": 0.9767907857894897,
+      "eval_runtime": 1.1234,
+      "eval_samples_per_second": 48.068,
+      "eval_steps_per_second": 24.034,
+      "step": 260
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 6.689363977592622e-08,
+      "loss": 0.9171,
+      "step": 261
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 6.039790612798275e-08,
+      "loss": 0.9939,
+      "step": 262
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 5.423002256262105e-08,
+      "loss": 0.9222,
+      "step": 263
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.839081796137929e-08,
+      "loss": 0.7726,
+      "step": 264
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.288107703571326e-08,
+      "loss": 0.9914,
+      "step": 265
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 3.770154022154221e-08,
+      "loss": 0.7231,
+      "step": 266
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 3.285290357974202e-08,
+      "loss": 0.9175,
+      "step": 267
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.8335818702606433e-08,
+      "loss": 1.1366,
+      "step": 268
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.4150892626280396e-08,
+      "loss": 0.7249,
+      "step": 269
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.0298687749182588e-08,
+      "loss": 0.8792,
+      "step": 270
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.677972175642639e-08,
+      "loss": 0.8566,
+      "step": 271
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.359446755025029e-08,
+      "loss": 0.8901,
+      "step": 272
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.0743353186466188e-08,
+      "loss": 0.703,
+      "step": 273
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 8.226761816934048e-09,
+      "loss": 1.1903,
+      "step": 274
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 6.045031638071131e-09,
+      "loss": 0.8815,
+      "step": 275
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 4.1984558454036265e-09,
+      "loss": 1.0494,
+      "step": 276
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.6872825941648416e-09,
+      "loss": 0.8609,
+      "step": 277
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.5117149659454877e-09,
+      "loss": 0.8315,
+      "step": 278
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 6.719109414038416e-10,
+      "loss": 0.8414,
+      "step": 279
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.679833790341201e-10,
+      "loss": 1.1134,
+      "step": 280
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.9774754047393799,
+      "eval_runtime": 1.1258,
+      "eval_samples_per_second": 47.964,
+      "eval_steps_per_second": 23.982,
+      "step": 280
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 0.9491,
+      "step": 281
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 281,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 2.455259734396109e+16,
+  "trial_name": null,
+  "trial_params": null
+}

stealthwriter/dsafsaf/checkpoint-281/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af07f8a65ed126f71edce62e7a398dab92c21ecd8dc3161672f50eadb47eaa35
+size 4475

stealthwriter/dsafsaf/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": "float32",
+  "transformers_version": "4.35.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

stealthwriter/dsafsaf/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.35.0.dev0"
+}

stealthwriter/dsafsaf/pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d3b3719331884697a43230c825540b383f7e255c3dbe1a79c085eaab9b21f52
+size 9886732660

stealthwriter/dsafsaf/pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad55395888283422fec7d6a01e7ffcb216129677d55f0a8e4b93fb5b4b894fde
+size 5121655723

stealthwriter/dsafsaf/pytorch_model.bin.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 15008284672
+  },
+  "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-00002-of-00002.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-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-00002-of-00002.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-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-00002-of-00002.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-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"
+  }
+}

stealthwriter/dsafsaf/special_tokens_map.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "</s>",
+  "unk_token": "<unk>"
+}

stealthwriter/dsafsaf/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

stealthwriter/dsafsaf/tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "tokenizer_file": "/root/.cache/huggingface/hub/models--mistralai--Mistral-7B-v0.1/snapshots/60e27e7bebd4aaf2edf6f4d172346bfc95e2ae40/tokenizer.json",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}

stealthwriter/dsafsaf/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af07f8a65ed126f71edce62e7a398dab92c21ecd8dc3161672f50eadb47eaa35
+size 4475