Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "LangTech-MT/salamandraTA-7b-instruct-WMT25",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.2",
+  "use_cache": true,
+  "vocab_size": 256000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.40.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1449f2ff6bac84dda2a059d7732b7f88cb8eecf4279a4210f57bf12c1f505b6
+size 4982973048

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87fe3d13f9eb376caa32055d17597091578d570f7223b8f41c563c7e5ee804e0
+size 4995660232

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:135591fad45d33091fe6f3eeb39cd1b5b0e1fe897cec26fa75facae0941e8ed6
+size 3460482936

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63d24d6f9ebc2f6eeeea78813c10e14695ecf9eccad494302dd6f2d66276cdae
+size 2097152128

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 15536234496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24478f59c0becedddd0ffccd76fa792d729c72ab727cad5c7d3d09e91a2ae9e8
+size 15688405

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc18ce2d9b7ec559db25711b607b4a3458b212a57c7cedb99f7fd191a32f3dac
+size 4630100

tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "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
+    },
+    "4": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 8192,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,1820 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.99676052828308,
+  "eval_steps": 50,
+  "global_step": 250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00398704211313232,
+      "grad_norm": 9.156251733736836,
+      "learning_rate": 1.25e-08,
+      "loss": 0.4883,
+      "step": 1
+    },
+    {
+      "epoch": 0.00797408422626464,
+      "grad_norm": 7.641311713353261,
+      "learning_rate": 2.5e-08,
+      "loss": 0.4775,
+      "step": 2
+    },
+    {
+      "epoch": 0.01196112633939696,
+      "grad_norm": 7.002160302119551,
+      "learning_rate": 3.75e-08,
+      "loss": 0.5044,
+      "step": 3
+    },
+    {
+      "epoch": 0.01594816845252928,
+      "grad_norm": 7.682635116919073,
+      "learning_rate": 5e-08,
+      "loss": 0.4728,
+      "step": 4
+    },
+    {
+      "epoch": 0.0199352105656616,
+      "grad_norm": 7.579024597234938,
+      "learning_rate": 6.25e-08,
+      "loss": 0.4901,
+      "step": 5
+    },
+    {
+      "epoch": 0.02392225267879392,
+      "grad_norm": 6.218191696817879,
+      "learning_rate": 7.5e-08,
+      "loss": 0.4433,
+      "step": 6
+    },
+    {
+      "epoch": 0.02790929479192624,
+      "grad_norm": 7.684664309310537,
+      "learning_rate": 8.75e-08,
+      "loss": 0.4918,
+      "step": 7
+    },
+    {
+      "epoch": 0.03189633690505856,
+      "grad_norm": 6.608057893845388,
+      "learning_rate": 1e-07,
+      "loss": 0.4526,
+      "step": 8
+    },
+    {
+      "epoch": 0.03588337901819088,
+      "grad_norm": 5.507325619842992,
+      "learning_rate": 9.999578688879085e-08,
+      "loss": 0.424,
+      "step": 9
+    },
+    {
+      "epoch": 0.0398704211313232,
+      "grad_norm": 6.8245248598022386,
+      "learning_rate": 9.998314826517563e-08,
+      "loss": 0.4765,
+      "step": 10
+    },
+    {
+      "epoch": 0.04385746324445552,
+      "grad_norm": 6.559286082311362,
+      "learning_rate": 9.996208625907139e-08,
+      "loss": 0.4719,
+      "step": 11
+    },
+    {
+      "epoch": 0.04784450535758784,
+      "grad_norm": 18.293173957429236,
+      "learning_rate": 9.993260441994115e-08,
+      "loss": 0.4569,
+      "step": 12
+    },
+    {
+      "epoch": 0.05183154747072016,
+      "grad_norm": 7.636755632200349,
+      "learning_rate": 9.989470771619553e-08,
+      "loss": 0.5194,
+      "step": 13
+    },
+    {
+      "epoch": 0.05581858958385248,
+      "grad_norm": 7.522014639042285,
+      "learning_rate": 9.984840253435567e-08,
+      "loss": 0.5358,
+      "step": 14
+    },
+    {
+      "epoch": 0.0598056316969848,
+      "grad_norm": 8.964337975338674,
+      "learning_rate": 9.979369667797675e-08,
+      "loss": 0.4125,
+      "step": 15
+    },
+    {
+      "epoch": 0.06379267381011712,
+      "grad_norm": 6.225184508063474,
+      "learning_rate": 9.973059936633305e-08,
+      "loss": 0.4531,
+      "step": 16
+    },
+    {
+      "epoch": 0.06777971592324944,
+      "grad_norm": 5.936181981049077,
+      "learning_rate": 9.965912123286424e-08,
+      "loss": 0.4585,
+      "step": 17
+    },
+    {
+      "epoch": 0.07176675803638176,
+      "grad_norm": 5.625548455247542,
+      "learning_rate": 9.95792743233833e-08,
+      "loss": 0.4302,
+      "step": 18
+    },
+    {
+      "epoch": 0.07575380014951408,
+      "grad_norm": 7.757674890432492,
+      "learning_rate": 9.949107209404663e-08,
+      "loss": 0.4938,
+      "step": 19
+    },
+    {
+      "epoch": 0.0797408422626464,
+      "grad_norm": 6.185654385562492,
+      "learning_rate": 9.939452940908626e-08,
+      "loss": 0.4376,
+      "step": 20
+    },
+    {
+      "epoch": 0.08372788437577872,
+      "grad_norm": 7.603778678268903,
+      "learning_rate": 9.92896625383049e-08,
+      "loss": 0.506,
+      "step": 21
+    },
+    {
+      "epoch": 0.08771492648891104,
+      "grad_norm": 6.280904505306035,
+      "learning_rate": 9.917648915433412e-08,
+      "loss": 0.4829,
+      "step": 22
+    },
+    {
+      "epoch": 0.09170196860204335,
+      "grad_norm": 8.173842501720133,
+      "learning_rate": 9.905502832965602e-08,
+      "loss": 0.4877,
+      "step": 23
+    },
+    {
+      "epoch": 0.09568901071517567,
+      "grad_norm": 8.162294252031966,
+      "learning_rate": 9.892530053338907e-08,
+      "loss": 0.4594,
+      "step": 24
+    },
+    {
+      "epoch": 0.09967605282830799,
+      "grad_norm": 7.360210086981354,
+      "learning_rate": 9.878732762783859e-08,
+      "loss": 0.456,
+      "step": 25
+    },
+    {
+      "epoch": 0.10366309494144033,
+      "grad_norm": 6.897442170254265,
+      "learning_rate": 9.864113286481236e-08,
+      "loss": 0.4967,
+      "step": 26
+    },
+    {
+      "epoch": 0.10765013705457264,
+      "grad_norm": 6.428986769746803,
+      "learning_rate": 9.848674088170219e-08,
+      "loss": 0.4884,
+      "step": 27
+    },
+    {
+      "epoch": 0.11163717916770496,
+      "grad_norm": 6.004914789770407,
+      "learning_rate": 9.832417769733185e-08,
+      "loss": 0.4481,
+      "step": 28
+    },
+    {
+      "epoch": 0.11562422128083728,
+      "grad_norm": 7.240214554723545,
+      "learning_rate": 9.815347070757231e-08,
+      "loss": 0.4439,
+      "step": 29
+    },
+    {
+      "epoch": 0.1196112633939696,
+      "grad_norm": 5.98579641000705,
+      "learning_rate": 9.797464868072487e-08,
+      "loss": 0.417,
+      "step": 30
+    },
+    {
+      "epoch": 0.12359830550710192,
+      "grad_norm": 9.0662187561823,
+      "learning_rate": 9.778774175267294e-08,
+      "loss": 0.5113,
+      "step": 31
+    },
+    {
+      "epoch": 0.12758534762023424,
+      "grad_norm": 7.341034824460957,
+      "learning_rate": 9.759278142180347e-08,
+      "loss": 0.4678,
+      "step": 32
+    },
+    {
+      "epoch": 0.13157238973336655,
+      "grad_norm": 6.900575078597561,
+      "learning_rate": 9.73898005436987e-08,
+      "loss": 0.451,
+      "step": 33
+    },
+    {
+      "epoch": 0.13555943184649888,
+      "grad_norm": 14.973287755680815,
+      "learning_rate": 9.71788333255991e-08,
+      "loss": 0.5319,
+      "step": 34
+    },
+    {
+      "epoch": 0.1395464739596312,
+      "grad_norm": 5.800184375948775,
+      "learning_rate": 9.695991532063874e-08,
+      "loss": 0.4358,
+      "step": 35
+    },
+    {
+      "epoch": 0.14353351607276352,
+      "grad_norm": 6.438083485206764,
+      "learning_rate": 9.673308342185365e-08,
+      "loss": 0.4978,
+      "step": 36
+    },
+    {
+      "epoch": 0.14752055818589585,
+      "grad_norm": 6.459883801130323,
+      "learning_rate": 9.649837585596444e-08,
+      "loss": 0.4258,
+      "step": 37
+    },
+    {
+      "epoch": 0.15150760029902816,
+      "grad_norm": 5.786060457735028,
+      "learning_rate": 9.625583217693418e-08,
+      "loss": 0.416,
+      "step": 38
+    },
+    {
+      "epoch": 0.1554946424121605,
+      "grad_norm": 6.701075492910882,
+      "learning_rate": 9.600549325930259e-08,
+      "loss": 0.4435,
+      "step": 39
+    },
+    {
+      "epoch": 0.1594816845252928,
+      "grad_norm": 7.743558218731265,
+      "learning_rate": 9.574740129129766e-08,
+      "loss": 0.4825,
+      "step": 40
+    },
+    {
+      "epoch": 0.16346872663842513,
+      "grad_norm": 6.8972929678221195,
+      "learning_rate": 9.548159976772592e-08,
+      "loss": 0.492,
+      "step": 41
+    },
+    {
+      "epoch": 0.16745576875155743,
+      "grad_norm": 7.6561401961084155,
+      "learning_rate": 9.52081334826425e-08,
+      "loss": 0.4899,
+      "step": 42
+    },
+    {
+      "epoch": 0.17144281086468977,
+      "grad_norm": 6.951859004365199,
+      "learning_rate": 9.492704852180226e-08,
+      "loss": 0.5009,
+      "step": 43
+    },
+    {
+      "epoch": 0.17542985297782207,
+      "grad_norm": 7.3380219048694455,
+      "learning_rate": 9.463839225489319e-08,
+      "loss": 0.4509,
+      "step": 44
+    },
+    {
+      "epoch": 0.1794168950909544,
+      "grad_norm": 6.092995009526921,
+      "learning_rate": 9.434221332755338e-08,
+      "loss": 0.4661,
+      "step": 45
+    },
+    {
+      "epoch": 0.1834039372040867,
+      "grad_norm": 6.801272907698648,
+      "learning_rate": 9.403856165317321e-08,
+      "loss": 0.4354,
+      "step": 46
+    },
+    {
+      "epoch": 0.18739097931721904,
+      "grad_norm": 6.237346623374169,
+      "learning_rate": 9.37274884044836e-08,
+      "loss": 0.4531,
+      "step": 47
+    },
+    {
+      "epoch": 0.19137802143035135,
+      "grad_norm": 6.313222762578173,
+      "learning_rate": 9.340904600493219e-08,
+      "loss": 0.5044,
+      "step": 48
+    },
+    {
+      "epoch": 0.19536506354348368,
+      "grad_norm": 5.873552541255695,
+      "learning_rate": 9.308328811984869e-08,
+      "loss": 0.4442,
+      "step": 49
+    },
+    {
+      "epoch": 0.19935210565661599,
+      "grad_norm": 7.106553964788742,
+      "learning_rate": 9.275026964740101e-08,
+      "loss": 0.4773,
+      "step": 50
+    },
+    {
+      "epoch": 0.19935210565661599,
+      "eval_loss": 0.4586050808429718,
+      "eval_runtime": 74.0333,
+      "eval_samples_per_second": 8.753,
+      "eval_steps_per_second": 0.284,
+      "step": 50
+    },
+    {
+      "epoch": 0.20333914776974832,
+      "grad_norm": 6.967997071839054,
+      "learning_rate": 9.241004670934347e-08,
+      "loss": 0.5036,
+      "step": 51
+    },
+    {
+      "epoch": 0.20732618988288065,
+      "grad_norm": 8.096409324272887,
+      "learning_rate": 9.206267664155906e-08,
+      "loss": 0.4417,
+      "step": 52
+    },
+    {
+      "epoch": 0.21131323199601296,
+      "grad_norm": 6.10798394237715,
+      "learning_rate": 9.170821798439683e-08,
+      "loss": 0.4473,
+      "step": 53
+    },
+    {
+      "epoch": 0.2153002741091453,
+      "grad_norm": 7.688633439955139,
+      "learning_rate": 9.134673047280644e-08,
+      "loss": 0.4816,
+      "step": 54
+    },
+    {
+      "epoch": 0.2192873162222776,
+      "grad_norm": 5.734845427093103,
+      "learning_rate": 9.097827502627135e-08,
+      "loss": 0.4268,
+      "step": 55
+    },
+    {
+      "epoch": 0.22327435833540993,
+      "grad_norm": 6.245256812701611,
+      "learning_rate": 9.06029137385425e-08,
+      "loss": 0.4521,
+      "step": 56
+    },
+    {
+      "epoch": 0.22726140044854223,
+      "grad_norm": 7.272601532380688,
+      "learning_rate": 9.022070986717378e-08,
+      "loss": 0.436,
+      "step": 57
+    },
+    {
+      "epoch": 0.23124844256167457,
+      "grad_norm": 9.629444523181556,
+      "learning_rate": 8.983172782286179e-08,
+      "loss": 0.5213,
+      "step": 58
+    },
+    {
+      "epoch": 0.23523548467480687,
+      "grad_norm": 6.820025823061756,
+      "learning_rate": 8.9436033158591e-08,
+      "loss": 0.439,
+      "step": 59
+    },
+    {
+      "epoch": 0.2392225267879392,
+      "grad_norm": 6.177834469326089,
+      "learning_rate": 8.90336925585864e-08,
+      "loss": 0.4357,
+      "step": 60
+    },
+    {
+      "epoch": 0.2432095689010715,
+      "grad_norm": 8.31158953839588,
+      "learning_rate": 8.862477382707567e-08,
+      "loss": 0.4411,
+      "step": 61
+    },
+    {
+      "epoch": 0.24719661101420384,
+      "grad_norm": 6.177344295513886,
+      "learning_rate": 8.820934587686246e-08,
+      "loss": 0.4503,
+      "step": 62
+    },
+    {
+      "epoch": 0.25118365312733615,
+      "grad_norm": 9.227184775907928,
+      "learning_rate": 8.778747871771291e-08,
+      "loss": 0.5161,
+      "step": 63
+    },
+    {
+      "epoch": 0.2551706952404685,
+      "grad_norm": 6.248589728946233,
+      "learning_rate": 8.735924344455732e-08,
+      "loss": 0.42,
+      "step": 64
+    },
+    {
+      "epoch": 0.2591577373536008,
+      "grad_norm": 6.369085651552229,
+      "learning_rate": 8.692471222550886e-08,
+      "loss": 0.4321,
+      "step": 65
+    },
+    {
+      "epoch": 0.2631447794667331,
+      "grad_norm": 8.183071001319046,
+      "learning_rate": 8.64839582897015e-08,
+      "loss": 0.468,
+      "step": 66
+    },
+    {
+      "epoch": 0.2671318215798654,
+      "grad_norm": 9.786250423376547,
+      "learning_rate": 8.603705591494915e-08,
+      "loss": 0.4475,
+      "step": 67
+    },
+    {
+      "epoch": 0.27111886369299776,
+      "grad_norm": 5.904583544720359,
+      "learning_rate": 8.5584080415228e-08,
+      "loss": 0.3876,
+      "step": 68
+    },
+    {
+      "epoch": 0.2751059058061301,
+      "grad_norm": 6.440549410086924,
+      "learning_rate": 8.512510812798425e-08,
+      "loss": 0.4754,
+      "step": 69
+    },
+    {
+      "epoch": 0.2790929479192624,
+      "grad_norm": 6.805238787465053,
+      "learning_rate": 8.466021640126945e-08,
+      "loss": 0.4967,
+      "step": 70
+    },
+    {
+      "epoch": 0.2830799900323947,
+      "grad_norm": 5.8518789643478675,
+      "learning_rate": 8.418948358070535e-08,
+      "loss": 0.4129,
+      "step": 71
+    },
+    {
+      "epoch": 0.28706703214552703,
+      "grad_norm": 5.591004141287658,
+      "learning_rate": 8.371298899628089e-08,
+      "loss": 0.4501,
+      "step": 72
+    },
+    {
+      "epoch": 0.29105407425865937,
+      "grad_norm": 6.383984024537941,
+      "learning_rate": 8.323081294898307e-08,
+      "loss": 0.4334,
+      "step": 73
+    },
+    {
+      "epoch": 0.2950411163717917,
+      "grad_norm": 7.65193355223154,
+      "learning_rate": 8.274303669726426e-08,
+      "loss": 0.4322,
+      "step": 74
+    },
+    {
+      "epoch": 0.299028158484924,
+      "grad_norm": 7.432846175631774,
+      "learning_rate": 8.224974244334819e-08,
+      "loss": 0.4203,
+      "step": 75
+    },
+    {
+      "epoch": 0.3030152005980563,
+      "grad_norm": 5.998680272532642,
+      "learning_rate": 8.175101331937692e-08,
+      "loss": 0.4772,
+      "step": 76
+    },
+    {
+      "epoch": 0.30700224271118864,
+      "grad_norm": 5.709515594337801,
+      "learning_rate": 8.124693337340092e-08,
+      "loss": 0.4484,
+      "step": 77
+    },
+    {
+      "epoch": 0.310989284824321,
+      "grad_norm": 6.070249615204831,
+      "learning_rate": 8.073758755521505e-08,
+      "loss": 0.408,
+      "step": 78
+    },
+    {
+      "epoch": 0.31497632693745325,
+      "grad_norm": 7.069861563685416,
+      "learning_rate": 8.022306170204232e-08,
+      "loss": 0.411,
+      "step": 79
+    },
+    {
+      "epoch": 0.3189633690505856,
+      "grad_norm": 7.291042948678751,
+      "learning_rate": 7.970344252406831e-08,
+      "loss": 0.4839,
+      "step": 80
+    },
+    {
+      "epoch": 0.3229504111637179,
+      "grad_norm": 5.763308674592348,
+      "learning_rate": 7.917881758982836e-08,
+      "loss": 0.4621,
+      "step": 81
+    },
+    {
+      "epoch": 0.32693745327685025,
+      "grad_norm": 6.467826281866634,
+      "learning_rate": 7.864927531145011e-08,
+      "loss": 0.4552,
+      "step": 82
+    },
+    {
+      "epoch": 0.33092449538998253,
+      "grad_norm": 6.1366597047122236,
+      "learning_rate": 7.811490492975388e-08,
+      "loss": 0.4746,
+      "step": 83
+    },
+    {
+      "epoch": 0.33491153750311486,
+      "grad_norm": 6.032584302942195,
+      "learning_rate": 7.757579649921353e-08,
+      "loss": 0.434,
+      "step": 84
+    },
+    {
+      "epoch": 0.3388985796162472,
+      "grad_norm": 5.47794186471486,
+      "learning_rate": 7.703204087277987e-08,
+      "loss": 0.4403,
+      "step": 85
+    },
+    {
+      "epoch": 0.34288562172937953,
+      "grad_norm": 5.788504517476067,
+      "learning_rate": 7.648372968656994e-08,
+      "loss": 0.4432,
+      "step": 86
+    },
+    {
+      "epoch": 0.34687266384251186,
+      "grad_norm": 6.195478107211373,
+      "learning_rate": 7.593095534442386e-08,
+      "loss": 0.4691,
+      "step": 87
+    },
+    {
+      "epoch": 0.35085970595564414,
+      "grad_norm": 6.126101446046475,
+      "learning_rate": 7.537381100233278e-08,
+      "loss": 0.459,
+      "step": 88
+    },
+    {
+      "epoch": 0.3548467480687765,
+      "grad_norm": 6.455608974982698,
+      "learning_rate": 7.481239055273958e-08,
+      "loss": 0.4369,
+      "step": 89
+    },
+    {
+      "epoch": 0.3588337901819088,
+      "grad_norm": 5.579414423937279,
+      "learning_rate": 7.424678860871584e-08,
+      "loss": 0.4327,
+      "step": 90
+    },
+    {
+      "epoch": 0.36282083229504114,
+      "grad_norm": 7.383102739034827,
+      "learning_rate": 7.367710048801714e-08,
+      "loss": 0.5042,
+      "step": 91
+    },
+    {
+      "epoch": 0.3668078744081734,
+      "grad_norm": 7.937650460146875,
+      "learning_rate": 7.310342219701981e-08,
+      "loss": 0.4871,
+      "step": 92
+    },
+    {
+      "epoch": 0.37079491652130575,
+      "grad_norm": 6.314159698490653,
+      "learning_rate": 7.252585041454133e-08,
+      "loss": 0.4621,
+      "step": 93
+    },
+    {
+      "epoch": 0.3747819586344381,
+      "grad_norm": 8.30863265469435,
+      "learning_rate": 7.194448247554779e-08,
+      "loss": 0.4854,
+      "step": 94
+    },
+    {
+      "epoch": 0.3787690007475704,
+      "grad_norm": 6.103806645227341,
+      "learning_rate": 7.135941635475035e-08,
+      "loss": 0.4236,
+      "step": 95
+    },
+    {
+      "epoch": 0.3827560428607027,
+      "grad_norm": 9.149650017070357,
+      "learning_rate": 7.077075065009432e-08,
+      "loss": 0.5252,
+      "step": 96
+    },
+    {
+      "epoch": 0.386743084973835,
+      "grad_norm": 7.023660801901896,
+      "learning_rate": 7.017858456614283e-08,
+      "loss": 0.4392,
+      "step": 97
+    },
+    {
+      "epoch": 0.39073012708696736,
+      "grad_norm": 7.556140735712405,
+      "learning_rate": 6.958301789735851e-08,
+      "loss": 0.4196,
+      "step": 98
+    },
+    {
+      "epoch": 0.3947171692000997,
+      "grad_norm": 6.190622774872339,
+      "learning_rate": 6.898415101128569e-08,
+      "loss": 0.4762,
+      "step": 99
+    },
+    {
+      "epoch": 0.39870421131323197,
+      "grad_norm": 5.855755304308857,
+      "learning_rate": 6.8382084831636e-08,
+      "loss": 0.4178,
+      "step": 100
+    },
+    {
+      "epoch": 0.39870421131323197,
+      "eval_loss": 0.451620876789093,
+      "eval_runtime": 71.2114,
+      "eval_samples_per_second": 9.1,
+      "eval_steps_per_second": 0.295,
+      "step": 100
+    },
+    {
+      "epoch": 0.4026912534263643,
+      "grad_norm": 6.634837933711567,
+      "learning_rate": 6.777692082128023e-08,
+      "loss": 0.4868,
+      "step": 101
+    },
+    {
+      "epoch": 0.40667829553949664,
+      "grad_norm": 6.078481988795218,
+      "learning_rate": 6.716876096514943e-08,
+      "loss": 0.4958,
+      "step": 102
+    },
+    {
+      "epoch": 0.41066533765262897,
+      "grad_norm": 5.7682757622510135,
+      "learning_rate": 6.655770775304781e-08,
+      "loss": 0.4383,
+      "step": 103
+    },
+    {
+      "epoch": 0.4146523797657613,
+      "grad_norm": 11.318580322443957,
+      "learning_rate": 6.594386416238094e-08,
+      "loss": 0.4559,
+      "step": 104
+    },
+    {
+      "epoch": 0.4186394218788936,
+      "grad_norm": 8.18670651005329,
+      "learning_rate": 6.532733364080125e-08,
+      "loss": 0.4779,
+      "step": 105
+    },
+    {
+      "epoch": 0.4226264639920259,
+      "grad_norm": 7.3687772760874894,
+      "learning_rate": 6.470822008877481e-08,
+      "loss": 0.5323,
+      "step": 106
+    },
+    {
+      "epoch": 0.42661350610515825,
+      "grad_norm": 6.665381490491506,
+      "learning_rate": 6.408662784207149e-08,
+      "loss": 0.4505,
+      "step": 107
+    },
+    {
+      "epoch": 0.4306005482182906,
+      "grad_norm": 7.397695469825138,
+      "learning_rate": 6.346266165418172e-08,
+      "loss": 0.4419,
+      "step": 108
+    },
+    {
+      "epoch": 0.43458759033142286,
+      "grad_norm": 6.593718700219311,
+      "learning_rate": 6.283642667866316e-08,
+      "loss": 0.4784,
+      "step": 109
+    },
+    {
+      "epoch": 0.4385746324445552,
+      "grad_norm": 6.969250878148417,
+      "learning_rate": 6.220802845141957e-08,
+      "loss": 0.4487,
+      "step": 110
+    },
+    {
+      "epoch": 0.4425616745576875,
+      "grad_norm": 6.425017285535306,
+      "learning_rate": 6.157757287291557e-08,
+      "loss": 0.4498,
+      "step": 111
+    },
+    {
+      "epoch": 0.44654871667081986,
+      "grad_norm": 5.931276261231684,
+      "learning_rate": 6.094516619032975e-08,
+      "loss": 0.4192,
+      "step": 112
+    },
+    {
+      "epoch": 0.45053575878395213,
+      "grad_norm": 7.282499472024417,
+      "learning_rate": 6.031091497964941e-08,
+      "loss": 0.4705,
+      "step": 113
+    },
+    {
+      "epoch": 0.45452280089708447,
+      "grad_norm": 7.974555690697716,
+      "learning_rate": 5.967492612770998e-08,
+      "loss": 0.4848,
+      "step": 114
+    },
+    {
+      "epoch": 0.4585098430102168,
+      "grad_norm": 5.899114666728763,
+      "learning_rate": 5.90373068141819e-08,
+      "loss": 0.4307,
+      "step": 115
+    },
+    {
+      "epoch": 0.46249688512334913,
+      "grad_norm": 6.949922519818543,
+      "learning_rate": 5.839816449350824e-08,
+      "loss": 0.5115,
+      "step": 116
+    },
+    {
+      "epoch": 0.4664839272364814,
+      "grad_norm": 7.353840987209537,
+      "learning_rate": 5.775760687679603e-08,
+      "loss": 0.4934,
+      "step": 117
+    },
+    {
+      "epoch": 0.47047096934961374,
+      "grad_norm": 10.638106782489997,
+      "learning_rate": 5.711574191366426e-08,
+      "loss": 0.4256,
+      "step": 118
+    },
+    {
+      "epoch": 0.4744580114627461,
+      "grad_norm": 7.3437459089418535,
+      "learning_rate": 5.6472677774051766e-08,
+      "loss": 0.4771,
+      "step": 119
+    },
+    {
+      "epoch": 0.4784450535758784,
+      "grad_norm": 7.15321029976221,
+      "learning_rate": 5.5828522829987954e-08,
+      "loss": 0.5154,
+      "step": 120
+    },
+    {
+      "epoch": 0.48243209568901074,
+      "grad_norm": 8.624790811132232,
+      "learning_rate": 5.518338563732944e-08,
+      "loss": 0.4676,
+      "step": 121
+    },
+    {
+      "epoch": 0.486419137802143,
+      "grad_norm": 7.686541239358104,
+      "learning_rate": 5.4537374917465716e-08,
+      "loss": 0.4823,
+      "step": 122
+    },
+    {
+      "epoch": 0.49040617991527535,
+      "grad_norm": 6.3457601519701505,
+      "learning_rate": 5.3890599538996986e-08,
+      "loss": 0.4427,
+      "step": 123
+    },
+    {
+      "epoch": 0.4943932220284077,
+      "grad_norm": 6.991058776760594,
+      "learning_rate": 5.324316849938715e-08,
+      "loss": 0.4346,
+      "step": 124
+    },
+    {
+      "epoch": 0.49838026414154,
+      "grad_norm": 5.395012920850842,
+      "learning_rate": 5.259519090659499e-08,
+      "loss": 0.4408,
+      "step": 125
+    },
+    {
+      "epoch": 0.5023673062546723,
+      "grad_norm": 5.982705058259003,
+      "learning_rate": 5.194677596068688e-08,
+      "loss": 0.4828,
+      "step": 126
+    },
+    {
+      "epoch": 0.5063543483678047,
+      "grad_norm": 8.574025377323938,
+      "learning_rate": 5.129803293543391e-08,
+      "loss": 0.4323,
+      "step": 127
+    },
+    {
+      "epoch": 0.510341390480937,
+      "grad_norm": 6.58817373093353,
+      "learning_rate": 5.064907115989654e-08,
+      "loss": 0.4435,
+      "step": 128
+    },
+    {
+      "epoch": 0.5143284325940692,
+      "grad_norm": 6.832974722448896,
+      "learning_rate": 5e-08,
+      "loss": 0.5096,
+      "step": 129
+    },
+    {
+      "epoch": 0.5183154747072016,
+      "grad_norm": 9.623478197855597,
+      "learning_rate": 4.935092884010346e-08,
+      "loss": 0.4912,
+      "step": 130
+    },
+    {
+      "epoch": 0.5223025168203339,
+      "grad_norm": 7.930616120262299,
+      "learning_rate": 4.870196706456609e-08,
+      "loss": 0.4523,
+      "step": 131
+    },
+    {
+      "epoch": 0.5262895589334662,
+      "grad_norm": 7.438161560711993,
+      "learning_rate": 4.8053224039313114e-08,
+      "loss": 0.4531,
+      "step": 132
+    },
+    {
+      "epoch": 0.5302766010465986,
+      "grad_norm": 5.880279746532505,
+      "learning_rate": 4.740480909340502e-08,
+      "loss": 0.432,
+      "step": 133
+    },
+    {
+      "epoch": 0.5342636431597308,
+      "grad_norm": 5.9432376747466815,
+      "learning_rate": 4.6756831500612845e-08,
+      "loss": 0.4644,
+      "step": 134
+    },
+    {
+      "epoch": 0.5382506852728632,
+      "grad_norm": 5.371491126921796,
+      "learning_rate": 4.6109400461003e-08,
+      "loss": 0.429,
+      "step": 135
+    },
+    {
+      "epoch": 0.5422377273859955,
+      "grad_norm": 6.705749074478807,
+      "learning_rate": 4.5462625082534286e-08,
+      "loss": 0.4707,
+      "step": 136
+    },
+    {
+      "epoch": 0.5462247694991278,
+      "grad_norm": 5.571838061264798,
+      "learning_rate": 4.481661436267057e-08,
+      "loss": 0.4346,
+      "step": 137
+    },
+    {
+      "epoch": 0.5502118116122602,
+      "grad_norm": 7.292744461604267,
+      "learning_rate": 4.417147717001205e-08,
+      "loss": 0.5073,
+      "step": 138
+    },
+    {
+      "epoch": 0.5541988537253925,
+      "grad_norm": 9.152628243132607,
+      "learning_rate": 4.352732222594823e-08,
+      "loss": 0.4785,
+      "step": 139
+    },
+    {
+      "epoch": 0.5581858958385248,
+      "grad_norm": 6.1245576630803615,
+      "learning_rate": 4.2884258086335744e-08,
+      "loss": 0.4526,
+      "step": 140
+    },
+    {
+      "epoch": 0.5621729379516571,
+      "grad_norm": 6.372308445858203,
+      "learning_rate": 4.2242393123203984e-08,
+      "loss": 0.4091,
+      "step": 141
+    },
+    {
+      "epoch": 0.5661599800647894,
+      "grad_norm": 7.278650459118112,
+      "learning_rate": 4.160183550649175e-08,
+      "loss": 0.4541,
+      "step": 142
+    },
+    {
+      "epoch": 0.5701470221779218,
+      "grad_norm": 8.227128993696317,
+      "learning_rate": 4.0962693185818097e-08,
+      "loss": 0.425,
+      "step": 143
+    },
+    {
+      "epoch": 0.5741340642910541,
+      "grad_norm": 7.281260137701505,
+      "learning_rate": 4.032507387229002e-08,
+      "loss": 0.4514,
+      "step": 144
+    },
+    {
+      "epoch": 0.5781211064041863,
+      "grad_norm": 7.064444624899644,
+      "learning_rate": 3.96890850203506e-08,
+      "loss": 0.4687,
+      "step": 145
+    },
+    {
+      "epoch": 0.5821081485173187,
+      "grad_norm": 5.363543175646636,
+      "learning_rate": 3.905483380967026e-08,
+      "loss": 0.4029,
+      "step": 146
+    },
+    {
+      "epoch": 0.586095190630451,
+      "grad_norm": 5.856056039846867,
+      "learning_rate": 3.8422427127084435e-08,
+      "loss": 0.4749,
+      "step": 147
+    },
+    {
+      "epoch": 0.5900822327435834,
+      "grad_norm": 6.703738095783274,
+      "learning_rate": 3.779197154858044e-08,
+      "loss": 0.4276,
+      "step": 148
+    },
+    {
+      "epoch": 0.5940692748567157,
+      "grad_norm": 6.725204430528758,
+      "learning_rate": 3.716357332133686e-08,
+      "loss": 0.4879,
+      "step": 149
+    },
+    {
+      "epoch": 0.598056316969848,
+      "grad_norm": 6.379137493700261,
+      "learning_rate": 3.653733834581827e-08,
+      "loss": 0.4741,
+      "step": 150
+    },
+    {
+      "epoch": 0.598056316969848,
+      "eval_loss": 0.4493350684642792,
+      "eval_runtime": 75.7844,
+      "eval_samples_per_second": 8.551,
+      "eval_steps_per_second": 0.277,
+      "step": 150
+    },
+    {
+      "epoch": 0.6020433590829803,
+      "grad_norm": 7.605686837342965,
+      "learning_rate": 3.591337215792851e-08,
+      "loss": 0.442,
+      "step": 151
+    },
+    {
+      "epoch": 0.6060304011961126,
+      "grad_norm": 8.054167249209286,
+      "learning_rate": 3.529177991122518e-08,
+      "loss": 0.4425,
+      "step": 152
+    },
+    {
+      "epoch": 0.6100174433092449,
+      "grad_norm": 6.386288879010119,
+      "learning_rate": 3.4672666359198756e-08,
+      "loss": 0.4117,
+      "step": 153
+    },
+    {
+      "epoch": 0.6140044854223773,
+      "grad_norm": 6.590700921329393,
+      "learning_rate": 3.4056135837619073e-08,
+      "loss": 0.4691,
+      "step": 154
+    },
+    {
+      "epoch": 0.6179915275355096,
+      "grad_norm": 6.163593340870665,
+      "learning_rate": 3.344229224695219e-08,
+      "loss": 0.4349,
+      "step": 155
+    },
+    {
+      "epoch": 0.621978569648642,
+      "grad_norm": 7.195642036099686,
+      "learning_rate": 3.2831239034850586e-08,
+      "loss": 0.5294,
+      "step": 156
+    },
+    {
+      "epoch": 0.6259656117617742,
+      "grad_norm": 6.6941825252478315,
+      "learning_rate": 3.222307917871977e-08,
+      "loss": 0.4236,
+      "step": 157
+    },
+    {
+      "epoch": 0.6299526538749065,
+      "grad_norm": 5.406905917797537,
+      "learning_rate": 3.161791516836399e-08,
+      "loss": 0.4197,
+      "step": 158
+    },
+    {
+      "epoch": 0.6339396959880389,
+      "grad_norm": 6.706505833720426,
+      "learning_rate": 3.1015848988714305e-08,
+      "loss": 0.4241,
+      "step": 159
+    },
+    {
+      "epoch": 0.6379267381011712,
+      "grad_norm": 5.375636850013274,
+      "learning_rate": 3.041698210264149e-08,
+      "loss": 0.4366,
+      "step": 160
+    },
+    {
+      "epoch": 0.6419137802143036,
+      "grad_norm": 9.383381904933621,
+      "learning_rate": 2.9821415433857174e-08,
+      "loss": 0.4818,
+      "step": 161
+    },
+    {
+      "epoch": 0.6459008223274358,
+      "grad_norm": 6.8119146688206245,
+      "learning_rate": 2.9229249349905684e-08,
+      "loss": 0.4864,
+      "step": 162
+    },
+    {
+      "epoch": 0.6498878644405681,
+      "grad_norm": 5.45280687790607,
+      "learning_rate": 2.864058364524964e-08,
+      "loss": 0.4284,
+      "step": 163
+    },
+    {
+      "epoch": 0.6538749065537005,
+      "grad_norm": 13.604366869502437,
+      "learning_rate": 2.8055517524452217e-08,
+      "loss": 0.4379,
+      "step": 164
+    },
+    {
+      "epoch": 0.6578619486668328,
+      "grad_norm": 7.716259519393842,
+      "learning_rate": 2.747414958545866e-08,
+      "loss": 0.4654,
+      "step": 165
+    },
+    {
+      "epoch": 0.6618489907799651,
+      "grad_norm": 5.988651381092336,
+      "learning_rate": 2.6896577802980186e-08,
+      "loss": 0.4456,
+      "step": 166
+    },
+    {
+      "epoch": 0.6658360328930975,
+      "grad_norm": 5.338443815582462,
+      "learning_rate": 2.632289951198285e-08,
+      "loss": 0.4385,
+      "step": 167
+    },
+    {
+      "epoch": 0.6698230750062297,
+      "grad_norm": 6.004227776146297,
+      "learning_rate": 2.575321139128417e-08,
+      "loss": 0.463,
+      "step": 168
+    },
+    {
+      "epoch": 0.6738101171193621,
+      "grad_norm": 6.299737418389095,
+      "learning_rate": 2.5187609447260417e-08,
+      "loss": 0.4082,
+      "step": 169
+    },
+    {
+      "epoch": 0.6777971592324944,
+      "grad_norm": 7.271307907461702,
+      "learning_rate": 2.4626188997667217e-08,
+      "loss": 0.4921,
+      "step": 170
+    },
+    {
+      "epoch": 0.6817842013456267,
+      "grad_norm": 5.592644829878934,
+      "learning_rate": 2.4069044655576138e-08,
+      "loss": 0.4465,
+      "step": 171
+    },
+    {
+      "epoch": 0.6857712434587591,
+      "grad_norm": 6.367424972175415,
+      "learning_rate": 2.351627031343008e-08,
+      "loss": 0.45,
+      "step": 172
+    },
+    {
+      "epoch": 0.6897582855718913,
+      "grad_norm": 7.504229989072114,
+      "learning_rate": 2.2967959127220138e-08,
+      "loss": 0.4565,
+      "step": 173
+    },
+    {
+      "epoch": 0.6937453276850237,
+      "grad_norm": 5.828403856391156,
+      "learning_rate": 2.242420350078647e-08,
+      "loss": 0.4435,
+      "step": 174
+    },
+    {
+      "epoch": 0.697732369798156,
+      "grad_norm": 7.84838040158763,
+      "learning_rate": 2.188509507024611e-08,
+      "loss": 0.4581,
+      "step": 175
+    },
+    {
+      "epoch": 0.7017194119112883,
+      "grad_norm": 5.989208514187919,
+      "learning_rate": 2.1350724688549905e-08,
+      "loss": 0.4286,
+      "step": 176
+    },
+    {
+      "epoch": 0.7057064540244207,
+      "grad_norm": 8.851899840133688,
+      "learning_rate": 2.0821182410171635e-08,
+      "loss": 0.533,
+      "step": 177
+    },
+    {
+      "epoch": 0.709693496137553,
+      "grad_norm": 7.042686599938601,
+      "learning_rate": 2.0296557475931687e-08,
+      "loss": 0.4555,
+      "step": 178
+    },
+    {
+      "epoch": 0.7136805382506852,
+      "grad_norm": 7.298487782307313,
+      "learning_rate": 1.9776938297957685e-08,
+      "loss": 0.4469,
+      "step": 179
+    },
+    {
+      "epoch": 0.7176675803638176,
+      "grad_norm": 6.536161176333382,
+      "learning_rate": 1.9262412444784958e-08,
+      "loss": 0.48,
+      "step": 180
+    },
+    {
+      "epoch": 0.7216546224769499,
+      "grad_norm": 6.246356987647083,
+      "learning_rate": 1.8753066626599085e-08,
+      "loss": 0.4321,
+      "step": 181
+    },
+    {
+      "epoch": 0.7256416645900823,
+      "grad_norm": 6.501572611291869,
+      "learning_rate": 1.8248986680623073e-08,
+      "loss": 0.449,
+      "step": 182
+    },
+    {
+      "epoch": 0.7296287067032146,
+      "grad_norm": 6.27753282110284,
+      "learning_rate": 1.7750257556651805e-08,
+      "loss": 0.4549,
+      "step": 183
+    },
+    {
+      "epoch": 0.7336157488163468,
+      "grad_norm": 6.067180972256904,
+      "learning_rate": 1.725696330273575e-08,
+      "loss": 0.4093,
+      "step": 184
+    },
+    {
+      "epoch": 0.7376027909294792,
+      "grad_norm": 6.586415133603967,
+      "learning_rate": 1.676918705101693e-08,
+      "loss": 0.4455,
+      "step": 185
+    },
+    {
+      "epoch": 0.7415898330426115,
+      "grad_norm": 6.7332751793041,
+      "learning_rate": 1.6287011003719102e-08,
+      "loss": 0.4794,
+      "step": 186
+    },
+    {
+      "epoch": 0.7455768751557438,
+      "grad_norm": 6.0276428665863095,
+      "learning_rate": 1.581051641929465e-08,
+      "loss": 0.4488,
+      "step": 187
+    },
+    {
+      "epoch": 0.7495639172688762,
+      "grad_norm": 6.677120251131567,
+      "learning_rate": 1.5339783598730567e-08,
+      "loss": 0.4383,
+      "step": 188
+    },
+    {
+      "epoch": 0.7535509593820084,
+      "grad_norm": 8.067179235763694,
+      "learning_rate": 1.4874891872015732e-08,
+      "loss": 0.4711,
+      "step": 189
+    },
+    {
+      "epoch": 0.7575380014951408,
+      "grad_norm": 6.777077403070564,
+      "learning_rate": 1.4415919584771996e-08,
+      "loss": 0.4544,
+      "step": 190
+    },
+    {
+      "epoch": 0.7615250436082731,
+      "grad_norm": 8.311380616014057,
+      "learning_rate": 1.3962944085050832e-08,
+      "loss": 0.4586,
+      "step": 191
+    },
+    {
+      "epoch": 0.7655120857214054,
+      "grad_norm": 7.365330627154824,
+      "learning_rate": 1.3516041710298498e-08,
+      "loss": 0.4942,
+      "step": 192
+    },
+    {
+      "epoch": 0.7694991278345378,
+      "grad_norm": 6.500787198774549,
+      "learning_rate": 1.3075287774491145e-08,
+      "loss": 0.4559,
+      "step": 193
+    },
+    {
+      "epoch": 0.77348616994767,
+      "grad_norm": 7.436601926479534,
+      "learning_rate": 1.2640756555442683e-08,
+      "loss": 0.4728,
+      "step": 194
+    },
+    {
+      "epoch": 0.7774732120608024,
+      "grad_norm": 7.925458730363356,
+      "learning_rate": 1.2212521282287091e-08,
+      "loss": 0.4496,
+      "step": 195
+    },
+    {
+      "epoch": 0.7814602541739347,
+      "grad_norm": 6.648877237056558,
+      "learning_rate": 1.179065412313755e-08,
+      "loss": 0.4859,
+      "step": 196
+    },
+    {
+      "epoch": 0.785447296287067,
+      "grad_norm": 6.675351215173198,
+      "learning_rate": 1.137522617292434e-08,
+      "loss": 0.4467,
+      "step": 197
+    },
+    {
+      "epoch": 0.7894343384001994,
+      "grad_norm": 5.563909781426479,
+      "learning_rate": 1.0966307441413597e-08,
+      "loss": 0.4429,
+      "step": 198
+    },
+    {
+      "epoch": 0.7934213805133317,
+      "grad_norm": 6.9266683327552006,
+      "learning_rate": 1.0563966841408994e-08,
+      "loss": 0.4413,
+      "step": 199
+    },
+    {
+      "epoch": 0.7974084226264639,
+      "grad_norm": 6.537815958619651,
+      "learning_rate": 1.0168272177138198e-08,
+      "loss": 0.4346,
+      "step": 200
+    },
+    {
+      "epoch": 0.7974084226264639,
+      "eval_loss": 0.4485699236392975,
+      "eval_runtime": 76.202,
+      "eval_samples_per_second": 8.504,
+      "eval_steps_per_second": 0.276,
+      "step": 200
+    },
+    {
+      "epoch": 0.8013954647395963,
+      "grad_norm": 7.4693962701161105,
+      "learning_rate": 9.779290132826223e-09,
+      "loss": 0.3963,
+      "step": 201
+    },
+    {
+      "epoch": 0.8053825068527286,
+      "grad_norm": 5.517945803547769,
+      "learning_rate": 9.39708626145751e-09,
+      "loss": 0.4022,
+      "step": 202
+    },
+    {
+      "epoch": 0.809369548965861,
+      "grad_norm": 7.349665612759144,
+      "learning_rate": 9.021724973728634e-09,
+      "loss": 0.4368,
+      "step": 203
+    },
+    {
+      "epoch": 0.8133565910789933,
+      "grad_norm": 6.946233079984625,
+      "learning_rate": 8.653269527193569e-09,
+      "loss": 0.4391,
+      "step": 204
+    },
+    {
+      "epoch": 0.8173436331921256,
+      "grad_norm": 6.693142374031141,
+      "learning_rate": 8.291782015603176e-09,
+      "loss": 0.4612,
+      "step": 205
+    },
+    {
+      "epoch": 0.8213306753052579,
+      "grad_norm": 5.83420175163265,
+      "learning_rate": 7.937323358440933e-09,
+      "loss": 0.4715,
+      "step": 206
+    },
+    {
+      "epoch": 0.8253177174183902,
+      "grad_norm": 7.069096436199669,
+      "learning_rate": 7.58995329065653e-09,
+      "loss": 0.4213,
+      "step": 207
+    },
+    {
+      "epoch": 0.8293047595315226,
+      "grad_norm": 6.668905267480719,
+      "learning_rate": 7.249730352598999e-09,
+      "loss": 0.4861,
+      "step": 208
+    },
+    {
+      "epoch": 0.8332918016446549,
+      "grad_norm": 6.104057412693027,
+      "learning_rate": 6.916711880151305e-09,
+      "loss": 0.4423,
+      "step": 209
+    },
+    {
+      "epoch": 0.8372788437577872,
+      "grad_norm": 6.841749749760555,
+      "learning_rate": 6.59095399506781e-09,
+      "loss": 0.4773,
+      "step": 210
+    },
+    {
+      "epoch": 0.8412658858709195,
+      "grad_norm": 5.9626508834983944,
+      "learning_rate": 6.2725115955164e-09,
+      "loss": 0.4532,
+      "step": 211
+    },
+    {
+      "epoch": 0.8452529279840518,
+      "grad_norm": 6.019796949536336,
+      "learning_rate": 5.9614383468267916e-09,
+      "loss": 0.5179,
+      "step": 212
+    },
+    {
+      "epoch": 0.8492399700971841,
+      "grad_norm": 10.406714794262832,
+      "learning_rate": 5.6577866724466295e-09,
+      "loss": 0.4899,
+      "step": 213
+    },
+    {
+      "epoch": 0.8532270122103165,
+      "grad_norm": 6.150289346178211,
+      "learning_rate": 5.3616077451068166e-09,
+      "loss": 0.4298,
+      "step": 214
+    },
+    {
+      "epoch": 0.8572140543234488,
+      "grad_norm": 7.4191763083819025,
+      "learning_rate": 5.072951478197723e-09,
+      "loss": 0.4836,
+      "step": 215
+    },
+    {
+      "epoch": 0.8612010964365812,
+      "grad_norm": 6.1119960010157595,
+      "learning_rate": 4.79186651735749e-09,
+      "loss": 0.4593,
+      "step": 216
+    },
+    {
+      "epoch": 0.8651881385497134,
+      "grad_norm": 6.333977298951743,
+      "learning_rate": 4.5184002322740775e-09,
+      "loss": 0.4548,
+      "step": 217
+    },
+    {
+      "epoch": 0.8691751806628457,
+      "grad_norm": 8.87758962797358,
+      "learning_rate": 4.252598708702343e-09,
+      "loss": 0.4525,
+      "step": 218
+    },
+    {
+      "epoch": 0.8731622227759781,
+      "grad_norm": 6.438508677158466,
+      "learning_rate": 3.994506740697406e-09,
+      "loss": 0.4509,
+      "step": 219
+    },
+    {
+      "epoch": 0.8771492648891104,
+      "grad_norm": 5.76307692763536,
+      "learning_rate": 3.744167823065814e-09,
+      "loss": 0.4175,
+      "step": 220
+    },
+    {
+      "epoch": 0.8811363070022427,
+      "grad_norm": 7.669151784950902,
+      "learning_rate": 3.5016241440355586e-09,
+      "loss": 0.4992,
+      "step": 221
+    },
+    {
+      "epoch": 0.885123349115375,
+      "grad_norm": 8.018295215720205,
+      "learning_rate": 3.2669165781463393e-09,
+      "loss": 0.512,
+      "step": 222
+    },
+    {
+      "epoch": 0.8891103912285073,
+      "grad_norm": 7.259097463453489,
+      "learning_rate": 3.0400846793612543e-09,
+      "loss": 0.5463,
+      "step": 223
+    },
+    {
+      "epoch": 0.8930974333416397,
+      "grad_norm": 5.8574975302337835,
+      "learning_rate": 2.8211666744009044e-09,
+      "loss": 0.4137,
+      "step": 224
+    },
+    {
+      "epoch": 0.897084475454772,
+      "grad_norm": 6.320630337402214,
+      "learning_rate": 2.6101994563013095e-09,
+      "loss": 0.4451,
+      "step": 225
+    },
+    {
+      "epoch": 0.9010715175679043,
+      "grad_norm": 6.105492797379247,
+      "learning_rate": 2.407218578196524e-09,
+      "loss": 0.4613,
+      "step": 226
+    },
+    {
+      "epoch": 0.9050585596810367,
+      "grad_norm": 5.314977694335711,
+      "learning_rate": 2.212258247327059e-09,
+      "loss": 0.4284,
+      "step": 227
+    },
+    {
+      "epoch": 0.9090456017941689,
+      "grad_norm": 6.368859438455821,
+      "learning_rate": 2.025351319275137e-09,
+      "loss": 0.4289,
+      "step": 228
+    },
+    {
+      "epoch": 0.9130326439073013,
+      "grad_norm": 6.77904205932906,
+      "learning_rate": 1.8465292924276843e-09,
+      "loss": 0.4157,
+      "step": 229
+    },
+    {
+      "epoch": 0.9170196860204336,
+      "grad_norm": 6.822595436793625,
+      "learning_rate": 1.6758223026681507e-09,
+      "loss": 0.419,
+      "step": 230
+    },
+    {
+      "epoch": 0.9210067281335659,
+      "grad_norm": 7.1866614302952385,
+      "learning_rate": 1.5132591182978106e-09,
+      "loss": 0.4561,
+      "step": 231
+    },
+    {
+      "epoch": 0.9249937702466983,
+      "grad_norm": 5.230743591364083,
+      "learning_rate": 1.3588671351876358e-09,
+      "loss": 0.4377,
+      "step": 232
+    },
+    {
+      "epoch": 0.9289808123598305,
+      "grad_norm": 6.900580375387765,
+      "learning_rate": 1.212672372161405e-09,
+      "loss": 0.4413,
+      "step": 233
+    },
+    {
+      "epoch": 0.9329678544729628,
+      "grad_norm": 7.585412803106988,
+      "learning_rate": 1.0746994666109233e-09,
+      "loss": 0.4735,
+      "step": 234
+    },
+    {
+      "epoch": 0.9369548965860952,
+      "grad_norm": 8.167127844205128,
+      "learning_rate": 9.449716703439803e-10,
+      "loss": 0.4883,
+      "step": 235
+    },
+    {
+      "epoch": 0.9409419386992275,
+      "grad_norm": 5.9559564289019615,
+      "learning_rate": 8.235108456658812e-10,
+      "loss": 0.4494,
+      "step": 236
+    },
+    {
+      "epoch": 0.9449289808123599,
+      "grad_norm": 6.549740564564768,
+      "learning_rate": 7.103374616951041e-10,
+      "loss": 0.438,
+      "step": 237
+    },
+    {
+      "epoch": 0.9489160229254922,
+      "grad_norm": 5.986607697957542,
+      "learning_rate": 6.054705909137425e-10,
+      "loss": 0.4474,
+      "step": 238
+    },
+    {
+      "epoch": 0.9529030650386244,
+      "grad_norm": 5.415909364361658,
+      "learning_rate": 5.089279059533658e-10,
+      "loss": 0.5038,
+      "step": 239
+    },
+    {
+      "epoch": 0.9568901071517568,
+      "grad_norm": 6.59487853417713,
+      "learning_rate": 4.2072567661668446e-10,
+      "loss": 0.4584,
+      "step": 240
+    },
+    {
+      "epoch": 0.9608771492648891,
+      "grad_norm": 5.681688230535626,
+      "learning_rate": 3.4087876713574937e-10,
+      "loss": 0.3994,
+      "step": 241
+    },
+    {
+      "epoch": 0.9648641913780215,
+      "grad_norm": 5.320992875826051,
+      "learning_rate": 2.69400633666933e-10,
+      "loss": 0.4583,
+      "step": 242
+    },
+    {
+      "epoch": 0.9688512334911538,
+      "grad_norm": 7.410942256757884,
+      "learning_rate": 2.0630332202324907e-10,
+      "loss": 0.4758,
+      "step": 243
+    },
+    {
+      "epoch": 0.972838275604286,
+      "grad_norm": 6.763191810144099,
+      "learning_rate": 1.5159746564433195e-10,
+      "loss": 0.4849,
+      "step": 244
+    },
+    {
+      "epoch": 0.9768253177174184,
+      "grad_norm": 6.972857506017931,
+      "learning_rate": 1.0529228380445898e-10,
+      "loss": 0.4874,
+      "step": 245
+    },
+    {
+      "epoch": 0.9808123598305507,
+      "grad_norm": 7.620651932265417,
+      "learning_rate": 6.739558005884882e-11,
+      "loss": 0.4817,
+      "step": 246
+    },
+    {
+      "epoch": 0.984799401943683,
+      "grad_norm": 6.612792516500234,
+      "learning_rate": 3.7913740928596783e-11,
+      "loss": 0.4511,
+      "step": 247
+    },
+    {
+      "epoch": 0.9887864440568154,
+      "grad_norm": 11.075682861844061,
+      "learning_rate": 1.685173482438018e-11,
+      "loss": 0.4447,
+      "step": 248
+    },
+    {
+      "epoch": 0.9927734861699476,
+      "grad_norm": 6.564735395340143,
+      "learning_rate": 4.2131112091559066e-12,
+      "loss": 0.4493,
+      "step": 249
+    },
+    {
+      "epoch": 0.99676052828308,
+      "grad_norm": 8.801767552010569,
+      "learning_rate": 0.0,
+      "loss": 0.4552,
+      "step": 250
+    },
+    {
+      "epoch": 0.99676052828308,
+      "eval_loss": 0.44849729537963867,
+      "eval_runtime": 76.4349,
+      "eval_samples_per_second": 8.478,
+      "eval_steps_per_second": 0.275,
+      "step": 250
+    },
+    {
+      "epoch": 0.99676052828308,
+      "step": 250,
+      "total_flos": 837309243064320.0,
+      "train_loss": 0.4584040036201477,
+      "train_runtime": 14021.6229,
+      "train_samples_per_second": 4.578,
+      "train_steps_per_second": 0.018
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 3,
+  "total_flos": 837309243064320.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ec3e79a3b1e4357a44065c0464c0e5f7b9d53d6b37e1ca0261d293a112212b3
+size 6776