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

checkpoint-15260/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "meta-llama/Llama-3.1-8B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "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": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0.dev0",
+  "use_cache": true,
+  "vocab_size": 128256
+}

checkpoint-15260/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.47.0.dev0"
+}

checkpoint-15260/model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca9c32fb2c49e4334e8d6366962dfde9e3ce313f12da6932182efa1819e7d5b4
+size 4886466168

checkpoint-15260/model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0901d2e156c6ec7a375c3e90ae5183970af0445d3dc0e53c031b45673775dd64
+size 4832007448

checkpoint-15260/model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afa0e22bcade9527b5aeb86066e139cc30979f8492c753ff3277e6189863ab97
+size 4999813112

checkpoint-15260/model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc4f5352f30ea036b0a4e24ba9b029dd94a2b30a716c81acc1c4a5e7bb47a042
+size 4999813128

checkpoint-15260/model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d9450b209df4cb026b6669e618fcdb6ff4f5bd0a711fb2e502afe0b95eb3ad7
+size 4832007496

checkpoint-15260/model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc341540d248248879144955e237347cb4f7c1f9a2c06b2ff8db4432b3828a6c
+size 4999813120

checkpoint-15260/model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ebb0b7cf9429c7212f117ffea57058b305053543993e5f3f65b73e965e62479
+size 2571158184

checkpoint-15260/model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 32121044992
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.norm.weight": "model-00007-of-00007.safetensors"
+  }
+}

checkpoint-15260/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fede8c800f57bd9dc62e33a17ab9eb4b4e33b494929e65bb152bc289502e2bc2
+size 15385036334

checkpoint-15260/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244

checkpoint-15260/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ce335347efaebf038b8915bc0a8d2d587a4a1aa08ad0e015b4bc7cc4fba634e
+size 1064

checkpoint-15260/trainer_state.json

@@ -0,0 +1,3477 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.20334736954320132,
+  "eval_steps": 500,
+  "global_step": 15260,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00041309098662118223,
+      "grad_norm": 3.3591651916503906,
+      "learning_rate": 1.0157273918741808e-06,
+      "loss": 0.6834,
+      "step": 31
+    },
+    {
+      "epoch": 0.0008261819732423645,
+      "grad_norm": 3.3040101528167725,
+      "learning_rate": 2.0314547837483616e-06,
+      "loss": 0.6549,
+      "step": 62
+    },
+    {
+      "epoch": 0.0012392729598635467,
+      "grad_norm": 3.4403798580169678,
+      "learning_rate": 3.0471821756225426e-06,
+      "loss": 0.6424,
+      "step": 93
+    },
+    {
+      "epoch": 0.001652363946484729,
+      "grad_norm": 3.1615188121795654,
+      "learning_rate": 4.062909567496723e-06,
+      "loss": 0.6389,
+      "step": 124
+    },
+    {
+      "epoch": 0.002065454933105911,
+      "grad_norm": 3.514648675918579,
+      "learning_rate": 5.078636959370905e-06,
+      "loss": 0.6299,
+      "step": 155
+    },
+    {
+      "epoch": 0.0024785459197270935,
+      "grad_norm": 3.482177257537842,
+      "learning_rate": 6.094364351245085e-06,
+      "loss": 0.6264,
+      "step": 186
+    },
+    {
+      "epoch": 0.002891636906348276,
+      "grad_norm": 2.943384885787964,
+      "learning_rate": 7.110091743119267e-06,
+      "loss": 0.6332,
+      "step": 217
+    },
+    {
+      "epoch": 0.003304727892969458,
+      "grad_norm": 2.944023847579956,
+      "learning_rate": 8.125819134993446e-06,
+      "loss": 0.6318,
+      "step": 248
+    },
+    {
+      "epoch": 0.0037178188795906402,
+      "grad_norm": 3.4448447227478027,
+      "learning_rate": 9.141546526867629e-06,
+      "loss": 0.6345,
+      "step": 279
+    },
+    {
+      "epoch": 0.004130909866211822,
+      "grad_norm": 2.7651798725128174,
+      "learning_rate": 1.015727391874181e-05,
+      "loss": 0.6385,
+      "step": 310
+    },
+    {
+      "epoch": 0.004544000852833005,
+      "grad_norm": 2.9972455501556396,
+      "learning_rate": 1.117300131061599e-05,
+      "loss": 0.6408,
+      "step": 341
+    },
+    {
+      "epoch": 0.004957091839454187,
+      "grad_norm": 3.3536224365234375,
+      "learning_rate": 1.218872870249017e-05,
+      "loss": 0.6334,
+      "step": 372
+    },
+    {
+      "epoch": 0.005370182826075369,
+      "grad_norm": 2.95772385597229,
+      "learning_rate": 1.3204456094364351e-05,
+      "loss": 0.6321,
+      "step": 403
+    },
+    {
+      "epoch": 0.005783273812696552,
+      "grad_norm": 2.87235164642334,
+      "learning_rate": 1.4220183486238533e-05,
+      "loss": 0.6274,
+      "step": 434
+    },
+    {
+      "epoch": 0.006196364799317734,
+      "grad_norm": 3.253079414367676,
+      "learning_rate": 1.5235910878112714e-05,
+      "loss": 0.6408,
+      "step": 465
+    },
+    {
+      "epoch": 0.006609455785938916,
+      "grad_norm": 2.500065803527832,
+      "learning_rate": 1.6251638269986893e-05,
+      "loss": 0.64,
+      "step": 496
+    },
+    {
+      "epoch": 0.007022546772560098,
+      "grad_norm": 2.9136173725128174,
+      "learning_rate": 1.7267365661861077e-05,
+      "loss": 0.6415,
+      "step": 527
+    },
+    {
+      "epoch": 0.0074356377591812805,
+      "grad_norm": 2.676680088043213,
+      "learning_rate": 1.8283093053735257e-05,
+      "loss": 0.64,
+      "step": 558
+    },
+    {
+      "epoch": 0.007848728745802462,
+      "grad_norm": 2.4697916507720947,
+      "learning_rate": 1.9298820445609438e-05,
+      "loss": 0.6303,
+      "step": 589
+    },
+    {
+      "epoch": 0.008261819732423644,
+      "grad_norm": 2.963353395462036,
+      "learning_rate": 2.031454783748362e-05,
+      "loss": 0.6334,
+      "step": 620
+    },
+    {
+      "epoch": 0.008674910719044826,
+      "grad_norm": 2.501999616622925,
+      "learning_rate": 2.13302752293578e-05,
+      "loss": 0.627,
+      "step": 651
+    },
+    {
+      "epoch": 0.00908800170566601,
+      "grad_norm": 2.571075677871704,
+      "learning_rate": 2.234600262123198e-05,
+      "loss": 0.6331,
+      "step": 682
+    },
+    {
+      "epoch": 0.009501092692287192,
+      "grad_norm": 2.383870840072632,
+      "learning_rate": 2.336173001310616e-05,
+      "loss": 0.6274,
+      "step": 713
+    },
+    {
+      "epoch": 0.009914183678908374,
+      "grad_norm": 2.434166669845581,
+      "learning_rate": 2.437745740498034e-05,
+      "loss": 0.632,
+      "step": 744
+    },
+    {
+      "epoch": 0.010327274665529556,
+      "grad_norm": 2.3138139247894287,
+      "learning_rate": 2.5393184796854525e-05,
+      "loss": 0.6346,
+      "step": 775
+    },
+    {
+      "epoch": 0.010740365652150738,
+      "grad_norm": 2.5973124504089355,
+      "learning_rate": 2.6408912188728702e-05,
+      "loss": 0.6401,
+      "step": 806
+    },
+    {
+      "epoch": 0.01115345663877192,
+      "grad_norm": 2.0346949100494385,
+      "learning_rate": 2.7424639580602886e-05,
+      "loss": 0.6321,
+      "step": 837
+    },
+    {
+      "epoch": 0.011566547625393104,
+      "grad_norm": 2.5783207416534424,
+      "learning_rate": 2.8440366972477066e-05,
+      "loss": 0.6242,
+      "step": 868
+    },
+    {
+      "epoch": 0.011979638612014286,
+      "grad_norm": 2.7078452110290527,
+      "learning_rate": 2.9456094364351244e-05,
+      "loss": 0.6291,
+      "step": 899
+    },
+    {
+      "epoch": 0.012392729598635467,
+      "grad_norm": 2.084425210952759,
+      "learning_rate": 3.0471821756225428e-05,
+      "loss": 0.6295,
+      "step": 930
+    },
+    {
+      "epoch": 0.01280582058525665,
+      "grad_norm": 1.9207690954208374,
+      "learning_rate": 3.148754914809961e-05,
+      "loss": 0.6315,
+      "step": 961
+    },
+    {
+      "epoch": 0.013218911571877831,
+      "grad_norm": 2.132145881652832,
+      "learning_rate": 3.2503276539973785e-05,
+      "loss": 0.6364,
+      "step": 992
+    },
+    {
+      "epoch": 0.013632002558499013,
+      "grad_norm": 2.3366384506225586,
+      "learning_rate": 3.351900393184797e-05,
+      "loss": 0.6302,
+      "step": 1023
+    },
+    {
+      "epoch": 0.014045093545120195,
+      "grad_norm": 2.1471712589263916,
+      "learning_rate": 3.453473132372215e-05,
+      "loss": 0.6296,
+      "step": 1054
+    },
+    {
+      "epoch": 0.014458184531741379,
+      "grad_norm": 1.8962008953094482,
+      "learning_rate": 3.555045871559633e-05,
+      "loss": 0.6269,
+      "step": 1085
+    },
+    {
+      "epoch": 0.014871275518362561,
+      "grad_norm": 2.0318596363067627,
+      "learning_rate": 3.6566186107470514e-05,
+      "loss": 0.6303,
+      "step": 1116
+    },
+    {
+      "epoch": 0.015284366504983743,
+      "grad_norm": 1.917946696281433,
+      "learning_rate": 3.7581913499344695e-05,
+      "loss": 0.6257,
+      "step": 1147
+    },
+    {
+      "epoch": 0.015697457491604925,
+      "grad_norm": 1.8561079502105713,
+      "learning_rate": 3.8597640891218876e-05,
+      "loss": 0.624,
+      "step": 1178
+    },
+    {
+      "epoch": 0.016110548478226107,
+      "grad_norm": 1.7843095064163208,
+      "learning_rate": 3.9613368283093056e-05,
+      "loss": 0.6283,
+      "step": 1209
+    },
+    {
+      "epoch": 0.01652363946484729,
+      "grad_norm": 2.211169958114624,
+      "learning_rate": 4.062909567496724e-05,
+      "loss": 0.6218,
+      "step": 1240
+    },
+    {
+      "epoch": 0.01693673045146847,
+      "grad_norm": 1.8634388446807861,
+      "learning_rate": 4.164482306684142e-05,
+      "loss": 0.6356,
+      "step": 1271
+    },
+    {
+      "epoch": 0.017349821438089653,
+      "grad_norm": 3.0655570030212402,
+      "learning_rate": 4.26605504587156e-05,
+      "loss": 0.6303,
+      "step": 1302
+    },
+    {
+      "epoch": 0.017762912424710835,
+      "grad_norm": 1.7919161319732666,
+      "learning_rate": 4.367627785058978e-05,
+      "loss": 0.6232,
+      "step": 1333
+    },
+    {
+      "epoch": 0.01817600341133202,
+      "grad_norm": 1.835038423538208,
+      "learning_rate": 4.469200524246396e-05,
+      "loss": 0.6285,
+      "step": 1364
+    },
+    {
+      "epoch": 0.018589094397953202,
+      "grad_norm": 2.1585254669189453,
+      "learning_rate": 4.570773263433814e-05,
+      "loss": 0.6218,
+      "step": 1395
+    },
+    {
+      "epoch": 0.019002185384574384,
+      "grad_norm": 1.9998375177383423,
+      "learning_rate": 4.672346002621232e-05,
+      "loss": 0.6271,
+      "step": 1426
+    },
+    {
+      "epoch": 0.019415276371195566,
+      "grad_norm": 1.9367185831069946,
+      "learning_rate": 4.77391874180865e-05,
+      "loss": 0.6251,
+      "step": 1457
+    },
+    {
+      "epoch": 0.019828367357816748,
+      "grad_norm": 1.9007997512817383,
+      "learning_rate": 4.875491480996068e-05,
+      "loss": 0.6294,
+      "step": 1488
+    },
+    {
+      "epoch": 0.02024145834443793,
+      "grad_norm": 2.1685807704925537,
+      "learning_rate": 4.977064220183487e-05,
+      "loss": 0.6234,
+      "step": 1519
+    },
+    {
+      "epoch": 0.020654549331059112,
+      "grad_norm": 1.8442130088806152,
+      "learning_rate": 4.9999915451558777e-05,
+      "loss": 0.617,
+      "step": 1550
+    },
+    {
+      "epoch": 0.021067640317680294,
+      "grad_norm": 1.7781652212142944,
+      "learning_rate": 4.999955597496219e-05,
+      "loss": 0.6288,
+      "step": 1581
+    },
+    {
+      "epoch": 0.021480731304301476,
+      "grad_norm": 1.6424139738082886,
+      "learning_rate": 4.9998914381774255e-05,
+      "loss": 0.6307,
+      "step": 1612
+    },
+    {
+      "epoch": 0.021893822290922658,
+      "grad_norm": 2.124312400817871,
+      "learning_rate": 4.999799067923527e-05,
+      "loss": 0.6219,
+      "step": 1643
+    },
+    {
+      "epoch": 0.02230691327754384,
+      "grad_norm": 1.968117117881775,
+      "learning_rate": 4.999678487776908e-05,
+      "loss": 0.6209,
+      "step": 1674
+    },
+    {
+      "epoch": 0.02272000426416502,
+      "grad_norm": 1.8158947229385376,
+      "learning_rate": 4.9995296990983006e-05,
+      "loss": 0.6186,
+      "step": 1705
+    },
+    {
+      "epoch": 0.023133095250786207,
+      "grad_norm": 1.8896212577819824,
+      "learning_rate": 4.999352703566763e-05,
+      "loss": 0.62,
+      "step": 1736
+    },
+    {
+      "epoch": 0.02354618623740739,
+      "grad_norm": 1.733493685722351,
+      "learning_rate": 4.999147503179668e-05,
+      "loss": 0.621,
+      "step": 1767
+    },
+    {
+      "epoch": 0.02395927722402857,
+      "grad_norm": 1.620137333869934,
+      "learning_rate": 4.998914100252672e-05,
+      "loss": 0.6148,
+      "step": 1798
+    },
+    {
+      "epoch": 0.024372368210649753,
+      "grad_norm": 1.6356101036071777,
+      "learning_rate": 4.998652497419696e-05,
+      "loss": 0.6158,
+      "step": 1829
+    },
+    {
+      "epoch": 0.024785459197270935,
+      "grad_norm": 1.7796778678894043,
+      "learning_rate": 4.9983626976328927e-05,
+      "loss": 0.6135,
+      "step": 1860
+    },
+    {
+      "epoch": 0.025198550183892117,
+      "grad_norm": 1.6276317834854126,
+      "learning_rate": 4.998044704162613e-05,
+      "loss": 0.6156,
+      "step": 1891
+    },
+    {
+      "epoch": 0.0256116411705133,
+      "grad_norm": 1.5687456130981445,
+      "learning_rate": 4.9976985205973705e-05,
+      "loss": 0.6097,
+      "step": 1922
+    },
+    {
+      "epoch": 0.02602473215713448,
+      "grad_norm": 1.6068204641342163,
+      "learning_rate": 4.997324150843799e-05,
+      "loss": 0.5995,
+      "step": 1953
+    },
+    {
+      "epoch": 0.026437823143755663,
+      "grad_norm": 1.5601444244384766,
+      "learning_rate": 4.99692159912661e-05,
+      "loss": 0.6095,
+      "step": 1984
+    },
+    {
+      "epoch": 0.026850914130376845,
+      "grad_norm": 1.5028727054595947,
+      "learning_rate": 4.996490869988546e-05,
+      "loss": 0.6035,
+      "step": 2015
+    },
+    {
+      "epoch": 0.027264005116998027,
+      "grad_norm": 1.6428122520446777,
+      "learning_rate": 4.996031968290326e-05,
+      "loss": 0.6066,
+      "step": 2046
+    },
+    {
+      "epoch": 0.02767709610361921,
+      "grad_norm": 1.7156198024749756,
+      "learning_rate": 4.995544899210594e-05,
+      "loss": 0.6013,
+      "step": 2077
+    },
+    {
+      "epoch": 0.02809018709024039,
+      "grad_norm": 1.6048359870910645,
+      "learning_rate": 4.9950296682458583e-05,
+      "loss": 0.6089,
+      "step": 2108
+    },
+    {
+      "epoch": 0.028503278076861576,
+      "grad_norm": 1.6720808744430542,
+      "learning_rate": 4.994486281210429e-05,
+      "loss": 0.6015,
+      "step": 2139
+    },
+    {
+      "epoch": 0.028916369063482758,
+      "grad_norm": 1.5579414367675781,
+      "learning_rate": 4.9939147442363566e-05,
+      "loss": 0.606,
+      "step": 2170
+    },
+    {
+      "epoch": 0.02932946005010394,
+      "grad_norm": 1.536623477935791,
+      "learning_rate": 4.9933150637733574e-05,
+      "loss": 0.6031,
+      "step": 2201
+    },
+    {
+      "epoch": 0.029742551036725122,
+      "grad_norm": 1.5001758337020874,
+      "learning_rate": 4.992687246588743e-05,
+      "loss": 0.5982,
+      "step": 2232
+    },
+    {
+      "epoch": 0.030155642023346304,
+      "grad_norm": 1.956465721130371,
+      "learning_rate": 4.992031299767347e-05,
+      "loss": 0.6026,
+      "step": 2263
+    },
+    {
+      "epoch": 0.030568733009967486,
+      "grad_norm": 1.5761971473693848,
+      "learning_rate": 4.9913472307114386e-05,
+      "loss": 0.608,
+      "step": 2294
+    },
+    {
+      "epoch": 0.030981823996588668,
+      "grad_norm": 1.4833664894104004,
+      "learning_rate": 4.9906350471406446e-05,
+      "loss": 0.6023,
+      "step": 2325
+    },
+    {
+      "epoch": 0.03139491498320985,
+      "grad_norm": 1.6575111150741577,
+      "learning_rate": 4.989894757091861e-05,
+      "loss": 0.6056,
+      "step": 2356
+    },
+    {
+      "epoch": 0.031808005969831035,
+      "grad_norm": 1.7202379703521729,
+      "learning_rate": 4.989126368919158e-05,
+      "loss": 0.6042,
+      "step": 2387
+    },
+    {
+      "epoch": 0.032221096956452214,
+      "grad_norm": 1.527782917022705,
+      "learning_rate": 4.988329891293693e-05,
+      "loss": 0.6042,
+      "step": 2418
+    },
+    {
+      "epoch": 0.0326341879430734,
+      "grad_norm": 1.434414267539978,
+      "learning_rate": 4.987505333203608e-05,
+      "loss": 0.6047,
+      "step": 2449
+    },
+    {
+      "epoch": 0.03304727892969458,
+      "grad_norm": 1.4155853986740112,
+      "learning_rate": 4.9866527039539276e-05,
+      "loss": 0.6031,
+      "step": 2480
+    },
+    {
+      "epoch": 0.03346036991631576,
+      "grad_norm": 1.3213967084884644,
+      "learning_rate": 4.9857720131664594e-05,
+      "loss": 0.591,
+      "step": 2511
+    },
+    {
+      "epoch": 0.03387346090293694,
+      "grad_norm": 1.6172468662261963,
+      "learning_rate": 4.9848632707796773e-05,
+      "loss": 0.6005,
+      "step": 2542
+    },
+    {
+      "epoch": 0.03428655188955813,
+      "grad_norm": 1.791569709777832,
+      "learning_rate": 4.9839264870486155e-05,
+      "loss": 0.5972,
+      "step": 2573
+    },
+    {
+      "epoch": 0.034699642876179305,
+      "grad_norm": 1.6133856773376465,
+      "learning_rate": 4.9829616725447526e-05,
+      "loss": 0.6088,
+      "step": 2604
+    },
+    {
+      "epoch": 0.03511273386280049,
+      "grad_norm": 1.3674331903457642,
+      "learning_rate": 4.981968838155888e-05,
+      "loss": 0.6059,
+      "step": 2635
+    },
+    {
+      "epoch": 0.03552582484942167,
+      "grad_norm": 1.3905473947525024,
+      "learning_rate": 4.980947995086024e-05,
+      "loss": 0.5945,
+      "step": 2666
+    },
+    {
+      "epoch": 0.035938915836042855,
+      "grad_norm": 1.8068715333938599,
+      "learning_rate": 4.979899154855234e-05,
+      "loss": 0.5926,
+      "step": 2697
+    },
+    {
+      "epoch": 0.03635200682266404,
+      "grad_norm": 1.9621700048446655,
+      "learning_rate": 4.9788223292995386e-05,
+      "loss": 0.5894,
+      "step": 2728
+    },
+    {
+      "epoch": 0.03676509780928522,
+      "grad_norm": 1.363703966140747,
+      "learning_rate": 4.977717530570768e-05,
+      "loss": 0.5966,
+      "step": 2759
+    },
+    {
+      "epoch": 0.037178188795906404,
+      "grad_norm": 1.3365380764007568,
+      "learning_rate": 4.976584771136425e-05,
+      "loss": 0.5951,
+      "step": 2790
+    },
+    {
+      "epoch": 0.03759127978252758,
+      "grad_norm": 1.5703483819961548,
+      "learning_rate": 4.975424063779547e-05,
+      "loss": 0.5881,
+      "step": 2821
+    },
+    {
+      "epoch": 0.03800437076914877,
+      "grad_norm": 1.41889226436615,
+      "learning_rate": 4.974235421598557e-05,
+      "loss": 0.5894,
+      "step": 2852
+    },
+    {
+      "epoch": 0.03841746175576995,
+      "grad_norm": 1.3354650735855103,
+      "learning_rate": 4.973018858007122e-05,
+      "loss": 0.5985,
+      "step": 2883
+    },
+    {
+      "epoch": 0.03883055274239113,
+      "grad_norm": 1.3462773561477661,
+      "learning_rate": 4.9717743867339963e-05,
+      "loss": 0.5842,
+      "step": 2914
+    },
+    {
+      "epoch": 0.03924364372901231,
+      "grad_norm": 1.3955717086791992,
+      "learning_rate": 4.9705020218228695e-05,
+      "loss": 0.5949,
+      "step": 2945
+    },
+    {
+      "epoch": 0.039656734715633496,
+      "grad_norm": 1.56218683719635,
+      "learning_rate": 4.969201777632205e-05,
+      "loss": 0.5819,
+      "step": 2976
+    },
+    {
+      "epoch": 0.040069825702254674,
+      "grad_norm": 1.273589849472046,
+      "learning_rate": 4.9678736688350846e-05,
+      "loss": 0.5862,
+      "step": 3007
+    },
+    {
+      "epoch": 0.04048291668887586,
+      "grad_norm": 1.2699215412139893,
+      "learning_rate": 4.966517710419033e-05,
+      "loss": 0.5861,
+      "step": 3038
+    },
+    {
+      "epoch": 0.04089600767549704,
+      "grad_norm": 1.3422695398330688,
+      "learning_rate": 4.965133917685858e-05,
+      "loss": 0.5895,
+      "step": 3069
+    },
+    {
+      "epoch": 0.041309098662118224,
+      "grad_norm": 1.3061139583587646,
+      "learning_rate": 4.9637223062514714e-05,
+      "loss": 0.5841,
+      "step": 3100
+    },
+    {
+      "epoch": 0.04172218964873941,
+      "grad_norm": 1.4134674072265625,
+      "learning_rate": 4.962282892045718e-05,
+      "loss": 0.5884,
+      "step": 3131
+    },
+    {
+      "epoch": 0.04213528063536059,
+      "grad_norm": 1.620926022529602,
+      "learning_rate": 4.9608156913121904e-05,
+      "loss": 0.5892,
+      "step": 3162
+    },
+    {
+      "epoch": 0.04254837162198177,
+      "grad_norm": 1.6183459758758545,
+      "learning_rate": 4.959320720608049e-05,
+      "loss": 0.5905,
+      "step": 3193
+    },
+    {
+      "epoch": 0.04296146260860295,
+      "grad_norm": 1.388850212097168,
+      "learning_rate": 4.9577979968038354e-05,
+      "loss": 0.5877,
+      "step": 3224
+    },
+    {
+      "epoch": 0.04337455359522414,
+      "grad_norm": 1.3144453763961792,
+      "learning_rate": 4.956247537083282e-05,
+      "loss": 0.586,
+      "step": 3255
+    },
+    {
+      "epoch": 0.043787644581845316,
+      "grad_norm": 1.2794479131698608,
+      "learning_rate": 4.9546693589431145e-05,
+      "loss": 0.5867,
+      "step": 3286
+    },
+    {
+      "epoch": 0.0442007355684665,
+      "grad_norm": 1.3948591947555542,
+      "learning_rate": 4.9530634801928595e-05,
+      "loss": 0.5826,
+      "step": 3317
+    },
+    {
+      "epoch": 0.04461382655508768,
+      "grad_norm": 1.706746220588684,
+      "learning_rate": 4.9514299189546395e-05,
+      "loss": 0.5824,
+      "step": 3348
+    },
+    {
+      "epoch": 0.045026917541708865,
+      "grad_norm": 1.3201781511306763,
+      "learning_rate": 4.949768693662973e-05,
+      "loss": 0.5756,
+      "step": 3379
+    },
+    {
+      "epoch": 0.04544000852833004,
+      "grad_norm": 1.3768137693405151,
+      "learning_rate": 4.948079823064559e-05,
+      "loss": 0.5811,
+      "step": 3410
+    },
+    {
+      "epoch": 0.04585309951495123,
+      "grad_norm": 1.5180764198303223,
+      "learning_rate": 4.946363326218074e-05,
+      "loss": 0.5883,
+      "step": 3441
+    },
+    {
+      "epoch": 0.046266190501572414,
+      "grad_norm": 1.3262442350387573,
+      "learning_rate": 4.9446192224939525e-05,
+      "loss": 0.5891,
+      "step": 3472
+    },
+    {
+      "epoch": 0.04667928148819359,
+      "grad_norm": 1.2817314863204956,
+      "learning_rate": 4.942847531574167e-05,
+      "loss": 0.5864,
+      "step": 3503
+    },
+    {
+      "epoch": 0.04709237247481478,
+      "grad_norm": 1.367293119430542,
+      "learning_rate": 4.941048273452008e-05,
+      "loss": 0.5707,
+      "step": 3534
+    },
+    {
+      "epoch": 0.04750546346143596,
+      "grad_norm": 1.3828052282333374,
+      "learning_rate": 4.9392214684318605e-05,
+      "loss": 0.5836,
+      "step": 3565
+    },
+    {
+      "epoch": 0.04791855444805714,
+      "grad_norm": 1.3188467025756836,
+      "learning_rate": 4.93736713712897e-05,
+      "loss": 0.5751,
+      "step": 3596
+    },
+    {
+      "epoch": 0.04833164543467832,
+      "grad_norm": 1.4477969408035278,
+      "learning_rate": 4.9354853004692124e-05,
+      "loss": 0.5759,
+      "step": 3627
+    },
+    {
+      "epoch": 0.048744736421299506,
+      "grad_norm": 20.127796173095703,
+      "learning_rate": 4.93357597968886e-05,
+      "loss": 0.5881,
+      "step": 3658
+    },
+    {
+      "epoch": 0.049157827407920685,
+      "grad_norm": 1.3451824188232422,
+      "learning_rate": 4.931639196334338e-05,
+      "loss": 0.5751,
+      "step": 3689
+    },
+    {
+      "epoch": 0.04957091839454187,
+      "grad_norm": 1.2557615041732788,
+      "learning_rate": 4.9296749722619826e-05,
+      "loss": 0.5727,
+      "step": 3720
+    },
+    {
+      "epoch": 0.04998400938116305,
+      "grad_norm": 1.2731627225875854,
+      "learning_rate": 4.9276833296377966e-05,
+      "loss": 0.5828,
+      "step": 3751
+    },
+    {
+      "epoch": 0.050397100367784234,
+      "grad_norm": 1.2297345399856567,
+      "learning_rate": 4.925664290937196e-05,
+      "loss": 0.5802,
+      "step": 3782
+    },
+    {
+      "epoch": 0.05081019135440541,
+      "grad_norm": 1.4189480543136597,
+      "learning_rate": 4.9236178789447576e-05,
+      "loss": 0.5858,
+      "step": 3813
+    },
+    {
+      "epoch": 0.0512232823410266,
+      "grad_norm": 1.4226466417312622,
+      "learning_rate": 4.921544116753962e-05,
+      "loss": 0.5826,
+      "step": 3844
+    },
+    {
+      "epoch": 0.05163637332764778,
+      "grad_norm": 1.2986515760421753,
+      "learning_rate": 4.919443027766935e-05,
+      "loss": 0.5792,
+      "step": 3875
+    },
+    {
+      "epoch": 0.05204946431426896,
+      "grad_norm": 1.2760885953903198,
+      "learning_rate": 4.91731463569418e-05,
+      "loss": 0.5714,
+      "step": 3906
+    },
+    {
+      "epoch": 0.05246255530089015,
+      "grad_norm": 1.3039038181304932,
+      "learning_rate": 4.915158964554312e-05,
+      "loss": 0.5869,
+      "step": 3937
+    },
+    {
+      "epoch": 0.052875646287511326,
+      "grad_norm": 1.3332126140594482,
+      "learning_rate": 4.912976038673786e-05,
+      "loss": 0.5733,
+      "step": 3968
+    },
+    {
+      "epoch": 0.05328873727413251,
+      "grad_norm": 1.3061742782592773,
+      "learning_rate": 4.9107658826866254e-05,
+      "loss": 0.5784,
+      "step": 3999
+    },
+    {
+      "epoch": 0.05370182826075369,
+      "grad_norm": 1.3973617553710938,
+      "learning_rate": 4.908528521534139e-05,
+      "loss": 0.578,
+      "step": 4030
+    },
+    {
+      "epoch": 0.054114919247374875,
+      "grad_norm": 1.345142126083374,
+      "learning_rate": 4.906263980464644e-05,
+      "loss": 0.5676,
+      "step": 4061
+    },
+    {
+      "epoch": 0.05452801023399605,
+      "grad_norm": 1.3678765296936035,
+      "learning_rate": 4.903972285033178e-05,
+      "loss": 0.5772,
+      "step": 4092
+    },
+    {
+      "epoch": 0.05494110122061724,
+      "grad_norm": 1.4278219938278198,
+      "learning_rate": 4.901653461101213e-05,
+      "loss": 0.5793,
+      "step": 4123
+    },
+    {
+      "epoch": 0.05535419220723842,
+      "grad_norm": 1.20429265499115,
+      "learning_rate": 4.8993075348363626e-05,
+      "loss": 0.5663,
+      "step": 4154
+    },
+    {
+      "epoch": 0.0557672831938596,
+      "grad_norm": 1.292257308959961,
+      "learning_rate": 4.896934532712084e-05,
+      "loss": 0.5752,
+      "step": 4185
+    },
+    {
+      "epoch": 0.05618037418048078,
+      "grad_norm": 1.2514420747756958,
+      "learning_rate": 4.8945344815073846e-05,
+      "loss": 0.5716,
+      "step": 4216
+    },
+    {
+      "epoch": 0.05659346516710197,
+      "grad_norm": 1.3282150030136108,
+      "learning_rate": 4.892107408306516e-05,
+      "loss": 0.5797,
+      "step": 4247
+    },
+    {
+      "epoch": 0.05700655615372315,
+      "grad_norm": 1.1990079879760742,
+      "learning_rate": 4.889653340498669e-05,
+      "loss": 0.5754,
+      "step": 4278
+    },
+    {
+      "epoch": 0.05741964714034433,
+      "grad_norm": 1.2512881755828857,
+      "learning_rate": 4.8871723057776664e-05,
+      "loss": 0.578,
+      "step": 4309
+    },
+    {
+      "epoch": 0.057832738126965516,
+      "grad_norm": 1.289668321609497,
+      "learning_rate": 4.8846643321416476e-05,
+      "loss": 0.5679,
+      "step": 4340
+    },
+    {
+      "epoch": 0.058245829113586695,
+      "grad_norm": 1.1814261674880981,
+      "learning_rate": 4.882129447892753e-05,
+      "loss": 0.5736,
+      "step": 4371
+    },
+    {
+      "epoch": 0.05865892010020788,
+      "grad_norm": 1.3042793273925781,
+      "learning_rate": 4.8795676816368076e-05,
+      "loss": 0.5688,
+      "step": 4402
+    },
+    {
+      "epoch": 0.05907201108682906,
+      "grad_norm": 1.3468403816223145,
+      "learning_rate": 4.876979062282995e-05,
+      "loss": 0.5717,
+      "step": 4433
+    },
+    {
+      "epoch": 0.059485102073450244,
+      "grad_norm": 1.3107612133026123,
+      "learning_rate": 4.8743636190435325e-05,
+      "loss": 0.5751,
+      "step": 4464
+    },
+    {
+      "epoch": 0.05989819306007142,
+      "grad_norm": 1.2376316785812378,
+      "learning_rate": 4.871721381433344e-05,
+      "loss": 0.5577,
+      "step": 4495
+    },
+    {
+      "epoch": 0.06031128404669261,
+      "grad_norm": 1.724004864692688,
+      "learning_rate": 4.869052379269719e-05,
+      "loss": 0.5775,
+      "step": 4526
+    },
+    {
+      "epoch": 0.060724375033313786,
+      "grad_norm": 1.266945481300354,
+      "learning_rate": 4.866356642671985e-05,
+      "loss": 0.5691,
+      "step": 4557
+    },
+    {
+      "epoch": 0.06113746601993497,
+      "grad_norm": 1.3230117559432983,
+      "learning_rate": 4.8636342020611634e-05,
+      "loss": 0.5771,
+      "step": 4588
+    },
+    {
+      "epoch": 0.06155055700655616,
+      "grad_norm": 1.1369415521621704,
+      "learning_rate": 4.860885088159626e-05,
+      "loss": 0.5635,
+      "step": 4619
+    },
+    {
+      "epoch": 0.061963647993177336,
+      "grad_norm": 1.468989610671997,
+      "learning_rate": 4.858109331990751e-05,
+      "loss": 0.5703,
+      "step": 4650
+    },
+    {
+      "epoch": 0.06237673897979852,
+      "grad_norm": 1.1481618881225586,
+      "learning_rate": 4.855306964878567e-05,
+      "loss": 0.5727,
+      "step": 4681
+    },
+    {
+      "epoch": 0.0627898299664197,
+      "grad_norm": 1.312706708908081,
+      "learning_rate": 4.8524780184474084e-05,
+      "loss": 0.566,
+      "step": 4712
+    },
+    {
+      "epoch": 0.06320292095304088,
+      "grad_norm": 23.95269012451172,
+      "learning_rate": 4.8496225246215496e-05,
+      "loss": 0.5687,
+      "step": 4743
+    },
+    {
+      "epoch": 0.06361601193966207,
+      "grad_norm": 1.4113848209381104,
+      "learning_rate": 4.8467405156248505e-05,
+      "loss": 0.5711,
+      "step": 4774
+    },
+    {
+      "epoch": 0.06402910292628325,
+      "grad_norm": 1.1625652313232422,
+      "learning_rate": 4.843832023980392e-05,
+      "loss": 0.57,
+      "step": 4805
+    },
+    {
+      "epoch": 0.06444219391290443,
+      "grad_norm": 1.2240279912948608,
+      "learning_rate": 4.840897082510106e-05,
+      "loss": 0.5706,
+      "step": 4836
+    },
+    {
+      "epoch": 0.0648552848995256,
+      "grad_norm": 1.2450612783432007,
+      "learning_rate": 4.8379357243344084e-05,
+      "loss": 0.5571,
+      "step": 4867
+    },
+    {
+      "epoch": 0.0652683758861468,
+      "grad_norm": 1.1748895645141602,
+      "learning_rate": 4.8349479828718236e-05,
+      "loss": 0.563,
+      "step": 4898
+    },
+    {
+      "epoch": 0.06568146687276798,
+      "grad_norm": 1.1516320705413818,
+      "learning_rate": 4.8319338918386075e-05,
+      "loss": 0.56,
+      "step": 4929
+    },
+    {
+      "epoch": 0.06609455785938916,
+      "grad_norm": 1.0675004720687866,
+      "learning_rate": 4.828893485248369e-05,
+      "loss": 0.5694,
+      "step": 4960
+    },
+    {
+      "epoch": 0.06650764884601033,
+      "grad_norm": 1.2876821756362915,
+      "learning_rate": 4.825826797411682e-05,
+      "loss": 0.5666,
+      "step": 4991
+    },
+    {
+      "epoch": 0.06692073983263153,
+      "grad_norm": 1.2281044721603394,
+      "learning_rate": 4.822733862935702e-05,
+      "loss": 0.5611,
+      "step": 5022
+    },
+    {
+      "epoch": 0.0673338308192527,
+      "grad_norm": 1.2479503154754639,
+      "learning_rate": 4.819614716723775e-05,
+      "loss": 0.5616,
+      "step": 5053
+    },
+    {
+      "epoch": 0.06774692180587388,
+      "grad_norm": 0.9844783544540405,
+      "learning_rate": 4.8164693939750425e-05,
+      "loss": 0.556,
+      "step": 5084
+    },
+    {
+      "epoch": 0.06816001279249508,
+      "grad_norm": 1.342161774635315,
+      "learning_rate": 4.813297930184042e-05,
+      "loss": 0.5659,
+      "step": 5115
+    },
+    {
+      "epoch": 0.06857310377911625,
+      "grad_norm": 1.2998915910720825,
+      "learning_rate": 4.810100361140314e-05,
+      "loss": 0.564,
+      "step": 5146
+    },
+    {
+      "epoch": 0.06898619476573743,
+      "grad_norm": 1.202837347984314,
+      "learning_rate": 4.8068767229279885e-05,
+      "loss": 0.5688,
+      "step": 5177
+    },
+    {
+      "epoch": 0.06939928575235861,
+      "grad_norm": 1.2763055562973022,
+      "learning_rate": 4.8036270519253854e-05,
+      "loss": 0.561,
+      "step": 5208
+    },
+    {
+      "epoch": 0.0698123767389798,
+      "grad_norm": 1.2596797943115234,
+      "learning_rate": 4.8003513848046e-05,
+      "loss": 0.5583,
+      "step": 5239
+    },
+    {
+      "epoch": 0.07022546772560098,
+      "grad_norm": 1.1315211057662964,
+      "learning_rate": 4.79704975853109e-05,
+      "loss": 0.5654,
+      "step": 5270
+    },
+    {
+      "epoch": 0.07063855871222216,
+      "grad_norm": 1.275377869606018,
+      "learning_rate": 4.793722210363262e-05,
+      "loss": 0.5565,
+      "step": 5301
+    },
+    {
+      "epoch": 0.07105164969884334,
+      "grad_norm": 1.1248124837875366,
+      "learning_rate": 4.7903687778520414e-05,
+      "loss": 0.5564,
+      "step": 5332
+    },
+    {
+      "epoch": 0.07146474068546453,
+      "grad_norm": 1.1564768552780151,
+      "learning_rate": 4.7869894988404593e-05,
+      "loss": 0.5664,
+      "step": 5363
+    },
+    {
+      "epoch": 0.07187783167208571,
+      "grad_norm": 1.3657585382461548,
+      "learning_rate": 4.783584411463221e-05,
+      "loss": 0.5595,
+      "step": 5394
+    },
+    {
+      "epoch": 0.07229092265870689,
+      "grad_norm": 1.2559267282485962,
+      "learning_rate": 4.780153554146274e-05,
+      "loss": 0.5589,
+      "step": 5425
+    },
+    {
+      "epoch": 0.07270401364532808,
+      "grad_norm": 1.172601342201233,
+      "learning_rate": 4.7766969656063766e-05,
+      "loss": 0.563,
+      "step": 5456
+    },
+    {
+      "epoch": 0.07311710463194926,
+      "grad_norm": 1.1219208240509033,
+      "learning_rate": 4.773214684850662e-05,
+      "loss": 0.557,
+      "step": 5487
+    },
+    {
+      "epoch": 0.07353019561857044,
+      "grad_norm": 1.1428426504135132,
+      "learning_rate": 4.769706751176193e-05,
+      "loss": 0.5651,
+      "step": 5518
+    },
+    {
+      "epoch": 0.07394328660519162,
+      "grad_norm": 1.116365909576416,
+      "learning_rate": 4.7661732041695264e-05,
+      "loss": 0.5625,
+      "step": 5549
+    },
+    {
+      "epoch": 0.07435637759181281,
+      "grad_norm": 1.141745924949646,
+      "learning_rate": 4.762614083706258e-05,
+      "loss": 0.5609,
+      "step": 5580
+    },
+    {
+      "epoch": 0.07476946857843399,
+      "grad_norm": 1.2823870182037354,
+      "learning_rate": 4.759029429950581e-05,
+      "loss": 0.5563,
+      "step": 5611
+    },
+    {
+      "epoch": 0.07518255956505517,
+      "grad_norm": 1.0877517461776733,
+      "learning_rate": 4.7554192833548235e-05,
+      "loss": 0.5602,
+      "step": 5642
+    },
+    {
+      "epoch": 0.07559565055167634,
+      "grad_norm": 1.309289813041687,
+      "learning_rate": 4.751783684659e-05,
+      "loss": 0.5627,
+      "step": 5673
+    },
+    {
+      "epoch": 0.07600874153829754,
+      "grad_norm": 1.1390682458877563,
+      "learning_rate": 4.748122674890348e-05,
+      "loss": 0.5637,
+      "step": 5704
+    },
+    {
+      "epoch": 0.07642183252491871,
+      "grad_norm": 1.0977051258087158,
+      "learning_rate": 4.7444362953628654e-05,
+      "loss": 0.553,
+      "step": 5735
+    },
+    {
+      "epoch": 0.0768349235115399,
+      "grad_norm": 1.2870690822601318,
+      "learning_rate": 4.7407245876768424e-05,
+      "loss": 0.558,
+      "step": 5766
+    },
+    {
+      "epoch": 0.07724801449816109,
+      "grad_norm": 1.2272379398345947,
+      "learning_rate": 4.736987593718397e-05,
+      "loss": 0.5561,
+      "step": 5797
+    },
+    {
+      "epoch": 0.07766110548478226,
+      "grad_norm": 1.0588089227676392,
+      "learning_rate": 4.733225355658999e-05,
+      "loss": 0.5502,
+      "step": 5828
+    },
+    {
+      "epoch": 0.07807419647140344,
+      "grad_norm": 1.0750998258590698,
+      "learning_rate": 4.7294379159549926e-05,
+      "loss": 0.5561,
+      "step": 5859
+    },
+    {
+      "epoch": 0.07848728745802462,
+      "grad_norm": 1.137747883796692,
+      "learning_rate": 4.725625317347119e-05,
+      "loss": 0.5538,
+      "step": 5890
+    },
+    {
+      "epoch": 0.07890037844464581,
+      "grad_norm": 1.166258454322815,
+      "learning_rate": 4.7217876028600374e-05,
+      "loss": 0.553,
+      "step": 5921
+    },
+    {
+      "epoch": 0.07931346943126699,
+      "grad_norm": 1.2771128416061401,
+      "learning_rate": 4.717924815801832e-05,
+      "loss": 0.5635,
+      "step": 5952
+    },
+    {
+      "epoch": 0.07972656041788817,
+      "grad_norm": 1.1782628297805786,
+      "learning_rate": 4.714036999763532e-05,
+      "loss": 0.5579,
+      "step": 5983
+    },
+    {
+      "epoch": 0.08013965140450935,
+      "grad_norm": 1.206446647644043,
+      "learning_rate": 4.7101241986186116e-05,
+      "loss": 0.565,
+      "step": 6014
+    },
+    {
+      "epoch": 0.08055274239113054,
+      "grad_norm": 1.4244260787963867,
+      "learning_rate": 4.7061864565225e-05,
+      "loss": 0.5532,
+      "step": 6045
+    },
+    {
+      "epoch": 0.08096583337775172,
+      "grad_norm": 1.107866644859314,
+      "learning_rate": 4.702223817912081e-05,
+      "loss": 0.5488,
+      "step": 6076
+    },
+    {
+      "epoch": 0.0813789243643729,
+      "grad_norm": 1.1759666204452515,
+      "learning_rate": 4.698236327505195e-05,
+      "loss": 0.5461,
+      "step": 6107
+    },
+    {
+      "epoch": 0.08179201535099408,
+      "grad_norm": 1.1076208353042603,
+      "learning_rate": 4.694224030300127e-05,
+      "loss": 0.5596,
+      "step": 6138
+    },
+    {
+      "epoch": 0.08220510633761527,
+      "grad_norm": 1.1178481578826904,
+      "learning_rate": 4.690186971575107e-05,
+      "loss": 0.5559,
+      "step": 6169
+    },
+    {
+      "epoch": 0.08261819732423645,
+      "grad_norm": 1.0817649364471436,
+      "learning_rate": 4.6861251968877916e-05,
+      "loss": 0.5541,
+      "step": 6200
+    },
+    {
+      "epoch": 0.08303128831085763,
+      "grad_norm": 1.1345518827438354,
+      "learning_rate": 4.68203875207476e-05,
+      "loss": 0.5515,
+      "step": 6231
+    },
+    {
+      "epoch": 0.08344437929747882,
+      "grad_norm": 1.1468344926834106,
+      "learning_rate": 4.677927683250983e-05,
+      "loss": 0.5469,
+      "step": 6262
+    },
+    {
+      "epoch": 0.0838574702841,
+      "grad_norm": 1.0362135171890259,
+      "learning_rate": 4.6737920368093156e-05,
+      "loss": 0.5663,
+      "step": 6293
+    },
+    {
+      "epoch": 0.08427056127072118,
+      "grad_norm": 1.2291909456253052,
+      "learning_rate": 4.669631859419965e-05,
+      "loss": 0.5594,
+      "step": 6324
+    },
+    {
+      "epoch": 0.08468365225734235,
+      "grad_norm": 1.179858922958374,
+      "learning_rate": 4.6654471980299676e-05,
+      "loss": 0.5618,
+      "step": 6355
+    },
+    {
+      "epoch": 0.08509674324396355,
+      "grad_norm": 1.2003235816955566,
+      "learning_rate": 4.661238099862658e-05,
+      "loss": 0.5437,
+      "step": 6386
+    },
+    {
+      "epoch": 0.08550983423058472,
+      "grad_norm": 1.0736212730407715,
+      "learning_rate": 4.657004612417138e-05,
+      "loss": 0.5492,
+      "step": 6417
+    },
+    {
+      "epoch": 0.0859229252172059,
+      "grad_norm": 1.1783486604690552,
+      "learning_rate": 4.6527467834677374e-05,
+      "loss": 0.5579,
+      "step": 6448
+    },
+    {
+      "epoch": 0.08633601620382708,
+      "grad_norm": 1.0574225187301636,
+      "learning_rate": 4.648464661063478e-05,
+      "loss": 0.548,
+      "step": 6479
+    },
+    {
+      "epoch": 0.08674910719044827,
+      "grad_norm": 1.1196519136428833,
+      "learning_rate": 4.6441582935275264e-05,
+      "loss": 0.549,
+      "step": 6510
+    },
+    {
+      "epoch": 0.08716219817706945,
+      "grad_norm": 1.0147607326507568,
+      "learning_rate": 4.6398277294566586e-05,
+      "loss": 0.5518,
+      "step": 6541
+    },
+    {
+      "epoch": 0.08757528916369063,
+      "grad_norm": 1.0568827390670776,
+      "learning_rate": 4.6354730177207e-05,
+      "loss": 0.5494,
+      "step": 6572
+    },
+    {
+      "epoch": 0.08798838015031182,
+      "grad_norm": 1.1435816287994385,
+      "learning_rate": 4.6310942074619787e-05,
+      "loss": 0.5549,
+      "step": 6603
+    },
+    {
+      "epoch": 0.088401471136933,
+      "grad_norm": 1.01443612575531,
+      "learning_rate": 4.626691348094777e-05,
+      "loss": 0.5594,
+      "step": 6634
+    },
+    {
+      "epoch": 0.08881456212355418,
+      "grad_norm": 1.1523023843765259,
+      "learning_rate": 4.622264489304762e-05,
+      "loss": 0.5507,
+      "step": 6665
+    },
+    {
+      "epoch": 0.08922765311017536,
+      "grad_norm": 1.1647075414657593,
+      "learning_rate": 4.617813681048434e-05,
+      "loss": 0.5458,
+      "step": 6696
+    },
+    {
+      "epoch": 0.08964074409679655,
+      "grad_norm": 1.179513692855835,
+      "learning_rate": 4.61333897355256e-05,
+      "loss": 0.5481,
+      "step": 6727
+    },
+    {
+      "epoch": 0.09005383508341773,
+      "grad_norm": 1.1108922958374023,
+      "learning_rate": 4.608840417313604e-05,
+      "loss": 0.5521,
+      "step": 6758
+    },
+    {
+      "epoch": 0.09046692607003891,
+      "grad_norm": 1.126660704612732,
+      "learning_rate": 4.6043180630971646e-05,
+      "loss": 0.5478,
+      "step": 6789
+    },
+    {
+      "epoch": 0.09088001705666009,
+      "grad_norm": 1.2302749156951904,
+      "learning_rate": 4.599771961937391e-05,
+      "loss": 0.5533,
+      "step": 6820
+    },
+    {
+      "epoch": 0.09129310804328128,
+      "grad_norm": 1.0990760326385498,
+      "learning_rate": 4.5952021651364204e-05,
+      "loss": 0.5478,
+      "step": 6851
+    },
+    {
+      "epoch": 0.09170619902990246,
+      "grad_norm": 1.0545024871826172,
+      "learning_rate": 4.590608724263786e-05,
+      "loss": 0.5485,
+      "step": 6882
+    },
+    {
+      "epoch": 0.09211929001652364,
+      "grad_norm": 1.2572954893112183,
+      "learning_rate": 4.585991691155845e-05,
+      "loss": 0.549,
+      "step": 6913
+    },
+    {
+      "epoch": 0.09253238100314483,
+      "grad_norm": 1.0393617153167725,
+      "learning_rate": 4.581351117915188e-05,
+      "loss": 0.5468,
+      "step": 6944
+    },
+    {
+      "epoch": 0.09294547198976601,
+      "grad_norm": 1.166468620300293,
+      "learning_rate": 4.5766870569100534e-05,
+      "loss": 0.5533,
+      "step": 6975
+    },
+    {
+      "epoch": 0.09335856297638719,
+      "grad_norm": 1.0553635358810425,
+      "learning_rate": 4.571999560773736e-05,
+      "loss": 0.5522,
+      "step": 7006
+    },
+    {
+      "epoch": 0.09377165396300836,
+      "grad_norm": 1.1469920873641968,
+      "learning_rate": 4.5672886824039915e-05,
+      "loss": 0.5435,
+      "step": 7037
+    },
+    {
+      "epoch": 0.09418474494962956,
+      "grad_norm": 1.146141767501831,
+      "learning_rate": 4.5625544749624435e-05,
+      "loss": 0.5517,
+      "step": 7068
+    },
+    {
+      "epoch": 0.09459783593625073,
+      "grad_norm": 1.1021755933761597,
+      "learning_rate": 4.5577969918739794e-05,
+      "loss": 0.5409,
+      "step": 7099
+    },
+    {
+      "epoch": 0.09501092692287191,
+      "grad_norm": 1.1548715829849243,
+      "learning_rate": 4.5530162868261486e-05,
+      "loss": 0.5499,
+      "step": 7130
+    },
+    {
+      "epoch": 0.09542401790949309,
+      "grad_norm": 1.1067438125610352,
+      "learning_rate": 4.548212413768558e-05,
+      "loss": 0.556,
+      "step": 7161
+    },
+    {
+      "epoch": 0.09583710889611428,
+      "grad_norm": 1.0406980514526367,
+      "learning_rate": 4.543385426912261e-05,
+      "loss": 0.5579,
+      "step": 7192
+    },
+    {
+      "epoch": 0.09625019988273546,
+      "grad_norm": 1.1400694847106934,
+      "learning_rate": 4.53853538072915e-05,
+      "loss": 0.5433,
+      "step": 7223
+    },
+    {
+      "epoch": 0.09666329086935664,
+      "grad_norm": 1.0272783041000366,
+      "learning_rate": 4.533662329951336e-05,
+      "loss": 0.5435,
+      "step": 7254
+    },
+    {
+      "epoch": 0.09707638185597782,
+      "grad_norm": 1.1258125305175781,
+      "learning_rate": 4.528766329570536e-05,
+      "loss": 0.5516,
+      "step": 7285
+    },
+    {
+      "epoch": 0.09748947284259901,
+      "grad_norm": 1.1714351177215576,
+      "learning_rate": 4.523847434837447e-05,
+      "loss": 0.5444,
+      "step": 7316
+    },
+    {
+      "epoch": 0.09790256382922019,
+      "grad_norm": 1.0947203636169434,
+      "learning_rate": 4.518905701261128e-05,
+      "loss": 0.5519,
+      "step": 7347
+    },
+    {
+      "epoch": 0.09831565481584137,
+      "grad_norm": 1.1234745979309082,
+      "learning_rate": 4.5139411846083715e-05,
+      "loss": 0.5473,
+      "step": 7378
+    },
+    {
+      "epoch": 0.09872874580246256,
+      "grad_norm": 1.1082202196121216,
+      "learning_rate": 4.508953940903073e-05,
+      "loss": 0.5523,
+      "step": 7409
+    },
+    {
+      "epoch": 0.09914183678908374,
+      "grad_norm": 0.9947293400764465,
+      "learning_rate": 4.5039440264255994e-05,
+      "loss": 0.5414,
+      "step": 7440
+    },
+    {
+      "epoch": 0.09955492777570492,
+      "grad_norm": 1.1444759368896484,
+      "learning_rate": 4.498911497712155e-05,
+      "loss": 0.5384,
+      "step": 7471
+    },
+    {
+      "epoch": 0.0999680187623261,
+      "grad_norm": 1.0334067344665527,
+      "learning_rate": 4.493856411554142e-05,
+      "loss": 0.544,
+      "step": 7502
+    },
+    {
+      "epoch": 0.10038110974894729,
+      "grad_norm": 1.1002888679504395,
+      "learning_rate": 4.4887788249975206e-05,
+      "loss": 0.543,
+      "step": 7533
+    },
+    {
+      "epoch": 0.10079420073556847,
+      "grad_norm": 1.0718462467193604,
+      "learning_rate": 4.4836787953421656e-05,
+      "loss": 0.5506,
+      "step": 7564
+    },
+    {
+      "epoch": 0.10120729172218965,
+      "grad_norm": 1.183435082435608,
+      "learning_rate": 4.478556380141218e-05,
+      "loss": 0.5504,
+      "step": 7595
+    },
+    {
+      "epoch": 0.10162038270881082,
+      "grad_norm": 1.103873372077942,
+      "learning_rate": 4.4734116372004375e-05,
+      "loss": 0.5423,
+      "step": 7626
+    },
+    {
+      "epoch": 0.10203347369543202,
+      "grad_norm": 1.0666998624801636,
+      "learning_rate": 4.4682446245775477e-05,
+      "loss": 0.5413,
+      "step": 7657
+    },
+    {
+      "epoch": 0.1024465646820532,
+      "grad_norm": 1.063583493232727,
+      "learning_rate": 4.463055400581586e-05,
+      "loss": 0.5421,
+      "step": 7688
+    },
+    {
+      "epoch": 0.10285965566867437,
+      "grad_norm": 1.0938667058944702,
+      "learning_rate": 4.4578440237722374e-05,
+      "loss": 0.5456,
+      "step": 7719
+    },
+    {
+      "epoch": 0.10327274665529557,
+      "grad_norm": 1.0393413305282593,
+      "learning_rate": 4.452610552959183e-05,
+      "loss": 0.5434,
+      "step": 7750
+    },
+    {
+      "epoch": 0.10368583764191674,
+      "grad_norm": 1.25576651096344,
+      "learning_rate": 4.447355047201428e-05,
+      "loss": 0.5445,
+      "step": 7781
+    },
+    {
+      "epoch": 0.10409892862853792,
+      "grad_norm": 1.1197351217269897,
+      "learning_rate": 4.4420775658066414e-05,
+      "loss": 0.5344,
+      "step": 7812
+    },
+    {
+      "epoch": 0.1045120196151591,
+      "grad_norm": 1.1641823053359985,
+      "learning_rate": 4.436778168330484e-05,
+      "loss": 0.5402,
+      "step": 7843
+    },
+    {
+      "epoch": 0.1049251106017803,
+      "grad_norm": 1.0780788660049438,
+      "learning_rate": 4.4314569145759353e-05,
+      "loss": 0.5425,
+      "step": 7874
+    },
+    {
+      "epoch": 0.10533820158840147,
+      "grad_norm": 0.9938019514083862,
+      "learning_rate": 4.42611386459262e-05,
+      "loss": 0.5399,
+      "step": 7905
+    },
+    {
+      "epoch": 0.10575129257502265,
+      "grad_norm": 1.0470157861709595,
+      "learning_rate": 4.420749078676133e-05,
+      "loss": 0.5446,
+      "step": 7936
+    },
+    {
+      "epoch": 0.10616438356164383,
+      "grad_norm": 1.0025862455368042,
+      "learning_rate": 4.4153626173673516e-05,
+      "loss": 0.5454,
+      "step": 7967
+    },
+    {
+      "epoch": 0.10657747454826502,
+      "grad_norm": 1.056709885597229,
+      "learning_rate": 4.409954541451762e-05,
+      "loss": 0.5425,
+      "step": 7998
+    },
+    {
+      "epoch": 0.1069905655348862,
+      "grad_norm": 1.0551162958145142,
+      "learning_rate": 4.404524911958764e-05,
+      "loss": 0.5479,
+      "step": 8029
+    },
+    {
+      "epoch": 0.10740365652150738,
+      "grad_norm": 0.9484571814537048,
+      "learning_rate": 4.399073790160989e-05,
+      "loss": 0.5392,
+      "step": 8060
+    },
+    {
+      "epoch": 0.10781674750812857,
+      "grad_norm": 1.1029967069625854,
+      "learning_rate": 4.393601237573607e-05,
+      "loss": 0.5374,
+      "step": 8091
+    },
+    {
+      "epoch": 0.10822983849474975,
+      "grad_norm": 1.0562816858291626,
+      "learning_rate": 4.388107315953628e-05,
+      "loss": 0.5456,
+      "step": 8122
+    },
+    {
+      "epoch": 0.10864292948137093,
+      "grad_norm": 0.9414563179016113,
+      "learning_rate": 4.382592087299212e-05,
+      "loss": 0.54,
+      "step": 8153
+    },
+    {
+      "epoch": 0.1090560204679921,
+      "grad_norm": 1.0779579877853394,
+      "learning_rate": 4.377055613848964e-05,
+      "loss": 0.5364,
+      "step": 8184
+    },
+    {
+      "epoch": 0.1094691114546133,
+      "grad_norm": 1.0555373430252075,
+      "learning_rate": 4.3714979580812355e-05,
+      "loss": 0.5409,
+      "step": 8215
+    },
+    {
+      "epoch": 0.10988220244123448,
+      "grad_norm": 1.0759061574935913,
+      "learning_rate": 4.365919182713416e-05,
+      "loss": 0.5508,
+      "step": 8246
+    },
+    {
+      "epoch": 0.11029529342785566,
+      "grad_norm": 1.0753331184387207,
+      "learning_rate": 4.360319350701226e-05,
+      "loss": 0.5351,
+      "step": 8277
+    },
+    {
+      "epoch": 0.11070838441447683,
+      "grad_norm": 1.102331280708313,
+      "learning_rate": 4.3546985252380115e-05,
+      "loss": 0.5394,
+      "step": 8308
+    },
+    {
+      "epoch": 0.11112147540109803,
+      "grad_norm": 1.12419855594635,
+      "learning_rate": 4.349056769754021e-05,
+      "loss": 0.5348,
+      "step": 8339
+    },
+    {
+      "epoch": 0.1115345663877192,
+      "grad_norm": 0.9056191444396973,
+      "learning_rate": 4.3433941479156994e-05,
+      "loss": 0.5406,
+      "step": 8370
+    },
+    {
+      "epoch": 0.11194765737434038,
+      "grad_norm": 0.9976474046707153,
+      "learning_rate": 4.3377107236249647e-05,
+      "loss": 0.5391,
+      "step": 8401
+    },
+    {
+      "epoch": 0.11236074836096156,
+      "grad_norm": 1.0282542705535889,
+      "learning_rate": 4.332006561018488e-05,
+      "loss": 0.5419,
+      "step": 8432
+    },
+    {
+      "epoch": 0.11277383934758275,
+      "grad_norm": 0.9166244268417358,
+      "learning_rate": 4.3262817244669683e-05,
+      "loss": 0.5298,
+      "step": 8463
+    },
+    {
+      "epoch": 0.11318693033420393,
+      "grad_norm": 0.9751563668251038,
+      "learning_rate": 4.3205362785744083e-05,
+      "loss": 0.5426,
+      "step": 8494
+    },
+    {
+      "epoch": 0.11360002132082511,
+      "grad_norm": 1.0983715057373047,
+      "learning_rate": 4.314770288177384e-05,
+      "loss": 0.5312,
+      "step": 8525
+    },
+    {
+      "epoch": 0.1140131123074463,
+      "grad_norm": 1.097991943359375,
+      "learning_rate": 4.308983818344313e-05,
+      "loss": 0.5481,
+      "step": 8556
+    },
+    {
+      "epoch": 0.11442620329406748,
+      "grad_norm": 0.9918488264083862,
+      "learning_rate": 4.3031769343747206e-05,
+      "loss": 0.5395,
+      "step": 8587
+    },
+    {
+      "epoch": 0.11483929428068866,
+      "grad_norm": 1.0054724216461182,
+      "learning_rate": 4.297349701798505e-05,
+      "loss": 0.5476,
+      "step": 8618
+    },
+    {
+      "epoch": 0.11525238526730984,
+      "grad_norm": 1.1166927814483643,
+      "learning_rate": 4.2915021863751916e-05,
+      "loss": 0.532,
+      "step": 8649
+    },
+    {
+      "epoch": 0.11566547625393103,
+      "grad_norm": 1.0510430335998535,
+      "learning_rate": 4.285634454093198e-05,
+      "loss": 0.5416,
+      "step": 8680
+    },
+    {
+      "epoch": 0.11607856724055221,
+      "grad_norm": 1.0040204524993896,
+      "learning_rate": 4.279746571169086e-05,
+      "loss": 0.5371,
+      "step": 8711
+    },
+    {
+      "epoch": 0.11649165822717339,
+      "grad_norm": 1.09479820728302,
+      "learning_rate": 4.2738386040468136e-05,
+      "loss": 0.5331,
+      "step": 8742
+    },
+    {
+      "epoch": 0.11690474921379457,
+      "grad_norm": 1.0672197341918945,
+      "learning_rate": 4.2679106193969866e-05,
+      "loss": 0.5312,
+      "step": 8773
+    },
+    {
+      "epoch": 0.11731784020041576,
+      "grad_norm": 1.0281586647033691,
+      "learning_rate": 4.261962684116106e-05,
+      "loss": 0.5369,
+      "step": 8804
+    },
+    {
+      "epoch": 0.11773093118703694,
+      "grad_norm": 1.0801249742507935,
+      "learning_rate": 4.2559948653258145e-05,
+      "loss": 0.5431,
+      "step": 8835
+    },
+    {
+      "epoch": 0.11814402217365812,
+      "grad_norm": 1.0619101524353027,
+      "learning_rate": 4.250007230372134e-05,
+      "loss": 0.5422,
+      "step": 8866
+    },
+    {
+      "epoch": 0.11855711316027931,
+      "grad_norm": 1.2274117469787598,
+      "learning_rate": 4.2439998468247126e-05,
+      "loss": 0.5389,
+      "step": 8897
+    },
+    {
+      "epoch": 0.11897020414690049,
+      "grad_norm": 0.9519650936126709,
+      "learning_rate": 4.2379727824760566e-05,
+      "loss": 0.538,
+      "step": 8928
+    },
+    {
+      "epoch": 0.11938329513352167,
+      "grad_norm": 0.9227287769317627,
+      "learning_rate": 4.231926105340768e-05,
+      "loss": 0.5433,
+      "step": 8959
+    },
+    {
+      "epoch": 0.11979638612014284,
+      "grad_norm": 0.9438409805297852,
+      "learning_rate": 4.225859883654776e-05,
+      "loss": 0.522,
+      "step": 8990
+    },
+    {
+      "epoch": 0.12020947710676404,
+      "grad_norm": 1.0697333812713623,
+      "learning_rate": 4.219774185874569e-05,
+      "loss": 0.5349,
+      "step": 9021
+    },
+    {
+      "epoch": 0.12062256809338522,
+      "grad_norm": 1.2234184741973877,
+      "learning_rate": 4.213669080676418e-05,
+      "loss": 0.5452,
+      "step": 9052
+    },
+    {
+      "epoch": 0.1210356590800064,
+      "grad_norm": 0.9209390878677368,
+      "learning_rate": 4.2075446369556056e-05,
+      "loss": 0.5394,
+      "step": 9083
+    },
+    {
+      "epoch": 0.12144875006662757,
+      "grad_norm": 1.0253406763076782,
+      "learning_rate": 4.201400923825648e-05,
+      "loss": 0.5285,
+      "step": 9114
+    },
+    {
+      "epoch": 0.12186184105324877,
+      "grad_norm": 0.9712972640991211,
+      "learning_rate": 4.195238010617511e-05,
+      "loss": 0.5406,
+      "step": 9145
+    },
+    {
+      "epoch": 0.12227493203986994,
+      "grad_norm": 1.061253547668457,
+      "learning_rate": 4.1890559668788344e-05,
+      "loss": 0.5395,
+      "step": 9176
+    },
+    {
+      "epoch": 0.12268802302649112,
+      "grad_norm": 1.013018250465393,
+      "learning_rate": 4.1828548623731405e-05,
+      "loss": 0.5393,
+      "step": 9207
+    },
+    {
+      "epoch": 0.12310111401311231,
+      "grad_norm": 1.0512638092041016,
+      "learning_rate": 4.1766347670790506e-05,
+      "loss": 0.5365,
+      "step": 9238
+    },
+    {
+      "epoch": 0.12351420499973349,
+      "grad_norm": 1.135778784751892,
+      "learning_rate": 4.170395751189495e-05,
+      "loss": 0.5355,
+      "step": 9269
+    },
+    {
+      "epoch": 0.12392729598635467,
+      "grad_norm": 1.0950368642807007,
+      "learning_rate": 4.164137885110921e-05,
+      "loss": 0.533,
+      "step": 9300
+    },
+    {
+      "epoch": 0.12434038697297585,
+      "grad_norm": 0.9458414912223816,
+      "learning_rate": 4.157861239462495e-05,
+      "loss": 0.5363,
+      "step": 9331
+    },
+    {
+      "epoch": 0.12475347795959704,
+      "grad_norm": 1.1690454483032227,
+      "learning_rate": 4.1515658850753114e-05,
+      "loss": 0.5359,
+      "step": 9362
+    },
+    {
+      "epoch": 0.12516656894621822,
+      "grad_norm": 0.9780842065811157,
+      "learning_rate": 4.145251892991588e-05,
+      "loss": 0.5388,
+      "step": 9393
+    },
+    {
+      "epoch": 0.1255796599328394,
+      "grad_norm": 1.0521118640899658,
+      "learning_rate": 4.138919334463868e-05,
+      "loss": 0.5308,
+      "step": 9424
+    },
+    {
+      "epoch": 0.12599275091946058,
+      "grad_norm": 1.0956649780273438,
+      "learning_rate": 4.1325682809542124e-05,
+      "loss": 0.5373,
+      "step": 9455
+    },
+    {
+      "epoch": 0.12640584190608176,
+      "grad_norm": 1.0126162767410278,
+      "learning_rate": 4.126198804133398e-05,
+      "loss": 0.542,
+      "step": 9486
+    },
+    {
+      "epoch": 0.12681893289270293,
+      "grad_norm": 0.9837974309921265,
+      "learning_rate": 4.1198109758801055e-05,
+      "loss": 0.5345,
+      "step": 9517
+    },
+    {
+      "epoch": 0.12723202387932414,
+      "grad_norm": 1.0982171297073364,
+      "learning_rate": 4.113404868280107e-05,
+      "loss": 0.5434,
+      "step": 9548
+    },
+    {
+      "epoch": 0.12764511486594532,
+      "grad_norm": 1.1318964958190918,
+      "learning_rate": 4.106980553625457e-05,
+      "loss": 0.5373,
+      "step": 9579
+    },
+    {
+      "epoch": 0.1280582058525665,
+      "grad_norm": 1.057239294052124,
+      "learning_rate": 4.100538104413674e-05,
+      "loss": 0.5284,
+      "step": 9610
+    },
+    {
+      "epoch": 0.12847129683918768,
+      "grad_norm": 0.9291283488273621,
+      "learning_rate": 4.09407759334692e-05,
+      "loss": 0.5318,
+      "step": 9641
+    },
+    {
+      "epoch": 0.12888438782580885,
+      "grad_norm": 0.9519195556640625,
+      "learning_rate": 4.087599093331186e-05,
+      "loss": 0.5356,
+      "step": 9672
+    },
+    {
+      "epoch": 0.12929747881243003,
+      "grad_norm": 1.1019799709320068,
+      "learning_rate": 4.081102677475462e-05,
+      "loss": 0.5385,
+      "step": 9703
+    },
+    {
+      "epoch": 0.1297105697990512,
+      "grad_norm": 1.037335753440857,
+      "learning_rate": 4.0745884190909194e-05,
+      "loss": 0.5369,
+      "step": 9734
+    },
+    {
+      "epoch": 0.13012366078567242,
+      "grad_norm": 1.1294643878936768,
+      "learning_rate": 4.0680563916900796e-05,
+      "loss": 0.5391,
+      "step": 9765
+    },
+    {
+      "epoch": 0.1305367517722936,
+      "grad_norm": 1.0396963357925415,
+      "learning_rate": 4.0615066689859815e-05,
+      "loss": 0.5307,
+      "step": 9796
+    },
+    {
+      "epoch": 0.13094984275891478,
+      "grad_norm": 0.9373095035552979,
+      "learning_rate": 4.0549393248913584e-05,
+      "loss": 0.5283,
+      "step": 9827
+    },
+    {
+      "epoch": 0.13136293374553595,
+      "grad_norm": 1.0402830839157104,
+      "learning_rate": 4.048354433517794e-05,
+      "loss": 0.537,
+      "step": 9858
+    },
+    {
+      "epoch": 0.13177602473215713,
+      "grad_norm": 0.9721314907073975,
+      "learning_rate": 4.0417520691748916e-05,
+      "loss": 0.5337,
+      "step": 9889
+    },
+    {
+      "epoch": 0.1321891157187783,
+      "grad_norm": 1.034576654434204,
+      "learning_rate": 4.035132306369438e-05,
+      "loss": 0.5293,
+      "step": 9920
+    },
+    {
+      "epoch": 0.1326022067053995,
+      "grad_norm": 0.9360691905021667,
+      "learning_rate": 4.028495219804555e-05,
+      "loss": 0.5231,
+      "step": 9951
+    },
+    {
+      "epoch": 0.13301529769202067,
+      "grad_norm": 0.9475832581520081,
+      "learning_rate": 4.021840884378864e-05,
+      "loss": 0.5333,
+      "step": 9982
+    },
+    {
+      "epoch": 0.13342838867864187,
+      "grad_norm": 1.2746984958648682,
+      "learning_rate": 4.015169375185633e-05,
+      "loss": 0.533,
+      "step": 10013
+    },
+    {
+      "epoch": 0.13384147966526305,
+      "grad_norm": 0.9263701438903809,
+      "learning_rate": 4.0084807675119396e-05,
+      "loss": 0.5333,
+      "step": 10044
+    },
+    {
+      "epoch": 0.13425457065188423,
+      "grad_norm": 1.1046397686004639,
+      "learning_rate": 4.0017751368378106e-05,
+      "loss": 0.5231,
+      "step": 10075
+    },
+    {
+      "epoch": 0.1346676616385054,
+      "grad_norm": 0.9775460958480835,
+      "learning_rate": 3.995052558835377e-05,
+      "loss": 0.5293,
+      "step": 10106
+    },
+    {
+      "epoch": 0.1350807526251266,
+      "grad_norm": 1.0007810592651367,
+      "learning_rate": 3.988313109368017e-05,
+      "loss": 0.532,
+      "step": 10137
+    },
+    {
+      "epoch": 0.13549384361174777,
+      "grad_norm": 0.9684426188468933,
+      "learning_rate": 3.981556864489504e-05,
+      "loss": 0.5325,
+      "step": 10168
+    },
+    {
+      "epoch": 0.13590693459836894,
+      "grad_norm": 0.9456707239151001,
+      "learning_rate": 3.974783900443142e-05,
+      "loss": 0.5318,
+      "step": 10199
+    },
+    {
+      "epoch": 0.13632002558499015,
+      "grad_norm": 0.9617980718612671,
+      "learning_rate": 3.9679942936609095e-05,
+      "loss": 0.5343,
+      "step": 10230
+    },
+    {
+      "epoch": 0.13673311657161133,
+      "grad_norm": 0.8974958062171936,
+      "learning_rate": 3.961188120762596e-05,
+      "loss": 0.5366,
+      "step": 10261
+    },
+    {
+      "epoch": 0.1371462075582325,
+      "grad_norm": 0.9820188283920288,
+      "learning_rate": 3.954365458554938e-05,
+      "loss": 0.5324,
+      "step": 10292
+    },
+    {
+      "epoch": 0.1375592985448537,
+      "grad_norm": 0.9622596502304077,
+      "learning_rate": 3.947526384030751e-05,
+      "loss": 0.5341,
+      "step": 10323
+    },
+    {
+      "epoch": 0.13797238953147486,
+      "grad_norm": 0.9804188013076782,
+      "learning_rate": 3.9406709743680624e-05,
+      "loss": 0.5378,
+      "step": 10354
+    },
+    {
+      "epoch": 0.13838548051809604,
+      "grad_norm": 0.9729393124580383,
+      "learning_rate": 3.9337993069292366e-05,
+      "loss": 0.5272,
+      "step": 10385
+    },
+    {
+      "epoch": 0.13879857150471722,
+      "grad_norm": 0.92665034532547,
+      "learning_rate": 3.926911459260109e-05,
+      "loss": 0.5303,
+      "step": 10416
+    },
+    {
+      "epoch": 0.13921166249133843,
+      "grad_norm": 0.9971998929977417,
+      "learning_rate": 3.920007509089102e-05,
+      "loss": 0.5252,
+      "step": 10447
+    },
+    {
+      "epoch": 0.1396247534779596,
+      "grad_norm": 1.0753793716430664,
+      "learning_rate": 3.913087534326357e-05,
+      "loss": 0.537,
+      "step": 10478
+    },
+    {
+      "epoch": 0.14003784446458079,
+      "grad_norm": 0.9312607645988464,
+      "learning_rate": 3.9061516130628475e-05,
+      "loss": 0.5316,
+      "step": 10509
+    },
+    {
+      "epoch": 0.14045093545120196,
+      "grad_norm": 17.248607635498047,
+      "learning_rate": 3.8991998235695025e-05,
+      "loss": 0.526,
+      "step": 10540
+    },
+    {
+      "epoch": 0.14086402643782314,
+      "grad_norm": 1.0167644023895264,
+      "learning_rate": 3.8922322442963224e-05,
+      "loss": 0.5238,
+      "step": 10571
+    },
+    {
+      "epoch": 0.14127711742444432,
+      "grad_norm": 0.9811276197433472,
+      "learning_rate": 3.885248953871491e-05,
+      "loss": 0.5328,
+      "step": 10602
+    },
+    {
+      "epoch": 0.1416902084110655,
+      "grad_norm": 1.129286289215088,
+      "learning_rate": 3.8782500311004915e-05,
+      "loss": 0.5275,
+      "step": 10633
+    },
+    {
+      "epoch": 0.14210329939768668,
+      "grad_norm": 1.0486767292022705,
+      "learning_rate": 3.871235554965218e-05,
+      "loss": 0.5272,
+      "step": 10664
+    },
+    {
+      "epoch": 0.14251639038430788,
+      "grad_norm": 0.9465457201004028,
+      "learning_rate": 3.864205604623078e-05,
+      "loss": 0.5248,
+      "step": 10695
+    },
+    {
+      "epoch": 0.14292948137092906,
+      "grad_norm": 0.9920647144317627,
+      "learning_rate": 3.857160259406107e-05,
+      "loss": 0.5245,
+      "step": 10726
+    },
+    {
+      "epoch": 0.14334257235755024,
+      "grad_norm": 0.9076328873634338,
+      "learning_rate": 3.8500995988200674e-05,
+      "loss": 0.529,
+      "step": 10757
+    },
+    {
+      "epoch": 0.14375566334417142,
+      "grad_norm": 0.9154751300811768,
+      "learning_rate": 3.843023702543556e-05,
+      "loss": 0.5306,
+      "step": 10788
+    },
+    {
+      "epoch": 0.1441687543307926,
+      "grad_norm": 0.9825078248977661,
+      "learning_rate": 3.8359326504270984e-05,
+      "loss": 0.5198,
+      "step": 10819
+    },
+    {
+      "epoch": 0.14458184531741378,
+      "grad_norm": 0.9019172787666321,
+      "learning_rate": 3.828826522492255e-05,
+      "loss": 0.5292,
+      "step": 10850
+    },
+    {
+      "epoch": 0.14499493630403495,
+      "grad_norm": 1.0313316583633423,
+      "learning_rate": 3.821705398930713e-05,
+      "loss": 0.5265,
+      "step": 10881
+    },
+    {
+      "epoch": 0.14540802729065616,
+      "grad_norm": 0.9543335437774658,
+      "learning_rate": 3.814569360103385e-05,
+      "loss": 0.5287,
+      "step": 10912
+    },
+    {
+      "epoch": 0.14582111827727734,
+      "grad_norm": 0.9947319626808167,
+      "learning_rate": 3.807418486539499e-05,
+      "loss": 0.5199,
+      "step": 10943
+    },
+    {
+      "epoch": 0.14623420926389852,
+      "grad_norm": 0.8942686319351196,
+      "learning_rate": 3.80025285893569e-05,
+      "loss": 0.5295,
+      "step": 10974
+    },
+    {
+      "epoch": 0.1466473002505197,
+      "grad_norm": 0.9580740332603455,
+      "learning_rate": 3.793072558155093e-05,
+      "loss": 0.5283,
+      "step": 11005
+    },
+    {
+      "epoch": 0.14706039123714088,
+      "grad_norm": 0.9931619763374329,
+      "learning_rate": 3.785877665226426e-05,
+      "loss": 0.5247,
+      "step": 11036
+    },
+    {
+      "epoch": 0.14747348222376205,
+      "grad_norm": 0.9722700119018555,
+      "learning_rate": 3.778668261343079e-05,
+      "loss": 0.5155,
+      "step": 11067
+    },
+    {
+      "epoch": 0.14788657321038323,
+      "grad_norm": 0.9177893400192261,
+      "learning_rate": 3.771444427862192e-05,
+      "loss": 0.5352,
+      "step": 11098
+    },
+    {
+      "epoch": 0.1482996641970044,
+      "grad_norm": 0.8644802570343018,
+      "learning_rate": 3.7642062463037465e-05,
+      "loss": 0.5291,
+      "step": 11129
+    },
+    {
+      "epoch": 0.14871275518362562,
+      "grad_norm": 0.966018795967102,
+      "learning_rate": 3.7569537983496373e-05,
+      "loss": 0.5287,
+      "step": 11160
+    },
+    {
+      "epoch": 0.1491258461702468,
+      "grad_norm": 1.011587381362915,
+      "learning_rate": 3.749687165842753e-05,
+      "loss": 0.5311,
+      "step": 11191
+    },
+    {
+      "epoch": 0.14953893715686797,
+      "grad_norm": 0.8799782395362854,
+      "learning_rate": 3.7424064307860536e-05,
+      "loss": 0.5317,
+      "step": 11222
+    },
+    {
+      "epoch": 0.14995202814348915,
+      "grad_norm": 1.0629059076309204,
+      "learning_rate": 3.735111675341645e-05,
+      "loss": 0.5258,
+      "step": 11253
+    },
+    {
+      "epoch": 0.15036511913011033,
+      "grad_norm": 0.9715782999992371,
+      "learning_rate": 3.7278029818298524e-05,
+      "loss": 0.5226,
+      "step": 11284
+    },
+    {
+      "epoch": 0.1507782101167315,
+      "grad_norm": 0.9714763760566711,
+      "learning_rate": 3.720480432728287e-05,
+      "loss": 0.5273,
+      "step": 11315
+    },
+    {
+      "epoch": 0.1511913011033527,
+      "grad_norm": 1.0213080644607544,
+      "learning_rate": 3.71314411067092e-05,
+      "loss": 0.531,
+      "step": 11346
+    },
+    {
+      "epoch": 0.1516043920899739,
+      "grad_norm": 0.9357346892356873,
+      "learning_rate": 3.70579409844715e-05,
+      "loss": 0.5263,
+      "step": 11377
+    },
+    {
+      "epoch": 0.15201748307659507,
+      "grad_norm": 0.8755837678909302,
+      "learning_rate": 3.698430479000865e-05,
+      "loss": 0.5258,
+      "step": 11408
+    },
+    {
+      "epoch": 0.15243057406321625,
+      "grad_norm": 1.0663820505142212,
+      "learning_rate": 3.691053335429509e-05,
+      "loss": 0.5307,
+      "step": 11439
+    },
+    {
+      "epoch": 0.15284366504983743,
+      "grad_norm": 1.00916588306427,
+      "learning_rate": 3.683662750983147e-05,
+      "loss": 0.5313,
+      "step": 11470
+    },
+    {
+      "epoch": 0.1532567560364586,
+      "grad_norm": 0.9121434092521667,
+      "learning_rate": 3.676258809063518e-05,
+      "loss": 0.5223,
+      "step": 11501
+    },
+    {
+      "epoch": 0.1536698470230798,
+      "grad_norm": 1.0766927003860474,
+      "learning_rate": 3.6688415932231004e-05,
+      "loss": 0.5292,
+      "step": 11532
+    },
+    {
+      "epoch": 0.15408293800970096,
+      "grad_norm": 0.9861842393875122,
+      "learning_rate": 3.661411187164166e-05,
+      "loss": 0.5308,
+      "step": 11563
+    },
+    {
+      "epoch": 0.15449602899632217,
+      "grad_norm": 0.9004590511322021,
+      "learning_rate": 3.65396767473784e-05,
+      "loss": 0.5248,
+      "step": 11594
+    },
+    {
+      "epoch": 0.15490911998294335,
+      "grad_norm": 0.9889851808547974,
+      "learning_rate": 3.6465111399431465e-05,
+      "loss": 0.5238,
+      "step": 11625
+    },
+    {
+      "epoch": 0.15532221096956453,
+      "grad_norm": 0.9279220104217529,
+      "learning_rate": 3.6390416669260674e-05,
+      "loss": 0.5256,
+      "step": 11656
+    },
+    {
+      "epoch": 0.1557353019561857,
+      "grad_norm": 0.9274734854698181,
+      "learning_rate": 3.63155933997859e-05,
+      "loss": 0.5251,
+      "step": 11687
+    },
+    {
+      "epoch": 0.15614839294280689,
+      "grad_norm": 0.9462859630584717,
+      "learning_rate": 3.624064243537758e-05,
+      "loss": 0.5194,
+      "step": 11718
+    },
+    {
+      "epoch": 0.15656148392942806,
+      "grad_norm": 0.9593139290809631,
+      "learning_rate": 3.616556462184716e-05,
+      "loss": 0.5309,
+      "step": 11749
+    },
+    {
+      "epoch": 0.15697457491604924,
+      "grad_norm": 0.9378939867019653,
+      "learning_rate": 3.609036080643755e-05,
+      "loss": 0.5202,
+      "step": 11780
+    },
+    {
+      "epoch": 0.15738766590267042,
+      "grad_norm": 0.9623219966888428,
+      "learning_rate": 3.60150318378136e-05,
+      "loss": 0.5305,
+      "step": 11811
+    },
+    {
+      "epoch": 0.15780075688929163,
+      "grad_norm": 0.9675399661064148,
+      "learning_rate": 3.5939578566052465e-05,
+      "loss": 0.517,
+      "step": 11842
+    },
+    {
+      "epoch": 0.1582138478759128,
+      "grad_norm": 0.879499077796936,
+      "learning_rate": 3.586400184263408e-05,
+      "loss": 0.5173,
+      "step": 11873
+    },
+    {
+      "epoch": 0.15862693886253398,
+      "grad_norm": 0.9628081321716309,
+      "learning_rate": 3.578830252043148e-05,
+      "loss": 0.5168,
+      "step": 11904
+    },
+    {
+      "epoch": 0.15904002984915516,
+      "grad_norm": 0.9134719371795654,
+      "learning_rate": 3.571248145370125e-05,
+      "loss": 0.5238,
+      "step": 11935
+    },
+    {
+      "epoch": 0.15945312083577634,
+      "grad_norm": 1.1653165817260742,
+      "learning_rate": 3.5636539498073794e-05,
+      "loss": 0.5315,
+      "step": 11966
+    },
+    {
+      "epoch": 0.15986621182239752,
+      "grad_norm": 0.9131725430488586,
+      "learning_rate": 3.556047751054378e-05,
+      "loss": 0.5241,
+      "step": 11997
+    },
+    {
+      "epoch": 0.1602793028090187,
+      "grad_norm": 0.9258815050125122,
+      "learning_rate": 3.548429634946039e-05,
+      "loss": 0.5217,
+      "step": 12028
+    },
+    {
+      "epoch": 0.1606923937956399,
+      "grad_norm": 1.0134795904159546,
+      "learning_rate": 3.540799687451768e-05,
+      "loss": 0.5227,
+      "step": 12059
+    },
+    {
+      "epoch": 0.16110548478226108,
+      "grad_norm": 1.0026469230651855,
+      "learning_rate": 3.533157994674485e-05,
+      "loss": 0.5211,
+      "step": 12090
+    },
+    {
+      "epoch": 0.16151857576888226,
+      "grad_norm": 1.0012801885604858,
+      "learning_rate": 3.5255046428496546e-05,
+      "loss": 0.5326,
+      "step": 12121
+    },
+    {
+      "epoch": 0.16193166675550344,
+      "grad_norm": 1.0209020376205444,
+      "learning_rate": 3.517839718344311e-05,
+      "loss": 0.5201,
+      "step": 12152
+    },
+    {
+      "epoch": 0.16234475774212462,
+      "grad_norm": 0.9673867225646973,
+      "learning_rate": 3.510163307656086e-05,
+      "loss": 0.5241,
+      "step": 12183
+    },
+    {
+      "epoch": 0.1627578487287458,
+      "grad_norm": 1.1046918630599976,
+      "learning_rate": 3.5024754974122324e-05,
+      "loss": 0.5298,
+      "step": 12214
+    },
+    {
+      "epoch": 0.16317093971536697,
+      "grad_norm": 1.052362084388733,
+      "learning_rate": 3.494776374368643e-05,
+      "loss": 0.5304,
+      "step": 12245
+    },
+    {
+      "epoch": 0.16358403070198815,
+      "grad_norm": 3.204735279083252,
+      "learning_rate": 3.4870660254088724e-05,
+      "loss": 0.5238,
+      "step": 12276
+    },
+    {
+      "epoch": 0.16399712168860936,
+      "grad_norm": 0.8798376321792603,
+      "learning_rate": 3.479344537543164e-05,
+      "loss": 0.5219,
+      "step": 12307
+    },
+    {
+      "epoch": 0.16441021267523054,
+      "grad_norm": 1.0525151491165161,
+      "learning_rate": 3.4716119979074565e-05,
+      "loss": 0.5268,
+      "step": 12338
+    },
+    {
+      "epoch": 0.16482330366185172,
+      "grad_norm": 0.9635462164878845,
+      "learning_rate": 3.463868493762412e-05,
+      "loss": 0.5209,
+      "step": 12369
+    },
+    {
+      "epoch": 0.1652363946484729,
+      "grad_norm": 0.9930406808853149,
+      "learning_rate": 3.456114112492418e-05,
+      "loss": 0.5276,
+      "step": 12400
+    },
+    {
+      "epoch": 0.16564948563509407,
+      "grad_norm": 1.0104107856750488,
+      "learning_rate": 3.4483489416046164e-05,
+      "loss": 0.5256,
+      "step": 12431
+    },
+    {
+      "epoch": 0.16606257662171525,
+      "grad_norm": 0.915980339050293,
+      "learning_rate": 3.440573068727905e-05,
+      "loss": 0.5282,
+      "step": 12462
+    },
+    {
+      "epoch": 0.16647566760833643,
+      "grad_norm": 1.0312139987945557,
+      "learning_rate": 3.4327865816119495e-05,
+      "loss": 0.5198,
+      "step": 12493
+    },
+    {
+      "epoch": 0.16688875859495764,
+      "grad_norm": 0.9392731785774231,
+      "learning_rate": 3.4249895681262025e-05,
+      "loss": 0.5219,
+      "step": 12524
+    },
+    {
+      "epoch": 0.16730184958157882,
+      "grad_norm": 0.9843175411224365,
+      "learning_rate": 3.417182116258899e-05,
+      "loss": 0.5183,
+      "step": 12555
+    },
+    {
+      "epoch": 0.1677149405682,
+      "grad_norm": 0.950403094291687,
+      "learning_rate": 3.409364314116074e-05,
+      "loss": 0.5231,
+      "step": 12586
+    },
+    {
+      "epoch": 0.16812803155482117,
+      "grad_norm": 0.9682847261428833,
+      "learning_rate": 3.401536249920559e-05,
+      "loss": 0.5099,
+      "step": 12617
+    },
+    {
+      "epoch": 0.16854112254144235,
+      "grad_norm": 0.8852219581604004,
+      "learning_rate": 3.393698012010998e-05,
+      "loss": 0.525,
+      "step": 12648
+    },
+    {
+      "epoch": 0.16895421352806353,
+      "grad_norm": 0.9549787640571594,
+      "learning_rate": 3.385849688840839e-05,
+      "loss": 0.5168,
+      "step": 12679
+    },
+    {
+      "epoch": 0.1693673045146847,
+      "grad_norm": 1.054442048072815,
+      "learning_rate": 3.3779913689773414e-05,
+      "loss": 0.5222,
+      "step": 12710
+    },
+    {
+      "epoch": 0.16978039550130591,
+      "grad_norm": 0.8877145051956177,
+      "learning_rate": 3.370123141100578e-05,
+      "loss": 0.526,
+      "step": 12741
+    },
+    {
+      "epoch": 0.1701934864879271,
+      "grad_norm": 0.9739840626716614,
+      "learning_rate": 3.3622450940024305e-05,
+      "loss": 0.5201,
+      "step": 12772
+    },
+    {
+      "epoch": 0.17060657747454827,
+      "grad_norm": 0.8343369960784912,
+      "learning_rate": 3.35435731658559e-05,
+      "loss": 0.527,
+      "step": 12803
+    },
+    {
+      "epoch": 0.17101966846116945,
+      "grad_norm": 0.8745070099830627,
+      "learning_rate": 3.346459897862552e-05,
+      "loss": 0.531,
+      "step": 12834
+    },
+    {
+      "epoch": 0.17143275944779063,
+      "grad_norm": 0.912939190864563,
+      "learning_rate": 3.338552926954613e-05,
+      "loss": 0.5166,
+      "step": 12865
+    },
+    {
+      "epoch": 0.1718458504344118,
+      "grad_norm": 0.9602261781692505,
+      "learning_rate": 3.330636493090868e-05,
+      "loss": 0.5206,
+      "step": 12896
+    },
+    {
+      "epoch": 0.17225894142103299,
+      "grad_norm": 0.8753561973571777,
+      "learning_rate": 3.322710685607193e-05,
+      "loss": 0.5182,
+      "step": 12927
+    },
+    {
+      "epoch": 0.17267203240765416,
+      "grad_norm": 0.9468370676040649,
+      "learning_rate": 3.314775593945251e-05,
+      "loss": 0.5157,
+      "step": 12958
+    },
+    {
+      "epoch": 0.17308512339427537,
+      "grad_norm": 0.8600547313690186,
+      "learning_rate": 3.3068313076514714e-05,
+      "loss": 0.5208,
+      "step": 12989
+    },
+    {
+      "epoch": 0.17349821438089655,
+      "grad_norm": 1.0036487579345703,
+      "learning_rate": 3.298877916376047e-05,
+      "loss": 0.5121,
+      "step": 13020
+    },
+    {
+      "epoch": 0.17391130536751773,
+      "grad_norm": 1.1333731412887573,
+      "learning_rate": 3.290915509871915e-05,
+      "loss": 0.5177,
+      "step": 13051
+    },
+    {
+      "epoch": 0.1743243963541389,
+      "grad_norm": 0.9600626826286316,
+      "learning_rate": 3.282944177993753e-05,
+      "loss": 0.5185,
+      "step": 13082
+    },
+    {
+      "epoch": 0.17473748734076008,
+      "grad_norm": 1.0184615850448608,
+      "learning_rate": 3.274964010696957e-05,
+      "loss": 0.5258,
+      "step": 13113
+    },
+    {
+      "epoch": 0.17515057832738126,
+      "grad_norm": 0.9132828712463379,
+      "learning_rate": 3.266975098036629e-05,
+      "loss": 0.5184,
+      "step": 13144
+    },
+    {
+      "epoch": 0.17556366931400244,
+      "grad_norm": 1.0502389669418335,
+      "learning_rate": 3.258977530166562e-05,
+      "loss": 0.5263,
+      "step": 13175
+    },
+    {
+      "epoch": 0.17597676030062365,
+      "grad_norm": 0.9535905718803406,
+      "learning_rate": 3.250971397338227e-05,
+      "loss": 0.5177,
+      "step": 13206
+    },
+    {
+      "epoch": 0.17638985128724483,
+      "grad_norm": 1.026796579360962,
+      "learning_rate": 3.2429567898997404e-05,
+      "loss": 0.5189,
+      "step": 13237
+    },
+    {
+      "epoch": 0.176802942273866,
+      "grad_norm": 0.9277759194374084,
+      "learning_rate": 3.234933798294859e-05,
+      "loss": 0.5242,
+      "step": 13268
+    },
+    {
+      "epoch": 0.17721603326048718,
+      "grad_norm": 0.9420998096466064,
+      "learning_rate": 3.2269025130619535e-05,
+      "loss": 0.5229,
+      "step": 13299
+    },
+    {
+      "epoch": 0.17762912424710836,
+      "grad_norm": 0.8295450806617737,
+      "learning_rate": 3.218863024832985e-05,
+      "loss": 0.5119,
+      "step": 13330
+    },
+    {
+      "epoch": 0.17804221523372954,
+      "grad_norm": 0.8931427001953125,
+      "learning_rate": 3.2108154243324864e-05,
+      "loss": 0.5195,
+      "step": 13361
+    },
+    {
+      "epoch": 0.17845530622035072,
+      "grad_norm": 0.9380717873573303,
+      "learning_rate": 3.2027598023765345e-05,
+      "loss": 0.5188,
+      "step": 13392
+    },
+    {
+      "epoch": 0.1788683972069719,
+      "grad_norm": 0.9600290656089783,
+      "learning_rate": 3.194696249871729e-05,
+      "loss": 0.5169,
+      "step": 13423
+    },
+    {
+      "epoch": 0.1792814881935931,
+      "grad_norm": 1.0242196321487427,
+      "learning_rate": 3.186624857814164e-05,
+      "loss": 0.5225,
+      "step": 13454
+    },
+    {
+      "epoch": 0.17969457918021428,
+      "grad_norm": 0.8887470364570618,
+      "learning_rate": 3.178545717288401e-05,
+      "loss": 0.5299,
+      "step": 13485
+    },
+    {
+      "epoch": 0.18010767016683546,
+      "grad_norm": 0.9874518513679504,
+      "learning_rate": 3.170458919466444e-05,
+      "loss": 0.5194,
+      "step": 13516
+    },
+    {
+      "epoch": 0.18052076115345664,
+      "grad_norm": 0.9211225509643555,
+      "learning_rate": 3.1623645556067063e-05,
+      "loss": 0.5191,
+      "step": 13547
+    },
+    {
+      "epoch": 0.18093385214007782,
+      "grad_norm": 0.8895942568778992,
+      "learning_rate": 3.154262717052985e-05,
+      "loss": 0.5123,
+      "step": 13578
+    },
+    {
+      "epoch": 0.181346943126699,
+      "grad_norm": 1.074035882949829,
+      "learning_rate": 3.146153495233426e-05,
+      "loss": 0.5196,
+      "step": 13609
+    },
+    {
+      "epoch": 0.18176003411332017,
+      "grad_norm": 0.8590953946113586,
+      "learning_rate": 3.1380369816594944e-05,
+      "loss": 0.5123,
+      "step": 13640
+    },
+    {
+      "epoch": 0.18217312509994138,
+      "grad_norm": 0.9919266104698181,
+      "learning_rate": 3.129913267924946e-05,
+      "loss": 0.5111,
+      "step": 13671
+    },
+    {
+      "epoch": 0.18258621608656256,
+      "grad_norm": 0.8908241391181946,
+      "learning_rate": 3.121782445704782e-05,
+      "loss": 0.5181,
+      "step": 13702
+    },
+    {
+      "epoch": 0.18299930707318374,
+      "grad_norm": 0.9257848858833313,
+      "learning_rate": 3.11364460675423e-05,
+      "loss": 0.5147,
+      "step": 13733
+    },
+    {
+      "epoch": 0.18341239805980492,
+      "grad_norm": 0.9790043830871582,
+      "learning_rate": 3.1054998429076934e-05,
+      "loss": 0.5212,
+      "step": 13764
+    },
+    {
+      "epoch": 0.1838254890464261,
+      "grad_norm": 0.9997586011886597,
+      "learning_rate": 3.097348246077728e-05,
+      "loss": 0.5148,
+      "step": 13795
+    },
+    {
+      "epoch": 0.18423858003304727,
+      "grad_norm": 0.9129127860069275,
+      "learning_rate": 3.0891899082539924e-05,
+      "loss": 0.5111,
+      "step": 13826
+    },
+    {
+      "epoch": 0.18465167101966845,
+      "grad_norm": 0.9921712875366211,
+      "learning_rate": 3.0810249215022233e-05,
+      "loss": 0.5182,
+      "step": 13857
+    },
+    {
+      "epoch": 0.18506476200628966,
+      "grad_norm": 0.889397382736206,
+      "learning_rate": 3.0728533779631865e-05,
+      "loss": 0.5202,
+      "step": 13888
+    },
+    {
+      "epoch": 0.18547785299291084,
+      "grad_norm": 0.9874172210693359,
+      "learning_rate": 3.064675369851637e-05,
+      "loss": 0.5172,
+      "step": 13919
+    },
+    {
+      "epoch": 0.18589094397953201,
+      "grad_norm": 0.9039093852043152,
+      "learning_rate": 3.056490989455289e-05,
+      "loss": 0.5278,
+      "step": 13950
+    },
+    {
+      "epoch": 0.1863040349661532,
+      "grad_norm": 0.8875586986541748,
+      "learning_rate": 3.0483003291337596e-05,
+      "loss": 0.5182,
+      "step": 13981
+    },
+    {
+      "epoch": 0.18671712595277437,
+      "grad_norm": 0.8930432200431824,
+      "learning_rate": 3.040103481317539e-05,
+      "loss": 0.5169,
+      "step": 14012
+    },
+    {
+      "epoch": 0.18713021693939555,
+      "grad_norm": 1.0020161867141724,
+      "learning_rate": 3.03190053850694e-05,
+      "loss": 0.5192,
+      "step": 14043
+    },
+    {
+      "epoch": 0.18754330792601673,
+      "grad_norm": 0.8742198944091797,
+      "learning_rate": 3.0236915932710573e-05,
+      "loss": 0.5077,
+      "step": 14074
+    },
+    {
+      "epoch": 0.1879563989126379,
+      "grad_norm": 0.9943242073059082,
+      "learning_rate": 3.0154767382467232e-05,
+      "loss": 0.5226,
+      "step": 14105
+    },
+    {
+      "epoch": 0.1883694898992591,
+      "grad_norm": 0.9345620274543762,
+      "learning_rate": 3.0072560661374582e-05,
+      "loss": 0.5102,
+      "step": 14136
+    },
+    {
+      "epoch": 0.1887825808858803,
+      "grad_norm": 0.9132478833198547,
+      "learning_rate": 2.999029669712431e-05,
+      "loss": 0.5197,
+      "step": 14167
+    },
+    {
+      "epoch": 0.18919567187250147,
+      "grad_norm": 0.8798980712890625,
+      "learning_rate": 2.990797641805408e-05,
+      "loss": 0.5047,
+      "step": 14198
+    },
+    {
+      "epoch": 0.18960876285912265,
+      "grad_norm": 0.9469364285469055,
+      "learning_rate": 2.982560075313704e-05,
+      "loss": 0.5164,
+      "step": 14229
+    },
+    {
+      "epoch": 0.19002185384574383,
+      "grad_norm": 0.9300420880317688,
+      "learning_rate": 2.9743170631971368e-05,
+      "loss": 0.5222,
+      "step": 14260
+    },
+    {
+      "epoch": 0.190434944832365,
+      "grad_norm": 0.9043737649917603,
+      "learning_rate": 2.9660686984769792e-05,
+      "loss": 0.5066,
+      "step": 14291
+    },
+    {
+      "epoch": 0.19084803581898618,
+      "grad_norm": 0.9041194319725037,
+      "learning_rate": 2.9578150742349047e-05,
+      "loss": 0.5205,
+      "step": 14322
+    },
+    {
+      "epoch": 0.1912611268056074,
+      "grad_norm": 0.8952019810676575,
+      "learning_rate": 2.949556283611942e-05,
+      "loss": 0.5158,
+      "step": 14353
+    },
+    {
+      "epoch": 0.19167421779222857,
+      "grad_norm": 0.9866005778312683,
+      "learning_rate": 2.9412924198074206e-05,
+      "loss": 0.5106,
+      "step": 14384
+    },
+    {
+      "epoch": 0.19208730877884975,
+      "grad_norm": 0.8866041302680969,
+      "learning_rate": 2.9330235760779208e-05,
+      "loss": 0.5091,
+      "step": 14415
+    },
+    {
+      "epoch": 0.19250039976547093,
+      "grad_norm": 0.9534942507743835,
+      "learning_rate": 2.9247498457362188e-05,
+      "loss": 0.5152,
+      "step": 14446
+    },
+    {
+      "epoch": 0.1929134907520921,
+      "grad_norm": 0.9449177980422974,
+      "learning_rate": 2.9164713221502373e-05,
+      "loss": 0.5189,
+      "step": 14477
+    },
+    {
+      "epoch": 0.19332658173871328,
+      "grad_norm": 0.9900373816490173,
+      "learning_rate": 2.9081880987419912e-05,
+      "loss": 0.5171,
+      "step": 14508
+    },
+    {
+      "epoch": 0.19373967272533446,
+      "grad_norm": 0.9714763164520264,
+      "learning_rate": 2.8999002689865296e-05,
+      "loss": 0.5187,
+      "step": 14539
+    },
+    {
+      "epoch": 0.19415276371195564,
+      "grad_norm": 0.9779321551322937,
+      "learning_rate": 2.8916079264108852e-05,
+      "loss": 0.5206,
+      "step": 14570
+    },
+    {
+      "epoch": 0.19456585469857685,
+      "grad_norm": 0.8970730304718018,
+      "learning_rate": 2.883311164593017e-05,
+      "loss": 0.5161,
+      "step": 14601
+    },
+    {
+      "epoch": 0.19497894568519802,
+      "grad_norm": 0.9319660663604736,
+      "learning_rate": 2.875010077160754e-05,
+      "loss": 0.5075,
+      "step": 14632
+    },
+    {
+      "epoch": 0.1953920366718192,
+      "grad_norm": 0.8656150698661804,
+      "learning_rate": 2.866704757790741e-05,
+      "loss": 0.5199,
+      "step": 14663
+    },
+    {
+      "epoch": 0.19580512765844038,
+      "grad_norm": 0.8861721754074097,
+      "learning_rate": 2.858395300207376e-05,
+      "loss": 0.5083,
+      "step": 14694
+    },
+    {
+      "epoch": 0.19621821864506156,
+      "grad_norm": 0.9757127165794373,
+      "learning_rate": 2.8500817981817607e-05,
+      "loss": 0.5117,
+      "step": 14725
+    },
+    {
+      "epoch": 0.19663130963168274,
+      "grad_norm": 0.8593602180480957,
+      "learning_rate": 2.8417643455306336e-05,
+      "loss": 0.5151,
+      "step": 14756
+    },
+    {
+      "epoch": 0.19704440061830392,
+      "grad_norm": 0.9756207466125488,
+      "learning_rate": 2.8334430361153185e-05,
+      "loss": 0.5133,
+      "step": 14787
+    },
+    {
+      "epoch": 0.19745749160492512,
+      "grad_norm": 0.8687728047370911,
+      "learning_rate": 2.8251179638406612e-05,
+      "loss": 0.511,
+      "step": 14818
+    },
+    {
+      "epoch": 0.1978705825915463,
+      "grad_norm": 0.9320461750030518,
+      "learning_rate": 2.8167892226539704e-05,
+      "loss": 0.5148,
+      "step": 14849
+    },
+    {
+      "epoch": 0.19828367357816748,
+      "grad_norm": 0.904463529586792,
+      "learning_rate": 2.8084569065439588e-05,
+      "loss": 0.5182,
+      "step": 14880
+    },
+    {
+      "epoch": 0.19869676456478866,
+      "grad_norm": 0.8591788411140442,
+      "learning_rate": 2.8001211095396807e-05,
+      "loss": 0.511,
+      "step": 14911
+    },
+    {
+      "epoch": 0.19910985555140984,
+      "grad_norm": 1.0128686428070068,
+      "learning_rate": 2.791781925709473e-05,
+      "loss": 0.5202,
+      "step": 14942
+    },
+    {
+      "epoch": 0.19952294653803102,
+      "grad_norm": 1.059459924697876,
+      "learning_rate": 2.7834394491598908e-05,
+      "loss": 0.5152,
+      "step": 14973
+    },
+    {
+      "epoch": 0.1999360375246522,
+      "grad_norm": 1.2768211364746094,
+      "learning_rate": 2.7750937740346485e-05,
+      "loss": 0.5143,
+      "step": 15004
+    },
+    {
+      "epoch": 0.2003491285112734,
+      "grad_norm": 0.8835700750350952,
+      "learning_rate": 2.7667449945135564e-05,
+      "loss": 0.5111,
+      "step": 15035
+    },
+    {
+      "epoch": 0.20076221949789458,
+      "grad_norm": 0.9363453388214111,
+      "learning_rate": 2.7583932048114557e-05,
+      "loss": 0.5218,
+      "step": 15066
+    },
+    {
+      "epoch": 0.20117531048451576,
+      "grad_norm": 0.917850136756897,
+      "learning_rate": 2.7500384991771587e-05,
+      "loss": 0.5131,
+      "step": 15097
+    },
+    {
+      "epoch": 0.20158840147113694,
+      "grad_norm": 0.971145510673523,
+      "learning_rate": 2.7416809718923825e-05,
+      "loss": 0.5127,
+      "step": 15128
+    },
+    {
+      "epoch": 0.20200149245775811,
+      "grad_norm": 0.8991430401802063,
+      "learning_rate": 2.7333207172706864e-05,
+      "loss": 0.5127,
+      "step": 15159
+    },
+    {
+      "epoch": 0.2024145834443793,
+      "grad_norm": 0.9158385396003723,
+      "learning_rate": 2.7249578296564088e-05,
+      "loss": 0.5191,
+      "step": 15190
+    },
+    {
+      "epoch": 0.20282767443100047,
+      "grad_norm": 0.9155390858650208,
+      "learning_rate": 2.7165924034235973e-05,
+      "loss": 0.516,
+      "step": 15221
+    },
+    {
+      "epoch": 0.20324076541762165,
+      "grad_norm": 0.8593025207519531,
+      "learning_rate": 2.708224532974953e-05,
+      "loss": 0.5072,
+      "step": 15252
+    }
+  ],
+  "logging_steps": 31,
+  "max_steps": 30517,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 7630,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1258280394232955e+19,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-15260/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b625e00d3c9c951bf58d8e86629dc426b5ba69ab20f73252787562f5e27c9af
+size 5432

checkpoint-22890/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "meta-llama/Llama-3.1-8B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "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": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0.dev0",
+  "use_cache": true,
+  "vocab_size": 128256
+}

checkpoint-22890/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.47.0.dev0"
+}

checkpoint-22890/model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f814eb2cf72f45c86bd1a98c997db136f5d37454ed74f9a815ae1ea45e9ea58
+size 4886466168

checkpoint-22890/model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0901d2e156c6ec7a375c3e90ae5183970af0445d3dc0e53c031b45673775dd64
+size 4832007448

checkpoint-22890/model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afa0e22bcade9527b5aeb86066e139cc30979f8492c753ff3277e6189863ab97
+size 4999813112

checkpoint-22890/model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc4f5352f30ea036b0a4e24ba9b029dd94a2b30a716c81acc1c4a5e7bb47a042
+size 4999813128

checkpoint-22890/model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d9450b209df4cb026b6669e618fcdb6ff4f5bd0a711fb2e502afe0b95eb3ad7
+size 4832007496

checkpoint-22890/model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3fea4f82871abfacee9b64a2dac7104daed1af3d23269b67b6cecfcb8872e40
+size 4999813120

checkpoint-22890/model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76d70e00b54d34c4642d15cc3f6cae29c176caa061f10385339292ca39bd1f82
+size 2571158184

checkpoint-22890/model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 32121044992
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.norm.weight": "model-00007-of-00007.safetensors"
+  }
+}

checkpoint-22890/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5e0e6b683bbe30a4e1a8d54353f13d3b69f89632f764a95e1e3ab6b3f534c88
+size 15385036334

checkpoint-22890/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244

checkpoint-22890/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cceae98d85860224f83926a9c2d0797a9f4411abc8a933e66f23226e9ba794a
+size 1064

checkpoint-22890/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b625e00d3c9c951bf58d8e86629dc426b5ba69ab20f73252787562f5e27c9af
+size 5432

checkpoint-30517/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "meta-llama/Llama-3.1-8B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "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": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0.dev0",
+  "use_cache": true,
+  "vocab_size": 128256
+}

checkpoint-30517/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.47.0.dev0"
+}

checkpoint-30517/model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad5f996129aa6baa244833a201e9a33aeeb2fd91202949351a625f9ef31a51c
+size 4886466168

checkpoint-30517/model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0901d2e156c6ec7a375c3e90ae5183970af0445d3dc0e53c031b45673775dd64
+size 4832007448

checkpoint-30517/model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afa0e22bcade9527b5aeb86066e139cc30979f8492c753ff3277e6189863ab97
+size 4999813112

checkpoint-30517/model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc4f5352f30ea036b0a4e24ba9b029dd94a2b30a716c81acc1c4a5e7bb47a042
+size 4999813128

checkpoint-30517/model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d9450b209df4cb026b6669e618fcdb6ff4f5bd0a711fb2e502afe0b95eb3ad7
+size 4832007496

checkpoint-30517/model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a98c1282cc811c9c732eab527de83ff484e3fbbd7a8f736910372105fb519cf9
+size 4999813120

checkpoint-30517/model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fd5fe4232a7a009b49a235f55ccf81900cbad0a9bf0873ea70977a52d5b8554
+size 2571158184

checkpoint-30517/model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 32121044992
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.norm.weight": "model-00007-of-00007.safetensors"
+  }
+}

checkpoint-30517/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a36b50bde8e65a82599500420c588e919eadb7cbe6f35c4a8afdc1a06430ea1f
+size 15385036334

checkpoint-30517/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244

checkpoint-30517/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d91c597306f26392e8da0d33a09fdcca77cfdeb5ad42248045521772fa3d64e
+size 1064

checkpoint-30517/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b625e00d3c9c951bf58d8e86629dc426b5ba69ab20f73252787562f5e27c9af
+size 5432

checkpoint-7630/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "meta-llama/Llama-3.1-8B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "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": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0.dev0",
+  "use_cache": true,
+  "vocab_size": 128256
+}

checkpoint-7630/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.47.0.dev0"
+}

checkpoint-7630/model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6796869cd77944cc18b6d282b11ed40aaecb5445d0e7940da44aa02293fe5136
+size 4886466168

checkpoint-7630/model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0901d2e156c6ec7a375c3e90ae5183970af0445d3dc0e53c031b45673775dd64
+size 4832007448