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:e63b65c07b5ce6557f697ab139801d4866335de9447edd6af4cb8cac4d1b9004
+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 sha256:31f1426382999cbc18bce154e5ff7ef92eb4fac993d4c4cc5ddffe842caaa081
+size 4999813120

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f2195de5d64253b75610534c8313fc7a255453cf488826b106de825d1c60081
+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 sha256:09d4cbd0f7fa4845fad8ae7d0ec23e1b534598170e2751da243e2ef424c33d16
+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": 0.22409457202121996,
+  "eval_steps": 500,
+  "global_step": 15260,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0004552379903445491,
+      "grad_norm": 3.354947090148926,
+      "learning_rate": 1.0157273918741808e-06,
+      "loss": 0.8621,
+      "step": 31
+    },
+    {
+      "epoch": 0.0009104759806890982,
+      "grad_norm": 3.194267511367798,
+      "learning_rate": 2.0314547837483616e-06,
+      "loss": 0.8454,
+      "step": 62
+    },
+    {
+      "epoch": 0.0013657139710336473,
+      "grad_norm": 3.3418407440185547,
+      "learning_rate": 3.0471821756225426e-06,
+      "loss": 0.8311,
+      "step": 93
+    },
+    {
+      "epoch": 0.0018209519613781964,
+      "grad_norm": 3.1537938117980957,
+      "learning_rate": 4.062909567496723e-06,
+      "loss": 0.8223,
+      "step": 124
+    },
+    {
+      "epoch": 0.0022761899517227454,
+      "grad_norm": 3.0637929439544678,
+      "learning_rate": 5.078636959370905e-06,
+      "loss": 0.8209,
+      "step": 155
+    },
+    {
+      "epoch": 0.0027314279420672946,
+      "grad_norm": 2.962575912475586,
+      "learning_rate": 6.094364351245085e-06,
+      "loss": 0.8156,
+      "step": 186
+    },
+    {
+      "epoch": 0.0031866659324118435,
+      "grad_norm": 3.23154878616333,
+      "learning_rate": 7.110091743119267e-06,
+      "loss": 0.8072,
+      "step": 217
+    },
+    {
+      "epoch": 0.0036419039227563927,
+      "grad_norm": 3.17885684967041,
+      "learning_rate": 8.125819134993446e-06,
+      "loss": 0.8193,
+      "step": 248
+    },
+    {
+      "epoch": 0.0040971419131009415,
+      "grad_norm": 3.3038201332092285,
+      "learning_rate": 9.141546526867629e-06,
+      "loss": 0.8186,
+      "step": 279
+    },
+    {
+      "epoch": 0.004552379903445491,
+      "grad_norm": 3.0357906818389893,
+      "learning_rate": 1.015727391874181e-05,
+      "loss": 0.8234,
+      "step": 310
+    },
+    {
+      "epoch": 0.00500761789379004,
+      "grad_norm": 2.925551652908325,
+      "learning_rate": 1.117300131061599e-05,
+      "loss": 0.8185,
+      "step": 341
+    },
+    {
+      "epoch": 0.005462855884134589,
+      "grad_norm": 3.0318872928619385,
+      "learning_rate": 1.218872870249017e-05,
+      "loss": 0.8191,
+      "step": 372
+    },
+    {
+      "epoch": 0.005918093874479138,
+      "grad_norm": 3.2019152641296387,
+      "learning_rate": 1.3204456094364351e-05,
+      "loss": 0.8166,
+      "step": 403
+    },
+    {
+      "epoch": 0.006373331864823687,
+      "grad_norm": 2.833339214324951,
+      "learning_rate": 1.4220183486238533e-05,
+      "loss": 0.8246,
+      "step": 434
+    },
+    {
+      "epoch": 0.006828569855168236,
+      "grad_norm": 3.1772501468658447,
+      "learning_rate": 1.5235910878112714e-05,
+      "loss": 0.8209,
+      "step": 465
+    },
+    {
+      "epoch": 0.0072838078455127854,
+      "grad_norm": 2.8447930812835693,
+      "learning_rate": 1.6251638269986893e-05,
+      "loss": 0.8146,
+      "step": 496
+    },
+    {
+      "epoch": 0.007739045835857335,
+      "grad_norm": 2.5160751342773438,
+      "learning_rate": 1.7267365661861077e-05,
+      "loss": 0.8217,
+      "step": 527
+    },
+    {
+      "epoch": 0.008194283826201883,
+      "grad_norm": 2.843844413757324,
+      "learning_rate": 1.8283093053735257e-05,
+      "loss": 0.8166,
+      "step": 558
+    },
+    {
+      "epoch": 0.008649521816546433,
+      "grad_norm": 2.6248440742492676,
+      "learning_rate": 1.9298820445609438e-05,
+      "loss": 0.8237,
+      "step": 589
+    },
+    {
+      "epoch": 0.009104759806890982,
+      "grad_norm": 2.7390968799591064,
+      "learning_rate": 2.031454783748362e-05,
+      "loss": 0.8201,
+      "step": 620
+    },
+    {
+      "epoch": 0.00955999779723553,
+      "grad_norm": 2.612004518508911,
+      "learning_rate": 2.13302752293578e-05,
+      "loss": 0.8228,
+      "step": 651
+    },
+    {
+      "epoch": 0.01001523578758008,
+      "grad_norm": 2.6713650226593018,
+      "learning_rate": 2.234600262123198e-05,
+      "loss": 0.8213,
+      "step": 682
+    },
+    {
+      "epoch": 0.010470473777924628,
+      "grad_norm": 2.400465726852417,
+      "learning_rate": 2.336173001310616e-05,
+      "loss": 0.8241,
+      "step": 713
+    },
+    {
+      "epoch": 0.010925711768269179,
+      "grad_norm": 2.335400104522705,
+      "learning_rate": 2.437745740498034e-05,
+      "loss": 0.8266,
+      "step": 744
+    },
+    {
+      "epoch": 0.011380949758613727,
+      "grad_norm": 2.907315731048584,
+      "learning_rate": 2.5393184796854525e-05,
+      "loss": 0.8359,
+      "step": 775
+    },
+    {
+      "epoch": 0.011836187748958275,
+      "grad_norm": 2.607116937637329,
+      "learning_rate": 2.6408912188728702e-05,
+      "loss": 0.8286,
+      "step": 806
+    },
+    {
+      "epoch": 0.012291425739302825,
+      "grad_norm": 2.42545223236084,
+      "learning_rate": 2.7424639580602886e-05,
+      "loss": 0.825,
+      "step": 837
+    },
+    {
+      "epoch": 0.012746663729647374,
+      "grad_norm": 2.744816780090332,
+      "learning_rate": 2.8440366972477066e-05,
+      "loss": 0.8273,
+      "step": 868
+    },
+    {
+      "epoch": 0.013201901719991924,
+      "grad_norm": 2.3429465293884277,
+      "learning_rate": 2.9456094364351244e-05,
+      "loss": 0.8264,
+      "step": 899
+    },
+    {
+      "epoch": 0.013657139710336472,
+      "grad_norm": 2.5894381999969482,
+      "learning_rate": 3.0471821756225428e-05,
+      "loss": 0.8201,
+      "step": 930
+    },
+    {
+      "epoch": 0.01411237770068102,
+      "grad_norm": 2.2879245281219482,
+      "learning_rate": 3.148754914809961e-05,
+      "loss": 0.825,
+      "step": 961
+    },
+    {
+      "epoch": 0.014567615691025571,
+      "grad_norm": 2.494351863861084,
+      "learning_rate": 3.2503276539973785e-05,
+      "loss": 0.831,
+      "step": 992
+    },
+    {
+      "epoch": 0.01502285368137012,
+      "grad_norm": 2.097228527069092,
+      "learning_rate": 3.351900393184797e-05,
+      "loss": 0.8159,
+      "step": 1023
+    },
+    {
+      "epoch": 0.01547809167171467,
+      "grad_norm": 2.2551915645599365,
+      "learning_rate": 3.453473132372215e-05,
+      "loss": 0.829,
+      "step": 1054
+    },
+    {
+      "epoch": 0.015933329662059216,
+      "grad_norm": 2.3283045291900635,
+      "learning_rate": 3.555045871559633e-05,
+      "loss": 0.8309,
+      "step": 1085
+    },
+    {
+      "epoch": 0.016388567652403766,
+      "grad_norm": 2.0557940006256104,
+      "learning_rate": 3.6566186107470514e-05,
+      "loss": 0.8257,
+      "step": 1116
+    },
+    {
+      "epoch": 0.016843805642748316,
+      "grad_norm": 2.0314512252807617,
+      "learning_rate": 3.7581913499344695e-05,
+      "loss": 0.8287,
+      "step": 1147
+    },
+    {
+      "epoch": 0.017299043633092866,
+      "grad_norm": 2.169879913330078,
+      "learning_rate": 3.8597640891218876e-05,
+      "loss": 0.8283,
+      "step": 1178
+    },
+    {
+      "epoch": 0.017754281623437413,
+      "grad_norm": 2.334822654724121,
+      "learning_rate": 3.9613368283093056e-05,
+      "loss": 0.8348,
+      "step": 1209
+    },
+    {
+      "epoch": 0.018209519613781963,
+      "grad_norm": 2.1586616039276123,
+      "learning_rate": 4.062909567496724e-05,
+      "loss": 0.823,
+      "step": 1240
+    },
+    {
+      "epoch": 0.018664757604126513,
+      "grad_norm": 2.255127429962158,
+      "learning_rate": 4.164482306684142e-05,
+      "loss": 0.8201,
+      "step": 1271
+    },
+    {
+      "epoch": 0.01911999559447106,
+      "grad_norm": 2.2057130336761475,
+      "learning_rate": 4.26605504587156e-05,
+      "loss": 0.8251,
+      "step": 1302
+    },
+    {
+      "epoch": 0.01957523358481561,
+      "grad_norm": 2.153062582015991,
+      "learning_rate": 4.367627785058978e-05,
+      "loss": 0.8328,
+      "step": 1333
+    },
+    {
+      "epoch": 0.02003047157516016,
+      "grad_norm": 2.1553568840026855,
+      "learning_rate": 4.469200524246396e-05,
+      "loss": 0.8218,
+      "step": 1364
+    },
+    {
+      "epoch": 0.020485709565504707,
+      "grad_norm": 2.005182981491089,
+      "learning_rate": 4.570773263433814e-05,
+      "loss": 0.8123,
+      "step": 1395
+    },
+    {
+      "epoch": 0.020940947555849257,
+      "grad_norm": 1.9253156185150146,
+      "learning_rate": 4.672346002621232e-05,
+      "loss": 0.8216,
+      "step": 1426
+    },
+    {
+      "epoch": 0.021396185546193807,
+      "grad_norm": 2.0112476348876953,
+      "learning_rate": 4.77391874180865e-05,
+      "loss": 0.8288,
+      "step": 1457
+    },
+    {
+      "epoch": 0.021851423536538357,
+      "grad_norm": 2.1911792755126953,
+      "learning_rate": 4.875491480996068e-05,
+      "loss": 0.8234,
+      "step": 1488
+    },
+    {
+      "epoch": 0.022306661526882904,
+      "grad_norm": 1.9842109680175781,
+      "learning_rate": 4.977064220183487e-05,
+      "loss": 0.8199,
+      "step": 1519
+    },
+    {
+      "epoch": 0.022761899517227454,
+      "grad_norm": 2.333308219909668,
+      "learning_rate": 4.9999915451558777e-05,
+      "loss": 0.8188,
+      "step": 1550
+    },
+    {
+      "epoch": 0.023217137507572004,
+      "grad_norm": 1.9667329788208008,
+      "learning_rate": 4.999955597496219e-05,
+      "loss": 0.8173,
+      "step": 1581
+    },
+    {
+      "epoch": 0.02367237549791655,
+      "grad_norm": 2.07018780708313,
+      "learning_rate": 4.9998914381774255e-05,
+      "loss": 0.8278,
+      "step": 1612
+    },
+    {
+      "epoch": 0.0241276134882611,
+      "grad_norm": 1.9434620141983032,
+      "learning_rate": 4.999799067923527e-05,
+      "loss": 0.8188,
+      "step": 1643
+    },
+    {
+      "epoch": 0.02458285147860565,
+      "grad_norm": 2.303523540496826,
+      "learning_rate": 4.999678487776908e-05,
+      "loss": 0.8169,
+      "step": 1674
+    },
+    {
+      "epoch": 0.025038089468950198,
+      "grad_norm": 1.9299540519714355,
+      "learning_rate": 4.9995296990983006e-05,
+      "loss": 0.8193,
+      "step": 1705
+    },
+    {
+      "epoch": 0.025493327459294748,
+      "grad_norm": 2.9125871658325195,
+      "learning_rate": 4.999352703566763e-05,
+      "loss": 0.8169,
+      "step": 1736
+    },
+    {
+      "epoch": 0.025948565449639298,
+      "grad_norm": 1.9595615863800049,
+      "learning_rate": 4.999147503179668e-05,
+      "loss": 0.8303,
+      "step": 1767
+    },
+    {
+      "epoch": 0.026403803439983848,
+      "grad_norm": 1.792854905128479,
+      "learning_rate": 4.998914100252672e-05,
+      "loss": 0.8316,
+      "step": 1798
+    },
+    {
+      "epoch": 0.026859041430328395,
+      "grad_norm": 1.9298927783966064,
+      "learning_rate": 4.998652497419696e-05,
+      "loss": 0.8241,
+      "step": 1829
+    },
+    {
+      "epoch": 0.027314279420672945,
+      "grad_norm": 2.0041086673736572,
+      "learning_rate": 4.9983626976328927e-05,
+      "loss": 0.8194,
+      "step": 1860
+    },
+    {
+      "epoch": 0.027769517411017495,
+      "grad_norm": 1.7287297248840332,
+      "learning_rate": 4.998044704162613e-05,
+      "loss": 0.8215,
+      "step": 1891
+    },
+    {
+      "epoch": 0.02822475540136204,
+      "grad_norm": 1.9918785095214844,
+      "learning_rate": 4.9976985205973705e-05,
+      "loss": 0.827,
+      "step": 1922
+    },
+    {
+      "epoch": 0.02867999339170659,
+      "grad_norm": 1.719894289970398,
+      "learning_rate": 4.997324150843799e-05,
+      "loss": 0.8195,
+      "step": 1953
+    },
+    {
+      "epoch": 0.029135231382051142,
+      "grad_norm": 1.8976550102233887,
+      "learning_rate": 4.99692159912661e-05,
+      "loss": 0.8255,
+      "step": 1984
+    },
+    {
+      "epoch": 0.02959046937239569,
+      "grad_norm": 1.935172200202942,
+      "learning_rate": 4.996490869988546e-05,
+      "loss": 0.8181,
+      "step": 2015
+    },
+    {
+      "epoch": 0.03004570736274024,
+      "grad_norm": 1.9780888557434082,
+      "learning_rate": 4.996031968290326e-05,
+      "loss": 0.8135,
+      "step": 2046
+    },
+    {
+      "epoch": 0.03050094535308479,
+      "grad_norm": 1.8524991273880005,
+      "learning_rate": 4.995544899210594e-05,
+      "loss": 0.8125,
+      "step": 2077
+    },
+    {
+      "epoch": 0.03095618334342934,
+      "grad_norm": 1.7355973720550537,
+      "learning_rate": 4.9950296682458583e-05,
+      "loss": 0.7994,
+      "step": 2108
+    },
+    {
+      "epoch": 0.031411421333773885,
+      "grad_norm": 1.6580488681793213,
+      "learning_rate": 4.994486281210429e-05,
+      "loss": 0.796,
+      "step": 2139
+    },
+    {
+      "epoch": 0.03186665932411843,
+      "grad_norm": 1.867573618888855,
+      "learning_rate": 4.9939147442363566e-05,
+      "loss": 0.8132,
+      "step": 2170
+    },
+    {
+      "epoch": 0.032321897314462986,
+      "grad_norm": 1.6070977449417114,
+      "learning_rate": 4.9933150637733574e-05,
+      "loss": 0.8077,
+      "step": 2201
+    },
+    {
+      "epoch": 0.03277713530480753,
+      "grad_norm": 1.7772935628890991,
+      "learning_rate": 4.992687246588743e-05,
+      "loss": 0.8082,
+      "step": 2232
+    },
+    {
+      "epoch": 0.033232373295152086,
+      "grad_norm": 1.8836694955825806,
+      "learning_rate": 4.992031299767347e-05,
+      "loss": 0.8064,
+      "step": 2263
+    },
+    {
+      "epoch": 0.03368761128549663,
+      "grad_norm": 3.3479881286621094,
+      "learning_rate": 4.9913472307114386e-05,
+      "loss": 0.7967,
+      "step": 2294
+    },
+    {
+      "epoch": 0.03414284927584118,
+      "grad_norm": 1.6765213012695312,
+      "learning_rate": 4.9906350471406446e-05,
+      "loss": 0.8051,
+      "step": 2325
+    },
+    {
+      "epoch": 0.03459808726618573,
+      "grad_norm": 1.6204607486724854,
+      "learning_rate": 4.989894757091861e-05,
+      "loss": 0.8046,
+      "step": 2356
+    },
+    {
+      "epoch": 0.03505332525653028,
+      "grad_norm": 1.829070806503296,
+      "learning_rate": 4.989126368919158e-05,
+      "loss": 0.8056,
+      "step": 2387
+    },
+    {
+      "epoch": 0.035508563246874826,
+      "grad_norm": 1.6405888795852661,
+      "learning_rate": 4.988329891293693e-05,
+      "loss": 0.7978,
+      "step": 2418
+    },
+    {
+      "epoch": 0.03596380123721938,
+      "grad_norm": 1.7973062992095947,
+      "learning_rate": 4.987505333203608e-05,
+      "loss": 0.8032,
+      "step": 2449
+    },
+    {
+      "epoch": 0.036419039227563926,
+      "grad_norm": 1.6353952884674072,
+      "learning_rate": 4.9866527039539276e-05,
+      "loss": 0.7962,
+      "step": 2480
+    },
+    {
+      "epoch": 0.03687427721790847,
+      "grad_norm": 1.7949732542037964,
+      "learning_rate": 4.9857720131664594e-05,
+      "loss": 0.8053,
+      "step": 2511
+    },
+    {
+      "epoch": 0.03732951520825303,
+      "grad_norm": 1.6451278924942017,
+      "learning_rate": 4.9848632707796773e-05,
+      "loss": 0.7996,
+      "step": 2542
+    },
+    {
+      "epoch": 0.03778475319859757,
+      "grad_norm": 2.481834888458252,
+      "learning_rate": 4.9839264870486155e-05,
+      "loss": 0.8063,
+      "step": 2573
+    },
+    {
+      "epoch": 0.03823999118894212,
+      "grad_norm": 1.6256147623062134,
+      "learning_rate": 4.9829616725447526e-05,
+      "loss": 0.8007,
+      "step": 2604
+    },
+    {
+      "epoch": 0.03869522917928667,
+      "grad_norm": 1.6175315380096436,
+      "learning_rate": 4.981968838155888e-05,
+      "loss": 0.7899,
+      "step": 2635
+    },
+    {
+      "epoch": 0.03915046716963122,
+      "grad_norm": 1.521621584892273,
+      "learning_rate": 4.980947995086024e-05,
+      "loss": 0.7897,
+      "step": 2666
+    },
+    {
+      "epoch": 0.03960570515997577,
+      "grad_norm": 1.6651875972747803,
+      "learning_rate": 4.979899154855234e-05,
+      "loss": 0.7977,
+      "step": 2697
+    },
+    {
+      "epoch": 0.04006094315032032,
+      "grad_norm": 1.6656596660614014,
+      "learning_rate": 4.9788223292995386e-05,
+      "loss": 0.7873,
+      "step": 2728
+    },
+    {
+      "epoch": 0.04051618114066487,
+      "grad_norm": 1.5026613473892212,
+      "learning_rate": 4.977717530570768e-05,
+      "loss": 0.7801,
+      "step": 2759
+    },
+    {
+      "epoch": 0.040971419131009414,
+      "grad_norm": 1.6516485214233398,
+      "learning_rate": 4.976584771136425e-05,
+      "loss": 0.7946,
+      "step": 2790
+    },
+    {
+      "epoch": 0.04142665712135397,
+      "grad_norm": 1.6548583507537842,
+      "learning_rate": 4.975424063779547e-05,
+      "loss": 0.7979,
+      "step": 2821
+    },
+    {
+      "epoch": 0.041881895111698514,
+      "grad_norm": 1.5374644994735718,
+      "learning_rate": 4.974235421598557e-05,
+      "loss": 0.7917,
+      "step": 2852
+    },
+    {
+      "epoch": 0.04233713310204307,
+      "grad_norm": 1.6639021635055542,
+      "learning_rate": 4.973018858007122e-05,
+      "loss": 0.7899,
+      "step": 2883
+    },
+    {
+      "epoch": 0.042792371092387614,
+      "grad_norm": 1.5152990818023682,
+      "learning_rate": 4.9717743867339963e-05,
+      "loss": 0.7863,
+      "step": 2914
+    },
+    {
+      "epoch": 0.04324760908273216,
+      "grad_norm": 1.761730432510376,
+      "learning_rate": 4.9705020218228695e-05,
+      "loss": 0.7862,
+      "step": 2945
+    },
+    {
+      "epoch": 0.043702847073076714,
+      "grad_norm": 1.6220827102661133,
+      "learning_rate": 4.969201777632205e-05,
+      "loss": 0.7971,
+      "step": 2976
+    },
+    {
+      "epoch": 0.04415808506342126,
+      "grad_norm": 1.5421055555343628,
+      "learning_rate": 4.9678736688350846e-05,
+      "loss": 0.7836,
+      "step": 3007
+    },
+    {
+      "epoch": 0.04461332305376581,
+      "grad_norm": 1.557054042816162,
+      "learning_rate": 4.966517710419033e-05,
+      "loss": 0.7973,
+      "step": 3038
+    },
+    {
+      "epoch": 0.04506856104411036,
+      "grad_norm": 1.6359279155731201,
+      "learning_rate": 4.965133917685858e-05,
+      "loss": 0.7913,
+      "step": 3069
+    },
+    {
+      "epoch": 0.04552379903445491,
+      "grad_norm": 1.5110820531845093,
+      "learning_rate": 4.9637223062514714e-05,
+      "loss": 0.7866,
+      "step": 3100
+    },
+    {
+      "epoch": 0.045979037024799455,
+      "grad_norm": 1.5999350547790527,
+      "learning_rate": 4.962282892045718e-05,
+      "loss": 0.7815,
+      "step": 3131
+    },
+    {
+      "epoch": 0.04643427501514401,
+      "grad_norm": 1.6365526914596558,
+      "learning_rate": 4.9608156913121904e-05,
+      "loss": 0.7853,
+      "step": 3162
+    },
+    {
+      "epoch": 0.046889513005488555,
+      "grad_norm": 1.4888262748718262,
+      "learning_rate": 4.959320720608049e-05,
+      "loss": 0.7855,
+      "step": 3193
+    },
+    {
+      "epoch": 0.0473447509958331,
+      "grad_norm": 1.6654419898986816,
+      "learning_rate": 4.9577979968038354e-05,
+      "loss": 0.7901,
+      "step": 3224
+    },
+    {
+      "epoch": 0.047799988986177655,
+      "grad_norm": 1.7072011232376099,
+      "learning_rate": 4.956247537083282e-05,
+      "loss": 0.7844,
+      "step": 3255
+    },
+    {
+      "epoch": 0.0482552269765222,
+      "grad_norm": 1.5382236242294312,
+      "learning_rate": 4.9546693589431145e-05,
+      "loss": 0.7679,
+      "step": 3286
+    },
+    {
+      "epoch": 0.04871046496686675,
+      "grad_norm": 1.6157864332199097,
+      "learning_rate": 4.9530634801928595e-05,
+      "loss": 0.7969,
+      "step": 3317
+    },
+    {
+      "epoch": 0.0491657029572113,
+      "grad_norm": 1.3994786739349365,
+      "learning_rate": 4.9514299189546395e-05,
+      "loss": 0.7805,
+      "step": 3348
+    },
+    {
+      "epoch": 0.04962094094755585,
+      "grad_norm": 1.595642328262329,
+      "learning_rate": 4.949768693662973e-05,
+      "loss": 0.792,
+      "step": 3379
+    },
+    {
+      "epoch": 0.050076178937900395,
+      "grad_norm": 1.5789110660552979,
+      "learning_rate": 4.948079823064559e-05,
+      "loss": 0.7945,
+      "step": 3410
+    },
+    {
+      "epoch": 0.05053141692824495,
+      "grad_norm": 1.4630874395370483,
+      "learning_rate": 4.946363326218074e-05,
+      "loss": 0.7798,
+      "step": 3441
+    },
+    {
+      "epoch": 0.050986654918589495,
+      "grad_norm": 1.6624780893325806,
+      "learning_rate": 4.9446192224939525e-05,
+      "loss": 0.7781,
+      "step": 3472
+    },
+    {
+      "epoch": 0.05144189290893404,
+      "grad_norm": 1.5291494131088257,
+      "learning_rate": 4.942847531574167e-05,
+      "loss": 0.7755,
+      "step": 3503
+    },
+    {
+      "epoch": 0.051897130899278596,
+      "grad_norm": 1.5021535158157349,
+      "learning_rate": 4.941048273452008e-05,
+      "loss": 0.7781,
+      "step": 3534
+    },
+    {
+      "epoch": 0.05235236888962314,
+      "grad_norm": 1.520340085029602,
+      "learning_rate": 4.9392214684318605e-05,
+      "loss": 0.7832,
+      "step": 3565
+    },
+    {
+      "epoch": 0.052807606879967696,
+      "grad_norm": 1.6593334674835205,
+      "learning_rate": 4.93736713712897e-05,
+      "loss": 0.7807,
+      "step": 3596
+    },
+    {
+      "epoch": 0.05326284487031224,
+      "grad_norm": 1.5201176404953003,
+      "learning_rate": 4.9354853004692124e-05,
+      "loss": 0.7839,
+      "step": 3627
+    },
+    {
+      "epoch": 0.05371808286065679,
+      "grad_norm": 1.4672085046768188,
+      "learning_rate": 4.93357597968886e-05,
+      "loss": 0.7749,
+      "step": 3658
+    },
+    {
+      "epoch": 0.05417332085100134,
+      "grad_norm": 1.5247095823287964,
+      "learning_rate": 4.931639196334338e-05,
+      "loss": 0.784,
+      "step": 3689
+    },
+    {
+      "epoch": 0.05462855884134589,
+      "grad_norm": 1.425585389137268,
+      "learning_rate": 4.9296749722619826e-05,
+      "loss": 0.783,
+      "step": 3720
+    },
+    {
+      "epoch": 0.055083796831690436,
+      "grad_norm": 1.5224754810333252,
+      "learning_rate": 4.9276833296377966e-05,
+      "loss": 0.7755,
+      "step": 3751
+    },
+    {
+      "epoch": 0.05553903482203499,
+      "grad_norm": 1.340252161026001,
+      "learning_rate": 4.925664290937196e-05,
+      "loss": 0.7727,
+      "step": 3782
+    },
+    {
+      "epoch": 0.055994272812379536,
+      "grad_norm": 1.5716209411621094,
+      "learning_rate": 4.9236178789447576e-05,
+      "loss": 0.7765,
+      "step": 3813
+    },
+    {
+      "epoch": 0.05644951080272408,
+      "grad_norm": 1.5179502964019775,
+      "learning_rate": 4.921544116753962e-05,
+      "loss": 0.771,
+      "step": 3844
+    },
+    {
+      "epoch": 0.05690474879306864,
+      "grad_norm": 1.570530891418457,
+      "learning_rate": 4.919443027766935e-05,
+      "loss": 0.7781,
+      "step": 3875
+    },
+    {
+      "epoch": 0.05735998678341318,
+      "grad_norm": 1.4464157819747925,
+      "learning_rate": 4.91731463569418e-05,
+      "loss": 0.7785,
+      "step": 3906
+    },
+    {
+      "epoch": 0.05781522477375773,
+      "grad_norm": 1.338505506515503,
+      "learning_rate": 4.915158964554312e-05,
+      "loss": 0.7737,
+      "step": 3937
+    },
+    {
+      "epoch": 0.058270462764102283,
+      "grad_norm": 1.4677704572677612,
+      "learning_rate": 4.912976038673786e-05,
+      "loss": 0.7754,
+      "step": 3968
+    },
+    {
+      "epoch": 0.05872570075444683,
+      "grad_norm": 1.440202236175537,
+      "learning_rate": 4.9107658826866254e-05,
+      "loss": 0.7815,
+      "step": 3999
+    },
+    {
+      "epoch": 0.05918093874479138,
+      "grad_norm": 1.4083667993545532,
+      "learning_rate": 4.908528521534139e-05,
+      "loss": 0.7693,
+      "step": 4030
+    },
+    {
+      "epoch": 0.05963617673513593,
+      "grad_norm": 1.266140341758728,
+      "learning_rate": 4.906263980464644e-05,
+      "loss": 0.7847,
+      "step": 4061
+    },
+    {
+      "epoch": 0.06009141472548048,
+      "grad_norm": 1.313815951347351,
+      "learning_rate": 4.903972285033178e-05,
+      "loss": 0.7801,
+      "step": 4092
+    },
+    {
+      "epoch": 0.060546652715825024,
+      "grad_norm": 1.7150321006774902,
+      "learning_rate": 4.901653461101213e-05,
+      "loss": 0.7675,
+      "step": 4123
+    },
+    {
+      "epoch": 0.06100189070616958,
+      "grad_norm": 1.4845250844955444,
+      "learning_rate": 4.8993075348363626e-05,
+      "loss": 0.7643,
+      "step": 4154
+    },
+    {
+      "epoch": 0.061457128696514124,
+      "grad_norm": 1.3258192539215088,
+      "learning_rate": 4.896934532712084e-05,
+      "loss": 0.7753,
+      "step": 4185
+    },
+    {
+      "epoch": 0.06191236668685868,
+      "grad_norm": 1.4659708738327026,
+      "learning_rate": 4.8945344815073846e-05,
+      "loss": 0.763,
+      "step": 4216
+    },
+    {
+      "epoch": 0.062367604677203224,
+      "grad_norm": 1.4512019157409668,
+      "learning_rate": 4.892107408306516e-05,
+      "loss": 0.7663,
+      "step": 4247
+    },
+    {
+      "epoch": 0.06282284266754777,
+      "grad_norm": 1.4622727632522583,
+      "learning_rate": 4.889653340498669e-05,
+      "loss": 0.772,
+      "step": 4278
+    },
+    {
+      "epoch": 0.06327808065789232,
+      "grad_norm": 1.3177098035812378,
+      "learning_rate": 4.8871723057776664e-05,
+      "loss": 0.7665,
+      "step": 4309
+    },
+    {
+      "epoch": 0.06373331864823686,
+      "grad_norm": 1.3955334424972534,
+      "learning_rate": 4.8846643321416476e-05,
+      "loss": 0.7717,
+      "step": 4340
+    },
+    {
+      "epoch": 0.06418855663858142,
+      "grad_norm": 1.4321017265319824,
+      "learning_rate": 4.882129447892753e-05,
+      "loss": 0.7639,
+      "step": 4371
+    },
+    {
+      "epoch": 0.06464379462892597,
+      "grad_norm": 1.4852508306503296,
+      "learning_rate": 4.8795676816368076e-05,
+      "loss": 0.7606,
+      "step": 4402
+    },
+    {
+      "epoch": 0.06509903261927051,
+      "grad_norm": 1.4605242013931274,
+      "learning_rate": 4.876979062282995e-05,
+      "loss": 0.7646,
+      "step": 4433
+    },
+    {
+      "epoch": 0.06555427060961506,
+      "grad_norm": 1.4694074392318726,
+      "learning_rate": 4.8743636190435325e-05,
+      "loss": 0.7649,
+      "step": 4464
+    },
+    {
+      "epoch": 0.06600950859995962,
+      "grad_norm": 1.2886863946914673,
+      "learning_rate": 4.871721381433344e-05,
+      "loss": 0.7709,
+      "step": 4495
+    },
+    {
+      "epoch": 0.06646474659030417,
+      "grad_norm": 1.2294282913208008,
+      "learning_rate": 4.869052379269719e-05,
+      "loss": 0.7654,
+      "step": 4526
+    },
+    {
+      "epoch": 0.06691998458064871,
+      "grad_norm": 1.4652395248413086,
+      "learning_rate": 4.866356642671985e-05,
+      "loss": 0.7626,
+      "step": 4557
+    },
+    {
+      "epoch": 0.06737522257099327,
+      "grad_norm": 1.3832221031188965,
+      "learning_rate": 4.8636342020611634e-05,
+      "loss": 0.7685,
+      "step": 4588
+    },
+    {
+      "epoch": 0.06783046056133782,
+      "grad_norm": 1.3281147480010986,
+      "learning_rate": 4.860885088159626e-05,
+      "loss": 0.7659,
+      "step": 4619
+    },
+    {
+      "epoch": 0.06828569855168236,
+      "grad_norm": 1.4158588647842407,
+      "learning_rate": 4.858109331990751e-05,
+      "loss": 0.7678,
+      "step": 4650
+    },
+    {
+      "epoch": 0.06874093654202691,
+      "grad_norm": 1.4169031381607056,
+      "learning_rate": 4.855306964878567e-05,
+      "loss": 0.7759,
+      "step": 4681
+    },
+    {
+      "epoch": 0.06919617453237147,
+      "grad_norm": 1.3807917833328247,
+      "learning_rate": 4.8524780184474084e-05,
+      "loss": 0.766,
+      "step": 4712
+    },
+    {
+      "epoch": 0.069651412522716,
+      "grad_norm": 1.4099223613739014,
+      "learning_rate": 4.8496225246215496e-05,
+      "loss": 0.7607,
+      "step": 4743
+    },
+    {
+      "epoch": 0.07010665051306056,
+      "grad_norm": 1.504549503326416,
+      "learning_rate": 4.8467405156248505e-05,
+      "loss": 0.764,
+      "step": 4774
+    },
+    {
+      "epoch": 0.07056188850340511,
+      "grad_norm": 1.595380187034607,
+      "learning_rate": 4.843832023980392e-05,
+      "loss": 0.7638,
+      "step": 4805
+    },
+    {
+      "epoch": 0.07101712649374965,
+      "grad_norm": 1.250127911567688,
+      "learning_rate": 4.840897082510106e-05,
+      "loss": 0.7612,
+      "step": 4836
+    },
+    {
+      "epoch": 0.0714723644840942,
+      "grad_norm": 1.549315094947815,
+      "learning_rate": 4.8379357243344084e-05,
+      "loss": 0.7682,
+      "step": 4867
+    },
+    {
+      "epoch": 0.07192760247443876,
+      "grad_norm": 1.2536250352859497,
+      "learning_rate": 4.8349479828718236e-05,
+      "loss": 0.7667,
+      "step": 4898
+    },
+    {
+      "epoch": 0.0723828404647833,
+      "grad_norm": 1.4117034673690796,
+      "learning_rate": 4.8319338918386075e-05,
+      "loss": 0.7566,
+      "step": 4929
+    },
+    {
+      "epoch": 0.07283807845512785,
+      "grad_norm": 1.4547215700149536,
+      "learning_rate": 4.828893485248369e-05,
+      "loss": 0.7836,
+      "step": 4960
+    },
+    {
+      "epoch": 0.0732933164454724,
+      "grad_norm": 1.4076682329177856,
+      "learning_rate": 4.825826797411682e-05,
+      "loss": 0.7651,
+      "step": 4991
+    },
+    {
+      "epoch": 0.07374855443581695,
+      "grad_norm": 1.2911306619644165,
+      "learning_rate": 4.822733862935702e-05,
+      "loss": 0.7645,
+      "step": 5022
+    },
+    {
+      "epoch": 0.0742037924261615,
+      "grad_norm": 1.3982489109039307,
+      "learning_rate": 4.819614716723775e-05,
+      "loss": 0.7654,
+      "step": 5053
+    },
+    {
+      "epoch": 0.07465903041650605,
+      "grad_norm": 1.434875726699829,
+      "learning_rate": 4.8164693939750425e-05,
+      "loss": 0.7633,
+      "step": 5084
+    },
+    {
+      "epoch": 0.07511426840685059,
+      "grad_norm": 1.4181441068649292,
+      "learning_rate": 4.813297930184042e-05,
+      "loss": 0.7586,
+      "step": 5115
+    },
+    {
+      "epoch": 0.07556950639719515,
+      "grad_norm": 1.3030534982681274,
+      "learning_rate": 4.810100361140314e-05,
+      "loss": 0.7581,
+      "step": 5146
+    },
+    {
+      "epoch": 0.0760247443875397,
+      "grad_norm": 1.3619349002838135,
+      "learning_rate": 4.8068767229279885e-05,
+      "loss": 0.7646,
+      "step": 5177
+    },
+    {
+      "epoch": 0.07647998237788424,
+      "grad_norm": 1.4117941856384277,
+      "learning_rate": 4.8036270519253854e-05,
+      "loss": 0.76,
+      "step": 5208
+    },
+    {
+      "epoch": 0.0769352203682288,
+      "grad_norm": 1.3789417743682861,
+      "learning_rate": 4.8003513848046e-05,
+      "loss": 0.7608,
+      "step": 5239
+    },
+    {
+      "epoch": 0.07739045835857335,
+      "grad_norm": 1.4750028848648071,
+      "learning_rate": 4.79704975853109e-05,
+      "loss": 0.767,
+      "step": 5270
+    },
+    {
+      "epoch": 0.07784569634891789,
+      "grad_norm": 1.604878306388855,
+      "learning_rate": 4.793722210363262e-05,
+      "loss": 0.7546,
+      "step": 5301
+    },
+    {
+      "epoch": 0.07830093433926244,
+      "grad_norm": 1.3198168277740479,
+      "learning_rate": 4.7903687778520414e-05,
+      "loss": 0.7647,
+      "step": 5332
+    },
+    {
+      "epoch": 0.078756172329607,
+      "grad_norm": 1.4350367784500122,
+      "learning_rate": 4.7869894988404593e-05,
+      "loss": 0.7566,
+      "step": 5363
+    },
+    {
+      "epoch": 0.07921141031995153,
+      "grad_norm": 1.2926212549209595,
+      "learning_rate": 4.783584411463221e-05,
+      "loss": 0.7588,
+      "step": 5394
+    },
+    {
+      "epoch": 0.07966664831029609,
+      "grad_norm": 1.3848434686660767,
+      "learning_rate": 4.780153554146274e-05,
+      "loss": 0.7568,
+      "step": 5425
+    },
+    {
+      "epoch": 0.08012188630064064,
+      "grad_norm": 1.265429139137268,
+      "learning_rate": 4.7766969656063766e-05,
+      "loss": 0.764,
+      "step": 5456
+    },
+    {
+      "epoch": 0.08057712429098518,
+      "grad_norm": 1.5596004724502563,
+      "learning_rate": 4.773214684850662e-05,
+      "loss": 0.7484,
+      "step": 5487
+    },
+    {
+      "epoch": 0.08103236228132973,
+      "grad_norm": 1.2046922445297241,
+      "learning_rate": 4.769706751176193e-05,
+      "loss": 0.7555,
+      "step": 5518
+    },
+    {
+      "epoch": 0.08148760027167429,
+      "grad_norm": 1.2367156744003296,
+      "learning_rate": 4.7661732041695264e-05,
+      "loss": 0.7494,
+      "step": 5549
+    },
+    {
+      "epoch": 0.08194283826201883,
+      "grad_norm": 1.4023075103759766,
+      "learning_rate": 4.762614083706258e-05,
+      "loss": 0.7629,
+      "step": 5580
+    },
+    {
+      "epoch": 0.08239807625236338,
+      "grad_norm": 1.5371898412704468,
+      "learning_rate": 4.759029429950581e-05,
+      "loss": 0.7504,
+      "step": 5611
+    },
+    {
+      "epoch": 0.08285331424270793,
+      "grad_norm": 1.3951853513717651,
+      "learning_rate": 4.7554192833548235e-05,
+      "loss": 0.7554,
+      "step": 5642
+    },
+    {
+      "epoch": 0.08330855223305247,
+      "grad_norm": 1.318542242050171,
+      "learning_rate": 4.751783684659e-05,
+      "loss": 0.7445,
+      "step": 5673
+    },
+    {
+      "epoch": 0.08376379022339703,
+      "grad_norm": 1.2884353399276733,
+      "learning_rate": 4.748122674890348e-05,
+      "loss": 0.7557,
+      "step": 5704
+    },
+    {
+      "epoch": 0.08421902821374158,
+      "grad_norm": 1.4121450185775757,
+      "learning_rate": 4.7444362953628654e-05,
+      "loss": 0.7578,
+      "step": 5735
+    },
+    {
+      "epoch": 0.08467426620408613,
+      "grad_norm": 1.5590519905090332,
+      "learning_rate": 4.7407245876768424e-05,
+      "loss": 0.7532,
+      "step": 5766
+    },
+    {
+      "epoch": 0.08512950419443067,
+      "grad_norm": 1.324658989906311,
+      "learning_rate": 4.736987593718397e-05,
+      "loss": 0.7483,
+      "step": 5797
+    },
+    {
+      "epoch": 0.08558474218477523,
+      "grad_norm": 1.3753433227539062,
+      "learning_rate": 4.733225355658999e-05,
+      "loss": 0.7645,
+      "step": 5828
+    },
+    {
+      "epoch": 0.08603998017511978,
+      "grad_norm": 1.2180614471435547,
+      "learning_rate": 4.7294379159549926e-05,
+      "loss": 0.7506,
+      "step": 5859
+    },
+    {
+      "epoch": 0.08649521816546432,
+      "grad_norm": 1.4321558475494385,
+      "learning_rate": 4.725625317347119e-05,
+      "loss": 0.758,
+      "step": 5890
+    },
+    {
+      "epoch": 0.08695045615580888,
+      "grad_norm": 1.253527283668518,
+      "learning_rate": 4.7217876028600374e-05,
+      "loss": 0.7507,
+      "step": 5921
+    },
+    {
+      "epoch": 0.08740569414615343,
+      "grad_norm": 1.3596974611282349,
+      "learning_rate": 4.717924815801832e-05,
+      "loss": 0.753,
+      "step": 5952
+    },
+    {
+      "epoch": 0.08786093213649797,
+      "grad_norm": 1.3011499643325806,
+      "learning_rate": 4.714036999763532e-05,
+      "loss": 0.7574,
+      "step": 5983
+    },
+    {
+      "epoch": 0.08831617012684252,
+      "grad_norm": 1.3742843866348267,
+      "learning_rate": 4.7101241986186116e-05,
+      "loss": 0.7478,
+      "step": 6014
+    },
+    {
+      "epoch": 0.08877140811718708,
+      "grad_norm": 1.3200472593307495,
+      "learning_rate": 4.7061864565225e-05,
+      "loss": 0.7524,
+      "step": 6045
+    },
+    {
+      "epoch": 0.08922664610753162,
+      "grad_norm": 1.1689510345458984,
+      "learning_rate": 4.702223817912081e-05,
+      "loss": 0.762,
+      "step": 6076
+    },
+    {
+      "epoch": 0.08968188409787617,
+      "grad_norm": 1.303377628326416,
+      "learning_rate": 4.698236327505195e-05,
+      "loss": 0.7487,
+      "step": 6107
+    },
+    {
+      "epoch": 0.09013712208822072,
+      "grad_norm": 1.2742568254470825,
+      "learning_rate": 4.694224030300127e-05,
+      "loss": 0.7539,
+      "step": 6138
+    },
+    {
+      "epoch": 0.09059236007856526,
+      "grad_norm": 1.4071948528289795,
+      "learning_rate": 4.690186971575107e-05,
+      "loss": 0.7564,
+      "step": 6169
+    },
+    {
+      "epoch": 0.09104759806890982,
+      "grad_norm": 1.2735074758529663,
+      "learning_rate": 4.6861251968877916e-05,
+      "loss": 0.7528,
+      "step": 6200
+    },
+    {
+      "epoch": 0.09150283605925437,
+      "grad_norm": 1.198225498199463,
+      "learning_rate": 4.68203875207476e-05,
+      "loss": 0.7559,
+      "step": 6231
+    },
+    {
+      "epoch": 0.09195807404959891,
+      "grad_norm": 1.3141562938690186,
+      "learning_rate": 4.677927683250983e-05,
+      "loss": 0.7478,
+      "step": 6262
+    },
+    {
+      "epoch": 0.09241331203994346,
+      "grad_norm": 1.3102765083312988,
+      "learning_rate": 4.6737920368093156e-05,
+      "loss": 0.755,
+      "step": 6293
+    },
+    {
+      "epoch": 0.09286855003028802,
+      "grad_norm": 1.1865342855453491,
+      "learning_rate": 4.669631859419965e-05,
+      "loss": 0.7492,
+      "step": 6324
+    },
+    {
+      "epoch": 0.09332378802063256,
+      "grad_norm": 1.3457741737365723,
+      "learning_rate": 4.6654471980299676e-05,
+      "loss": 0.7498,
+      "step": 6355
+    },
+    {
+      "epoch": 0.09377902601097711,
+      "grad_norm": 1.2267104387283325,
+      "learning_rate": 4.661238099862658e-05,
+      "loss": 0.7419,
+      "step": 6386
+    },
+    {
+      "epoch": 0.09423426400132166,
+      "grad_norm": 1.4682426452636719,
+      "learning_rate": 4.657004612417138e-05,
+      "loss": 0.7474,
+      "step": 6417
+    },
+    {
+      "epoch": 0.0946895019916662,
+      "grad_norm": 1.366281270980835,
+      "learning_rate": 4.6527467834677374e-05,
+      "loss": 0.7478,
+      "step": 6448
+    },
+    {
+      "epoch": 0.09514473998201076,
+      "grad_norm": 1.2895044088363647,
+      "learning_rate": 4.648464661063478e-05,
+      "loss": 0.7538,
+      "step": 6479
+    },
+    {
+      "epoch": 0.09559997797235531,
+      "grad_norm": 1.199654221534729,
+      "learning_rate": 4.6441582935275264e-05,
+      "loss": 0.7512,
+      "step": 6510
+    },
+    {
+      "epoch": 0.09605521596269985,
+      "grad_norm": 1.178707242012024,
+      "learning_rate": 4.6398277294566586e-05,
+      "loss": 0.7504,
+      "step": 6541
+    },
+    {
+      "epoch": 0.0965104539530444,
+      "grad_norm": 1.4963469505310059,
+      "learning_rate": 4.6354730177207e-05,
+      "loss": 0.7574,
+      "step": 6572
+    },
+    {
+      "epoch": 0.09696569194338896,
+      "grad_norm": 1.312418818473816,
+      "learning_rate": 4.6310942074619787e-05,
+      "loss": 0.7476,
+      "step": 6603
+    },
+    {
+      "epoch": 0.0974209299337335,
+      "grad_norm": 1.1745465993881226,
+      "learning_rate": 4.626691348094777e-05,
+      "loss": 0.7428,
+      "step": 6634
+    },
+    {
+      "epoch": 0.09787616792407805,
+      "grad_norm": 1.4050241708755493,
+      "learning_rate": 4.622264489304762e-05,
+      "loss": 0.74,
+      "step": 6665
+    },
+    {
+      "epoch": 0.0983314059144226,
+      "grad_norm": 1.3154901266098022,
+      "learning_rate": 4.617813681048434e-05,
+      "loss": 0.7456,
+      "step": 6696
+    },
+    {
+      "epoch": 0.09878664390476714,
+      "grad_norm": 1.2204554080963135,
+      "learning_rate": 4.61333897355256e-05,
+      "loss": 0.7467,
+      "step": 6727
+    },
+    {
+      "epoch": 0.0992418818951117,
+      "grad_norm": 1.1468600034713745,
+      "learning_rate": 4.608840417313604e-05,
+      "loss": 0.7394,
+      "step": 6758
+    },
+    {
+      "epoch": 0.09969711988545625,
+      "grad_norm": 1.359215259552002,
+      "learning_rate": 4.6043180630971646e-05,
+      "loss": 0.738,
+      "step": 6789
+    },
+    {
+      "epoch": 0.10015235787580079,
+      "grad_norm": 1.3530089855194092,
+      "learning_rate": 4.599771961937391e-05,
+      "loss": 0.7475,
+      "step": 6820
+    },
+    {
+      "epoch": 0.10060759586614534,
+      "grad_norm": 1.2479960918426514,
+      "learning_rate": 4.5952021651364204e-05,
+      "loss": 0.7471,
+      "step": 6851
+    },
+    {
+      "epoch": 0.1010628338564899,
+      "grad_norm": 1.2646889686584473,
+      "learning_rate": 4.590608724263786e-05,
+      "loss": 0.7517,
+      "step": 6882
+    },
+    {
+      "epoch": 0.10151807184683444,
+      "grad_norm": 1.1519280672073364,
+      "learning_rate": 4.585991691155845e-05,
+      "loss": 0.7557,
+      "step": 6913
+    },
+    {
+      "epoch": 0.10197330983717899,
+      "grad_norm": 1.3348654508590698,
+      "learning_rate": 4.581351117915188e-05,
+      "loss": 0.7484,
+      "step": 6944
+    },
+    {
+      "epoch": 0.10242854782752354,
+      "grad_norm": 2.228433132171631,
+      "learning_rate": 4.5766870569100534e-05,
+      "loss": 0.7489,
+      "step": 6975
+    },
+    {
+      "epoch": 0.10288378581786808,
+      "grad_norm": 1.1797115802764893,
+      "learning_rate": 4.571999560773736e-05,
+      "loss": 0.7547,
+      "step": 7006
+    },
+    {
+      "epoch": 0.10333902380821264,
+      "grad_norm": 1.2607511281967163,
+      "learning_rate": 4.5672886824039915e-05,
+      "loss": 0.7404,
+      "step": 7037
+    },
+    {
+      "epoch": 0.10379426179855719,
+      "grad_norm": 1.2686676979064941,
+      "learning_rate": 4.5625544749624435e-05,
+      "loss": 0.7438,
+      "step": 7068
+    },
+    {
+      "epoch": 0.10424949978890174,
+      "grad_norm": 1.3977618217468262,
+      "learning_rate": 4.5577969918739794e-05,
+      "loss": 0.7374,
+      "step": 7099
+    },
+    {
+      "epoch": 0.10470473777924628,
+      "grad_norm": 1.2950663566589355,
+      "learning_rate": 4.5530162868261486e-05,
+      "loss": 0.7398,
+      "step": 7130
+    },
+    {
+      "epoch": 0.10515997576959084,
+      "grad_norm": 1.3718290328979492,
+      "learning_rate": 4.548212413768558e-05,
+      "loss": 0.7531,
+      "step": 7161
+    },
+    {
+      "epoch": 0.10561521375993539,
+      "grad_norm": 1.403624176979065,
+      "learning_rate": 4.543385426912261e-05,
+      "loss": 0.7517,
+      "step": 7192
+    },
+    {
+      "epoch": 0.10607045175027993,
+      "grad_norm": 1.2086013555526733,
+      "learning_rate": 4.53853538072915e-05,
+      "loss": 0.7292,
+      "step": 7223
+    },
+    {
+      "epoch": 0.10652568974062449,
+      "grad_norm": 1.1994200944900513,
+      "learning_rate": 4.533662329951336e-05,
+      "loss": 0.7405,
+      "step": 7254
+    },
+    {
+      "epoch": 0.10698092773096904,
+      "grad_norm": 1.2708337306976318,
+      "learning_rate": 4.528766329570536e-05,
+      "loss": 0.742,
+      "step": 7285
+    },
+    {
+      "epoch": 0.10743616572131358,
+      "grad_norm": 1.3050458431243896,
+      "learning_rate": 4.523847434837447e-05,
+      "loss": 0.7432,
+      "step": 7316
+    },
+    {
+      "epoch": 0.10789140371165813,
+      "grad_norm": 1.1547353267669678,
+      "learning_rate": 4.518905701261128e-05,
+      "loss": 0.7442,
+      "step": 7347
+    },
+    {
+      "epoch": 0.10834664170200269,
+      "grad_norm": 1.1920067071914673,
+      "learning_rate": 4.5139411846083715e-05,
+      "loss": 0.7481,
+      "step": 7378
+    },
+    {
+      "epoch": 0.10880187969234723,
+      "grad_norm": 1.2883577346801758,
+      "learning_rate": 4.508953940903073e-05,
+      "loss": 0.7385,
+      "step": 7409
+    },
+    {
+      "epoch": 0.10925711768269178,
+      "grad_norm": 1.1537138223648071,
+      "learning_rate": 4.5039440264255994e-05,
+      "loss": 0.7504,
+      "step": 7440
+    },
+    {
+      "epoch": 0.10971235567303633,
+      "grad_norm": 1.1870883703231812,
+      "learning_rate": 4.498911497712155e-05,
+      "loss": 0.7407,
+      "step": 7471
+    },
+    {
+      "epoch": 0.11016759366338087,
+      "grad_norm": 1.17220139503479,
+      "learning_rate": 4.493856411554142e-05,
+      "loss": 0.7411,
+      "step": 7502
+    },
+    {
+      "epoch": 0.11062283165372543,
+      "grad_norm": 1.3021382093429565,
+      "learning_rate": 4.4887788249975206e-05,
+      "loss": 0.7389,
+      "step": 7533
+    },
+    {
+      "epoch": 0.11107806964406998,
+      "grad_norm": 1.1180227994918823,
+      "learning_rate": 4.4836787953421656e-05,
+      "loss": 0.7392,
+      "step": 7564
+    },
+    {
+      "epoch": 0.11153330763441452,
+      "grad_norm": 1.2459032535552979,
+      "learning_rate": 4.478556380141218e-05,
+      "loss": 0.7426,
+      "step": 7595
+    },
+    {
+      "epoch": 0.11198854562475907,
+      "grad_norm": 1.1883258819580078,
+      "learning_rate": 4.4734116372004375e-05,
+      "loss": 0.7387,
+      "step": 7626
+    },
+    {
+      "epoch": 0.11244378361510363,
+      "grad_norm": 1.1959495544433594,
+      "learning_rate": 4.4682446245775477e-05,
+      "loss": 0.7504,
+      "step": 7657
+    },
+    {
+      "epoch": 0.11289902160544817,
+      "grad_norm": 1.1768792867660522,
+      "learning_rate": 4.463055400581586e-05,
+      "loss": 0.7429,
+      "step": 7688
+    },
+    {
+      "epoch": 0.11335425959579272,
+      "grad_norm": 1.1907637119293213,
+      "learning_rate": 4.4578440237722374e-05,
+      "loss": 0.7348,
+      "step": 7719
+    },
+    {
+      "epoch": 0.11380949758613727,
+      "grad_norm": 1.2876102924346924,
+      "learning_rate": 4.452610552959183e-05,
+      "loss": 0.7324,
+      "step": 7750
+    },
+    {
+      "epoch": 0.11426473557648181,
+      "grad_norm": 1.2925732135772705,
+      "learning_rate": 4.447355047201428e-05,
+      "loss": 0.7389,
+      "step": 7781
+    },
+    {
+      "epoch": 0.11471997356682637,
+      "grad_norm": 1.2278777360916138,
+      "learning_rate": 4.4420775658066414e-05,
+      "loss": 0.7354,
+      "step": 7812
+    },
+    {
+      "epoch": 0.11517521155717092,
+      "grad_norm": 1.1406846046447754,
+      "learning_rate": 4.436778168330484e-05,
+      "loss": 0.7427,
+      "step": 7843
+    },
+    {
+      "epoch": 0.11563044954751546,
+      "grad_norm": 1.3335959911346436,
+      "learning_rate": 4.4314569145759353e-05,
+      "loss": 0.7352,
+      "step": 7874
+    },
+    {
+      "epoch": 0.11608568753786001,
+      "grad_norm": 1.169438362121582,
+      "learning_rate": 4.42611386459262e-05,
+      "loss": 0.7442,
+      "step": 7905
+    },
+    {
+      "epoch": 0.11654092552820457,
+      "grad_norm": 1.1747533082962036,
+      "learning_rate": 4.420749078676133e-05,
+      "loss": 0.7403,
+      "step": 7936
+    },
+    {
+      "epoch": 0.1169961635185491,
+      "grad_norm": 1.1429502964019775,
+      "learning_rate": 4.4153626173673516e-05,
+      "loss": 0.7429,
+      "step": 7967
+    },
+    {
+      "epoch": 0.11745140150889366,
+      "grad_norm": 1.1959199905395508,
+      "learning_rate": 4.409954541451762e-05,
+      "loss": 0.7321,
+      "step": 7998
+    },
+    {
+      "epoch": 0.11790663949923821,
+      "grad_norm": 1.1771682500839233,
+      "learning_rate": 4.404524911958764e-05,
+      "loss": 0.7409,
+      "step": 8029
+    },
+    {
+      "epoch": 0.11836187748958275,
+      "grad_norm": 1.2091805934906006,
+      "learning_rate": 4.399073790160989e-05,
+      "loss": 0.7383,
+      "step": 8060
+    },
+    {
+      "epoch": 0.11881711547992731,
+      "grad_norm": 1.2129122018814087,
+      "learning_rate": 4.393601237573607e-05,
+      "loss": 0.7406,
+      "step": 8091
+    },
+    {
+      "epoch": 0.11927235347027186,
+      "grad_norm": 1.1697229146957397,
+      "learning_rate": 4.388107315953628e-05,
+      "loss": 0.7417,
+      "step": 8122
+    },
+    {
+      "epoch": 0.1197275914606164,
+      "grad_norm": 1.3066540956497192,
+      "learning_rate": 4.382592087299212e-05,
+      "loss": 0.7313,
+      "step": 8153
+    },
+    {
+      "epoch": 0.12018282945096095,
+      "grad_norm": 1.201402187347412,
+      "learning_rate": 4.377055613848964e-05,
+      "loss": 0.7368,
+      "step": 8184
+    },
+    {
+      "epoch": 0.12063806744130551,
+      "grad_norm": 1.2905657291412354,
+      "learning_rate": 4.3714979580812355e-05,
+      "loss": 0.7418,
+      "step": 8215
+    },
+    {
+      "epoch": 0.12109330543165005,
+      "grad_norm": 1.3703011274337769,
+      "learning_rate": 4.365919182713416e-05,
+      "loss": 0.739,
+      "step": 8246
+    },
+    {
+      "epoch": 0.1215485434219946,
+      "grad_norm": 1.1984279155731201,
+      "learning_rate": 4.360319350701226e-05,
+      "loss": 0.7267,
+      "step": 8277
+    },
+    {
+      "epoch": 0.12200378141233915,
+      "grad_norm": 1.2148597240447998,
+      "learning_rate": 4.3546985252380115e-05,
+      "loss": 0.7428,
+      "step": 8308
+    },
+    {
+      "epoch": 0.12245901940268371,
+      "grad_norm": 1.248827338218689,
+      "learning_rate": 4.349056769754021e-05,
+      "loss": 0.7417,
+      "step": 8339
+    },
+    {
+      "epoch": 0.12291425739302825,
+      "grad_norm": 1.1947282552719116,
+      "learning_rate": 4.3433941479156994e-05,
+      "loss": 0.7415,
+      "step": 8370
+    },
+    {
+      "epoch": 0.1233694953833728,
+      "grad_norm": 1.411094069480896,
+      "learning_rate": 4.3377107236249647e-05,
+      "loss": 0.7339,
+      "step": 8401
+    },
+    {
+      "epoch": 0.12382473337371736,
+      "grad_norm": 1.2265312671661377,
+      "learning_rate": 4.332006561018488e-05,
+      "loss": 0.739,
+      "step": 8432
+    },
+    {
+      "epoch": 0.1242799713640619,
+      "grad_norm": 1.2488131523132324,
+      "learning_rate": 4.3262817244669683e-05,
+      "loss": 0.731,
+      "step": 8463
+    },
+    {
+      "epoch": 0.12473520935440645,
+      "grad_norm": 1.3681105375289917,
+      "learning_rate": 4.3205362785744083e-05,
+      "loss": 0.7391,
+      "step": 8494
+    },
+    {
+      "epoch": 0.125190447344751,
+      "grad_norm": 1.162979245185852,
+      "learning_rate": 4.314770288177384e-05,
+      "loss": 0.7335,
+      "step": 8525
+    },
+    {
+      "epoch": 0.12564568533509554,
+      "grad_norm": 1.1419830322265625,
+      "learning_rate": 4.308983818344313e-05,
+      "loss": 0.7267,
+      "step": 8556
+    },
+    {
+      "epoch": 0.1261009233254401,
+      "grad_norm": 1.134889841079712,
+      "learning_rate": 4.3031769343747206e-05,
+      "loss": 0.7335,
+      "step": 8587
+    },
+    {
+      "epoch": 0.12655616131578465,
+      "grad_norm": 1.1606464385986328,
+      "learning_rate": 4.297349701798505e-05,
+      "loss": 0.73,
+      "step": 8618
+    },
+    {
+      "epoch": 0.1270113993061292,
+      "grad_norm": 1.210892915725708,
+      "learning_rate": 4.2915021863751916e-05,
+      "loss": 0.7414,
+      "step": 8649
+    },
+    {
+      "epoch": 0.12746663729647373,
+      "grad_norm": 1.2415282726287842,
+      "learning_rate": 4.285634454093198e-05,
+      "loss": 0.7331,
+      "step": 8680
+    },
+    {
+      "epoch": 0.12792187528681828,
+      "grad_norm": 1.1473466157913208,
+      "learning_rate": 4.279746571169086e-05,
+      "loss": 0.7245,
+      "step": 8711
+    },
+    {
+      "epoch": 0.12837711327716284,
+      "grad_norm": 1.2628551721572876,
+      "learning_rate": 4.2738386040468136e-05,
+      "loss": 0.7236,
+      "step": 8742
+    },
+    {
+      "epoch": 0.1288323512675074,
+      "grad_norm": 1.1773896217346191,
+      "learning_rate": 4.2679106193969866e-05,
+      "loss": 0.7423,
+      "step": 8773
+    },
+    {
+      "epoch": 0.12928758925785194,
+      "grad_norm": 1.3294051885604858,
+      "learning_rate": 4.261962684116106e-05,
+      "loss": 0.7305,
+      "step": 8804
+    },
+    {
+      "epoch": 0.1297428272481965,
+      "grad_norm": 1.3396165370941162,
+      "learning_rate": 4.2559948653258145e-05,
+      "loss": 0.7381,
+      "step": 8835
+    },
+    {
+      "epoch": 0.13019806523854102,
+      "grad_norm": 1.1799919605255127,
+      "learning_rate": 4.250007230372134e-05,
+      "loss": 0.7266,
+      "step": 8866
+    },
+    {
+      "epoch": 0.13065330322888558,
+      "grad_norm": 1.034415364265442,
+      "learning_rate": 4.2439998468247126e-05,
+      "loss": 0.7234,
+      "step": 8897
+    },
+    {
+      "epoch": 0.13110854121923013,
+      "grad_norm": 1.0857855081558228,
+      "learning_rate": 4.2379727824760566e-05,
+      "loss": 0.7228,
+      "step": 8928
+    },
+    {
+      "epoch": 0.13156377920957468,
+      "grad_norm": 1.2164474725723267,
+      "learning_rate": 4.231926105340768e-05,
+      "loss": 0.7326,
+      "step": 8959
+    },
+    {
+      "epoch": 0.13201901719991924,
+      "grad_norm": 1.2720903158187866,
+      "learning_rate": 4.225859883654776e-05,
+      "loss": 0.7355,
+      "step": 8990
+    },
+    {
+      "epoch": 0.1324742551902638,
+      "grad_norm": 1.3475810289382935,
+      "learning_rate": 4.219774185874569e-05,
+      "loss": 0.7347,
+      "step": 9021
+    },
+    {
+      "epoch": 0.13292949318060834,
+      "grad_norm": 1.1008576154708862,
+      "learning_rate": 4.213669080676418e-05,
+      "loss": 0.731,
+      "step": 9052
+    },
+    {
+      "epoch": 0.13338473117095287,
+      "grad_norm": 1.2972562313079834,
+      "learning_rate": 4.2075446369556056e-05,
+      "loss": 0.7275,
+      "step": 9083
+    },
+    {
+      "epoch": 0.13383996916129742,
+      "grad_norm": 1.1450635194778442,
+      "learning_rate": 4.201400923825648e-05,
+      "loss": 0.7326,
+      "step": 9114
+    },
+    {
+      "epoch": 0.13429520715164198,
+      "grad_norm": 1.1544524431228638,
+      "learning_rate": 4.195238010617511e-05,
+      "loss": 0.734,
+      "step": 9145
+    },
+    {
+      "epoch": 0.13475044514198653,
+      "grad_norm": 1.2136210203170776,
+      "learning_rate": 4.1890559668788344e-05,
+      "loss": 0.7313,
+      "step": 9176
+    },
+    {
+      "epoch": 0.13520568313233108,
+      "grad_norm": 1.1666619777679443,
+      "learning_rate": 4.1828548623731405e-05,
+      "loss": 0.7329,
+      "step": 9207
+    },
+    {
+      "epoch": 0.13566092112267564,
+      "grad_norm": 1.271567702293396,
+      "learning_rate": 4.1766347670790506e-05,
+      "loss": 0.7399,
+      "step": 9238
+    },
+    {
+      "epoch": 0.13611615911302016,
+      "grad_norm": 1.22068452835083,
+      "learning_rate": 4.170395751189495e-05,
+      "loss": 0.7233,
+      "step": 9269
+    },
+    {
+      "epoch": 0.13657139710336472,
+      "grad_norm": 1.2430123090744019,
+      "learning_rate": 4.164137885110921e-05,
+      "loss": 0.7325,
+      "step": 9300
+    },
+    {
+      "epoch": 0.13702663509370927,
+      "grad_norm": 1.254123330116272,
+      "learning_rate": 4.157861239462495e-05,
+      "loss": 0.7229,
+      "step": 9331
+    },
+    {
+      "epoch": 0.13748187308405382,
+      "grad_norm": 1.1151642799377441,
+      "learning_rate": 4.1515658850753114e-05,
+      "loss": 0.735,
+      "step": 9362
+    },
+    {
+      "epoch": 0.13793711107439838,
+      "grad_norm": 1.3190901279449463,
+      "learning_rate": 4.145251892991588e-05,
+      "loss": 0.7279,
+      "step": 9393
+    },
+    {
+      "epoch": 0.13839234906474293,
+      "grad_norm": 1.145297646522522,
+      "learning_rate": 4.138919334463868e-05,
+      "loss": 0.7303,
+      "step": 9424
+    },
+    {
+      "epoch": 0.13884758705508746,
+      "grad_norm": 1.1102197170257568,
+      "learning_rate": 4.1325682809542124e-05,
+      "loss": 0.7317,
+      "step": 9455
+    },
+    {
+      "epoch": 0.139302825045432,
+      "grad_norm": 1.1502071619033813,
+      "learning_rate": 4.126198804133398e-05,
+      "loss": 0.7239,
+      "step": 9486
+    },
+    {
+      "epoch": 0.13975806303577656,
+      "grad_norm": 1.1646157503128052,
+      "learning_rate": 4.1198109758801055e-05,
+      "loss": 0.7344,
+      "step": 9517
+    },
+    {
+      "epoch": 0.14021330102612112,
+      "grad_norm": 1.106126070022583,
+      "learning_rate": 4.113404868280107e-05,
+      "loss": 0.7218,
+      "step": 9548
+    },
+    {
+      "epoch": 0.14066853901646567,
+      "grad_norm": 1.2062433958053589,
+      "learning_rate": 4.106980553625457e-05,
+      "loss": 0.7309,
+      "step": 9579
+    },
+    {
+      "epoch": 0.14112377700681022,
+      "grad_norm": 1.1536740064620972,
+      "learning_rate": 4.100538104413674e-05,
+      "loss": 0.732,
+      "step": 9610
+    },
+    {
+      "epoch": 0.14157901499715475,
+      "grad_norm": 1.2121433019638062,
+      "learning_rate": 4.09407759334692e-05,
+      "loss": 0.7284,
+      "step": 9641
+    },
+    {
+      "epoch": 0.1420342529874993,
+      "grad_norm": 1.0838932991027832,
+      "learning_rate": 4.087599093331186e-05,
+      "loss": 0.7194,
+      "step": 9672
+    },
+    {
+      "epoch": 0.14248949097784386,
+      "grad_norm": 1.2161401510238647,
+      "learning_rate": 4.081102677475462e-05,
+      "loss": 0.7225,
+      "step": 9703
+    },
+    {
+      "epoch": 0.1429447289681884,
+      "grad_norm": 1.1768158674240112,
+      "learning_rate": 4.0745884190909194e-05,
+      "loss": 0.7284,
+      "step": 9734
+    },
+    {
+      "epoch": 0.14339996695853297,
+      "grad_norm": 1.0994865894317627,
+      "learning_rate": 4.0680563916900796e-05,
+      "loss": 0.7262,
+      "step": 9765
+    },
+    {
+      "epoch": 0.14385520494887752,
+      "grad_norm": 1.1083378791809082,
+      "learning_rate": 4.0615066689859815e-05,
+      "loss": 0.7365,
+      "step": 9796
+    },
+    {
+      "epoch": 0.14431044293922204,
+      "grad_norm": 1.2145380973815918,
+      "learning_rate": 4.0549393248913584e-05,
+      "loss": 0.7175,
+      "step": 9827
+    },
+    {
+      "epoch": 0.1447656809295666,
+      "grad_norm": 1.2533223628997803,
+      "learning_rate": 4.048354433517794e-05,
+      "loss": 0.7227,
+      "step": 9858
+    },
+    {
+      "epoch": 0.14522091891991115,
+      "grad_norm": 1.1712641716003418,
+      "learning_rate": 4.0417520691748916e-05,
+      "loss": 0.7339,
+      "step": 9889
+    },
+    {
+      "epoch": 0.1456761569102557,
+      "grad_norm": 1.193190097808838,
+      "learning_rate": 4.035132306369438e-05,
+      "loss": 0.7224,
+      "step": 9920
+    },
+    {
+      "epoch": 0.14613139490060026,
+      "grad_norm": 1.1931018829345703,
+      "learning_rate": 4.028495219804555e-05,
+      "loss": 0.7301,
+      "step": 9951
+    },
+    {
+      "epoch": 0.1465866328909448,
+      "grad_norm": 1.1219127178192139,
+      "learning_rate": 4.021840884378864e-05,
+      "loss": 0.7243,
+      "step": 9982
+    },
+    {
+      "epoch": 0.14704187088128934,
+      "grad_norm": 1.2533178329467773,
+      "learning_rate": 4.015169375185633e-05,
+      "loss": 0.7243,
+      "step": 10013
+    },
+    {
+      "epoch": 0.1474971088716339,
+      "grad_norm": 1.2068380117416382,
+      "learning_rate": 4.0084807675119396e-05,
+      "loss": 0.7293,
+      "step": 10044
+    },
+    {
+      "epoch": 0.14795234686197845,
+      "grad_norm": 1.1291258335113525,
+      "learning_rate": 4.0017751368378106e-05,
+      "loss": 0.7342,
+      "step": 10075
+    },
+    {
+      "epoch": 0.148407584852323,
+      "grad_norm": 1.1120283603668213,
+      "learning_rate": 3.995052558835377e-05,
+      "loss": 0.7291,
+      "step": 10106
+    },
+    {
+      "epoch": 0.14886282284266755,
+      "grad_norm": 1.154776930809021,
+      "learning_rate": 3.988313109368017e-05,
+      "loss": 0.7236,
+      "step": 10137
+    },
+    {
+      "epoch": 0.1493180608330121,
+      "grad_norm": 1.1486085653305054,
+      "learning_rate": 3.981556864489504e-05,
+      "loss": 0.7249,
+      "step": 10168
+    },
+    {
+      "epoch": 0.14977329882335666,
+      "grad_norm": 1.1259063482284546,
+      "learning_rate": 3.974783900443142e-05,
+      "loss": 0.727,
+      "step": 10199
+    },
+    {
+      "epoch": 0.15022853681370119,
+      "grad_norm": 1.2017011642456055,
+      "learning_rate": 3.9679942936609095e-05,
+      "loss": 0.7229,
+      "step": 10230
+    },
+    {
+      "epoch": 0.15068377480404574,
+      "grad_norm": 1.2615267038345337,
+      "learning_rate": 3.961188120762596e-05,
+      "loss": 0.7253,
+      "step": 10261
+    },
+    {
+      "epoch": 0.1511390127943903,
+      "grad_norm": 1.1844033002853394,
+      "learning_rate": 3.954365458554938e-05,
+      "loss": 0.7274,
+      "step": 10292
+    },
+    {
+      "epoch": 0.15159425078473485,
+      "grad_norm": 1.0273635387420654,
+      "learning_rate": 3.947526384030751e-05,
+      "loss": 0.7273,
+      "step": 10323
+    },
+    {
+      "epoch": 0.1520494887750794,
+      "grad_norm": 1.1291526556015015,
+      "learning_rate": 3.9406709743680624e-05,
+      "loss": 0.7247,
+      "step": 10354
+    },
+    {
+      "epoch": 0.15250472676542395,
+      "grad_norm": 1.0321513414382935,
+      "learning_rate": 3.9337993069292366e-05,
+      "loss": 0.7205,
+      "step": 10385
+    },
+    {
+      "epoch": 0.15295996475576848,
+      "grad_norm": 1.140831708908081,
+      "learning_rate": 3.926911459260109e-05,
+      "loss": 0.7141,
+      "step": 10416
+    },
+    {
+      "epoch": 0.15341520274611303,
+      "grad_norm": 1.1521825790405273,
+      "learning_rate": 3.920007509089102e-05,
+      "loss": 0.7276,
+      "step": 10447
+    },
+    {
+      "epoch": 0.1538704407364576,
+      "grad_norm": 1.1163930892944336,
+      "learning_rate": 3.913087534326357e-05,
+      "loss": 0.7115,
+      "step": 10478
+    },
+    {
+      "epoch": 0.15432567872680214,
+      "grad_norm": 1.1592880487442017,
+      "learning_rate": 3.9061516130628475e-05,
+      "loss": 0.7275,
+      "step": 10509
+    },
+    {
+      "epoch": 0.1547809167171467,
+      "grad_norm": 1.1489180326461792,
+      "learning_rate": 3.8991998235695025e-05,
+      "loss": 0.7343,
+      "step": 10540
+    },
+    {
+      "epoch": 0.15523615470749125,
+      "grad_norm": 1.1153382062911987,
+      "learning_rate": 3.8922322442963224e-05,
+      "loss": 0.7304,
+      "step": 10571
+    },
+    {
+      "epoch": 0.15569139269783577,
+      "grad_norm": 1.2471085786819458,
+      "learning_rate": 3.885248953871491e-05,
+      "loss": 0.7287,
+      "step": 10602
+    },
+    {
+      "epoch": 0.15614663068818033,
+      "grad_norm": 1.1999790668487549,
+      "learning_rate": 3.8782500311004915e-05,
+      "loss": 0.7337,
+      "step": 10633
+    },
+    {
+      "epoch": 0.15660186867852488,
+      "grad_norm": 1.303769588470459,
+      "learning_rate": 3.871235554965218e-05,
+      "loss": 0.7199,
+      "step": 10664
+    },
+    {
+      "epoch": 0.15705710666886943,
+      "grad_norm": 1.1471834182739258,
+      "learning_rate": 3.864205604623078e-05,
+      "loss": 0.7178,
+      "step": 10695
+    },
+    {
+      "epoch": 0.157512344659214,
+      "grad_norm": 1.089218020439148,
+      "learning_rate": 3.857160259406107e-05,
+      "loss": 0.7173,
+      "step": 10726
+    },
+    {
+      "epoch": 0.15796758264955854,
+      "grad_norm": 1.0770212411880493,
+      "learning_rate": 3.8500995988200674e-05,
+      "loss": 0.7202,
+      "step": 10757
+    },
+    {
+      "epoch": 0.15842282063990307,
+      "grad_norm": 1.0965075492858887,
+      "learning_rate": 3.843023702543556e-05,
+      "loss": 0.7267,
+      "step": 10788
+    },
+    {
+      "epoch": 0.15887805863024762,
+      "grad_norm": 1.1376181840896606,
+      "learning_rate": 3.8359326504270984e-05,
+      "loss": 0.7128,
+      "step": 10819
+    },
+    {
+      "epoch": 0.15933329662059217,
+      "grad_norm": 1.1273307800292969,
+      "learning_rate": 3.828826522492255e-05,
+      "loss": 0.7196,
+      "step": 10850
+    },
+    {
+      "epoch": 0.15978853461093673,
+      "grad_norm": 1.151166558265686,
+      "learning_rate": 3.821705398930713e-05,
+      "loss": 0.7239,
+      "step": 10881
+    },
+    {
+      "epoch": 0.16024377260128128,
+      "grad_norm": 1.0326038599014282,
+      "learning_rate": 3.814569360103385e-05,
+      "loss": 0.7209,
+      "step": 10912
+    },
+    {
+      "epoch": 0.16069901059162583,
+      "grad_norm": 1.1757500171661377,
+      "learning_rate": 3.807418486539499e-05,
+      "loss": 0.7235,
+      "step": 10943
+    },
+    {
+      "epoch": 0.16115424858197036,
+      "grad_norm": 1.1348350048065186,
+      "learning_rate": 3.80025285893569e-05,
+      "loss": 0.7214,
+      "step": 10974
+    },
+    {
+      "epoch": 0.16160948657231491,
+      "grad_norm": 1.1032580137252808,
+      "learning_rate": 3.793072558155093e-05,
+      "loss": 0.7232,
+      "step": 11005
+    },
+    {
+      "epoch": 0.16206472456265947,
+      "grad_norm": 1.0477440357208252,
+      "learning_rate": 3.785877665226426e-05,
+      "loss": 0.7185,
+      "step": 11036
+    },
+    {
+      "epoch": 0.16251996255300402,
+      "grad_norm": 1.0568618774414062,
+      "learning_rate": 3.778668261343079e-05,
+      "loss": 0.723,
+      "step": 11067
+    },
+    {
+      "epoch": 0.16297520054334858,
+      "grad_norm": 1.066054105758667,
+      "learning_rate": 3.771444427862192e-05,
+      "loss": 0.7111,
+      "step": 11098
+    },
+    {
+      "epoch": 0.16343043853369313,
+      "grad_norm": 1.108907699584961,
+      "learning_rate": 3.7642062463037465e-05,
+      "loss": 0.7158,
+      "step": 11129
+    },
+    {
+      "epoch": 0.16388567652403765,
+      "grad_norm": 0.9510675072669983,
+      "learning_rate": 3.7569537983496373e-05,
+      "loss": 0.7209,
+      "step": 11160
+    },
+    {
+      "epoch": 0.1643409145143822,
+      "grad_norm": 1.0409342050552368,
+      "learning_rate": 3.749687165842753e-05,
+      "loss": 0.7181,
+      "step": 11191
+    },
+    {
+      "epoch": 0.16479615250472676,
+      "grad_norm": 1.0607185363769531,
+      "learning_rate": 3.7424064307860536e-05,
+      "loss": 0.7214,
+      "step": 11222
+    },
+    {
+      "epoch": 0.16525139049507132,
+      "grad_norm": 1.5347952842712402,
+      "learning_rate": 3.735111675341645e-05,
+      "loss": 0.7216,
+      "step": 11253
+    },
+    {
+      "epoch": 0.16570662848541587,
+      "grad_norm": 1.1136394739151,
+      "learning_rate": 3.7278029818298524e-05,
+      "loss": 0.7169,
+      "step": 11284
+    },
+    {
+      "epoch": 0.16616186647576042,
+      "grad_norm": 1.0864076614379883,
+      "learning_rate": 3.720480432728287e-05,
+      "loss": 0.7144,
+      "step": 11315
+    },
+    {
+      "epoch": 0.16661710446610495,
+      "grad_norm": 1.199810266494751,
+      "learning_rate": 3.71314411067092e-05,
+      "loss": 0.7192,
+      "step": 11346
+    },
+    {
+      "epoch": 0.1670723424564495,
+      "grad_norm": 1.096343994140625,
+      "learning_rate": 3.70579409844715e-05,
+      "loss": 0.7197,
+      "step": 11377
+    },
+    {
+      "epoch": 0.16752758044679406,
+      "grad_norm": 1.1140949726104736,
+      "learning_rate": 3.698430479000865e-05,
+      "loss": 0.727,
+      "step": 11408
+    },
+    {
+      "epoch": 0.1679828184371386,
+      "grad_norm": 1.140215277671814,
+      "learning_rate": 3.691053335429509e-05,
+      "loss": 0.7125,
+      "step": 11439
+    },
+    {
+      "epoch": 0.16843805642748316,
+      "grad_norm": 1.1289955377578735,
+      "learning_rate": 3.683662750983147e-05,
+      "loss": 0.7119,
+      "step": 11470
+    },
+    {
+      "epoch": 0.16889329441782772,
+      "grad_norm": 1.1218159198760986,
+      "learning_rate": 3.676258809063518e-05,
+      "loss": 0.7191,
+      "step": 11501
+    },
+    {
+      "epoch": 0.16934853240817227,
+      "grad_norm": 1.1016902923583984,
+      "learning_rate": 3.6688415932231004e-05,
+      "loss": 0.7231,
+      "step": 11532
+    },
+    {
+      "epoch": 0.1698037703985168,
+      "grad_norm": 1.0611400604248047,
+      "learning_rate": 3.661411187164166e-05,
+      "loss": 0.7242,
+      "step": 11563
+    },
+    {
+      "epoch": 0.17025900838886135,
+      "grad_norm": 1.1272419691085815,
+      "learning_rate": 3.65396767473784e-05,
+      "loss": 0.7122,
+      "step": 11594
+    },
+    {
+      "epoch": 0.1707142463792059,
+      "grad_norm": 1.0000230073928833,
+      "learning_rate": 3.6465111399431465e-05,
+      "loss": 0.714,
+      "step": 11625
+    },
+    {
+      "epoch": 0.17116948436955046,
+      "grad_norm": 1.1173810958862305,
+      "learning_rate": 3.6390416669260674e-05,
+      "loss": 0.7225,
+      "step": 11656
+    },
+    {
+      "epoch": 0.171624722359895,
+      "grad_norm": 1.1445261240005493,
+      "learning_rate": 3.63155933997859e-05,
+      "loss": 0.7234,
+      "step": 11687
+    },
+    {
+      "epoch": 0.17207996035023956,
+      "grad_norm": 1.1363463401794434,
+      "learning_rate": 3.624064243537758e-05,
+      "loss": 0.7195,
+      "step": 11718
+    },
+    {
+      "epoch": 0.1725351983405841,
+      "grad_norm": 1.1406384706497192,
+      "learning_rate": 3.616556462184716e-05,
+      "loss": 0.7181,
+      "step": 11749
+    },
+    {
+      "epoch": 0.17299043633092864,
+      "grad_norm": 1.0934033393859863,
+      "learning_rate": 3.609036080643755e-05,
+      "loss": 0.7142,
+      "step": 11780
+    },
+    {
+      "epoch": 0.1734456743212732,
+      "grad_norm": 1.1739163398742676,
+      "learning_rate": 3.60150318378136e-05,
+      "loss": 0.7206,
+      "step": 11811
+    },
+    {
+      "epoch": 0.17390091231161775,
+      "grad_norm": 1.1040031909942627,
+      "learning_rate": 3.5939578566052465e-05,
+      "loss": 0.7142,
+      "step": 11842
+    },
+    {
+      "epoch": 0.1743561503019623,
+      "grad_norm": 1.0491020679473877,
+      "learning_rate": 3.586400184263408e-05,
+      "loss": 0.7142,
+      "step": 11873
+    },
+    {
+      "epoch": 0.17481138829230686,
+      "grad_norm": 1.1212310791015625,
+      "learning_rate": 3.578830252043148e-05,
+      "loss": 0.7148,
+      "step": 11904
+    },
+    {
+      "epoch": 0.17526662628265138,
+      "grad_norm": 1.1223775148391724,
+      "learning_rate": 3.571248145370125e-05,
+      "loss": 0.7184,
+      "step": 11935
+    },
+    {
+      "epoch": 0.17572186427299594,
+      "grad_norm": 1.1271427869796753,
+      "learning_rate": 3.5636539498073794e-05,
+      "loss": 0.7195,
+      "step": 11966
+    },
+    {
+      "epoch": 0.1761771022633405,
+      "grad_norm": 1.0874998569488525,
+      "learning_rate": 3.556047751054378e-05,
+      "loss": 0.7226,
+      "step": 11997
+    },
+    {
+      "epoch": 0.17663234025368504,
+      "grad_norm": 1.1189168691635132,
+      "learning_rate": 3.548429634946039e-05,
+      "loss": 0.7136,
+      "step": 12028
+    },
+    {
+      "epoch": 0.1770875782440296,
+      "grad_norm": 1.1366541385650635,
+      "learning_rate": 3.540799687451768e-05,
+      "loss": 0.7187,
+      "step": 12059
+    },
+    {
+      "epoch": 0.17754281623437415,
+      "grad_norm": 1.0756332874298096,
+      "learning_rate": 3.533157994674485e-05,
+      "loss": 0.7085,
+      "step": 12090
+    },
+    {
+      "epoch": 0.17799805422471868,
+      "grad_norm": 1.1229898929595947,
+      "learning_rate": 3.5255046428496546e-05,
+      "loss": 0.7259,
+      "step": 12121
+    },
+    {
+      "epoch": 0.17845329221506323,
+      "grad_norm": 0.97579425573349,
+      "learning_rate": 3.517839718344311e-05,
+      "loss": 0.7141,
+      "step": 12152
+    },
+    {
+      "epoch": 0.17890853020540778,
+      "grad_norm": 1.155372977256775,
+      "learning_rate": 3.510163307656086e-05,
+      "loss": 0.7102,
+      "step": 12183
+    },
+    {
+      "epoch": 0.17936376819575234,
+      "grad_norm": 1.114054560661316,
+      "learning_rate": 3.5024754974122324e-05,
+      "loss": 0.7099,
+      "step": 12214
+    },
+    {
+      "epoch": 0.1798190061860969,
+      "grad_norm": 1.1974929571151733,
+      "learning_rate": 3.494776374368643e-05,
+      "loss": 0.7229,
+      "step": 12245
+    },
+    {
+      "epoch": 0.18027424417644144,
+      "grad_norm": 1.0634280443191528,
+      "learning_rate": 3.4870660254088724e-05,
+      "loss": 0.7091,
+      "step": 12276
+    },
+    {
+      "epoch": 0.18072948216678597,
+      "grad_norm": 1.0801422595977783,
+      "learning_rate": 3.479344537543164e-05,
+      "loss": 0.7162,
+      "step": 12307
+    },
+    {
+      "epoch": 0.18118472015713052,
+      "grad_norm": 1.0427660942077637,
+      "learning_rate": 3.4716119979074565e-05,
+      "loss": 0.7175,
+      "step": 12338
+    },
+    {
+      "epoch": 0.18163995814747508,
+      "grad_norm": 1.1020700931549072,
+      "learning_rate": 3.463868493762412e-05,
+      "loss": 0.7129,
+      "step": 12369
+    },
+    {
+      "epoch": 0.18209519613781963,
+      "grad_norm": 1.0598516464233398,
+      "learning_rate": 3.456114112492418e-05,
+      "loss": 0.7106,
+      "step": 12400
+    },
+    {
+      "epoch": 0.18255043412816419,
+      "grad_norm": 1.0527369976043701,
+      "learning_rate": 3.4483489416046164e-05,
+      "loss": 0.7074,
+      "step": 12431
+    },
+    {
+      "epoch": 0.18300567211850874,
+      "grad_norm": 1.1209337711334229,
+      "learning_rate": 3.440573068727905e-05,
+      "loss": 0.7084,
+      "step": 12462
+    },
+    {
+      "epoch": 0.18346091010885326,
+      "grad_norm": 1.075538992881775,
+      "learning_rate": 3.4327865816119495e-05,
+      "loss": 0.7129,
+      "step": 12493
+    },
+    {
+      "epoch": 0.18391614809919782,
+      "grad_norm": 1.1929987668991089,
+      "learning_rate": 3.4249895681262025e-05,
+      "loss": 0.7143,
+      "step": 12524
+    },
+    {
+      "epoch": 0.18437138608954237,
+      "grad_norm": 1.1039793491363525,
+      "learning_rate": 3.417182116258899e-05,
+      "loss": 0.7133,
+      "step": 12555
+    },
+    {
+      "epoch": 0.18482662407988693,
+      "grad_norm": 1.0911282300949097,
+      "learning_rate": 3.409364314116074e-05,
+      "loss": 0.7184,
+      "step": 12586
+    },
+    {
+      "epoch": 0.18528186207023148,
+      "grad_norm": 1.0749549865722656,
+      "learning_rate": 3.401536249920559e-05,
+      "loss": 0.7134,
+      "step": 12617
+    },
+    {
+      "epoch": 0.18573710006057603,
+      "grad_norm": 1.1577101945877075,
+      "learning_rate": 3.393698012010998e-05,
+      "loss": 0.7189,
+      "step": 12648
+    },
+    {
+      "epoch": 0.18619233805092056,
+      "grad_norm": 1.0742738246917725,
+      "learning_rate": 3.385849688840839e-05,
+      "loss": 0.7139,
+      "step": 12679
+    },
+    {
+      "epoch": 0.1866475760412651,
+      "grad_norm": 1.0930507183074951,
+      "learning_rate": 3.3779913689773414e-05,
+      "loss": 0.71,
+      "step": 12710
+    },
+    {
+      "epoch": 0.18710281403160967,
+      "grad_norm": 1.106213927268982,
+      "learning_rate": 3.370123141100578e-05,
+      "loss": 0.7149,
+      "step": 12741
+    },
+    {
+      "epoch": 0.18755805202195422,
+      "grad_norm": 1.1760305166244507,
+      "learning_rate": 3.3622450940024305e-05,
+      "loss": 0.7111,
+      "step": 12772
+    },
+    {
+      "epoch": 0.18801329001229877,
+      "grad_norm": 1.0691040754318237,
+      "learning_rate": 3.35435731658559e-05,
+      "loss": 0.7226,
+      "step": 12803
+    },
+    {
+      "epoch": 0.18846852800264333,
+      "grad_norm": 1.125360131263733,
+      "learning_rate": 3.346459897862552e-05,
+      "loss": 0.7189,
+      "step": 12834
+    },
+    {
+      "epoch": 0.18892376599298788,
+      "grad_norm": 0.998501718044281,
+      "learning_rate": 3.338552926954613e-05,
+      "loss": 0.7135,
+      "step": 12865
+    },
+    {
+      "epoch": 0.1893790039833324,
+      "grad_norm": 1.159458041191101,
+      "learning_rate": 3.330636493090868e-05,
+      "loss": 0.7097,
+      "step": 12896
+    },
+    {
+      "epoch": 0.18983424197367696,
+      "grad_norm": 1.0852668285369873,
+      "learning_rate": 3.322710685607193e-05,
+      "loss": 0.7159,
+      "step": 12927
+    },
+    {
+      "epoch": 0.1902894799640215,
+      "grad_norm": 1.04311203956604,
+      "learning_rate": 3.314775593945251e-05,
+      "loss": 0.7095,
+      "step": 12958
+    },
+    {
+      "epoch": 0.19074471795436607,
+      "grad_norm": 1.18183434009552,
+      "learning_rate": 3.3068313076514714e-05,
+      "loss": 0.7202,
+      "step": 12989
+    },
+    {
+      "epoch": 0.19119995594471062,
+      "grad_norm": 1.053841233253479,
+      "learning_rate": 3.298877916376047e-05,
+      "loss": 0.7124,
+      "step": 13020
+    },
+    {
+      "epoch": 0.19165519393505517,
+      "grad_norm": 1.0783239603042603,
+      "learning_rate": 3.290915509871915e-05,
+      "loss": 0.7213,
+      "step": 13051
+    },
+    {
+      "epoch": 0.1921104319253997,
+      "grad_norm": 1.0454438924789429,
+      "learning_rate": 3.282944177993753e-05,
+      "loss": 0.7176,
+      "step": 13082
+    },
+    {
+      "epoch": 0.19256566991574425,
+      "grad_norm": 0.9800693988800049,
+      "learning_rate": 3.274964010696957e-05,
+      "loss": 0.7114,
+      "step": 13113
+    },
+    {
+      "epoch": 0.1930209079060888,
+      "grad_norm": 1.0425992012023926,
+      "learning_rate": 3.266975098036629e-05,
+      "loss": 0.7068,
+      "step": 13144
+    },
+    {
+      "epoch": 0.19347614589643336,
+      "grad_norm": 1.049523115158081,
+      "learning_rate": 3.258977530166562e-05,
+      "loss": 0.7179,
+      "step": 13175
+    },
+    {
+      "epoch": 0.1939313838867779,
+      "grad_norm": 1.0716999769210815,
+      "learning_rate": 3.250971397338227e-05,
+      "loss": 0.7055,
+      "step": 13206
+    },
+    {
+      "epoch": 0.19438662187712247,
+      "grad_norm": 1.143379807472229,
+      "learning_rate": 3.2429567898997404e-05,
+      "loss": 0.705,
+      "step": 13237
+    },
+    {
+      "epoch": 0.194841859867467,
+      "grad_norm": 1.0960956811904907,
+      "learning_rate": 3.234933798294859e-05,
+      "loss": 0.7074,
+      "step": 13268
+    },
+    {
+      "epoch": 0.19529709785781155,
+      "grad_norm": 4.071056842803955,
+      "learning_rate": 3.2269025130619535e-05,
+      "loss": 0.7081,
+      "step": 13299
+    },
+    {
+      "epoch": 0.1957523358481561,
+      "grad_norm": 1.0089994668960571,
+      "learning_rate": 3.218863024832985e-05,
+      "loss": 0.7112,
+      "step": 13330
+    },
+    {
+      "epoch": 0.19620757383850065,
+      "grad_norm": 1.036939263343811,
+      "learning_rate": 3.2108154243324864e-05,
+      "loss": 0.707,
+      "step": 13361
+    },
+    {
+      "epoch": 0.1966628118288452,
+      "grad_norm": 1.0934596061706543,
+      "learning_rate": 3.2027598023765345e-05,
+      "loss": 0.7116,
+      "step": 13392
+    },
+    {
+      "epoch": 0.19711804981918976,
+      "grad_norm": 0.9786377549171448,
+      "learning_rate": 3.194696249871729e-05,
+      "loss": 0.7033,
+      "step": 13423
+    },
+    {
+      "epoch": 0.1975732878095343,
+      "grad_norm": 1.1358857154846191,
+      "learning_rate": 3.186624857814164e-05,
+      "loss": 0.7076,
+      "step": 13454
+    },
+    {
+      "epoch": 0.19802852579987884,
+      "grad_norm": 1.0696585178375244,
+      "learning_rate": 3.178545717288401e-05,
+      "loss": 0.7038,
+      "step": 13485
+    },
+    {
+      "epoch": 0.1984837637902234,
+      "grad_norm": 1.1593236923217773,
+      "learning_rate": 3.170458919466444e-05,
+      "loss": 0.7081,
+      "step": 13516
+    },
+    {
+      "epoch": 0.19893900178056795,
+      "grad_norm": 1.1371269226074219,
+      "learning_rate": 3.1623645556067063e-05,
+      "loss": 0.7096,
+      "step": 13547
+    },
+    {
+      "epoch": 0.1993942397709125,
+      "grad_norm": 1.1223064661026,
+      "learning_rate": 3.154262717052985e-05,
+      "loss": 0.7112,
+      "step": 13578
+    },
+    {
+      "epoch": 0.19984947776125705,
+      "grad_norm": 1.1869999170303345,
+      "learning_rate": 3.146153495233426e-05,
+      "loss": 0.7064,
+      "step": 13609
+    },
+    {
+      "epoch": 0.20030471575160158,
+      "grad_norm": 1.0449695587158203,
+      "learning_rate": 3.1380369816594944e-05,
+      "loss": 0.715,
+      "step": 13640
+    },
+    {
+      "epoch": 0.20075995374194613,
+      "grad_norm": 1.041473388671875,
+      "learning_rate": 3.129913267924946e-05,
+      "loss": 0.7117,
+      "step": 13671
+    },
+    {
+      "epoch": 0.2012151917322907,
+      "grad_norm": 1.0208512544631958,
+      "learning_rate": 3.121782445704782e-05,
+      "loss": 0.7068,
+      "step": 13702
+    },
+    {
+      "epoch": 0.20167042972263524,
+      "grad_norm": 0.9912329316139221,
+      "learning_rate": 3.11364460675423e-05,
+      "loss": 0.7095,
+      "step": 13733
+    },
+    {
+      "epoch": 0.2021256677129798,
+      "grad_norm": 0.9953168630599976,
+      "learning_rate": 3.1054998429076934e-05,
+      "loss": 0.7025,
+      "step": 13764
+    },
+    {
+      "epoch": 0.20258090570332435,
+      "grad_norm": 1.0568119287490845,
+      "learning_rate": 3.097348246077728e-05,
+      "loss": 0.7076,
+      "step": 13795
+    },
+    {
+      "epoch": 0.20303614369366887,
+      "grad_norm": 0.9954741597175598,
+      "learning_rate": 3.0891899082539924e-05,
+      "loss": 0.7105,
+      "step": 13826
+    },
+    {
+      "epoch": 0.20349138168401343,
+      "grad_norm": 1.0687825679779053,
+      "learning_rate": 3.0810249215022233e-05,
+      "loss": 0.7024,
+      "step": 13857
+    },
+    {
+      "epoch": 0.20394661967435798,
+      "grad_norm": 1.0794721841812134,
+      "learning_rate": 3.0728533779631865e-05,
+      "loss": 0.6996,
+      "step": 13888
+    },
+    {
+      "epoch": 0.20440185766470254,
+      "grad_norm": 1.1260164976119995,
+      "learning_rate": 3.064675369851637e-05,
+      "loss": 0.709,
+      "step": 13919
+    },
+    {
+      "epoch": 0.2048570956550471,
+      "grad_norm": 1.0633211135864258,
+      "learning_rate": 3.056490989455289e-05,
+      "loss": 0.7125,
+      "step": 13950
+    },
+    {
+      "epoch": 0.20531233364539164,
+      "grad_norm": 0.9579554796218872,
+      "learning_rate": 3.0483003291337596e-05,
+      "loss": 0.6983,
+      "step": 13981
+    },
+    {
+      "epoch": 0.20576757163573617,
+      "grad_norm": 1.0886019468307495,
+      "learning_rate": 3.040103481317539e-05,
+      "loss": 0.7076,
+      "step": 14012
+    },
+    {
+      "epoch": 0.20622280962608072,
+      "grad_norm": 1.0991545915603638,
+      "learning_rate": 3.03190053850694e-05,
+      "loss": 0.7003,
+      "step": 14043
+    },
+    {
+      "epoch": 0.20667804761642528,
+      "grad_norm": 0.9896078705787659,
+      "learning_rate": 3.0236915932710573e-05,
+      "loss": 0.6963,
+      "step": 14074
+    },
+    {
+      "epoch": 0.20713328560676983,
+      "grad_norm": 1.0856597423553467,
+      "learning_rate": 3.0154767382467232e-05,
+      "loss": 0.6977,
+      "step": 14105
+    },
+    {
+      "epoch": 0.20758852359711438,
+      "grad_norm": 1.0282793045043945,
+      "learning_rate": 3.0072560661374582e-05,
+      "loss": 0.704,
+      "step": 14136
+    },
+    {
+      "epoch": 0.20804376158745894,
+      "grad_norm": 1.0672529935836792,
+      "learning_rate": 2.999029669712431e-05,
+      "loss": 0.7134,
+      "step": 14167
+    },
+    {
+      "epoch": 0.2084989995778035,
+      "grad_norm": 1.1591187715530396,
+      "learning_rate": 2.990797641805408e-05,
+      "loss": 0.7058,
+      "step": 14198
+    },
+    {
+      "epoch": 0.20895423756814802,
+      "grad_norm": 0.9841179847717285,
+      "learning_rate": 2.982560075313704e-05,
+      "loss": 0.6952,
+      "step": 14229
+    },
+    {
+      "epoch": 0.20940947555849257,
+      "grad_norm": 1.099001407623291,
+      "learning_rate": 2.9743170631971368e-05,
+      "loss": 0.7048,
+      "step": 14260
+    },
+    {
+      "epoch": 0.20986471354883712,
+      "grad_norm": 1.0944379568099976,
+      "learning_rate": 2.9660686984769792e-05,
+      "loss": 0.7081,
+      "step": 14291
+    },
+    {
+      "epoch": 0.21031995153918168,
+      "grad_norm": 1.1136280298233032,
+      "learning_rate": 2.9578150742349047e-05,
+      "loss": 0.7057,
+      "step": 14322
+    },
+    {
+      "epoch": 0.21077518952952623,
+      "grad_norm": 1.1170709133148193,
+      "learning_rate": 2.949556283611942e-05,
+      "loss": 0.7048,
+      "step": 14353
+    },
+    {
+      "epoch": 0.21123042751987078,
+      "grad_norm": 1.025364875793457,
+      "learning_rate": 2.9412924198074206e-05,
+      "loss": 0.7069,
+      "step": 14384
+    },
+    {
+      "epoch": 0.2116856655102153,
+      "grad_norm": 1.078324794769287,
+      "learning_rate": 2.9330235760779208e-05,
+      "loss": 0.7042,
+      "step": 14415
+    },
+    {
+      "epoch": 0.21214090350055986,
+      "grad_norm": 1.3148599863052368,
+      "learning_rate": 2.9247498457362188e-05,
+      "loss": 0.7007,
+      "step": 14446
+    },
+    {
+      "epoch": 0.21259614149090442,
+      "grad_norm": 1.0996065139770508,
+      "learning_rate": 2.9164713221502373e-05,
+      "loss": 0.6961,
+      "step": 14477
+    },
+    {
+      "epoch": 0.21305137948124897,
+      "grad_norm": 1.0913583040237427,
+      "learning_rate": 2.9081880987419912e-05,
+      "loss": 0.7075,
+      "step": 14508
+    },
+    {
+      "epoch": 0.21350661747159352,
+      "grad_norm": 1.0781054496765137,
+      "learning_rate": 2.8999002689865296e-05,
+      "loss": 0.7039,
+      "step": 14539
+    },
+    {
+      "epoch": 0.21396185546193808,
+      "grad_norm": 1.1157950162887573,
+      "learning_rate": 2.8916079264108852e-05,
+      "loss": 0.7083,
+      "step": 14570
+    },
+    {
+      "epoch": 0.2144170934522826,
+      "grad_norm": 0.9876468181610107,
+      "learning_rate": 2.883311164593017e-05,
+      "loss": 0.7014,
+      "step": 14601
+    },
+    {
+      "epoch": 0.21487233144262716,
+      "grad_norm": 1.0070513486862183,
+      "learning_rate": 2.875010077160754e-05,
+      "loss": 0.7041,
+      "step": 14632
+    },
+    {
+      "epoch": 0.2153275694329717,
+      "grad_norm": 1.0021169185638428,
+      "learning_rate": 2.866704757790741e-05,
+      "loss": 0.7033,
+      "step": 14663
+    },
+    {
+      "epoch": 0.21578280742331626,
+      "grad_norm": 1.1217141151428223,
+      "learning_rate": 2.858395300207376e-05,
+      "loss": 0.7013,
+      "step": 14694
+    },
+    {
+      "epoch": 0.21623804541366082,
+      "grad_norm": 1.0865851640701294,
+      "learning_rate": 2.8500817981817607e-05,
+      "loss": 0.7048,
+      "step": 14725
+    },
+    {
+      "epoch": 0.21669328340400537,
+      "grad_norm": 1.1032036542892456,
+      "learning_rate": 2.8417643455306336e-05,
+      "loss": 0.6971,
+      "step": 14756
+    },
+    {
+      "epoch": 0.2171485213943499,
+      "grad_norm": 1.0487210750579834,
+      "learning_rate": 2.8334430361153185e-05,
+      "loss": 0.7009,
+      "step": 14787
+    },
+    {
+      "epoch": 0.21760375938469445,
+      "grad_norm": 1.1253623962402344,
+      "learning_rate": 2.8251179638406612e-05,
+      "loss": 0.699,
+      "step": 14818
+    },
+    {
+      "epoch": 0.218058997375039,
+      "grad_norm": 0.9654372930526733,
+      "learning_rate": 2.8167892226539704e-05,
+      "loss": 0.7046,
+      "step": 14849
+    },
+    {
+      "epoch": 0.21851423536538356,
+      "grad_norm": 1.0542151927947998,
+      "learning_rate": 2.8084569065439588e-05,
+      "loss": 0.7135,
+      "step": 14880
+    },
+    {
+      "epoch": 0.2189694733557281,
+      "grad_norm": 0.961097776889801,
+      "learning_rate": 2.8001211095396807e-05,
+      "loss": 0.7055,
+      "step": 14911
+    },
+    {
+      "epoch": 0.21942471134607267,
+      "grad_norm": 1.078316330909729,
+      "learning_rate": 2.791781925709473e-05,
+      "loss": 0.6999,
+      "step": 14942
+    },
+    {
+      "epoch": 0.2198799493364172,
+      "grad_norm": 0.9983609318733215,
+      "learning_rate": 2.7834394491598908e-05,
+      "loss": 0.7043,
+      "step": 14973
+    },
+    {
+      "epoch": 0.22033518732676174,
+      "grad_norm": 0.9962406754493713,
+      "learning_rate": 2.7750937740346485e-05,
+      "loss": 0.7011,
+      "step": 15004
+    },
+    {
+      "epoch": 0.2207904253171063,
+      "grad_norm": 1.0712863206863403,
+      "learning_rate": 2.7667449945135564e-05,
+      "loss": 0.7041,
+      "step": 15035
+    },
+    {
+      "epoch": 0.22124566330745085,
+      "grad_norm": 1.158698320388794,
+      "learning_rate": 2.7583932048114557e-05,
+      "loss": 0.6891,
+      "step": 15066
+    },
+    {
+      "epoch": 0.2217009012977954,
+      "grad_norm": 1.1255605220794678,
+      "learning_rate": 2.7500384991771587e-05,
+      "loss": 0.7069,
+      "step": 15097
+    },
+    {
+      "epoch": 0.22215613928813996,
+      "grad_norm": 1.0371211767196655,
+      "learning_rate": 2.7416809718923825e-05,
+      "loss": 0.6996,
+      "step": 15128
+    },
+    {
+      "epoch": 0.22261137727848448,
+      "grad_norm": 1.1083990335464478,
+      "learning_rate": 2.7333207172706864e-05,
+      "loss": 0.6997,
+      "step": 15159
+    },
+    {
+      "epoch": 0.22306661526882904,
+      "grad_norm": 0.9845923781394958,
+      "learning_rate": 2.7249578296564088e-05,
+      "loss": 0.6959,
+      "step": 15190
+    },
+    {
+      "epoch": 0.2235218532591736,
+      "grad_norm": 1.0511544942855835,
+      "learning_rate": 2.7165924034235973e-05,
+      "loss": 0.6991,
+      "step": 15221
+    },
+    {
+      "epoch": 0.22397709124951815,
+      "grad_norm": 1.1612592935562134,
+      "learning_rate": 2.708224532974953e-05,
+      "loss": 0.7084,
+      "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 sha256:6ed4953cdca2d8af8ebc2792354258114b96f58b0e585a4d7d071d70469682cb
+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 sha256:1450d36ebf639728d4ae63c8d854ff4a4bacc994ac6b48e9cce764fa81ba8412
+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 sha256:610fcddb75306213b71341192b37a9fc08c82d180062b15d28da5e66bb74a02d
+size 4999813120

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:608161459288f02586d4a5a441869a3d2b2361b9176bfca3939ba2a6f5ec4065
+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 sha256:4530276151fa8995be29523ecc9b2929e1999044eebeeb7268fedc43b973f18d
+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 sha256:6ed4953cdca2d8af8ebc2792354258114b96f58b0e585a4d7d071d70469682cb
+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 sha256:7a489f9386a826ddfe794ca7200012554eacf465d02fbc314fdab5189e81db0b
+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:e2b1ab1eb579cc374bb82d128869fea1b6492ae1b3ed1a22cb06d795ec76c993
+size 4999813120

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55839618416fa79d515339abc67233093d042a764fecfed22a08a60f5e4db542
+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:ee04b691ff4330135db2eaec0dfe2c25bdaa9ba8227e2994388c5097c57de830
+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 sha256:6ed4953cdca2d8af8ebc2792354258114b96f58b0e585a4d7d071d70469682cb
+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:db40356199cad920448b44313b7f686606544c9648372ae9c8810278ac1d164d
+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