Upload folder using huggingface_hub

config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "float32",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.57.1"
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6ef41e7587f8703b20e86cf251c9f225225d9dddf9fea6dbad489fa456a521b
+size 4972454376

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea46cd552e359a76b9aeaf21e5e3e8d0f4957ea9339236fd22fea831539213c5
+size 4832048608

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20a74db482e44746d78fecd375aed8f27a02aefa9b06107ffa6ffc014bd1a0e9
+size 4832048656

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10444cd196b394a0a30207005a57f705a0e5707669e4b75e9363a01e933780df
+size 4999855528

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87962b56a0b572b02ef141a572182f7b51d0b84a6274dc9b84f583df98755da7
+size 4832048672

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92a8ad751c3d358df6fe676c4b93e524b27784b6e6cc1e4fd956c006b292ebec
+size 4832048672

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dba7f5b1a2f31902a91c5c6383dbde46fa7e58927c9c80026f51998e06a66a94
+size 3462482728

model.safetensors.index.json

@@ -0,0 +1,407 @@
+{
+  "metadata": {
+    "total_parameters": 1023841920,
+    "total_size": 32762941440
+  },
+  "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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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-00003-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00003-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_norm.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-00003-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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-00004-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00004-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_norm.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-00004-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-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_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-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_norm.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_norm.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_norm.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_norm.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-00005-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00005-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-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00005-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_norm.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-00005-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00005-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-00005-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_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-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_norm.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_norm.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_norm.weight": "model-00001-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_norm.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_norm.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_norm.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-00006-of-00007.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00006-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_norm.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.32.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00007-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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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-00002-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-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-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00002-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_norm.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-00002-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_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.norm.weight": "model-00007-of-00007.safetensors"
+  }
+}

optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9796d009ce04d1abf6deedf5ef0a943f4661fe571f5d4c24c0c9e45a84c44d6e
+size 65526147703

pytorch_model_fsdp.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d946becb2cde30a4b3f99254055b09f3e82654f7e1b453ebf08153da7e2e9eab
+size 32763139380

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:706722fc41436bdb24c4016ab83fbbb62526893d41d4cf49a009fdb7bb4abb5e
+size 16389

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cd3c5bfb3f44d6324570cdf01e259d25d57145e7c5bcf8a356f6f7b56afdf24
+size 16389

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ada3d67296c7e68b4d424298393788e9698d123c0f49e21ffd505f02a1def057
+size 16389

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6abe268928ee44107d52539186bb325f6915b9fe7dafd490b17c58d29bd50783
+size 16389

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdabaa1468bbe8afa177e64e4dd55a0b2c5ac41e68d229b3d790a6cdd8fbf6fb
+size 16389

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20c4cea43dfd62d3a3364a4603fb39a847fae2cd95a7b7d8f43fb21cef815cde
+size 16389

rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c22599770b4a3567bdcbd40583c1c29ca81866b4f2fb6dbcf94bafecdef10d2
+size 16389

rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12f20736861ad603467227a1c08b4d09fd872a184e0c54c650a3ac14d130dfcd
+size 16389

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17b083d8c7d923250576a6ee07e92d3f7df1fcff3b14ffa01414c3d40f48abfb
+size 1465

trainer_state.json

@@ -0,0 +1,287 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9959404600811907,
+  "eval_steps": 46,
+  "global_step": 184,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0,
+      "eval_loss": 0.24147284030914307,
+      "eval_runtime": 107.1778,
+      "eval_samples_per_second": 16.953,
+      "eval_steps_per_second": 1.064,
+      "memory/device_reserved (GiB)": 28.19,
+      "memory/max_active (GiB)": 26.63,
+      "memory/max_allocated (GiB)": 26.26,
+      "step": 0
+    },
+    {
+      "epoch": 0.05412719891745602,
+      "grad_norm": 8.363861083984375,
+      "learning_rate": 0.00018,
+      "loss": 0.1752,
+      "memory/device_reserved (GiB)": 64.91,
+      "memory/max_active (GiB)": 52.45,
+      "memory/max_allocated (GiB)": 51.78,
+      "step": 10,
+      "tokens_per_second_per_gpu": 310.38
+    },
+    {
+      "epoch": 0.10825439783491204,
+      "grad_norm": 0.4600403308868408,
+      "learning_rate": 0.00019868265225415265,
+      "loss": 0.1183,
+      "memory/device_reserved (GiB)": 64.91,
+      "memory/max_active (GiB)": 52.45,
+      "memory/max_allocated (GiB)": 51.78,
+      "step": 20,
+      "tokens_per_second_per_gpu": 156.97
+    },
+    {
+      "epoch": 0.16238159675236807,
+      "grad_norm": 12.768329620361328,
+      "learning_rate": 0.00019417339962465082,
+      "loss": 0.0726,
+      "memory/device_reserved (GiB)": 64.91,
+      "memory/max_active (GiB)": 52.45,
+      "memory/max_allocated (GiB)": 51.78,
+      "step": 30,
+      "tokens_per_second_per_gpu": 137.13
+    },
+    {
+      "epoch": 0.2165087956698241,
+      "grad_norm": 0.653432309627533,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 0.0615,
+      "memory/device_reserved (GiB)": 64.91,
+      "memory/max_active (GiB)": 52.45,
+      "memory/max_allocated (GiB)": 51.78,
+      "step": 40,
+      "tokens_per_second_per_gpu": 158.28
+    },
+    {
+      "epoch": 0.2489851150202977,
+      "eval_loss": 0.046831097453832626,
+      "eval_runtime": 96.7088,
+      "eval_samples_per_second": 18.788,
+      "eval_steps_per_second": 1.179,
+      "memory/device_reserved (GiB)": 64.91,
+      "memory/max_active (GiB)": 52.45,
+      "memory/max_allocated (GiB)": 51.78,
+      "step": 46
+    },
+    {
+      "epoch": 0.2706359945872801,
+      "grad_norm": 0.16088107228279114,
+      "learning_rate": 0.00017621620551276366,
+      "loss": 0.0481,
+      "memory/device_reserved (GiB)": 64.65,
+      "memory/max_active (GiB)": 52.45,
+      "memory/max_allocated (GiB)": 51.78,
+      "step": 50,
+      "tokens_per_second_per_gpu": 59.42
+    },
+    {
+      "epoch": 0.32476319350473615,
+      "grad_norm": 0.16584952175617218,
+      "learning_rate": 0.0001633520580160424,
+      "loss": 0.0435,
+      "memory/device_reserved (GiB)": 64.65,
+      "memory/max_active (GiB)": 52.45,
+      "memory/max_allocated (GiB)": 51.78,
+      "step": 60,
+      "tokens_per_second_per_gpu": 159.29
+    },
+    {
+      "epoch": 0.37889039242219213,
+      "grad_norm": 0.15581363439559937,
+      "learning_rate": 0.00014842831533876195,
+      "loss": 0.0433,
+      "memory/device_reserved (GiB)": 64.65,
+      "memory/max_active (GiB)": 52.45,
+      "memory/max_allocated (GiB)": 51.78,
+      "step": 70,
+      "tokens_per_second_per_gpu": 164.18
+    },
+    {
+      "epoch": 0.4330175913396482,
+      "grad_norm": 0.18023453652858734,
+      "learning_rate": 0.000131930153013598,
+      "loss": 0.0388,
+      "memory/device_reserved (GiB)": 64.65,
+      "memory/max_active (GiB)": 52.45,
+      "memory/max_allocated (GiB)": 51.78,
+      "step": 80,
+      "tokens_per_second_per_gpu": 158.27
+    },
+    {
+      "epoch": 0.4871447902571042,
+      "grad_norm": 0.11095931380987167,
+      "learning_rate": 0.0001143939314474119,
+      "loss": 0.037,
+      "memory/device_reserved (GiB)": 64.65,
+      "memory/max_active (GiB)": 52.45,
+      "memory/max_allocated (GiB)": 51.78,
+      "step": 90,
+      "tokens_per_second_per_gpu": 153.75
+    },
+    {
+      "epoch": 0.4979702300405954,
+      "eval_loss": 0.03402535617351532,
+      "eval_runtime": 96.2571,
+      "eval_samples_per_second": 18.877,
+      "eval_steps_per_second": 1.184,
+      "memory/device_reserved (GiB)": 64.65,
+      "memory/max_active (GiB)": 52.45,
+      "memory/max_allocated (GiB)": 51.78,
+      "step": 92
+    },
+    {
+      "epoch": 0.5412719891745602,
+      "grad_norm": 0.13690994679927826,
+      "learning_rate": 9.638975867700638e-05,
+      "loss": 0.0336,
+      "memory/device_reserved (GiB)": 64.65,
+      "memory/max_active (GiB)": 52.45,
+      "memory/max_allocated (GiB)": 51.78,
+      "step": 100,
+      "tokens_per_second_per_gpu": 115.36
+    },
+    {
+      "epoch": 0.5953991880920162,
+      "grad_norm": 0.13492451608181,
+      "learning_rate": 7.85029559788976e-05,
+      "loss": 0.033,
+      "memory/device_reserved (GiB)": 64.65,
+      "memory/max_active (GiB)": 52.45,
+      "memory/max_allocated (GiB)": 51.78,
+      "step": 110,
+      "tokens_per_second_per_gpu": 149.14
+    },
+    {
+      "epoch": 0.6495263870094723,
+      "grad_norm": 0.14664411544799805,
+      "learning_rate": 6.13150288919161e-05,
+      "loss": 0.0296,
+      "memory/device_reserved (GiB)": 64.65,
+      "memory/max_active (GiB)": 52.45,
+      "memory/max_allocated (GiB)": 51.78,
+      "step": 120,
+      "tokens_per_second_per_gpu": 165.73
+    },
+    {
+      "epoch": 0.7036535859269283,
+      "grad_norm": 0.11641104519367218,
+      "learning_rate": 4.53847622906303e-05,
+      "loss": 0.0264,
+      "memory/device_reserved (GiB)": 64.65,
+      "memory/max_active (GiB)": 52.45,
+      "memory/max_allocated (GiB)": 51.78,
+      "step": 130,
+      "tokens_per_second_per_gpu": 156.66
+    },
+    {
+      "epoch": 0.7469553450608931,
+      "eval_loss": 0.02498817630112171,
+      "eval_runtime": 96.7701,
+      "eval_samples_per_second": 18.776,
+      "eval_steps_per_second": 1.178,
+      "memory/device_reserved (GiB)": 64.65,
+      "memory/max_active (GiB)": 52.45,
+      "memory/max_allocated (GiB)": 51.78,
+      "step": 138
+    },
+    {
+      "epoch": 0.7577807848443843,
+      "grad_norm": 0.13313885033130646,
+      "learning_rate": 3.123005411465766e-05,
+      "loss": 0.0262,
+      "memory/device_reserved (GiB)": 64.65,
+      "memory/max_active (GiB)": 52.45,
+      "memory/max_allocated (GiB)": 51.78,
+      "step": 140,
+      "tokens_per_second_per_gpu": 33.06
+    },
+    {
+      "epoch": 0.8119079837618404,
+      "grad_norm": 0.10679510235786438,
+      "learning_rate": 1.931107834499296e-05,
+      "loss": 0.0259,
+      "memory/device_reserved (GiB)": 64.65,
+      "memory/max_active (GiB)": 52.45,
+      "memory/max_allocated (GiB)": 51.78,
+      "step": 150,
+      "tokens_per_second_per_gpu": 155.66
+    },
+    {
+      "epoch": 0.8660351826792964,
+      "grad_norm": 0.11161984503269196,
+      "learning_rate": 1.0015324604249343e-05,
+      "loss": 0.0236,
+      "memory/device_reserved (GiB)": 64.65,
+      "memory/max_active (GiB)": 52.45,
+      "memory/max_allocated (GiB)": 51.78,
+      "step": 160,
+      "tokens_per_second_per_gpu": 154.09
+    },
+    {
+      "epoch": 0.9201623815967523,
+      "grad_norm": 0.13931050896644592,
+      "learning_rate": 3.6450007480777093e-06,
+      "loss": 0.0247,
+      "memory/device_reserved (GiB)": 64.65,
+      "memory/max_active (GiB)": 52.45,
+      "memory/max_allocated (GiB)": 51.78,
+      "step": 170,
+      "tokens_per_second_per_gpu": 157.52
+    },
+    {
+      "epoch": 0.9742895805142084,
+      "grad_norm": 0.10726571083068848,
+      "learning_rate": 4.072079934495765e-07,
+      "loss": 0.0252,
+      "memory/device_reserved (GiB)": 64.65,
+      "memory/max_active (GiB)": 52.45,
+      "memory/max_allocated (GiB)": 51.78,
+      "step": 180,
+      "tokens_per_second_per_gpu": 154.03
+    },
+    {
+      "epoch": 0.9959404600811907,
+      "eval_loss": 0.022342145442962646,
+      "eval_runtime": 96.6201,
+      "eval_samples_per_second": 18.806,
+      "eval_steps_per_second": 1.18,
+      "memory/device_reserved (GiB)": 64.65,
+      "memory/max_active (GiB)": 52.45,
+      "memory/max_allocated (GiB)": 51.78,
+      "step": 184
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 184,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.926139739798241e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}