Upload folder using huggingface_hub

.gitattributes

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

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 10,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.0",
+  "unsloth_version": "2024.9",
+  "use_cache": false,
+  "vocab_size": 131072
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 1024000,
+  "pad_token_id": 10,
+  "transformers_version": "4.51.0"
+}

latest

@@ -0,0 +1 @@
+global_step294

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:586cc7d13a1b477a182836e8110d76fb88240697d4df99289addb689b2c93ce6
+size 4865522496

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72c3ed28bc71762404059386f37f59de1aa879113d336a1b83b49bd66dc04f8f
+size 4907529424

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0567f636bb370118367a48f392bf7437f8177e8a8b6861b6880b6ec614115b76
+size 4907529456

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5af47265dccbd48173cc7095260122fadc3ed6d5637f3322fb555744d9cce783
+size 4907529456

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b17e6e824de9951b17e99b8d1c4b87ecec44bddc6a5017ae3431cab552355d2f
+size 4907496272

model.safetensors.index.json

@@ -0,0 +1,370 @@
+{
+  "metadata": {
+    "total_size": 24495564800
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00005-of-00005.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.norm.weight": "model-00005-of-00005.safetensors"
+  }
+}

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e735ed11597ed40a2b6854e0229902e1a21fedc0a0dbc608ca905fae57d5b06b
+size 15984

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ba3815fc0953b1b7f08cea092dfc0a62c4bbc2a2c68780d3f4dd0b5e22582a7
+size 15984

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:647ac15563fcad903adbb616e9b2c36b237a3ed5939d088620212da969930f6c
+size 15984

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93e3733c5b180986b7efbec17b663bf5231343d187374d184768fcd913797167
+size 15984

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9820ea4fec1b01f3da091290c3e8b5ddb86a3a3fa17285c248b64910c2d0b4f0
+size 15984

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7413035def085e41776a629afc94fc24fe5a955f1ad83b32f9b370ab60f9a18d
+size 15984

rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91e3953bcbf4089415abffbd914fbbe4580121f6c843eabbf70624c5ed144814
+size 15984

rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:369fde7bff4dfc0d6b9cf773cf9b0352696083f84763999e05a631ee6d52c5e3
+size 15984

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:827fe785a5aaf8655c5af1fd25111d6fc8b47e8673ff93408ec1613e782550d2
+size 1064

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc07f4f61632a89d8248b43f25649d6cc45200f8709e9d9bcd0414b00a4064e2
+size 17078342

trainer_state.json

@@ -0,0 +1,2156 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 37,
+  "global_step": 294,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003401360544217687,
+      "grad_norm": 106.7094005171616,
+      "learning_rate": 0.0,
+      "loss": 2.9268,
+      "step": 1
+    },
+    {
+      "epoch": 0.003401360544217687,
+      "eval_loss": 2.5302913188934326,
+      "eval_runtime": 3.7953,
+      "eval_samples_per_second": 14.492,
+      "eval_steps_per_second": 1.054,
+      "step": 1
+    },
+    {
+      "epoch": 0.006802721088435374,
+      "grad_norm": 57.97506009705182,
+      "learning_rate": 6.89655172413793e-08,
+      "loss": 2.0122,
+      "step": 2
+    },
+    {
+      "epoch": 0.01020408163265306,
+      "grad_norm": 116.23413141145363,
+      "learning_rate": 1.379310344827586e-07,
+      "loss": 2.6743,
+      "step": 3
+    },
+    {
+      "epoch": 0.013605442176870748,
+      "grad_norm": 21.262801374024775,
+      "learning_rate": 2.0689655172413793e-07,
+      "loss": 2.0743,
+      "step": 4
+    },
+    {
+      "epoch": 0.017006802721088437,
+      "grad_norm": 59.319984755304056,
+      "learning_rate": 2.758620689655172e-07,
+      "loss": 2.2775,
+      "step": 5
+    },
+    {
+      "epoch": 0.02040816326530612,
+      "grad_norm": 159.51320885432614,
+      "learning_rate": 3.4482758620689656e-07,
+      "loss": 2.1337,
+      "step": 6
+    },
+    {
+      "epoch": 0.023809523809523808,
+      "grad_norm": 87.93970940325055,
+      "learning_rate": 4.1379310344827586e-07,
+      "loss": 1.9061,
+      "step": 7
+    },
+    {
+      "epoch": 0.027210884353741496,
+      "grad_norm": 61.133777808660895,
+      "learning_rate": 4.827586206896552e-07,
+      "loss": 1.8118,
+      "step": 8
+    },
+    {
+      "epoch": 0.030612244897959183,
+      "grad_norm": 48.65887299035499,
+      "learning_rate": 5.517241379310344e-07,
+      "loss": 3.4095,
+      "step": 9
+    },
+    {
+      "epoch": 0.034013605442176874,
+      "grad_norm": 30.592687909719288,
+      "learning_rate": 6.206896551724138e-07,
+      "loss": 2.2398,
+      "step": 10
+    },
+    {
+      "epoch": 0.03741496598639456,
+      "grad_norm": 74.15295766799099,
+      "learning_rate": 6.896551724137931e-07,
+      "loss": 3.4425,
+      "step": 11
+    },
+    {
+      "epoch": 0.04081632653061224,
+      "grad_norm": 34.94892634385338,
+      "learning_rate": 7.586206896551724e-07,
+      "loss": 2.5405,
+      "step": 12
+    },
+    {
+      "epoch": 0.04421768707482993,
+      "grad_norm": 26.538521745061775,
+      "learning_rate": 8.275862068965517e-07,
+      "loss": 1.9614,
+      "step": 13
+    },
+    {
+      "epoch": 0.047619047619047616,
+      "grad_norm": 52.23979896259082,
+      "learning_rate": 8.96551724137931e-07,
+      "loss": 2.9785,
+      "step": 14
+    },
+    {
+      "epoch": 0.05102040816326531,
+      "grad_norm": 30.812143999051266,
+      "learning_rate": 9.655172413793103e-07,
+      "loss": 2.0185,
+      "step": 15
+    },
+    {
+      "epoch": 0.05442176870748299,
+      "grad_norm": 41.48478088374125,
+      "learning_rate": 1.0344827586206896e-06,
+      "loss": 2.1126,
+      "step": 16
+    },
+    {
+      "epoch": 0.05782312925170068,
+      "grad_norm": 29.347588210089675,
+      "learning_rate": 1.1034482758620688e-06,
+      "loss": 2.2078,
+      "step": 17
+    },
+    {
+      "epoch": 0.061224489795918366,
+      "grad_norm": 28.947554594850924,
+      "learning_rate": 1.172413793103448e-06,
+      "loss": 2.442,
+      "step": 18
+    },
+    {
+      "epoch": 0.06462585034013606,
+      "grad_norm": 32.28592513881342,
+      "learning_rate": 1.2413793103448275e-06,
+      "loss": 2.8683,
+      "step": 19
+    },
+    {
+      "epoch": 0.06802721088435375,
+      "grad_norm": 38.97631997775744,
+      "learning_rate": 1.3103448275862068e-06,
+      "loss": 2.4376,
+      "step": 20
+    },
+    {
+      "epoch": 0.07142857142857142,
+      "grad_norm": 43.775478156068516,
+      "learning_rate": 1.3793103448275862e-06,
+      "loss": 2.4167,
+      "step": 21
+    },
+    {
+      "epoch": 0.07482993197278912,
+      "grad_norm": 30.904260805899465,
+      "learning_rate": 1.4482758620689655e-06,
+      "loss": 2.6971,
+      "step": 22
+    },
+    {
+      "epoch": 0.0782312925170068,
+      "grad_norm": 48.202871069183985,
+      "learning_rate": 1.5172413793103447e-06,
+      "loss": 2.5093,
+      "step": 23
+    },
+    {
+      "epoch": 0.08163265306122448,
+      "grad_norm": 55.067186300198706,
+      "learning_rate": 1.5862068965517242e-06,
+      "loss": 2.0053,
+      "step": 24
+    },
+    {
+      "epoch": 0.08503401360544217,
+      "grad_norm": 38.486811757681096,
+      "learning_rate": 1.6551724137931035e-06,
+      "loss": 2.2475,
+      "step": 25
+    },
+    {
+      "epoch": 0.08843537414965986,
+      "grad_norm": 90.78568630900098,
+      "learning_rate": 1.7241379310344825e-06,
+      "loss": 3.8342,
+      "step": 26
+    },
+    {
+      "epoch": 0.09183673469387756,
+      "grad_norm": 23.32050516158788,
+      "learning_rate": 1.793103448275862e-06,
+      "loss": 2.2496,
+      "step": 27
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 25.01047005218693,
+      "learning_rate": 1.8620689655172412e-06,
+      "loss": 2.6991,
+      "step": 28
+    },
+    {
+      "epoch": 0.09863945578231292,
+      "grad_norm": 27.40209208002175,
+      "learning_rate": 1.9310344827586207e-06,
+      "loss": 2.7017,
+      "step": 29
+    },
+    {
+      "epoch": 0.10204081632653061,
+      "grad_norm": 16.372774250078056,
+      "learning_rate": 2e-06,
+      "loss": 2.1315,
+      "step": 30
+    },
+    {
+      "epoch": 0.1054421768707483,
+      "grad_norm": 34.32100924763162,
+      "learning_rate": 1.999984207714351e-06,
+      "loss": 2.4298,
+      "step": 31
+    },
+    {
+      "epoch": 0.10884353741496598,
+      "grad_norm": 49.15042168439896,
+      "learning_rate": 1.9999368313561964e-06,
+      "loss": 3.1687,
+      "step": 32
+    },
+    {
+      "epoch": 0.11224489795918367,
+      "grad_norm": 27.553221322487154,
+      "learning_rate": 1.9998578724218984e-06,
+      "loss": 2.307,
+      "step": 33
+    },
+    {
+      "epoch": 0.11564625850340136,
+      "grad_norm": 25.29898708562965,
+      "learning_rate": 1.999747333405341e-06,
+      "loss": 2.6711,
+      "step": 34
+    },
+    {
+      "epoch": 0.11904761904761904,
+      "grad_norm": 35.13639034121329,
+      "learning_rate": 1.9996052177978517e-06,
+      "loss": 2.2923,
+      "step": 35
+    },
+    {
+      "epoch": 0.12244897959183673,
+      "grad_norm": 61.904951168823246,
+      "learning_rate": 1.999431530088091e-06,
+      "loss": 3.0837,
+      "step": 36
+    },
+    {
+      "epoch": 0.12585034013605442,
+      "grad_norm": 43.72931173152359,
+      "learning_rate": 1.9992262757619108e-06,
+      "loss": 2.9055,
+      "step": 37
+    },
+    {
+      "epoch": 0.12585034013605442,
+      "eval_loss": 2.2881884574890137,
+      "eval_runtime": 3.7387,
+      "eval_samples_per_second": 14.711,
+      "eval_steps_per_second": 1.07,
+      "step": 37
+    },
+    {
+      "epoch": 0.1292517006802721,
+      "grad_norm": 75.128224809043,
+      "learning_rate": 1.9989894613021807e-06,
+      "loss": 3.9717,
+      "step": 38
+    },
+    {
+      "epoch": 0.1326530612244898,
+      "grad_norm": 6.423556290490496,
+      "learning_rate": 1.998721094188584e-06,
+      "loss": 1.6634,
+      "step": 39
+    },
+    {
+      "epoch": 0.1360544217687075,
+      "grad_norm": 8.952452652609857,
+      "learning_rate": 1.9984211828973816e-06,
+      "loss": 2.1183,
+      "step": 40
+    },
+    {
+      "epoch": 0.13945578231292516,
+      "grad_norm": 12.837161899787583,
+      "learning_rate": 1.998089736901142e-06,
+      "loss": 2.1306,
+      "step": 41
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 7.2779063942957825,
+      "learning_rate": 1.9977267666684456e-06,
+      "loss": 1.9831,
+      "step": 42
+    },
+    {
+      "epoch": 0.14625850340136054,
+      "grad_norm": 30.288569770228293,
+      "learning_rate": 1.9973322836635515e-06,
+      "loss": 2.1869,
+      "step": 43
+    },
+    {
+      "epoch": 0.14965986394557823,
+      "grad_norm": 11.672608976353168,
+      "learning_rate": 1.996906300346036e-06,
+      "loss": 1.9566,
+      "step": 44
+    },
+    {
+      "epoch": 0.15306122448979592,
+      "grad_norm": 14.837719065187358,
+      "learning_rate": 1.9964488301704e-06,
+      "loss": 2.2152,
+      "step": 45
+    },
+    {
+      "epoch": 0.1564625850340136,
+      "grad_norm": 18.558600033713702,
+      "learning_rate": 1.9959598875856427e-06,
+      "loss": 2.06,
+      "step": 46
+    },
+    {
+      "epoch": 0.1598639455782313,
+      "grad_norm": 17.161073648503006,
+      "learning_rate": 1.995439488034806e-06,
+      "loss": 2.0463,
+      "step": 47
+    },
+    {
+      "epoch": 0.16326530612244897,
+      "grad_norm": 10.944090642041195,
+      "learning_rate": 1.994887647954486e-06,
+      "loss": 1.9676,
+      "step": 48
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 30.260773919516463,
+      "learning_rate": 1.9943043847743164e-06,
+      "loss": 2.4235,
+      "step": 49
+    },
+    {
+      "epoch": 0.17006802721088435,
+      "grad_norm": 17.95874457178673,
+      "learning_rate": 1.9936897169164135e-06,
+      "loss": 2.4211,
+      "step": 50
+    },
+    {
+      "epoch": 0.17346938775510204,
+      "grad_norm": 29.32804844947439,
+      "learning_rate": 1.993043663794799e-06,
+      "loss": 2.2786,
+      "step": 51
+    },
+    {
+      "epoch": 0.17687074829931973,
+      "grad_norm": 31.224760731119037,
+      "learning_rate": 1.9923662458147826e-06,
+      "loss": 2.8374,
+      "step": 52
+    },
+    {
+      "epoch": 0.18027210884353742,
+      "grad_norm": 4.5045539325043205,
+      "learning_rate": 1.9916574843723217e-06,
+      "loss": 1.6301,
+      "step": 53
+    },
+    {
+      "epoch": 0.1836734693877551,
+      "grad_norm": 10.827050277516674,
+      "learning_rate": 1.9909174018533427e-06,
+      "loss": 2.0554,
+      "step": 54
+    },
+    {
+      "epoch": 0.1870748299319728,
+      "grad_norm": 17.063187262605883,
+      "learning_rate": 1.990146021633034e-06,
+      "loss": 2.4202,
+      "step": 55
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 3.946679947433292,
+      "learning_rate": 1.98934336807511e-06,
+      "loss": 1.7808,
+      "step": 56
+    },
+    {
+      "epoch": 0.19387755102040816,
+      "grad_norm": 8.431222224384186,
+      "learning_rate": 1.9885094665310388e-06,
+      "loss": 1.7766,
+      "step": 57
+    },
+    {
+      "epoch": 0.19727891156462585,
+      "grad_norm": 32.28667139462841,
+      "learning_rate": 1.9876443433392433e-06,
+      "loss": 2.2299,
+      "step": 58
+    },
+    {
+      "epoch": 0.20068027210884354,
+      "grad_norm": 11.950555724182584,
+      "learning_rate": 1.986748025824268e-06,
+      "loss": 1.928,
+      "step": 59
+    },
+    {
+      "epoch": 0.20408163265306123,
+      "grad_norm": 3.6059136679066977,
+      "learning_rate": 1.985820542295918e-06,
+      "loss": 1.7761,
+      "step": 60
+    },
+    {
+      "epoch": 0.20748299319727892,
+      "grad_norm": 41.40947345983446,
+      "learning_rate": 1.984861922048363e-06,
+      "loss": 2.6704,
+      "step": 61
+    },
+    {
+      "epoch": 0.2108843537414966,
+      "grad_norm": 30.634237938465816,
+      "learning_rate": 1.983872195359212e-06,
+      "loss": 2.7336,
+      "step": 62
+    },
+    {
+      "epoch": 0.21428571428571427,
+      "grad_norm": 3.760013022701194,
+      "learning_rate": 1.9828513934885587e-06,
+      "loss": 1.8831,
+      "step": 63
+    },
+    {
+      "epoch": 0.21768707482993196,
+      "grad_norm": 37.34059674722221,
+      "learning_rate": 1.981799548677993e-06,
+      "loss": 2.27,
+      "step": 64
+    },
+    {
+      "epoch": 0.22108843537414966,
+      "grad_norm": 11.009700618421736,
+      "learning_rate": 1.980716694149581e-06,
+      "loss": 1.9265,
+      "step": 65
+    },
+    {
+      "epoch": 0.22448979591836735,
+      "grad_norm": 17.609147027884987,
+      "learning_rate": 1.9796028641048194e-06,
+      "loss": 2.3411,
+      "step": 66
+    },
+    {
+      "epoch": 0.22789115646258504,
+      "grad_norm": 17.432142291951372,
+      "learning_rate": 1.978458093723553e-06,
+      "loss": 2.2213,
+      "step": 67
+    },
+    {
+      "epoch": 0.23129251700680273,
+      "grad_norm": 14.11664326231067,
+      "learning_rate": 1.9772824191628632e-06,
+      "loss": 2.0831,
+      "step": 68
+    },
+    {
+      "epoch": 0.23469387755102042,
+      "grad_norm": 37.456025944063875,
+      "learning_rate": 1.9760758775559273e-06,
+      "loss": 2.7494,
+      "step": 69
+    },
+    {
+      "epoch": 0.23809523809523808,
+      "grad_norm": 16.30994509129653,
+      "learning_rate": 1.974838507010844e-06,
+      "loss": 2.118,
+      "step": 70
+    },
+    {
+      "epoch": 0.24149659863945577,
+      "grad_norm": 25.92468917111241,
+      "learning_rate": 1.9735703466094324e-06,
+      "loss": 2.1656,
+      "step": 71
+    },
+    {
+      "epoch": 0.24489795918367346,
+      "grad_norm": 17.23253832018251,
+      "learning_rate": 1.972271436405994e-06,
+      "loss": 2.0787,
+      "step": 72
+    },
+    {
+      "epoch": 0.24829931972789115,
+      "grad_norm": 6.286286593272188,
+      "learning_rate": 1.970941817426052e-06,
+      "loss": 1.7458,
+      "step": 73
+    },
+    {
+      "epoch": 0.25170068027210885,
+      "grad_norm": 20.87004487229478,
+      "learning_rate": 1.969581531665051e-06,
+      "loss": 2.364,
+      "step": 74
+    },
+    {
+      "epoch": 0.25170068027210885,
+      "eval_loss": 2.240875482559204,
+      "eval_runtime": 3.7328,
+      "eval_samples_per_second": 14.734,
+      "eval_steps_per_second": 1.072,
+      "step": 74
+    },
+    {
+      "epoch": 0.25510204081632654,
+      "grad_norm": 22.83815781491435,
+      "learning_rate": 1.968190622087034e-06,
+      "loss": 2.2176,
+      "step": 75
+    },
+    {
+      "epoch": 0.2585034013605442,
+      "grad_norm": 39.2204163613504,
+      "learning_rate": 1.9667691326232835e-06,
+      "loss": 2.605,
+      "step": 76
+    },
+    {
+      "epoch": 0.2619047619047619,
+      "grad_norm": 9.599486970591897,
+      "learning_rate": 1.965317108170935e-06,
+      "loss": 2.1652,
+      "step": 77
+    },
+    {
+      "epoch": 0.2653061224489796,
+      "grad_norm": 3.7571781853463175,
+      "learning_rate": 1.9638345945915586e-06,
+      "loss": 1.6055,
+      "step": 78
+    },
+    {
+      "epoch": 0.2687074829931973,
+      "grad_norm": 7.064670527473922,
+      "learning_rate": 1.962321638709709e-06,
+      "loss": 1.9937,
+      "step": 79
+    },
+    {
+      "epoch": 0.272108843537415,
+      "grad_norm": 28.207901160479654,
+      "learning_rate": 1.9607782883114506e-06,
+      "loss": 2.2552,
+      "step": 80
+    },
+    {
+      "epoch": 0.2755102040816326,
+      "grad_norm": 15.991872570963396,
+      "learning_rate": 1.959204592142843e-06,
+      "loss": 2.1559,
+      "step": 81
+    },
+    {
+      "epoch": 0.2789115646258503,
+      "grad_norm": 13.401822104278665,
+      "learning_rate": 1.957600599908406e-06,
+      "loss": 2.1652,
+      "step": 82
+    },
+    {
+      "epoch": 0.282312925170068,
+      "grad_norm": 14.708704691038701,
+      "learning_rate": 1.9559663622695455e-06,
+      "loss": 1.9673,
+      "step": 83
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 3.3458550475032105,
+      "learning_rate": 1.954301930842958e-06,
+      "loss": 1.6917,
+      "step": 84
+    },
+    {
+      "epoch": 0.2891156462585034,
+      "grad_norm": 3.479853146114766,
+      "learning_rate": 1.9526073581989955e-06,
+      "loss": 1.624,
+      "step": 85
+    },
+    {
+      "epoch": 0.2925170068027211,
+      "grad_norm": 25.10854427551898,
+      "learning_rate": 1.950882697860009e-06,
+      "loss": 2.3626,
+      "step": 86
+    },
+    {
+      "epoch": 0.29591836734693877,
+      "grad_norm": 14.389114459997433,
+      "learning_rate": 1.9491280042986562e-06,
+      "loss": 2.0549,
+      "step": 87
+    },
+    {
+      "epoch": 0.29931972789115646,
+      "grad_norm": 17.72897272235088,
+      "learning_rate": 1.9473433329361802e-06,
+      "loss": 2.4525,
+      "step": 88
+    },
+    {
+      "epoch": 0.30272108843537415,
+      "grad_norm": 8.212788560084723,
+      "learning_rate": 1.945528740140662e-06,
+      "loss": 2.1368,
+      "step": 89
+    },
+    {
+      "epoch": 0.30612244897959184,
+      "grad_norm": 26.76274867022125,
+      "learning_rate": 1.943684283225236e-06,
+      "loss": 2.3735,
+      "step": 90
+    },
+    {
+      "epoch": 0.30952380952380953,
+      "grad_norm": 23.71630229663243,
+      "learning_rate": 1.941810020446284e-06,
+      "loss": 2.6005,
+      "step": 91
+    },
+    {
+      "epoch": 0.3129251700680272,
+      "grad_norm": 22.889738702248234,
+      "learning_rate": 1.9399060110015917e-06,
+      "loss": 2.6924,
+      "step": 92
+    },
+    {
+      "epoch": 0.3163265306122449,
+      "grad_norm": 32.54631787971477,
+      "learning_rate": 1.9379723150284814e-06,
+      "loss": 2.5301,
+      "step": 93
+    },
+    {
+      "epoch": 0.3197278911564626,
+      "grad_norm": 3.6877224549117344,
+      "learning_rate": 1.936008993601912e-06,
+      "loss": 1.6556,
+      "step": 94
+    },
+    {
+      "epoch": 0.3231292517006803,
+      "grad_norm": 33.682920637388364,
+      "learning_rate": 1.934016108732548e-06,
+      "loss": 2.3709,
+      "step": 95
+    },
+    {
+      "epoch": 0.32653061224489793,
+      "grad_norm": 19.342157148675135,
+      "learning_rate": 1.9319937233648045e-06,
+      "loss": 1.8713,
+      "step": 96
+    },
+    {
+      "epoch": 0.3299319727891156,
+      "grad_norm": 36.9446891807536,
+      "learning_rate": 1.929941901374856e-06,
+      "loss": 3.1666,
+      "step": 97
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 12.769242612326224,
+      "learning_rate": 1.9278607075686205e-06,
+      "loss": 2.2024,
+      "step": 98
+    },
+    {
+      "epoch": 0.336734693877551,
+      "grad_norm": 7.569149644914372,
+      "learning_rate": 1.9257502076797123e-06,
+      "loss": 1.8434,
+      "step": 99
+    },
+    {
+      "epoch": 0.3401360544217687,
+      "grad_norm": 18.672166864254265,
+      "learning_rate": 1.9236104683673653e-06,
+      "loss": 2.6262,
+      "step": 100
+    },
+    {
+      "epoch": 0.3435374149659864,
+      "grad_norm": 7.251393661314555,
+      "learning_rate": 1.9214415572143284e-06,
+      "loss": 1.8447,
+      "step": 101
+    },
+    {
+      "epoch": 0.3469387755102041,
+      "grad_norm": 25.8588617341962,
+      "learning_rate": 1.919243542724731e-06,
+      "loss": 2.3528,
+      "step": 102
+    },
+    {
+      "epoch": 0.35034013605442177,
+      "grad_norm": 21.00339285362203,
+      "learning_rate": 1.917016494321918e-06,
+      "loss": 2.462,
+      "step": 103
+    },
+    {
+      "epoch": 0.35374149659863946,
+      "grad_norm": 19.533037226832878,
+      "learning_rate": 1.9147604823462585e-06,
+      "loss": 2.3057,
+      "step": 104
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "grad_norm": 3.1087327492999286,
+      "learning_rate": 1.9124755780529243e-06,
+      "loss": 1.6935,
+      "step": 105
+    },
+    {
+      "epoch": 0.36054421768707484,
+      "grad_norm": 35.707396347148176,
+      "learning_rate": 1.910161853609637e-06,
+      "loss": 2.3652,
+      "step": 106
+    },
+    {
+      "epoch": 0.36394557823129253,
+      "grad_norm": 16.694934440145225,
+      "learning_rate": 1.9078193820943916e-06,
+      "loss": 2.6014,
+      "step": 107
+    },
+    {
+      "epoch": 0.3673469387755102,
+      "grad_norm": 12.946146725042743,
+      "learning_rate": 1.9054482374931466e-06,
+      "loss": 1.9379,
+      "step": 108
+    },
+    {
+      "epoch": 0.3707482993197279,
+      "grad_norm": 8.740650008889842,
+      "learning_rate": 1.9030484946974878e-06,
+      "loss": 1.9414,
+      "step": 109
+    },
+    {
+      "epoch": 0.3741496598639456,
+      "grad_norm": 23.13581690576701,
+      "learning_rate": 1.9006202295022629e-06,
+      "loss": 2.4563,
+      "step": 110
+    },
+    {
+      "epoch": 0.37755102040816324,
+      "grad_norm": 10.00026809536462,
+      "learning_rate": 1.8981635186031869e-06,
+      "loss": 1.8384,
+      "step": 111
+    },
+    {
+      "epoch": 0.37755102040816324,
+      "eval_loss": 2.2185332775115967,
+      "eval_runtime": 3.7603,
+      "eval_samples_per_second": 14.626,
+      "eval_steps_per_second": 1.064,
+      "step": 111
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 26.376801704138895,
+      "learning_rate": 1.89567843959442e-06,
+      "loss": 3.095,
+      "step": 112
+    },
+    {
+      "epoch": 0.3843537414965986,
+      "grad_norm": 31.801160647661863,
+      "learning_rate": 1.8931650709661176e-06,
+      "loss": 2.4186,
+      "step": 113
+    },
+    {
+      "epoch": 0.3877551020408163,
+      "grad_norm": 3.7202396333724406,
+      "learning_rate": 1.8906234921019504e-06,
+      "loss": 1.8483,
+      "step": 114
+    },
+    {
+      "epoch": 0.391156462585034,
+      "grad_norm": 20.22060079238643,
+      "learning_rate": 1.8880537832765975e-06,
+      "loss": 2.1247,
+      "step": 115
+    },
+    {
+      "epoch": 0.3945578231292517,
+      "grad_norm": 29.233218070907714,
+      "learning_rate": 1.8854560256532098e-06,
+      "loss": 2.3962,
+      "step": 116
+    },
+    {
+      "epoch": 0.3979591836734694,
+      "grad_norm": 12.311196195760077,
+      "learning_rate": 1.882830301280849e-06,
+      "loss": 1.9291,
+      "step": 117
+    },
+    {
+      "epoch": 0.4013605442176871,
+      "grad_norm": 24.022251844658836,
+      "learning_rate": 1.880176693091893e-06,
+      "loss": 2.0967,
+      "step": 118
+    },
+    {
+      "epoch": 0.40476190476190477,
+      "grad_norm": 15.5145598820515,
+      "learning_rate": 1.8774952848994193e-06,
+      "loss": 2.0164,
+      "step": 119
+    },
+    {
+      "epoch": 0.40816326530612246,
+      "grad_norm": 18.669552144287866,
+      "learning_rate": 1.874786161394556e-06,
+      "loss": 1.9074,
+      "step": 120
+    },
+    {
+      "epoch": 0.41156462585034015,
+      "grad_norm": 20.221669243742017,
+      "learning_rate": 1.8720494081438077e-06,
+      "loss": 2.0693,
+      "step": 121
+    },
+    {
+      "epoch": 0.41496598639455784,
+      "grad_norm": 40.16853982486705,
+      "learning_rate": 1.8692851115863521e-06,
+      "loss": 2.7133,
+      "step": 122
+    },
+    {
+      "epoch": 0.41836734693877553,
+      "grad_norm": 28.130765299643805,
+      "learning_rate": 1.8664933590313116e-06,
+      "loss": 2.3678,
+      "step": 123
+    },
+    {
+      "epoch": 0.4217687074829932,
+      "grad_norm": 3.285521259165442,
+      "learning_rate": 1.8636742386549936e-06,
+      "loss": 1.643,
+      "step": 124
+    },
+    {
+      "epoch": 0.42517006802721086,
+      "grad_norm": 14.918765530830019,
+      "learning_rate": 1.8608278394981065e-06,
+      "loss": 2.2832,
+      "step": 125
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 3.221047286582191,
+      "learning_rate": 1.8579542514629471e-06,
+      "loss": 1.7598,
+      "step": 126
+    },
+    {
+      "epoch": 0.43197278911564624,
+      "grad_norm": 30.02563146393063,
+      "learning_rate": 1.8550535653105621e-06,
+      "loss": 2.2684,
+      "step": 127
+    },
+    {
+      "epoch": 0.43537414965986393,
+      "grad_norm": 14.894051195947721,
+      "learning_rate": 1.8521258726578802e-06,
+      "loss": 2.2898,
+      "step": 128
+    },
+    {
+      "epoch": 0.4387755102040816,
+      "grad_norm": 31.346174242632404,
+      "learning_rate": 1.849171265974818e-06,
+      "loss": 2.4443,
+      "step": 129
+    },
+    {
+      "epoch": 0.4421768707482993,
+      "grad_norm": 18.396976082720574,
+      "learning_rate": 1.846189838581362e-06,
+      "loss": 2.4081,
+      "step": 130
+    },
+    {
+      "epoch": 0.445578231292517,
+      "grad_norm": 11.300098238275778,
+      "learning_rate": 1.843181684644617e-06,
+      "loss": 1.9707,
+      "step": 131
+    },
+    {
+      "epoch": 0.4489795918367347,
+      "grad_norm": 9.311622064720812,
+      "learning_rate": 1.8401468991758364e-06,
+      "loss": 2.0055,
+      "step": 132
+    },
+    {
+      "epoch": 0.4523809523809524,
+      "grad_norm": 17.268118260619143,
+      "learning_rate": 1.837085578027418e-06,
+      "loss": 2.1029,
+      "step": 133
+    },
+    {
+      "epoch": 0.4557823129251701,
+      "grad_norm": 13.534018757700077,
+      "learning_rate": 1.833997817889878e-06,
+      "loss": 1.6714,
+      "step": 134
+    },
+    {
+      "epoch": 0.45918367346938777,
+      "grad_norm": 25.67291091851184,
+      "learning_rate": 1.8308837162887962e-06,
+      "loss": 2.0809,
+      "step": 135
+    },
+    {
+      "epoch": 0.46258503401360546,
+      "grad_norm": 16.78554391811326,
+      "learning_rate": 1.827743371581737e-06,
+      "loss": 2.095,
+      "step": 136
+    },
+    {
+      "epoch": 0.46598639455782315,
+      "grad_norm": 7.0895304724541175,
+      "learning_rate": 1.8245768829551415e-06,
+      "loss": 2.0924,
+      "step": 137
+    },
+    {
+      "epoch": 0.46938775510204084,
+      "grad_norm": 28.325113542255774,
+      "learning_rate": 1.8213843504211956e-06,
+      "loss": 2.2312,
+      "step": 138
+    },
+    {
+      "epoch": 0.47278911564625853,
+      "grad_norm": 19.627621449351967,
+      "learning_rate": 1.8181658748146709e-06,
+      "loss": 2.1092,
+      "step": 139
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 3.253642214201976,
+      "learning_rate": 1.8149215577897394e-06,
+      "loss": 1.8119,
+      "step": 140
+    },
+    {
+      "epoch": 0.47959183673469385,
+      "grad_norm": 22.194249754011054,
+      "learning_rate": 1.8116515018167635e-06,
+      "loss": 1.8086,
+      "step": 141
+    },
+    {
+      "epoch": 0.48299319727891155,
+      "grad_norm": 3.291628206622755,
+      "learning_rate": 1.8083558101790595e-06,
+      "loss": 1.6961,
+      "step": 142
+    },
+    {
+      "epoch": 0.48639455782312924,
+      "grad_norm": 30.333797331495706,
+      "learning_rate": 1.8050345869696346e-06,
+      "loss": 2.4649,
+      "step": 143
+    },
+    {
+      "epoch": 0.4897959183673469,
+      "grad_norm": 35.46381155966904,
+      "learning_rate": 1.8016879370879004e-06,
+      "loss": 2.375,
+      "step": 144
+    },
+    {
+      "epoch": 0.4931972789115646,
+      "grad_norm": 10.065027530577671,
+      "learning_rate": 1.798315966236358e-06,
+      "loss": 1.7088,
+      "step": 145
+    },
+    {
+      "epoch": 0.4965986394557823,
+      "grad_norm": 31.969238069641904,
+      "learning_rate": 1.794918780917262e-06,
+      "loss": 2.2722,
+      "step": 146
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.1706943713916287,
+      "learning_rate": 1.791496488429254e-06,
+      "loss": 1.5129,
+      "step": 147
+    },
+    {
+      "epoch": 0.5034013605442177,
+      "grad_norm": 40.129409477941664,
+      "learning_rate": 1.7880491968639751e-06,
+      "loss": 2.8429,
+      "step": 148
+    },
+    {
+      "epoch": 0.5034013605442177,
+      "eval_loss": 2.2053215503692627,
+      "eval_runtime": 3.8702,
+      "eval_samples_per_second": 14.211,
+      "eval_steps_per_second": 1.034,
+      "step": 148
+    },
+    {
+      "epoch": 0.5068027210884354,
+      "grad_norm": 26.985890370710862,
+      "learning_rate": 1.7845770151026513e-06,
+      "loss": 2.3221,
+      "step": 149
+    },
+    {
+      "epoch": 0.5102040816326531,
+      "grad_norm": 34.746114296368646,
+      "learning_rate": 1.7810800528126553e-06,
+      "loss": 2.3499,
+      "step": 150
+    },
+    {
+      "epoch": 0.5136054421768708,
+      "grad_norm": 3.902076154967714,
+      "learning_rate": 1.7775584204440416e-06,
+      "loss": 1.7411,
+      "step": 151
+    },
+    {
+      "epoch": 0.5170068027210885,
+      "grad_norm": 27.80193827038684,
+      "learning_rate": 1.7740122292260594e-06,
+      "loss": 2.2895,
+      "step": 152
+    },
+    {
+      "epoch": 0.5204081632653061,
+      "grad_norm": 3.4114906810600685,
+      "learning_rate": 1.7704415911636375e-06,
+      "loss": 1.5119,
+      "step": 153
+    },
+    {
+      "epoch": 0.5238095238095238,
+      "grad_norm": 9.505522369554297,
+      "learning_rate": 1.7668466190338483e-06,
+      "loss": 1.844,
+      "step": 154
+    },
+    {
+      "epoch": 0.5272108843537415,
+      "grad_norm": 36.46998151934392,
+      "learning_rate": 1.7632274263823457e-06,
+      "loss": 2.4713,
+      "step": 155
+    },
+    {
+      "epoch": 0.5306122448979592,
+      "grad_norm": 17.765108257489125,
+      "learning_rate": 1.759584127519778e-06,
+      "loss": 2.2811,
+      "step": 156
+    },
+    {
+      "epoch": 0.5340136054421769,
+      "grad_norm": 14.148223114236801,
+      "learning_rate": 1.7559168375181775e-06,
+      "loss": 1.8442,
+      "step": 157
+    },
+    {
+      "epoch": 0.5374149659863946,
+      "grad_norm": 9.76402372234183,
+      "learning_rate": 1.7522256722073273e-06,
+      "loss": 1.8945,
+      "step": 158
+    },
+    {
+      "epoch": 0.5408163265306123,
+      "grad_norm": 16.450896799860217,
+      "learning_rate": 1.748510748171101e-06,
+      "loss": 1.9574,
+      "step": 159
+    },
+    {
+      "epoch": 0.54421768707483,
+      "grad_norm": 3.912613042056259,
+      "learning_rate": 1.7447721827437819e-06,
+      "loss": 1.6032,
+      "step": 160
+    },
+    {
+      "epoch": 0.5476190476190477,
+      "grad_norm": 33.305605159021646,
+      "learning_rate": 1.7410100940063558e-06,
+      "loss": 2.4057,
+      "step": 161
+    },
+    {
+      "epoch": 0.5510204081632653,
+      "grad_norm": 38.319973023280475,
+      "learning_rate": 1.7372246007827833e-06,
+      "loss": 2.5925,
+      "step": 162
+    },
+    {
+      "epoch": 0.5544217687074829,
+      "grad_norm": 17.216523524482163,
+      "learning_rate": 1.7334158226362446e-06,
+      "loss": 2.0324,
+      "step": 163
+    },
+    {
+      "epoch": 0.5578231292517006,
+      "grad_norm": 4.9862323362748535,
+      "learning_rate": 1.7295838798653649e-06,
+      "loss": 1.7436,
+      "step": 164
+    },
+    {
+      "epoch": 0.5612244897959183,
+      "grad_norm": 4.0759355613648625,
+      "learning_rate": 1.7257288935004132e-06,
+      "loss": 1.7034,
+      "step": 165
+    },
+    {
+      "epoch": 0.564625850340136,
+      "grad_norm": 16.519960341878562,
+      "learning_rate": 1.7218509852994822e-06,
+      "loss": 2.115,
+      "step": 166
+    },
+    {
+      "epoch": 0.5680272108843537,
+      "grad_norm": 17.37824200525593,
+      "learning_rate": 1.7179502777446392e-06,
+      "loss": 2.0609,
+      "step": 167
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 39.604264809847564,
+      "learning_rate": 1.7140268940380605e-06,
+      "loss": 2.3861,
+      "step": 168
+    },
+    {
+      "epoch": 0.5748299319727891,
+      "grad_norm": 17.489048911326037,
+      "learning_rate": 1.7100809580981384e-06,
+      "loss": 1.9979,
+      "step": 169
+    },
+    {
+      "epoch": 0.5782312925170068,
+      "grad_norm": 6.642641185839537,
+      "learning_rate": 1.7061125945555679e-06,
+      "loss": 1.7533,
+      "step": 170
+    },
+    {
+      "epoch": 0.5816326530612245,
+      "grad_norm": 41.437166409250736,
+      "learning_rate": 1.70212192874941e-06,
+      "loss": 2.8676,
+      "step": 171
+    },
+    {
+      "epoch": 0.5850340136054422,
+      "grad_norm": 12.285090452877482,
+      "learning_rate": 1.6981090867231336e-06,
+      "loss": 1.8715,
+      "step": 172
+    },
+    {
+      "epoch": 0.5884353741496599,
+      "grad_norm": 20.351266920257437,
+      "learning_rate": 1.694074195220634e-06,
+      "loss": 2.5238,
+      "step": 173
+    },
+    {
+      "epoch": 0.5918367346938775,
+      "grad_norm": 13.128678816386138,
+      "learning_rate": 1.6900173816822289e-06,
+      "loss": 1.7191,
+      "step": 174
+    },
+    {
+      "epoch": 0.5952380952380952,
+      "grad_norm": 3.1331026154409565,
+      "learning_rate": 1.6859387742406358e-06,
+      "loss": 1.7885,
+      "step": 175
+    },
+    {
+      "epoch": 0.5986394557823129,
+      "grad_norm": 12.273944679120639,
+      "learning_rate": 1.6818385017169212e-06,
+      "loss": 1.9361,
+      "step": 176
+    },
+    {
+      "epoch": 0.6020408163265306,
+      "grad_norm": 18.988287394873876,
+      "learning_rate": 1.6777166936164354e-06,
+      "loss": 2.118,
+      "step": 177
+    },
+    {
+      "epoch": 0.6054421768707483,
+      "grad_norm": 13.330413347581118,
+      "learning_rate": 1.6735734801247202e-06,
+      "loss": 1.9923,
+      "step": 178
+    },
+    {
+      "epoch": 0.608843537414966,
+      "grad_norm": 8.528660885149025,
+      "learning_rate": 1.6694089921033976e-06,
+      "loss": 1.6938,
+      "step": 179
+    },
+    {
+      "epoch": 0.6122448979591837,
+      "grad_norm": 28.049589150374253,
+      "learning_rate": 1.6652233610860364e-06,
+      "loss": 2.4092,
+      "step": 180
+    },
+    {
+      "epoch": 0.6156462585034014,
+      "grad_norm": 19.077236893577115,
+      "learning_rate": 1.6610167192739978e-06,
+      "loss": 2.3235,
+      "step": 181
+    },
+    {
+      "epoch": 0.6190476190476191,
+      "grad_norm": 23.109888095114325,
+      "learning_rate": 1.6567891995322603e-06,
+      "loss": 2.2678,
+      "step": 182
+    },
+    {
+      "epoch": 0.6224489795918368,
+      "grad_norm": 19.456776496200867,
+      "learning_rate": 1.6525409353852221e-06,
+      "loss": 2.2764,
+      "step": 183
+    },
+    {
+      "epoch": 0.6258503401360545,
+      "grad_norm": 9.82404206796416,
+      "learning_rate": 1.6482720610124856e-06,
+      "loss": 1.8034,
+      "step": 184
+    },
+    {
+      "epoch": 0.6292517006802721,
+      "grad_norm": 24.2061776724548,
+      "learning_rate": 1.6439827112446173e-06,
+      "loss": 2.161,
+      "step": 185
+    },
+    {
+      "epoch": 0.6292517006802721,
+      "eval_loss": 2.194326400756836,
+      "eval_runtime": 3.7428,
+      "eval_samples_per_second": 14.695,
+      "eval_steps_per_second": 1.069,
+      "step": 185
+    },
+    {
+      "epoch": 0.6326530612244898,
+      "grad_norm": 30.469163171671003,
+      "learning_rate": 1.6396730215588912e-06,
+      "loss": 2.2773,
+      "step": 186
+    },
+    {
+      "epoch": 0.6360544217687075,
+      "grad_norm": 3.646917584621385,
+      "learning_rate": 1.6353431280750082e-06,
+      "loss": 1.5989,
+      "step": 187
+    },
+    {
+      "epoch": 0.6394557823129252,
+      "grad_norm": 30.30266588230692,
+      "learning_rate": 1.6309931675507978e-06,
+      "loss": 2.6169,
+      "step": 188
+    },
+    {
+      "epoch": 0.6428571428571429,
+      "grad_norm": 14.371186117614542,
+      "learning_rate": 1.6266232773778983e-06,
+      "loss": 1.9241,
+      "step": 189
+    },
+    {
+      "epoch": 0.6462585034013606,
+      "grad_norm": 18.71258411403636,
+      "learning_rate": 1.6222335955774176e-06,
+      "loss": 2.1737,
+      "step": 190
+    },
+    {
+      "epoch": 0.6496598639455783,
+      "grad_norm": 3.2723339662931585,
+      "learning_rate": 1.617824260795573e-06,
+      "loss": 1.8075,
+      "step": 191
+    },
+    {
+      "epoch": 0.6530612244897959,
+      "grad_norm": 16.496061968286824,
+      "learning_rate": 1.6133954122993139e-06,
+      "loss": 2.0147,
+      "step": 192
+    },
+    {
+      "epoch": 0.6564625850340136,
+      "grad_norm": 3.2013079969624805,
+      "learning_rate": 1.608947189971921e-06,
+      "loss": 1.6798,
+      "step": 193
+    },
+    {
+      "epoch": 0.6598639455782312,
+      "grad_norm": 20.981814890242124,
+      "learning_rate": 1.6044797343085898e-06,
+      "loss": 2.0425,
+      "step": 194
+    },
+    {
+      "epoch": 0.6632653061224489,
+      "grad_norm": 50.879018823375965,
+      "learning_rate": 1.599993186411992e-06,
+      "loss": 3.8504,
+      "step": 195
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 3.283241794235971,
+      "learning_rate": 1.59548768798782e-06,
+      "loss": 1.4971,
+      "step": 196
+    },
+    {
+      "epoch": 0.6700680272108843,
+      "grad_norm": 12.706772022061763,
+      "learning_rate": 1.5909633813403092e-06,
+      "loss": 1.9318,
+      "step": 197
+    },
+    {
+      "epoch": 0.673469387755102,
+      "grad_norm": 7.747043673117189,
+      "learning_rate": 1.5864204093677463e-06,
+      "loss": 1.8641,
+      "step": 198
+    },
+    {
+      "epoch": 0.6768707482993197,
+      "grad_norm": 12.685665761738797,
+      "learning_rate": 1.5818589155579529e-06,
+      "loss": 2.0781,
+      "step": 199
+    },
+    {
+      "epoch": 0.6802721088435374,
+      "grad_norm": 8.183695796856302,
+      "learning_rate": 1.5772790439837555e-06,
+      "loss": 2.1112,
+      "step": 200
+    },
+    {
+      "epoch": 0.6836734693877551,
+      "grad_norm": 3.6436475976280605,
+      "learning_rate": 1.572680939298435e-06,
+      "loss": 1.504,
+      "step": 201
+    },
+    {
+      "epoch": 0.6870748299319728,
+      "grad_norm": 7.765753459491514,
+      "learning_rate": 1.5680647467311555e-06,
+      "loss": 1.6113,
+      "step": 202
+    },
+    {
+      "epoch": 0.6904761904761905,
+      "grad_norm": 27.059590789587673,
+      "learning_rate": 1.563430612082382e-06,
+      "loss": 2.3797,
+      "step": 203
+    },
+    {
+      "epoch": 0.6938775510204082,
+      "grad_norm": 17.865181616406808,
+      "learning_rate": 1.5587786817192687e-06,
+      "loss": 2.2287,
+      "step": 204
+    },
+    {
+      "epoch": 0.6972789115646258,
+      "grad_norm": 11.50437842198177,
+      "learning_rate": 1.5541091025710434e-06,
+      "loss": 2.2926,
+      "step": 205
+    },
+    {
+      "epoch": 0.7006802721088435,
+      "grad_norm": 18.03962056520961,
+      "learning_rate": 1.5494220221243607e-06,
+      "loss": 2.3374,
+      "step": 206
+    },
+    {
+      "epoch": 0.7040816326530612,
+      "grad_norm": 19.808732477248256,
+      "learning_rate": 1.5447175884186478e-06,
+      "loss": 2.3215,
+      "step": 207
+    },
+    {
+      "epoch": 0.7074829931972789,
+      "grad_norm": 21.35228597761302,
+      "learning_rate": 1.539995950041426e-06,
+      "loss": 2.2378,
+      "step": 208
+    },
+    {
+      "epoch": 0.7108843537414966,
+      "grad_norm": 14.090932946927257,
+      "learning_rate": 1.5352572561236197e-06,
+      "loss": 2.22,
+      "step": 209
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 22.22875395969964,
+      "learning_rate": 1.5305016563348443e-06,
+      "loss": 2.44,
+      "step": 210
+    },
+    {
+      "epoch": 0.717687074829932,
+      "grad_norm": 12.732771656478363,
+      "learning_rate": 1.5257293008786807e-06,
+      "loss": 2.0598,
+      "step": 211
+    },
+    {
+      "epoch": 0.7210884353741497,
+      "grad_norm": 3.3024595151809777,
+      "learning_rate": 1.5209403404879303e-06,
+      "loss": 1.8514,
+      "step": 212
+    },
+    {
+      "epoch": 0.7244897959183674,
+      "grad_norm": 31.041628605811148,
+      "learning_rate": 1.5161349264198535e-06,
+      "loss": 2.4225,
+      "step": 213
+    },
+    {
+      "epoch": 0.7278911564625851,
+      "grad_norm": 11.866017531018645,
+      "learning_rate": 1.511313210451394e-06,
+      "loss": 1.9747,
+      "step": 214
+    },
+    {
+      "epoch": 0.7312925170068028,
+      "grad_norm": 23.77867996796224,
+      "learning_rate": 1.5064753448743832e-06,
+      "loss": 2.0971,
+      "step": 215
+    },
+    {
+      "epoch": 0.7346938775510204,
+      "grad_norm": 28.640512428374876,
+      "learning_rate": 1.5016214824907314e-06,
+      "loss": 2.2247,
+      "step": 216
+    },
+    {
+      "epoch": 0.7380952380952381,
+      "grad_norm": 9.463317499162777,
+      "learning_rate": 1.4967517766076015e-06,
+      "loss": 1.9511,
+      "step": 217
+    },
+    {
+      "epoch": 0.7414965986394558,
+      "grad_norm": 3.6132074342008336,
+      "learning_rate": 1.4918663810325659e-06,
+      "loss": 1.5643,
+      "step": 218
+    },
+    {
+      "epoch": 0.7448979591836735,
+      "grad_norm": 12.274299577611806,
+      "learning_rate": 1.4869654500687492e-06,
+      "loss": 2.0865,
+      "step": 219
+    },
+    {
+      "epoch": 0.7482993197278912,
+      "grad_norm": 9.577269499797044,
+      "learning_rate": 1.4820491385099555e-06,
+      "loss": 2.1494,
+      "step": 220
+    },
+    {
+      "epoch": 0.7517006802721088,
+      "grad_norm": 13.665325186622818,
+      "learning_rate": 1.477117601635777e-06,
+      "loss": 2.0676,
+      "step": 221
+    },
+    {
+      "epoch": 0.7551020408163265,
+      "grad_norm": 12.044556166373619,
+      "learning_rate": 1.4721709952066923e-06,
+      "loss": 1.7408,
+      "step": 222
+    },
+    {
+      "epoch": 0.7551020408163265,
+      "eval_loss": 2.1867611408233643,
+      "eval_runtime": 3.7388,
+      "eval_samples_per_second": 14.711,
+      "eval_steps_per_second": 1.07,
+      "step": 222
+    },
+    {
+      "epoch": 0.7585034013605442,
+      "grad_norm": 32.0866216128451,
+      "learning_rate": 1.4672094754591449e-06,
+      "loss": 2.6444,
+      "step": 223
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 26.272890838528287,
+      "learning_rate": 1.4622331991006082e-06,
+      "loss": 2.0286,
+      "step": 224
+    },
+    {
+      "epoch": 0.7653061224489796,
+      "grad_norm": 10.948966043777636,
+      "learning_rate": 1.4572423233046385e-06,
+      "loss": 1.8924,
+      "step": 225
+    },
+    {
+      "epoch": 0.7687074829931972,
+      "grad_norm": 10.041220633719293,
+      "learning_rate": 1.4522370057059079e-06,
+      "loss": 1.8589,
+      "step": 226
+    },
+    {
+      "epoch": 0.7721088435374149,
+      "grad_norm": 19.90849856575333,
+      "learning_rate": 1.447217404395227e-06,
+      "loss": 2.4632,
+      "step": 227
+    },
+    {
+      "epoch": 0.7755102040816326,
+      "grad_norm": 3.3718807752757134,
+      "learning_rate": 1.4421836779145511e-06,
+      "loss": 1.7402,
+      "step": 228
+    },
+    {
+      "epoch": 0.7789115646258503,
+      "grad_norm": 33.99543346002537,
+      "learning_rate": 1.4371359852519734e-06,
+      "loss": 2.9081,
+      "step": 229
+    },
+    {
+      "epoch": 0.782312925170068,
+      "grad_norm": 12.446391408704297,
+      "learning_rate": 1.4320744858367024e-06,
+      "loss": 2.0828,
+      "step": 230
+    },
+    {
+      "epoch": 0.7857142857142857,
+      "grad_norm": 26.19952152880794,
+      "learning_rate": 1.4269993395340277e-06,
+      "loss": 2.2178,
+      "step": 231
+    },
+    {
+      "epoch": 0.7891156462585034,
+      "grad_norm": 36.07799078718175,
+      "learning_rate": 1.4219107066402692e-06,
+      "loss": 2.6926,
+      "step": 232
+    },
+    {
+      "epoch": 0.7925170068027211,
+      "grad_norm": 11.216785179837261,
+      "learning_rate": 1.4168087478777152e-06,
+      "loss": 2.0393,
+      "step": 233
+    },
+    {
+      "epoch": 0.7959183673469388,
+      "grad_norm": 17.659830496744974,
+      "learning_rate": 1.4116936243895466e-06,
+      "loss": 2.1082,
+      "step": 234
+    },
+    {
+      "epoch": 0.7993197278911565,
+      "grad_norm": 17.001892765923902,
+      "learning_rate": 1.406565497734745e-06,
+      "loss": 1.9051,
+      "step": 235
+    },
+    {
+      "epoch": 0.8027210884353742,
+      "grad_norm": 31.896056687773818,
+      "learning_rate": 1.4014245298829935e-06,
+      "loss": 2.702,
+      "step": 236
+    },
+    {
+      "epoch": 0.8061224489795918,
+      "grad_norm": 6.972810630357569,
+      "learning_rate": 1.3962708832095568e-06,
+      "loss": 1.9466,
+      "step": 237
+    },
+    {
+      "epoch": 0.8095238095238095,
+      "grad_norm": 17.689383441039308,
+      "learning_rate": 1.3911047204901558e-06,
+      "loss": 2.3425,
+      "step": 238
+    },
+    {
+      "epoch": 0.8129251700680272,
+      "grad_norm": 16.46834046227904,
+      "learning_rate": 1.385926204895826e-06,
+      "loss": 2.1545,
+      "step": 239
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "grad_norm": 21.69161139742313,
+      "learning_rate": 1.3807354999877614e-06,
+      "loss": 2.3222,
+      "step": 240
+    },
+    {
+      "epoch": 0.8197278911564626,
+      "grad_norm": 3.411794366451801,
+      "learning_rate": 1.3755327697121522e-06,
+      "loss": 1.6492,
+      "step": 241
+    },
+    {
+      "epoch": 0.8231292517006803,
+      "grad_norm": 13.113564486849809,
+      "learning_rate": 1.3703181783950031e-06,
+      "loss": 2.0212,
+      "step": 242
+    },
+    {
+      "epoch": 0.826530612244898,
+      "grad_norm": 14.798483657902382,
+      "learning_rate": 1.3650918907369452e-06,
+      "loss": 2.1974,
+      "step": 243
+    },
+    {
+      "epoch": 0.8299319727891157,
+      "grad_norm": 10.19780084250851,
+      "learning_rate": 1.3598540718080345e-06,
+      "loss": 1.8543,
+      "step": 244
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 30.023251305313995,
+      "learning_rate": 1.3546048870425354e-06,
+      "loss": 2.2387,
+      "step": 245
+    },
+    {
+      "epoch": 0.8367346938775511,
+      "grad_norm": 22.321684071392564,
+      "learning_rate": 1.3493445022336994e-06,
+      "loss": 2.4305,
+      "step": 246
+    },
+    {
+      "epoch": 0.8401360544217688,
+      "grad_norm": 34.98925650288134,
+      "learning_rate": 1.3440730835285247e-06,
+      "loss": 2.4364,
+      "step": 247
+    },
+    {
+      "epoch": 0.8435374149659864,
+      "grad_norm": 3.161092974878791,
+      "learning_rate": 1.3387907974225116e-06,
+      "loss": 1.4885,
+      "step": 248
+    },
+    {
+      "epoch": 0.8469387755102041,
+      "grad_norm": 50.11899935337027,
+      "learning_rate": 1.3334978107544024e-06,
+      "loss": 2.3332,
+      "step": 249
+    },
+    {
+      "epoch": 0.8503401360544217,
+      "grad_norm": 15.05206270554561,
+      "learning_rate": 1.3281942907009112e-06,
+      "loss": 2.2131,
+      "step": 250
+    },
+    {
+      "epoch": 0.8537414965986394,
+      "grad_norm": 24.869549840961,
+      "learning_rate": 1.3228804047714462e-06,
+      "loss": 2.2264,
+      "step": 251
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 16.049594008906414,
+      "learning_rate": 1.317556320802816e-06,
+      "loss": 1.7228,
+      "step": 252
+    },
+    {
+      "epoch": 0.8605442176870748,
+      "grad_norm": 14.258214783846427,
+      "learning_rate": 1.31222220695393e-06,
+      "loss": 1.999,
+      "step": 253
+    },
+    {
+      "epoch": 0.8639455782312925,
+      "grad_norm": 3.3063413494205474,
+      "learning_rate": 1.3068782317004874e-06,
+      "loss": 1.4607,
+      "step": 254
+    },
+    {
+      "epoch": 0.8673469387755102,
+      "grad_norm": 8.831787955552995,
+      "learning_rate": 1.3015245638296563e-06,
+      "loss": 2.1192,
+      "step": 255
+    },
+    {
+      "epoch": 0.8707482993197279,
+      "grad_norm": 3.121872417027736,
+      "learning_rate": 1.296161372434741e-06,
+      "loss": 1.5467,
+      "step": 256
+    },
+    {
+      "epoch": 0.8741496598639455,
+      "grad_norm": 33.22351218100941,
+      "learning_rate": 1.2907888269098416e-06,
+      "loss": 2.3588,
+      "step": 257
+    },
+    {
+      "epoch": 0.8775510204081632,
+      "grad_norm": 3.188560179185641,
+      "learning_rate": 1.2854070969445064e-06,
+      "loss": 1.5405,
+      "step": 258
+    },
+    {
+      "epoch": 0.8809523809523809,
+      "grad_norm": 21.318069352021737,
+      "learning_rate": 1.2800163525183688e-06,
+      "loss": 2.2063,
+      "step": 259
+    },
+    {
+      "epoch": 0.8809523809523809,
+      "eval_loss": 2.1820290088653564,
+      "eval_runtime": 3.8534,
+      "eval_samples_per_second": 14.273,
+      "eval_steps_per_second": 1.038,
+      "step": 259
+    },
+    {
+      "epoch": 0.8843537414965986,
+      "grad_norm": 8.243323927611506,
+      "learning_rate": 1.2746167638957805e-06,
+      "loss": 1.8474,
+      "step": 260
+    },
+    {
+      "epoch": 0.8877551020408163,
+      "grad_norm": 28.909948439715215,
+      "learning_rate": 1.2692085016204333e-06,
+      "loss": 2.2626,
+      "step": 261
+    },
+    {
+      "epoch": 0.891156462585034,
+      "grad_norm": 3.0722449835450116,
+      "learning_rate": 1.2637917365099725e-06,
+      "loss": 1.6435,
+      "step": 262
+    },
+    {
+      "epoch": 0.8945578231292517,
+      "grad_norm": 29.871491992872432,
+      "learning_rate": 1.2583666396506023e-06,
+      "loss": 2.1498,
+      "step": 263
+    },
+    {
+      "epoch": 0.8979591836734694,
+      "grad_norm": 2.977539901133042,
+      "learning_rate": 1.2529333823916806e-06,
+      "loss": 1.7024,
+      "step": 264
+    },
+    {
+      "epoch": 0.9013605442176871,
+      "grad_norm": 16.47476152363902,
+      "learning_rate": 1.2474921363403094e-06,
+      "loss": 2.532,
+      "step": 265
+    },
+    {
+      "epoch": 0.9047619047619048,
+      "grad_norm": 13.022051400004793,
+      "learning_rate": 1.2420430733559124e-06,
+      "loss": 1.8884,
+      "step": 266
+    },
+    {
+      "epoch": 0.9081632653061225,
+      "grad_norm": 8.97804602434911,
+      "learning_rate": 1.2365863655448075e-06,
+      "loss": 1.7885,
+      "step": 267
+    },
+    {
+      "epoch": 0.9115646258503401,
+      "grad_norm": 16.047174726202446,
+      "learning_rate": 1.2311221852547721e-06,
+      "loss": 2.3363,
+      "step": 268
+    },
+    {
+      "epoch": 0.9149659863945578,
+      "grad_norm": 3.5763323384852765,
+      "learning_rate": 1.2256507050695977e-06,
+      "loss": 1.701,
+      "step": 269
+    },
+    {
+      "epoch": 0.9183673469387755,
+      "grad_norm": 26.929796973835796,
+      "learning_rate": 1.220172097803641e-06,
+      "loss": 2.3601,
+      "step": 270
+    },
+    {
+      "epoch": 0.9217687074829932,
+      "grad_norm": 22.50281840057178,
+      "learning_rate": 1.2146865364963633e-06,
+      "loss": 2.0693,
+      "step": 271
+    },
+    {
+      "epoch": 0.9251700680272109,
+      "grad_norm": 11.62602578923058,
+      "learning_rate": 1.2091941944068665e-06,
+      "loss": 1.9123,
+      "step": 272
+    },
+    {
+      "epoch": 0.9285714285714286,
+      "grad_norm": 16.841220035990798,
+      "learning_rate": 1.2036952450084214e-06,
+      "loss": 2.2163,
+      "step": 273
+    },
+    {
+      "epoch": 0.9319727891156463,
+      "grad_norm": 18.055133543008612,
+      "learning_rate": 1.1981898619829879e-06,
+      "loss": 2.2485,
+      "step": 274
+    },
+    {
+      "epoch": 0.935374149659864,
+      "grad_norm": 26.45820099458286,
+      "learning_rate": 1.1926782192157273e-06,
+      "loss": 2.1845,
+      "step": 275
+    },
+    {
+      "epoch": 0.9387755102040817,
+      "grad_norm": 3.334955291200548,
+      "learning_rate": 1.1871604907895148e-06,
+      "loss": 1.7059,
+      "step": 276
+    },
+    {
+      "epoch": 0.9421768707482994,
+      "grad_norm": 19.511242339983163,
+      "learning_rate": 1.1816368509794364e-06,
+      "loss": 2.3601,
+      "step": 277
+    },
+    {
+      "epoch": 0.9455782312925171,
+      "grad_norm": 21.146925953072365,
+      "learning_rate": 1.1761074742472882e-06,
+      "loss": 1.9957,
+      "step": 278
+    },
+    {
+      "epoch": 0.9489795918367347,
+      "grad_norm": 3.5535024021194452,
+      "learning_rate": 1.1705725352360633e-06,
+      "loss": 1.9249,
+      "step": 279
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 13.348912305071467,
+      "learning_rate": 1.165032208764438e-06,
+      "loss": 2.0641,
+      "step": 280
+    },
+    {
+      "epoch": 0.95578231292517,
+      "grad_norm": 12.61033318044152,
+      "learning_rate": 1.1594866698212483e-06,
+      "loss": 2.169,
+      "step": 281
+    },
+    {
+      "epoch": 0.9591836734693877,
+      "grad_norm": 28.256325358544956,
+      "learning_rate": 1.1539360935599644e-06,
+      "loss": 2.0952,
+      "step": 282
+    },
+    {
+      "epoch": 0.9625850340136054,
+      "grad_norm": 12.61302060729169,
+      "learning_rate": 1.1483806552931582e-06,
+      "loss": 1.9411,
+      "step": 283
+    },
+    {
+      "epoch": 0.9659863945578231,
+      "grad_norm": 8.711391665501074,
+      "learning_rate": 1.142820530486966e-06,
+      "loss": 1.7633,
+      "step": 284
+    },
+    {
+      "epoch": 0.9693877551020408,
+      "grad_norm": 35.95958496013491,
+      "learning_rate": 1.1372558947555455e-06,
+      "loss": 2.1904,
+      "step": 285
+    },
+    {
+      "epoch": 0.9727891156462585,
+      "grad_norm": 3.429092657849847,
+      "learning_rate": 1.131686923855531e-06,
+      "loss": 1.8276,
+      "step": 286
+    },
+    {
+      "epoch": 0.9761904761904762,
+      "grad_norm": 12.871658288368948,
+      "learning_rate": 1.1261137936804811e-06,
+      "loss": 2.0911,
+      "step": 287
+    },
+    {
+      "epoch": 0.9795918367346939,
+      "grad_norm": 13.217001333800638,
+      "learning_rate": 1.1205366802553228e-06,
+      "loss": 1.9614,
+      "step": 288
+    },
+    {
+      "epoch": 0.9829931972789115,
+      "grad_norm": 24.712172909538513,
+      "learning_rate": 1.1149557597307934e-06,
+      "loss": 2.0412,
+      "step": 289
+    },
+    {
+      "epoch": 0.9863945578231292,
+      "grad_norm": 10.412944718560512,
+      "learning_rate": 1.1093712083778746e-06,
+      "loss": 1.7787,
+      "step": 290
+    },
+    {
+      "epoch": 0.9897959183673469,
+      "grad_norm": 15.631851389191027,
+      "learning_rate": 1.1037832025822265e-06,
+      "loss": 2.3362,
+      "step": 291
+    },
+    {
+      "epoch": 0.9931972789115646,
+      "grad_norm": 12.135256117907334,
+      "learning_rate": 1.098191918838617e-06,
+      "loss": 2.0212,
+      "step": 292
+    },
+    {
+      "epoch": 0.9965986394557823,
+      "grad_norm": 13.057522322919077,
+      "learning_rate": 1.0925975337453462e-06,
+      "loss": 2.2842,
+      "step": 293
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 17.565324685523922,
+      "learning_rate": 1.0870002239986686e-06,
+      "loss": 2.5002,
+      "step": 294
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 588,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 294,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 95887829237760.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22a4947fe41739721780866b30349cfbf1192d28b19f4eacf333006a2df11a8c
+size 8376

zero_to_fp32.py

@@ -0,0 +1,674 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example:
+#   python zero_to_fp32.py . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import json
+from tqdm import tqdm
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering Sharded Weights'):
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               tag=None,
+                                               exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        state_dict_split = split_torch_state_dict_into_shards(state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard = {tensor: state_dict[tensor].contiguous() for tensor in tensors}
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard, output_path)
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument("output_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)