Upload folder using huggingface_hub

checkpoint-380/config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "GraniteForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attention_multiplier": 0.0078125,
+  "bos_token_id": 0,
+  "embedding_multiplier": 12.0,
+  "eos_token_id": 0,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12800,
+  "logits_scaling": 16.0,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "granite",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "residual_multiplier": 0.22,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "use_cache": false,
+  "vocab_size": 49159
+}

checkpoint-380/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "pad_token_id": 0,
+  "transformers_version": "4.52.4"
+}

checkpoint-380/model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6b621488f4aa7739ffcfde7cf80e20ed71ae5791f6259f0e0b2b56f7f21be99
+size 4957951616

checkpoint-380/model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbd2de23db8bf0a9b54dfc2d01036dc7917812102e294d94d5bf5e7d209198ff
+size 4991424704

checkpoint-380/model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9af050409a207877e3fb13181d30f3c0c106f8df8a38cf04c9ad05097372fd75
+size 4991424744

checkpoint-380/model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77ab9bbe9f27c2f5c9565218a03f7082d381a590958422a6bff3910906a3e247
+size 4991457736

checkpoint-380/model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0eeb3e5a77b15c7e78f9b1147808f3df54e174b8abcd98c638eb1ca0b7c2a4c
+size 4949482056

checkpoint-380/model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39834a29c4a91e2936452240c1ca875eac58c626c8deeadb57e849eca2cd8079
+size 4991424744

checkpoint-380/model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31531faaf37414ddf9fab980856df024c87fd318db0a2138e3da0e025447c4a2
+size 3615755992

checkpoint-380/model.safetensors.index.json

@@ -0,0 +1,370 @@
+{
+  "metadata": {
+    "total_size": 33488879616
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.norm.weight": "model-00007-of-00007.safetensors"
+  }
+}

checkpoint-380/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16abbe0c0ba6d6603cc72ef5a2dc3d83d06b2b3c22cd83c17a0b77b72c7fb9cd
+size 15920

checkpoint-380/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c863a4f05d27f58c1affe2733de4b154481039353ee0ffd5b0abeea24a24f6b8
+size 15920

checkpoint-380/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82952d4ed849dee40e4c4b84a8d56cc37d4c44be37fc2001e5e80091b2a72c4d
+size 15920

checkpoint-380/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e92a47f3db7cac55c25ab81fb45d2efe759b014ad043f30231496bf0652677b0
+size 15920

checkpoint-380/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64d323d43740d0e67694e960bc518c9d960be761a18bef2fd4ba6f5d29a7de88
+size 15920

checkpoint-380/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f957f4830ee6d2c1d72c1c4e7b5b4b1101d28b5c3ee048136166107200b92ff
+size 15920

checkpoint-380/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba64848e9a1561871d51c836ee082a69c089103b567cd4ce767e54a0c5cd45f0
+size 15920

checkpoint-380/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:731b85ade6fda0823a5d5b2b1a2eeea786af43696be44c878a8a6f4ce3628c0b
+size 15920

checkpoint-380/trainer_state.json

@@ -0,0 +1,566 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 380,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.026385224274406333,
+      "grad_norm": 107.23584747314453,
+      "learning_rate": 4.210526315789474e-07,
+      "loss": 5.622,
+      "step": 5
+    },
+    {
+      "epoch": 0.052770448548812667,
+      "grad_norm": 77.56803894042969,
+      "learning_rate": 9.473684210526317e-07,
+      "loss": 5.3488,
+      "step": 10
+    },
+    {
+      "epoch": 0.079155672823219,
+      "grad_norm": 60.997257232666016,
+      "learning_rate": 1.4736842105263159e-06,
+      "loss": 4.9812,
+      "step": 15
+    },
+    {
+      "epoch": 0.10554089709762533,
+      "grad_norm": 33.36190414428711,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 4.4552,
+      "step": 20
+    },
+    {
+      "epoch": 0.13192612137203166,
+      "grad_norm": 18.245769500732422,
+      "learning_rate": 2.5263157894736844e-06,
+      "loss": 4.0648,
+      "step": 25
+    },
+    {
+      "epoch": 0.158311345646438,
+      "grad_norm": 15.86693000793457,
+      "learning_rate": 3.052631578947369e-06,
+      "loss": 3.6069,
+      "step": 30
+    },
+    {
+      "epoch": 0.18469656992084432,
+      "grad_norm": 11.502686500549316,
+      "learning_rate": 3.578947368421053e-06,
+      "loss": 3.6728,
+      "step": 35
+    },
+    {
+      "epoch": 0.21108179419525067,
+      "grad_norm": 16.517114639282227,
+      "learning_rate": 4.105263157894737e-06,
+      "loss": 3.7924,
+      "step": 40
+    },
+    {
+      "epoch": 0.23746701846965698,
+      "grad_norm": 12.67491340637207,
+      "learning_rate": 4.631578947368421e-06,
+      "loss": 3.3256,
+      "step": 45
+    },
+    {
+      "epoch": 0.2638522427440633,
+      "grad_norm": 11.452499389648438,
+      "learning_rate": 5.157894736842106e-06,
+      "loss": 3.2939,
+      "step": 50
+    },
+    {
+      "epoch": 0.29023746701846964,
+      "grad_norm": 13.192882537841797,
+      "learning_rate": 5.68421052631579e-06,
+      "loss": 3.0344,
+      "step": 55
+    },
+    {
+      "epoch": 0.316622691292876,
+      "grad_norm": 11.595597267150879,
+      "learning_rate": 6.2105263157894745e-06,
+      "loss": 2.7082,
+      "step": 60
+    },
+    {
+      "epoch": 0.34300791556728233,
+      "grad_norm": 12.450468063354492,
+      "learning_rate": 6.736842105263158e-06,
+      "loss": 2.9807,
+      "step": 65
+    },
+    {
+      "epoch": 0.36939313984168864,
+      "grad_norm": 13.777202606201172,
+      "learning_rate": 7.263157894736843e-06,
+      "loss": 2.8359,
+      "step": 70
+    },
+    {
+      "epoch": 0.39577836411609496,
+      "grad_norm": 13.03334903717041,
+      "learning_rate": 7.789473684210526e-06,
+      "loss": 2.5446,
+      "step": 75
+    },
+    {
+      "epoch": 0.42216358839050133,
+      "grad_norm": 17.208057403564453,
+      "learning_rate": 8.315789473684212e-06,
+      "loss": 2.5668,
+      "step": 80
+    },
+    {
+      "epoch": 0.44854881266490765,
+      "grad_norm": 15.075675010681152,
+      "learning_rate": 8.842105263157895e-06,
+      "loss": 2.3511,
+      "step": 85
+    },
+    {
+      "epoch": 0.47493403693931396,
+      "grad_norm": 14.769970893859863,
+      "learning_rate": 9.36842105263158e-06,
+      "loss": 2.5317,
+      "step": 90
+    },
+    {
+      "epoch": 0.5013192612137203,
+      "grad_norm": 11.59249210357666,
+      "learning_rate": 9.894736842105264e-06,
+      "loss": 2.2466,
+      "step": 95
+    },
+    {
+      "epoch": 0.5277044854881267,
+      "grad_norm": 15.899335861206055,
+      "learning_rate": 9.999459967758384e-06,
+      "loss": 2.1577,
+      "step": 100
+    },
+    {
+      "epoch": 0.554089709762533,
+      "grad_norm": 18.471529006958008,
+      "learning_rate": 9.99726628670463e-06,
+      "loss": 1.9901,
+      "step": 105
+    },
+    {
+      "epoch": 0.5804749340369393,
+      "grad_norm": 13.399049758911133,
+      "learning_rate": 9.993385944658086e-06,
+      "loss": 1.9487,
+      "step": 110
+    },
+    {
+      "epoch": 0.6068601583113457,
+      "grad_norm": 11.711898803710938,
+      "learning_rate": 9.987820251299121e-06,
+      "loss": 1.6927,
+      "step": 115
+    },
+    {
+      "epoch": 0.633245382585752,
+      "grad_norm": 20.446998596191406,
+      "learning_rate": 9.980571085142381e-06,
+      "loss": 1.7541,
+      "step": 120
+    },
+    {
+      "epoch": 0.6596306068601583,
+      "grad_norm": 10.907441139221191,
+      "learning_rate": 9.971640892902742e-06,
+      "loss": 1.7187,
+      "step": 125
+    },
+    {
+      "epoch": 0.6860158311345647,
+      "grad_norm": 13.693713188171387,
+      "learning_rate": 9.961032688669519e-06,
+      "loss": 1.6546,
+      "step": 130
+    },
+    {
+      "epoch": 0.712401055408971,
+      "grad_norm": 9.666728019714355,
+      "learning_rate": 9.94875005288915e-06,
+      "loss": 1.6036,
+      "step": 135
+    },
+    {
+      "epoch": 0.7387862796833773,
+      "grad_norm": 12.30069637298584,
+      "learning_rate": 9.934797131156745e-06,
+      "loss": 1.3259,
+      "step": 140
+    },
+    {
+      "epoch": 0.7651715039577837,
+      "grad_norm": 10.972068786621094,
+      "learning_rate": 9.919178632816864e-06,
+      "loss": 1.3776,
+      "step": 145
+    },
+    {
+      "epoch": 0.7915567282321899,
+      "grad_norm": 13.099720001220703,
+      "learning_rate": 9.901899829374048e-06,
+      "loss": 1.2886,
+      "step": 150
+    },
+    {
+      "epoch": 0.8179419525065963,
+      "grad_norm": 9.663094520568848,
+      "learning_rate": 9.88296655271359e-06,
+      "loss": 1.133,
+      "step": 155
+    },
+    {
+      "epoch": 0.8443271767810027,
+      "grad_norm": 12.018184661865234,
+      "learning_rate": 9.862385193133181e-06,
+      "loss": 1.0579,
+      "step": 160
+    },
+    {
+      "epoch": 0.8707124010554089,
+      "grad_norm": 14.370702743530273,
+      "learning_rate": 9.840162697186075e-06,
+      "loss": 0.8807,
+      "step": 165
+    },
+    {
+      "epoch": 0.8970976253298153,
+      "grad_norm": 10.248346328735352,
+      "learning_rate": 9.81630656533651e-06,
+      "loss": 0.8824,
+      "step": 170
+    },
+    {
+      "epoch": 0.9234828496042217,
+      "grad_norm": 12.581779479980469,
+      "learning_rate": 9.79082484942818e-06,
+      "loss": 0.8748,
+      "step": 175
+    },
+    {
+      "epoch": 0.9498680738786279,
+      "grad_norm": 13.555765151977539,
+      "learning_rate": 9.763726149966596e-06,
+      "loss": 0.8773,
+      "step": 180
+    },
+    {
+      "epoch": 0.9762532981530343,
+      "grad_norm": 10.211019515991211,
+      "learning_rate": 9.735019613216281e-06,
+      "loss": 0.6417,
+      "step": 185
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 7.966390609741211,
+      "learning_rate": 9.704714928113743e-06,
+      "loss": 0.7403,
+      "step": 190
+    },
+    {
+      "epoch": 1.0263852242744063,
+      "grad_norm": 6.398619174957275,
+      "learning_rate": 9.672822322997305e-06,
+      "loss": 0.4215,
+      "step": 195
+    },
+    {
+      "epoch": 1.0527704485488127,
+      "grad_norm": 35.487972259521484,
+      "learning_rate": 9.639352562154862e-06,
+      "loss": 0.4103,
+      "step": 200
+    },
+    {
+      "epoch": 1.079155672823219,
+      "grad_norm": 10.25015926361084,
+      "learning_rate": 9.604316942190764e-06,
+      "loss": 0.4638,
+      "step": 205
+    },
+    {
+      "epoch": 1.1055408970976253,
+      "grad_norm": 7.6288533210754395,
+      "learning_rate": 9.567727288213005e-06,
+      "loss": 0.3847,
+      "step": 210
+    },
+    {
+      "epoch": 1.1319261213720317,
+      "grad_norm": 8.111388206481934,
+      "learning_rate": 9.529595949842077e-06,
+      "loss": 0.3595,
+      "step": 215
+    },
+    {
+      "epoch": 1.158311345646438,
+      "grad_norm": 12.408935546875,
+      "learning_rate": 9.489935797042741e-06,
+      "loss": 0.3109,
+      "step": 220
+    },
+    {
+      "epoch": 1.1846965699208443,
+      "grad_norm": 8.753190994262695,
+      "learning_rate": 9.448760215780218e-06,
+      "loss": 0.3323,
+      "step": 225
+    },
+    {
+      "epoch": 1.2110817941952507,
+      "grad_norm": 6.783555030822754,
+      "learning_rate": 9.406083103502184e-06,
+      "loss": 0.2708,
+      "step": 230
+    },
+    {
+      "epoch": 1.237467018469657,
+      "grad_norm": 5.595340728759766,
+      "learning_rate": 9.36191886444817e-06,
+      "loss": 0.2853,
+      "step": 235
+    },
+    {
+      "epoch": 1.2638522427440633,
+      "grad_norm": 7.698513031005859,
+      "learning_rate": 9.31628240478787e-06,
+      "loss": 0.2702,
+      "step": 240
+    },
+    {
+      "epoch": 1.2902374670184695,
+      "grad_norm": 12.008724212646484,
+      "learning_rate": 9.26918912759007e-06,
+      "loss": 0.3292,
+      "step": 245
+    },
+    {
+      "epoch": 1.316622691292876,
+      "grad_norm": 9.176492691040039,
+      "learning_rate": 9.220654927623855e-06,
+      "loss": 0.3311,
+      "step": 250
+    },
+    {
+      "epoch": 1.3430079155672823,
+      "grad_norm": 6.505499362945557,
+      "learning_rate": 9.17069618599385e-06,
+      "loss": 0.3127,
+      "step": 255
+    },
+    {
+      "epoch": 1.3693931398416885,
+      "grad_norm": 6.490231513977051,
+      "learning_rate": 9.119329764611336e-06,
+      "loss": 0.2215,
+      "step": 260
+    },
+    {
+      "epoch": 1.395778364116095,
+      "grad_norm": 6.836956977844238,
+      "learning_rate": 9.06657300050306e-06,
+      "loss": 0.2988,
+      "step": 265
+    },
+    {
+      "epoch": 1.4221635883905013,
+      "grad_norm": 7.263693332672119,
+      "learning_rate": 9.012443699959706e-06,
+      "loss": 0.2536,
+      "step": 270
+    },
+    {
+      "epoch": 1.4485488126649075,
+      "grad_norm": 7.557298183441162,
+      "learning_rate": 8.956960132525973e-06,
+      "loss": 0.2264,
+      "step": 275
+    },
+    {
+      "epoch": 1.474934036939314,
+      "grad_norm": 6.503325462341309,
+      "learning_rate": 8.900141024834296e-06,
+      "loss": 0.2262,
+      "step": 280
+    },
+    {
+      "epoch": 1.5013192612137203,
+      "grad_norm": 6.369277477264404,
+      "learning_rate": 8.842005554284296e-06,
+      "loss": 0.1801,
+      "step": 285
+    },
+    {
+      "epoch": 1.5277044854881265,
+      "grad_norm": 7.811641693115234,
+      "learning_rate": 8.782573342570084e-06,
+      "loss": 0.178,
+      "step": 290
+    },
+    {
+      "epoch": 1.554089709762533,
+      "grad_norm": 6.305844783782959,
+      "learning_rate": 8.721864449057614e-06,
+      "loss": 0.1599,
+      "step": 295
+    },
+    {
+      "epoch": 1.5804749340369393,
+      "grad_norm": 4.9031877517700195,
+      "learning_rate": 8.659899364014309e-06,
+      "loss": 0.154,
+      "step": 300
+    },
+    {
+      "epoch": 1.6068601583113455,
+      "grad_norm": 7.324002265930176,
+      "learning_rate": 8.596699001693257e-06,
+      "loss": 0.2359,
+      "step": 305
+    },
+    {
+      "epoch": 1.633245382585752,
+      "grad_norm": 6.51141881942749,
+      "learning_rate": 8.532284693274293e-06,
+      "loss": 0.2,
+      "step": 310
+    },
+    {
+      "epoch": 1.6596306068601583,
+      "grad_norm": 7.332818031311035,
+      "learning_rate": 8.466678179664378e-06,
+      "loss": 0.1767,
+      "step": 315
+    },
+    {
+      "epoch": 1.6860158311345645,
+      "grad_norm": 6.019137859344482,
+      "learning_rate": 8.39990160415967e-06,
+      "loss": 0.1794,
+      "step": 320
+    },
+    {
+      "epoch": 1.712401055408971,
+      "grad_norm": 6.589385986328125,
+      "learning_rate": 8.331977504971801e-06,
+      "loss": 0.1579,
+      "step": 325
+    },
+    {
+      "epoch": 1.7387862796833773,
+      "grad_norm": 9.24649429321289,
+      "learning_rate": 8.262928807620843e-06,
+      "loss": 0.1548,
+      "step": 330
+    },
+    {
+      "epoch": 1.7651715039577835,
+      "grad_norm": 6.103082180023193,
+      "learning_rate": 8.192778817197569e-06,
+      "loss": 0.1608,
+      "step": 335
+    },
+    {
+      "epoch": 1.79155672823219,
+      "grad_norm": 6.764271259307861,
+      "learning_rate": 8.12155121049759e-06,
+      "loss": 0.1456,
+      "step": 340
+    },
+    {
+      "epoch": 1.8179419525065963,
+      "grad_norm": 6.516699314117432,
+      "learning_rate": 8.049270028030045e-06,
+      "loss": 0.1675,
+      "step": 345
+    },
+    {
+      "epoch": 1.8443271767810026,
+      "grad_norm": 4.027854919433594,
+      "learning_rate": 7.975959665903526e-06,
+      "loss": 0.1311,
+      "step": 350
+    },
+    {
+      "epoch": 1.870712401055409,
+      "grad_norm": 4.875086784362793,
+      "learning_rate": 7.901644867591976e-06,
+      "loss": 0.1174,
+      "step": 355
+    },
+    {
+      "epoch": 1.8970976253298153,
+      "grad_norm": 5.186245441436768,
+      "learning_rate": 7.82635071558336e-06,
+      "loss": 0.0908,
+      "step": 360
+    },
+    {
+      "epoch": 1.9234828496042216,
+      "grad_norm": 4.586931228637695,
+      "learning_rate": 7.750102622913907e-06,
+      "loss": 0.1033,
+      "step": 365
+    },
+    {
+      "epoch": 1.949868073878628,
+      "grad_norm": 5.11731481552124,
+      "learning_rate": 7.672926324590778e-06,
+      "loss": 0.0793,
+      "step": 370
+    },
+    {
+      "epoch": 1.9762532981530343,
+      "grad_norm": 4.95916223526001,
+      "learning_rate": 7.594847868906076e-06,
+      "loss": 0.0849,
+      "step": 375
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 4.0288472175598145,
+      "learning_rate": 7.51589360864511e-06,
+      "loss": 0.0836,
+      "step": 380
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 950,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.180251151961948e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}