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 +1,27 @@
+{
+  "_name_or_path": "mistralai/Mistral-Small-24B-Instruct-2501",
+  "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": 32768,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 100000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0.dev0",
+  "use_cache": false,
+  "vocab_size": 131072
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "temperature": 0.15,
+  "transformers_version": "4.49.0.dev0"
+}

model-00001-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0bcf35d12ff37cf69dd09444517e1a6d0a44c9694c9d3b55ea9b0b3f0355ed0
+size 4781571736

model-00002-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67cdc0501f16a525d0bb43d3b6e65ba30da9eeb4207a0c5780a11f61f1d8d163
+size 4781592784

model-00003-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a206b5c868020535ad8f7b41c2e9bbcbaded994b300c246a444cfa9f61e84944
+size 4781592800

model-00004-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f395f6920b3f9fcb7e100906ffea53105501a73c667b6b44c10eb7426e9c0a53
+size 4886471600

model-00005-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8187236e597990d89571920381f39cd420854db1c9fbb0027fc4535668c78c7f
+size 4781592824

model-00006-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6e9221fd04b08475d89b21103889ad81004ef29cc2b7dd7f5208e1583f83ccc
+size 4781592816

model-00007-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:435fcf5079d31307096d4cb6a3beb610bcba1519c33d221ff538f96c10e027a4
+size 4886471600

model-00008-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f178b2ab96a24fde7ad2fcd4b2d326458c864775cf3cc4666dcc6be6fa671730
+size 4781592824

model-00009-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3957fc75c7f1d68afb97414654f144ed52241094ab3f017dcc94dbbf3c1430d0
+size 4781592816

model-00010-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:605d522736224363ea042fcffd316d1ecf399e0b51558f54dd065fea4b2d37fc
+size 3900777072

model.safetensors.index.json

@@ -0,0 +1,370 @@
+{
+  "metadata": {
+    "total_size": 47144806400
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00010-of-00010.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.norm.weight": "model-00010-of-00010.safetensors"
+  }
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df5241d096dfc14e65ed605e11f0bd49844990a98f2fd9d3b114957fdda14428
+size 936

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cf9097d4513154245c48236b6ec5137b7ee2a21c9f58f2cba798ea275c6026f
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54ead2a85729b37e7e4468371ab582795eec042a33ea5bd036a849ffd4bcb78d
+size 1000

special_tokens_map.json

@@ -0,0 +1,1026 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>",
+    "[INST]",
+    "[/INST]",
+    "[AVAILABLE_TOOLS]",
+    "[/AVAILABLE_TOOLS]",
+    "[TOOL_RESULTS]",
+    "[/TOOL_RESULTS]",
+    "[TOOL_CALLS]",
+    "[IMG]",
+    "<pad>",
+    "[IMG_BREAK]",
+    "[IMG_END]",
+    "[PREFIX]",
+    "[MIDDLE]",
+    "[SUFFIX]",
+    "[SYSTEM_PROMPT]",
+    "[/SYSTEM_PROMPT]",
+    "[TOOL_CONTENT]",
+    "<SPECIAL_20>",
+    "<SPECIAL_21>",
+    "<SPECIAL_22>",
+    "<SPECIAL_23>",
+    "<SPECIAL_24>",
+    "<SPECIAL_25>",
+    "<SPECIAL_26>",
+    "<SPECIAL_27>",
+    "<SPECIAL_28>",
+    "<SPECIAL_29>",
+    "<SPECIAL_30>",
+    "<SPECIAL_31>",
+    "<SPECIAL_32>",
+    "<SPECIAL_33>",
+    "<SPECIAL_34>",
+    "<SPECIAL_35>",
+    "<SPECIAL_36>",
+    "<SPECIAL_37>",
+    "<SPECIAL_38>",
+    "<SPECIAL_39>",
+    "<SPECIAL_40>",
+    "<SPECIAL_41>",
+    "<SPECIAL_42>",
+    "<SPECIAL_43>",
+    "<SPECIAL_44>",
+    "<SPECIAL_45>",
+    "<SPECIAL_46>",
+    "<SPECIAL_47>",
+    "<SPECIAL_48>",
+    "<SPECIAL_49>",
+    "<SPECIAL_50>",
+    "<SPECIAL_51>",
+    "<SPECIAL_52>",
+    "<SPECIAL_53>",
+    "<SPECIAL_54>",
+    "<SPECIAL_55>",
+    "<SPECIAL_56>",
+    "<SPECIAL_57>",
+    "<SPECIAL_58>",
+    "<SPECIAL_59>",
+    "<SPECIAL_60>",
+    "<SPECIAL_61>",
+    "<SPECIAL_62>",
+    "<SPECIAL_63>",
+    "<SPECIAL_64>",
+    "<SPECIAL_65>",
+    "<SPECIAL_66>",
+    "<SPECIAL_67>",
+    "<SPECIAL_68>",
+    "<SPECIAL_69>",
+    "<SPECIAL_70>",
+    "<SPECIAL_71>",
+    "<SPECIAL_72>",
+    "<SPECIAL_73>",
+    "<SPECIAL_74>",
+    "<SPECIAL_75>",
+    "<SPECIAL_76>",
+    "<SPECIAL_77>",
+    "<SPECIAL_78>",
+    "<SPECIAL_79>",
+    "<SPECIAL_80>",
+    "<SPECIAL_81>",
+    "<SPECIAL_82>",
+    "<SPECIAL_83>",
+    "<SPECIAL_84>",
+    "<SPECIAL_85>",
+    "<SPECIAL_86>",
+    "<SPECIAL_87>",
+    "<SPECIAL_88>",
+    "<SPECIAL_89>",
+    "<SPECIAL_90>",
+    "<SPECIAL_91>",
+    "<SPECIAL_92>",
+    "<SPECIAL_93>",
+    "<SPECIAL_94>",
+    "<SPECIAL_95>",
+    "<SPECIAL_96>",
+    "<SPECIAL_97>",
+    "<SPECIAL_98>",
+    "<SPECIAL_99>",
+    "<SPECIAL_100>",
+    "<SPECIAL_101>",
+    "<SPECIAL_102>",
+    "<SPECIAL_103>",
+    "<SPECIAL_104>",
+    "<SPECIAL_105>",
+    "<SPECIAL_106>",
+    "<SPECIAL_107>",
+    "<SPECIAL_108>",
+    "<SPECIAL_109>",
+    "<SPECIAL_110>",
+    "<SPECIAL_111>",
+    "<SPECIAL_112>",
+    "<SPECIAL_113>",
+    "<SPECIAL_114>",
+    "<SPECIAL_115>",
+    "<SPECIAL_116>",
+    "<SPECIAL_117>",
+    "<SPECIAL_118>",
+    "<SPECIAL_119>",
+    "<SPECIAL_120>",
+    "<SPECIAL_121>",
+    "<SPECIAL_122>",
+    "<SPECIAL_123>",
+    "<SPECIAL_124>",
+    "<SPECIAL_125>",
+    "<SPECIAL_126>",
+    "<SPECIAL_127>",
+    "<SPECIAL_128>",
+    "<SPECIAL_129>",
+    "<SPECIAL_130>",
+    "<SPECIAL_131>",
+    "<SPECIAL_132>",
+    "<SPECIAL_133>",
+    "<SPECIAL_134>",
+    "<SPECIAL_135>",
+    "<SPECIAL_136>",
+    "<SPECIAL_137>",
+    "<SPECIAL_138>",
+    "<SPECIAL_139>",
+    "<SPECIAL_140>",
+    "<SPECIAL_141>",
+    "<SPECIAL_142>",
+    "<SPECIAL_143>",
+    "<SPECIAL_144>",
+    "<SPECIAL_145>",
+    "<SPECIAL_146>",
+    "<SPECIAL_147>",
+    "<SPECIAL_148>",
+    "<SPECIAL_149>",
+    "<SPECIAL_150>",
+    "<SPECIAL_151>",
+    "<SPECIAL_152>",
+    "<SPECIAL_153>",
+    "<SPECIAL_154>",
+    "<SPECIAL_155>",
+    "<SPECIAL_156>",
+    "<SPECIAL_157>",
+    "<SPECIAL_158>",
+    "<SPECIAL_159>",
+    "<SPECIAL_160>",
+    "<SPECIAL_161>",
+    "<SPECIAL_162>",
+    "<SPECIAL_163>",
+    "<SPECIAL_164>",
+    "<SPECIAL_165>",
+    "<SPECIAL_166>",
+    "<SPECIAL_167>",
+    "<SPECIAL_168>",
+    "<SPECIAL_169>",
+    "<SPECIAL_170>",
+    "<SPECIAL_171>",
+    "<SPECIAL_172>",
+    "<SPECIAL_173>",
+    "<SPECIAL_174>",
+    "<SPECIAL_175>",
+    "<SPECIAL_176>",
+    "<SPECIAL_177>",
+    "<SPECIAL_178>",
+    "<SPECIAL_179>",
+    "<SPECIAL_180>",
+    "<SPECIAL_181>",
+    "<SPECIAL_182>",
+    "<SPECIAL_183>",
+    "<SPECIAL_184>",
+    "<SPECIAL_185>",
+    "<SPECIAL_186>",
+    "<SPECIAL_187>",
+    "<SPECIAL_188>",
+    "<SPECIAL_189>",
+    "<SPECIAL_190>",
+    "<SPECIAL_191>",
+    "<SPECIAL_192>",
+    "<SPECIAL_193>",
+    "<SPECIAL_194>",
+    "<SPECIAL_195>",
+    "<SPECIAL_196>",
+    "<SPECIAL_197>",
+    "<SPECIAL_198>",
+    "<SPECIAL_199>",
+    "<SPECIAL_200>",
+    "<SPECIAL_201>",
+    "<SPECIAL_202>",
+    "<SPECIAL_203>",
+    "<SPECIAL_204>",
+    "<SPECIAL_205>",
+    "<SPECIAL_206>",
+    "<SPECIAL_207>",
+    "<SPECIAL_208>",
+    "<SPECIAL_209>",
+    "<SPECIAL_210>",
+    "<SPECIAL_211>",
+    "<SPECIAL_212>",
+    "<SPECIAL_213>",
+    "<SPECIAL_214>",
+    "<SPECIAL_215>",
+    "<SPECIAL_216>",
+    "<SPECIAL_217>",
+    "<SPECIAL_218>",
+    "<SPECIAL_219>",
+    "<SPECIAL_220>",
+    "<SPECIAL_221>",
+    "<SPECIAL_222>",
+    "<SPECIAL_223>",
+    "<SPECIAL_224>",
+    "<SPECIAL_225>",
+    "<SPECIAL_226>",
+    "<SPECIAL_227>",
+    "<SPECIAL_228>",
+    "<SPECIAL_229>",
+    "<SPECIAL_230>",
+    "<SPECIAL_231>",
+    "<SPECIAL_232>",
+    "<SPECIAL_233>",
+    "<SPECIAL_234>",
+    "<SPECIAL_235>",
+    "<SPECIAL_236>",
+    "<SPECIAL_237>",
+    "<SPECIAL_238>",
+    "<SPECIAL_239>",
+    "<SPECIAL_240>",
+    "<SPECIAL_241>",
+    "<SPECIAL_242>",
+    "<SPECIAL_243>",
+    "<SPECIAL_244>",
+    "<SPECIAL_245>",
+    "<SPECIAL_246>",
+    "<SPECIAL_247>",
+    "<SPECIAL_248>",
+    "<SPECIAL_249>",
+    "<SPECIAL_250>",
+    "<SPECIAL_251>",
+    "<SPECIAL_252>",
+    "<SPECIAL_253>",
+    "<SPECIAL_254>",
+    "<SPECIAL_255>",
+    "<SPECIAL_256>",
+    "<SPECIAL_257>",
+    "<SPECIAL_258>",
+    "<SPECIAL_259>",
+    "<SPECIAL_260>",
+    "<SPECIAL_261>",
+    "<SPECIAL_262>",
+    "<SPECIAL_263>",
+    "<SPECIAL_264>",
+    "<SPECIAL_265>",
+    "<SPECIAL_266>",
+    "<SPECIAL_267>",
+    "<SPECIAL_268>",
+    "<SPECIAL_269>",
+    "<SPECIAL_270>",
+    "<SPECIAL_271>",
+    "<SPECIAL_272>",
+    "<SPECIAL_273>",
+    "<SPECIAL_274>",
+    "<SPECIAL_275>",
+    "<SPECIAL_276>",
+    "<SPECIAL_277>",
+    "<SPECIAL_278>",
+    "<SPECIAL_279>",
+    "<SPECIAL_280>",
+    "<SPECIAL_281>",
+    "<SPECIAL_282>",
+    "<SPECIAL_283>",
+    "<SPECIAL_284>",
+    "<SPECIAL_285>",
+    "<SPECIAL_286>",
+    "<SPECIAL_287>",
+    "<SPECIAL_288>",
+    "<SPECIAL_289>",
+    "<SPECIAL_290>",
+    "<SPECIAL_291>",
+    "<SPECIAL_292>",
+    "<SPECIAL_293>",
+    "<SPECIAL_294>",
+    "<SPECIAL_295>",
+    "<SPECIAL_296>",
+    "<SPECIAL_297>",
+    "<SPECIAL_298>",
+    "<SPECIAL_299>",
+    "<SPECIAL_300>",
+    "<SPECIAL_301>",
+    "<SPECIAL_302>",
+    "<SPECIAL_303>",
+    "<SPECIAL_304>",
+    "<SPECIAL_305>",
+    "<SPECIAL_306>",
+    "<SPECIAL_307>",
+    "<SPECIAL_308>",
+    "<SPECIAL_309>",
+    "<SPECIAL_310>",
+    "<SPECIAL_311>",
+    "<SPECIAL_312>",
+    "<SPECIAL_313>",
+    "<SPECIAL_314>",
+    "<SPECIAL_315>",
+    "<SPECIAL_316>",
+    "<SPECIAL_317>",
+    "<SPECIAL_318>",
+    "<SPECIAL_319>",
+    "<SPECIAL_320>",
+    "<SPECIAL_321>",
+    "<SPECIAL_322>",
+    "<SPECIAL_323>",
+    "<SPECIAL_324>",
+    "<SPECIAL_325>",
+    "<SPECIAL_326>",
+    "<SPECIAL_327>",
+    "<SPECIAL_328>",
+    "<SPECIAL_329>",
+    "<SPECIAL_330>",
+    "<SPECIAL_331>",
+    "<SPECIAL_332>",
+    "<SPECIAL_333>",
+    "<SPECIAL_334>",
+    "<SPECIAL_335>",
+    "<SPECIAL_336>",
+    "<SPECIAL_337>",
+    "<SPECIAL_338>",
+    "<SPECIAL_339>",
+    "<SPECIAL_340>",
+    "<SPECIAL_341>",
+    "<SPECIAL_342>",
+    "<SPECIAL_343>",
+    "<SPECIAL_344>",
+    "<SPECIAL_345>",
+    "<SPECIAL_346>",
+    "<SPECIAL_347>",
+    "<SPECIAL_348>",
+    "<SPECIAL_349>",
+    "<SPECIAL_350>",
+    "<SPECIAL_351>",
+    "<SPECIAL_352>",
+    "<SPECIAL_353>",
+    "<SPECIAL_354>",
+    "<SPECIAL_355>",
+    "<SPECIAL_356>",
+    "<SPECIAL_357>",
+    "<SPECIAL_358>",
+    "<SPECIAL_359>",
+    "<SPECIAL_360>",
+    "<SPECIAL_361>",
+    "<SPECIAL_362>",
+    "<SPECIAL_363>",
+    "<SPECIAL_364>",
+    "<SPECIAL_365>",
+    "<SPECIAL_366>",
+    "<SPECIAL_367>",
+    "<SPECIAL_368>",
+    "<SPECIAL_369>",
+    "<SPECIAL_370>",
+    "<SPECIAL_371>",
+    "<SPECIAL_372>",
+    "<SPECIAL_373>",
+    "<SPECIAL_374>",
+    "<SPECIAL_375>",
+    "<SPECIAL_376>",
+    "<SPECIAL_377>",
+    "<SPECIAL_378>",
+    "<SPECIAL_379>",
+    "<SPECIAL_380>",
+    "<SPECIAL_381>",
+    "<SPECIAL_382>",
+    "<SPECIAL_383>",
+    "<SPECIAL_384>",
+    "<SPECIAL_385>",
+    "<SPECIAL_386>",
+    "<SPECIAL_387>",
+    "<SPECIAL_388>",
+    "<SPECIAL_389>",
+    "<SPECIAL_390>",
+    "<SPECIAL_391>",
+    "<SPECIAL_392>",
+    "<SPECIAL_393>",
+    "<SPECIAL_394>",
+    "<SPECIAL_395>",
+    "<SPECIAL_396>",
+    "<SPECIAL_397>",
+    "<SPECIAL_398>",
+    "<SPECIAL_399>",
+    "<SPECIAL_400>",
+    "<SPECIAL_401>",
+    "<SPECIAL_402>",
+    "<SPECIAL_403>",
+    "<SPECIAL_404>",
+    "<SPECIAL_405>",
+    "<SPECIAL_406>",
+    "<SPECIAL_407>",
+    "<SPECIAL_408>",
+    "<SPECIAL_409>",
+    "<SPECIAL_410>",
+    "<SPECIAL_411>",
+    "<SPECIAL_412>",
+    "<SPECIAL_413>",
+    "<SPECIAL_414>",
+    "<SPECIAL_415>",
+    "<SPECIAL_416>",
+    "<SPECIAL_417>",
+    "<SPECIAL_418>",
+    "<SPECIAL_419>",
+    "<SPECIAL_420>",
+    "<SPECIAL_421>",
+    "<SPECIAL_422>",
+    "<SPECIAL_423>",
+    "<SPECIAL_424>",
+    "<SPECIAL_425>",
+    "<SPECIAL_426>",
+    "<SPECIAL_427>",
+    "<SPECIAL_428>",
+    "<SPECIAL_429>",
+    "<SPECIAL_430>",
+    "<SPECIAL_431>",
+    "<SPECIAL_432>",
+    "<SPECIAL_433>",
+    "<SPECIAL_434>",
+    "<SPECIAL_435>",
+    "<SPECIAL_436>",
+    "<SPECIAL_437>",
+    "<SPECIAL_438>",
+    "<SPECIAL_439>",
+    "<SPECIAL_440>",
+    "<SPECIAL_441>",
+    "<SPECIAL_442>",
+    "<SPECIAL_443>",
+    "<SPECIAL_444>",
+    "<SPECIAL_445>",
+    "<SPECIAL_446>",
+    "<SPECIAL_447>",
+    "<SPECIAL_448>",
+    "<SPECIAL_449>",
+    "<SPECIAL_450>",
+    "<SPECIAL_451>",
+    "<SPECIAL_452>",
+    "<SPECIAL_453>",
+    "<SPECIAL_454>",
+    "<SPECIAL_455>",
+    "<SPECIAL_456>",
+    "<SPECIAL_457>",
+    "<SPECIAL_458>",
+    "<SPECIAL_459>",
+    "<SPECIAL_460>",
+    "<SPECIAL_461>",
+    "<SPECIAL_462>",
+    "<SPECIAL_463>",
+    "<SPECIAL_464>",
+    "<SPECIAL_465>",
+    "<SPECIAL_466>",
+    "<SPECIAL_467>",
+    "<SPECIAL_468>",
+    "<SPECIAL_469>",
+    "<SPECIAL_470>",
+    "<SPECIAL_471>",
+    "<SPECIAL_472>",
+    "<SPECIAL_473>",
+    "<SPECIAL_474>",
+    "<SPECIAL_475>",
+    "<SPECIAL_476>",
+    "<SPECIAL_477>",
+    "<SPECIAL_478>",
+    "<SPECIAL_479>",
+    "<SPECIAL_480>",
+    "<SPECIAL_481>",
+    "<SPECIAL_482>",
+    "<SPECIAL_483>",
+    "<SPECIAL_484>",
+    "<SPECIAL_485>",
+    "<SPECIAL_486>",
+    "<SPECIAL_487>",
+    "<SPECIAL_488>",
+    "<SPECIAL_489>",
+    "<SPECIAL_490>",
+    "<SPECIAL_491>",
+    "<SPECIAL_492>",
+    "<SPECIAL_493>",
+    "<SPECIAL_494>",
+    "<SPECIAL_495>",
+    "<SPECIAL_496>",
+    "<SPECIAL_497>",
+    "<SPECIAL_498>",
+    "<SPECIAL_499>",
+    "<SPECIAL_500>",
+    "<SPECIAL_501>",
+    "<SPECIAL_502>",
+    "<SPECIAL_503>",
+    "<SPECIAL_504>",
+    "<SPECIAL_505>",
+    "<SPECIAL_506>",
+    "<SPECIAL_507>",
+    "<SPECIAL_508>",
+    "<SPECIAL_509>",
+    "<SPECIAL_510>",
+    "<SPECIAL_511>",
+    "<SPECIAL_512>",
+    "<SPECIAL_513>",
+    "<SPECIAL_514>",
+    "<SPECIAL_515>",
+    "<SPECIAL_516>",
+    "<SPECIAL_517>",
+    "<SPECIAL_518>",
+    "<SPECIAL_519>",
+    "<SPECIAL_520>",
+    "<SPECIAL_521>",
+    "<SPECIAL_522>",
+    "<SPECIAL_523>",
+    "<SPECIAL_524>",
+    "<SPECIAL_525>",
+    "<SPECIAL_526>",
+    "<SPECIAL_527>",
+    "<SPECIAL_528>",
+    "<SPECIAL_529>",
+    "<SPECIAL_530>",
+    "<SPECIAL_531>",
+    "<SPECIAL_532>",
+    "<SPECIAL_533>",
+    "<SPECIAL_534>",
+    "<SPECIAL_535>",
+    "<SPECIAL_536>",
+    "<SPECIAL_537>",
+    "<SPECIAL_538>",
+    "<SPECIAL_539>",
+    "<SPECIAL_540>",
+    "<SPECIAL_541>",
+    "<SPECIAL_542>",
+    "<SPECIAL_543>",
+    "<SPECIAL_544>",
+    "<SPECIAL_545>",
+    "<SPECIAL_546>",
+    "<SPECIAL_547>",
+    "<SPECIAL_548>",
+    "<SPECIAL_549>",
+    "<SPECIAL_550>",
+    "<SPECIAL_551>",
+    "<SPECIAL_552>",
+    "<SPECIAL_553>",
+    "<SPECIAL_554>",
+    "<SPECIAL_555>",
+    "<SPECIAL_556>",
+    "<SPECIAL_557>",
+    "<SPECIAL_558>",
+    "<SPECIAL_559>",
+    "<SPECIAL_560>",
+    "<SPECIAL_561>",
+    "<SPECIAL_562>",
+    "<SPECIAL_563>",
+    "<SPECIAL_564>",
+    "<SPECIAL_565>",
+    "<SPECIAL_566>",
+    "<SPECIAL_567>",
+    "<SPECIAL_568>",
+    "<SPECIAL_569>",
+    "<SPECIAL_570>",
+    "<SPECIAL_571>",
+    "<SPECIAL_572>",
+    "<SPECIAL_573>",
+    "<SPECIAL_574>",
+    "<SPECIAL_575>",
+    "<SPECIAL_576>",
+    "<SPECIAL_577>",
+    "<SPECIAL_578>",
+    "<SPECIAL_579>",
+    "<SPECIAL_580>",
+    "<SPECIAL_581>",
+    "<SPECIAL_582>",
+    "<SPECIAL_583>",
+    "<SPECIAL_584>",
+    "<SPECIAL_585>",
+    "<SPECIAL_586>",
+    "<SPECIAL_587>",
+    "<SPECIAL_588>",
+    "<SPECIAL_589>",
+    "<SPECIAL_590>",
+    "<SPECIAL_591>",
+    "<SPECIAL_592>",
+    "<SPECIAL_593>",
+    "<SPECIAL_594>",
+    "<SPECIAL_595>",
+    "<SPECIAL_596>",
+    "<SPECIAL_597>",
+    "<SPECIAL_598>",
+    "<SPECIAL_599>",
+    "<SPECIAL_600>",
+    "<SPECIAL_601>",
+    "<SPECIAL_602>",
+    "<SPECIAL_603>",
+    "<SPECIAL_604>",
+    "<SPECIAL_605>",
+    "<SPECIAL_606>",
+    "<SPECIAL_607>",
+    "<SPECIAL_608>",
+    "<SPECIAL_609>",
+    "<SPECIAL_610>",
+    "<SPECIAL_611>",
+    "<SPECIAL_612>",
+    "<SPECIAL_613>",
+    "<SPECIAL_614>",
+    "<SPECIAL_615>",
+    "<SPECIAL_616>",
+    "<SPECIAL_617>",
+    "<SPECIAL_618>",
+    "<SPECIAL_619>",
+    "<SPECIAL_620>",
+    "<SPECIAL_621>",
+    "<SPECIAL_622>",
+    "<SPECIAL_623>",
+    "<SPECIAL_624>",
+    "<SPECIAL_625>",
+    "<SPECIAL_626>",
+    "<SPECIAL_627>",
+    "<SPECIAL_628>",
+    "<SPECIAL_629>",
+    "<SPECIAL_630>",
+    "<SPECIAL_631>",
+    "<SPECIAL_632>",
+    "<SPECIAL_633>",
+    "<SPECIAL_634>",
+    "<SPECIAL_635>",
+    "<SPECIAL_636>",
+    "<SPECIAL_637>",
+    "<SPECIAL_638>",
+    "<SPECIAL_639>",
+    "<SPECIAL_640>",
+    "<SPECIAL_641>",
+    "<SPECIAL_642>",
+    "<SPECIAL_643>",
+    "<SPECIAL_644>",
+    "<SPECIAL_645>",
+    "<SPECIAL_646>",
+    "<SPECIAL_647>",
+    "<SPECIAL_648>",
+    "<SPECIAL_649>",
+    "<SPECIAL_650>",
+    "<SPECIAL_651>",
+    "<SPECIAL_652>",
+    "<SPECIAL_653>",
+    "<SPECIAL_654>",
+    "<SPECIAL_655>",
+    "<SPECIAL_656>",
+    "<SPECIAL_657>",
+    "<SPECIAL_658>",
+    "<SPECIAL_659>",
+    "<SPECIAL_660>",
+    "<SPECIAL_661>",
+    "<SPECIAL_662>",
+    "<SPECIAL_663>",
+    "<SPECIAL_664>",
+    "<SPECIAL_665>",
+    "<SPECIAL_666>",
+    "<SPECIAL_667>",
+    "<SPECIAL_668>",
+    "<SPECIAL_669>",
+    "<SPECIAL_670>",
+    "<SPECIAL_671>",
+    "<SPECIAL_672>",
+    "<SPECIAL_673>",
+    "<SPECIAL_674>",
+    "<SPECIAL_675>",
+    "<SPECIAL_676>",
+    "<SPECIAL_677>",
+    "<SPECIAL_678>",
+    "<SPECIAL_679>",
+    "<SPECIAL_680>",
+    "<SPECIAL_681>",
+    "<SPECIAL_682>",
+    "<SPECIAL_683>",
+    "<SPECIAL_684>",
+    "<SPECIAL_685>",
+    "<SPECIAL_686>",
+    "<SPECIAL_687>",
+    "<SPECIAL_688>",
+    "<SPECIAL_689>",
+    "<SPECIAL_690>",
+    "<SPECIAL_691>",
+    "<SPECIAL_692>",
+    "<SPECIAL_693>",
+    "<SPECIAL_694>",
+    "<SPECIAL_695>",
+    "<SPECIAL_696>",
+    "<SPECIAL_697>",
+    "<SPECIAL_698>",
+    "<SPECIAL_699>",
+    "<SPECIAL_700>",
+    "<SPECIAL_701>",
+    "<SPECIAL_702>",
+    "<SPECIAL_703>",
+    "<SPECIAL_704>",
+    "<SPECIAL_705>",
+    "<SPECIAL_706>",
+    "<SPECIAL_707>",
+    "<SPECIAL_708>",
+    "<SPECIAL_709>",
+    "<SPECIAL_710>",
+    "<SPECIAL_711>",
+    "<SPECIAL_712>",
+    "<SPECIAL_713>",
+    "<SPECIAL_714>",
+    "<SPECIAL_715>",
+    "<SPECIAL_716>",
+    "<SPECIAL_717>",
+    "<SPECIAL_718>",
+    "<SPECIAL_719>",
+    "<SPECIAL_720>",
+    "<SPECIAL_721>",
+    "<SPECIAL_722>",
+    "<SPECIAL_723>",
+    "<SPECIAL_724>",
+    "<SPECIAL_725>",
+    "<SPECIAL_726>",
+    "<SPECIAL_727>",
+    "<SPECIAL_728>",
+    "<SPECIAL_729>",
+    "<SPECIAL_730>",
+    "<SPECIAL_731>",
+    "<SPECIAL_732>",
+    "<SPECIAL_733>",
+    "<SPECIAL_734>",
+    "<SPECIAL_735>",
+    "<SPECIAL_736>",
+    "<SPECIAL_737>",
+    "<SPECIAL_738>",
+    "<SPECIAL_739>",
+    "<SPECIAL_740>",
+    "<SPECIAL_741>",
+    "<SPECIAL_742>",
+    "<SPECIAL_743>",
+    "<SPECIAL_744>",
+    "<SPECIAL_745>",
+    "<SPECIAL_746>",
+    "<SPECIAL_747>",
+    "<SPECIAL_748>",
+    "<SPECIAL_749>",
+    "<SPECIAL_750>",
+    "<SPECIAL_751>",
+    "<SPECIAL_752>",
+    "<SPECIAL_753>",
+    "<SPECIAL_754>",
+    "<SPECIAL_755>",
+    "<SPECIAL_756>",
+    "<SPECIAL_757>",
+    "<SPECIAL_758>",
+    "<SPECIAL_759>",
+    "<SPECIAL_760>",
+    "<SPECIAL_761>",
+    "<SPECIAL_762>",
+    "<SPECIAL_763>",
+    "<SPECIAL_764>",
+    "<SPECIAL_765>",
+    "<SPECIAL_766>",
+    "<SPECIAL_767>",
+    "<SPECIAL_768>",
+    "<SPECIAL_769>",
+    "<SPECIAL_770>",
+    "<SPECIAL_771>",
+    "<SPECIAL_772>",
+    "<SPECIAL_773>",
+    "<SPECIAL_774>",
+    "<SPECIAL_775>",
+    "<SPECIAL_776>",
+    "<SPECIAL_777>",
+    "<SPECIAL_778>",
+    "<SPECIAL_779>",
+    "<SPECIAL_780>",
+    "<SPECIAL_781>",
+    "<SPECIAL_782>",
+    "<SPECIAL_783>",
+    "<SPECIAL_784>",
+    "<SPECIAL_785>",
+    "<SPECIAL_786>",
+    "<SPECIAL_787>",
+    "<SPECIAL_788>",
+    "<SPECIAL_789>",
+    "<SPECIAL_790>",
+    "<SPECIAL_791>",
+    "<SPECIAL_792>",
+    "<SPECIAL_793>",
+    "<SPECIAL_794>",
+    "<SPECIAL_795>",
+    "<SPECIAL_796>",
+    "<SPECIAL_797>",
+    "<SPECIAL_798>",
+    "<SPECIAL_799>",
+    "<SPECIAL_800>",
+    "<SPECIAL_801>",
+    "<SPECIAL_802>",
+    "<SPECIAL_803>",
+    "<SPECIAL_804>",
+    "<SPECIAL_805>",
+    "<SPECIAL_806>",
+    "<SPECIAL_807>",
+    "<SPECIAL_808>",
+    "<SPECIAL_809>",
+    "<SPECIAL_810>",
+    "<SPECIAL_811>",
+    "<SPECIAL_812>",
+    "<SPECIAL_813>",
+    "<SPECIAL_814>",
+    "<SPECIAL_815>",
+    "<SPECIAL_816>",
+    "<SPECIAL_817>",
+    "<SPECIAL_818>",
+    "<SPECIAL_819>",
+    "<SPECIAL_820>",
+    "<SPECIAL_821>",
+    "<SPECIAL_822>",
+    "<SPECIAL_823>",
+    "<SPECIAL_824>",
+    "<SPECIAL_825>",
+    "<SPECIAL_826>",
+    "<SPECIAL_827>",
+    "<SPECIAL_828>",
+    "<SPECIAL_829>",
+    "<SPECIAL_830>",
+    "<SPECIAL_831>",
+    "<SPECIAL_832>",
+    "<SPECIAL_833>",
+    "<SPECIAL_834>",
+    "<SPECIAL_835>",
+    "<SPECIAL_836>",
+    "<SPECIAL_837>",
+    "<SPECIAL_838>",
+    "<SPECIAL_839>",
+    "<SPECIAL_840>",
+    "<SPECIAL_841>",
+    "<SPECIAL_842>",
+    "<SPECIAL_843>",
+    "<SPECIAL_844>",
+    "<SPECIAL_845>",
+    "<SPECIAL_846>",
+    "<SPECIAL_847>",
+    "<SPECIAL_848>",
+    "<SPECIAL_849>",
+    "<SPECIAL_850>",
+    "<SPECIAL_851>",
+    "<SPECIAL_852>",
+    "<SPECIAL_853>",
+    "<SPECIAL_854>",
+    "<SPECIAL_855>",
+    "<SPECIAL_856>",
+    "<SPECIAL_857>",
+    "<SPECIAL_858>",
+    "<SPECIAL_859>",
+    "<SPECIAL_860>",
+    "<SPECIAL_861>",
+    "<SPECIAL_862>",
+    "<SPECIAL_863>",
+    "<SPECIAL_864>",
+    "<SPECIAL_865>",
+    "<SPECIAL_866>",
+    "<SPECIAL_867>",
+    "<SPECIAL_868>",
+    "<SPECIAL_869>",
+    "<SPECIAL_870>",
+    "<SPECIAL_871>",
+    "<SPECIAL_872>",
+    "<SPECIAL_873>",
+    "<SPECIAL_874>",
+    "<SPECIAL_875>",
+    "<SPECIAL_876>",
+    "<SPECIAL_877>",
+    "<SPECIAL_878>",
+    "<SPECIAL_879>",
+    "<SPECIAL_880>",
+    "<SPECIAL_881>",
+    "<SPECIAL_882>",
+    "<SPECIAL_883>",
+    "<SPECIAL_884>",
+    "<SPECIAL_885>",
+    "<SPECIAL_886>",
+    "<SPECIAL_887>",
+    "<SPECIAL_888>",
+    "<SPECIAL_889>",
+    "<SPECIAL_890>",
+    "<SPECIAL_891>",
+    "<SPECIAL_892>",
+    "<SPECIAL_893>",
+    "<SPECIAL_894>",
+    "<SPECIAL_895>",
+    "<SPECIAL_896>",
+    "<SPECIAL_897>",
+    "<SPECIAL_898>",
+    "<SPECIAL_899>",
+    "<SPECIAL_900>",
+    "<SPECIAL_901>",
+    "<SPECIAL_902>",
+    "<SPECIAL_903>",
+    "<SPECIAL_904>",
+    "<SPECIAL_905>",
+    "<SPECIAL_906>",
+    "<SPECIAL_907>",
+    "<SPECIAL_908>",
+    "<SPECIAL_909>",
+    "<SPECIAL_910>",
+    "<SPECIAL_911>",
+    "<SPECIAL_912>",
+    "<SPECIAL_913>",
+    "<SPECIAL_914>",
+    "<SPECIAL_915>",
+    "<SPECIAL_916>",
+    "<SPECIAL_917>",
+    "<SPECIAL_918>",
+    "<SPECIAL_919>",
+    "<SPECIAL_920>",
+    "<SPECIAL_921>",
+    "<SPECIAL_922>",
+    "<SPECIAL_923>",
+    "<SPECIAL_924>",
+    "<SPECIAL_925>",
+    "<SPECIAL_926>",
+    "<SPECIAL_927>",
+    "<SPECIAL_928>",
+    "<SPECIAL_929>",
+    "<SPECIAL_930>",
+    "<SPECIAL_931>",
+    "<SPECIAL_932>",
+    "<SPECIAL_933>",
+    "<SPECIAL_934>",
+    "<SPECIAL_935>",
+    "<SPECIAL_936>",
+    "<SPECIAL_937>",
+    "<SPECIAL_938>",
+    "<SPECIAL_939>",
+    "<SPECIAL_940>",
+    "<SPECIAL_941>",
+    "<SPECIAL_942>",
+    "<SPECIAL_943>",
+    "<SPECIAL_944>",
+    "<SPECIAL_945>",
+    "<SPECIAL_946>",
+    "<SPECIAL_947>",
+    "<SPECIAL_948>",
+    "<SPECIAL_949>",
+    "<SPECIAL_950>",
+    "<SPECIAL_951>",
+    "<SPECIAL_952>",
+    "<SPECIAL_953>",
+    "<SPECIAL_954>",
+    "<SPECIAL_955>",
+    "<SPECIAL_956>",
+    "<SPECIAL_957>",
+    "<SPECIAL_958>",
+    "<SPECIAL_959>",
+    "<SPECIAL_960>",
+    "<SPECIAL_961>",
+    "<SPECIAL_962>",
+    "<SPECIAL_963>",
+    "<SPECIAL_964>",
+    "<SPECIAL_965>",
+    "<SPECIAL_966>",
+    "<SPECIAL_967>",
+    "<SPECIAL_968>",
+    "<SPECIAL_969>",
+    "<SPECIAL_970>",
+    "<SPECIAL_971>",
+    "<SPECIAL_972>",
+    "<SPECIAL_973>",
+    "<SPECIAL_974>",
+    "<SPECIAL_975>",
+    "<SPECIAL_976>",
+    "<SPECIAL_977>",
+    "<SPECIAL_978>",
+    "<SPECIAL_979>",
+    "<SPECIAL_980>",
+    "<SPECIAL_981>",
+    "<SPECIAL_982>",
+    "<SPECIAL_983>",
+    "<SPECIAL_984>",
+    "<SPECIAL_985>",
+    "<SPECIAL_986>",
+    "<SPECIAL_987>",
+    "<SPECIAL_988>",
+    "<SPECIAL_989>",
+    "<SPECIAL_990>",
+    "<SPECIAL_991>",
+    "<SPECIAL_992>",
+    "<SPECIAL_993>",
+    "<SPECIAL_994>",
+    "<SPECIAL_995>",
+    "<SPECIAL_996>",
+    "<SPECIAL_997>",
+    "<SPECIAL_998>",
+    "<SPECIAL_999>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "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:b76085f9923309d873994d444989f7eb6ec074b06f25b58f1e8d7b7741070949
+size 17078037

trainer_state.json

@@ -0,0 +1,1937 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5,
+  "eval_steps": 500,
+  "global_step": 272,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001838235294117647,
+      "grad_norm": 0.0,
+      "learning_rate": 2.0000000000000002e-07,
+      "loss": 1.9627,
+      "step": 1
+    },
+    {
+      "epoch": 0.003676470588235294,
+      "grad_norm": 0.0,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 1.6036,
+      "step": 2
+    },
+    {
+      "epoch": 0.0055147058823529415,
+      "grad_norm": 0.0,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 1.7333,
+      "step": 3
+    },
+    {
+      "epoch": 0.007352941176470588,
+      "grad_norm": 0.0,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 1.8948,
+      "step": 4
+    },
+    {
+      "epoch": 0.009191176470588236,
+      "grad_norm": 0.0,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.9561,
+      "step": 5
+    },
+    {
+      "epoch": 0.011029411764705883,
+      "grad_norm": 0.0,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 1.9726,
+      "step": 6
+    },
+    {
+      "epoch": 0.012867647058823529,
+      "grad_norm": 0.0,
+      "learning_rate": 1.4000000000000001e-06,
+      "loss": 1.7149,
+      "step": 7
+    },
+    {
+      "epoch": 0.014705882352941176,
+      "grad_norm": 0.0,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 1.8045,
+      "step": 8
+    },
+    {
+      "epoch": 0.016544117647058824,
+      "grad_norm": 0.0,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 1.9205,
+      "step": 9
+    },
+    {
+      "epoch": 0.01838235294117647,
+      "grad_norm": 0.0,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.6752,
+      "step": 10
+    },
+    {
+      "epoch": 0.02022058823529412,
+      "grad_norm": 0.0,
+      "learning_rate": 2.2e-06,
+      "loss": 1.8202,
+      "step": 11
+    },
+    {
+      "epoch": 0.022058823529411766,
+      "grad_norm": 0.0,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 1.7398,
+      "step": 12
+    },
+    {
+      "epoch": 0.02389705882352941,
+      "grad_norm": 0.0,
+      "learning_rate": 2.6e-06,
+      "loss": 1.6544,
+      "step": 13
+    },
+    {
+      "epoch": 0.025735294117647058,
+      "grad_norm": 0.0,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 1.7692,
+      "step": 14
+    },
+    {
+      "epoch": 0.027573529411764705,
+      "grad_norm": 0.0,
+      "learning_rate": 3e-06,
+      "loss": 1.5538,
+      "step": 15
+    },
+    {
+      "epoch": 0.029411764705882353,
+      "grad_norm": 0.0,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 1.7036,
+      "step": 16
+    },
+    {
+      "epoch": 0.03125,
+      "grad_norm": 0.0,
+      "learning_rate": 3.4000000000000005e-06,
+      "loss": 1.9272,
+      "step": 17
+    },
+    {
+      "epoch": 0.03308823529411765,
+      "grad_norm": 0.0,
+      "learning_rate": 3.6000000000000003e-06,
+      "loss": 2.07,
+      "step": 18
+    },
+    {
+      "epoch": 0.034926470588235295,
+      "grad_norm": 0.0,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 1.9225,
+      "step": 19
+    },
+    {
+      "epoch": 0.03676470588235294,
+      "grad_norm": 0.0,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.826,
+      "step": 20
+    },
+    {
+      "epoch": 0.03860294117647059,
+      "grad_norm": 0.0,
+      "learning_rate": 4.2000000000000004e-06,
+      "loss": 1.8512,
+      "step": 21
+    },
+    {
+      "epoch": 0.04044117647058824,
+      "grad_norm": 0.0,
+      "learning_rate": 4.4e-06,
+      "loss": 1.8073,
+      "step": 22
+    },
+    {
+      "epoch": 0.042279411764705885,
+      "grad_norm": 0.0,
+      "learning_rate": 4.600000000000001e-06,
+      "loss": 1.7605,
+      "step": 23
+    },
+    {
+      "epoch": 0.04411764705882353,
+      "grad_norm": 0.0,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 1.7736,
+      "step": 24
+    },
+    {
+      "epoch": 0.04595588235294118,
+      "grad_norm": 0.0,
+      "learning_rate": 5e-06,
+      "loss": 1.8242,
+      "step": 25
+    },
+    {
+      "epoch": 0.04779411764705882,
+      "grad_norm": 0.0,
+      "learning_rate": 4.999989082004443e-06,
+      "loss": 1.9721,
+      "step": 26
+    },
+    {
+      "epoch": 0.04963235294117647,
+      "grad_norm": 0.0,
+      "learning_rate": 4.999956328113134e-06,
+      "loss": 1.6345,
+      "step": 27
+    },
+    {
+      "epoch": 0.051470588235294115,
+      "grad_norm": 0.0,
+      "learning_rate": 4.999901738612159e-06,
+      "loss": 1.8167,
+      "step": 28
+    },
+    {
+      "epoch": 0.05330882352941176,
+      "grad_norm": 0.0,
+      "learning_rate": 4.999825313978322e-06,
+      "loss": 1.6142,
+      "step": 29
+    },
+    {
+      "epoch": 0.05514705882352941,
+      "grad_norm": 0.0,
+      "learning_rate": 4.999727054879149e-06,
+      "loss": 1.7084,
+      "step": 30
+    },
+    {
+      "epoch": 0.05698529411764706,
+      "grad_norm": 0.0,
+      "learning_rate": 4.999606962172872e-06,
+      "loss": 1.914,
+      "step": 31
+    },
+    {
+      "epoch": 0.058823529411764705,
+      "grad_norm": 0.0,
+      "learning_rate": 4.999465036908429e-06,
+      "loss": 1.7265,
+      "step": 32
+    },
+    {
+      "epoch": 0.06066176470588235,
+      "grad_norm": 0.0,
+      "learning_rate": 4.999301280325452e-06,
+      "loss": 1.577,
+      "step": 33
+    },
+    {
+      "epoch": 0.0625,
+      "grad_norm": 0.0,
+      "learning_rate": 4.999115693854255e-06,
+      "loss": 1.5012,
+      "step": 34
+    },
+    {
+      "epoch": 0.06433823529411764,
+      "grad_norm": 0.0,
+      "learning_rate": 4.998908279115825e-06,
+      "loss": 1.8455,
+      "step": 35
+    },
+    {
+      "epoch": 0.0661764705882353,
+      "grad_norm": 0.0,
+      "learning_rate": 4.998679037921803e-06,
+      "loss": 1.6987,
+      "step": 36
+    },
+    {
+      "epoch": 0.06801470588235294,
+      "grad_norm": 0.0,
+      "learning_rate": 4.998427972274473e-06,
+      "loss": 1.7191,
+      "step": 37
+    },
+    {
+      "epoch": 0.06985294117647059,
+      "grad_norm": 0.0,
+      "learning_rate": 4.998155084366744e-06,
+      "loss": 1.9945,
+      "step": 38
+    },
+    {
+      "epoch": 0.07169117647058823,
+      "grad_norm": 0.0,
+      "learning_rate": 4.997860376582123e-06,
+      "loss": 1.802,
+      "step": 39
+    },
+    {
+      "epoch": 0.07352941176470588,
+      "grad_norm": 0.0,
+      "learning_rate": 4.997543851494709e-06,
+      "loss": 1.7097,
+      "step": 40
+    },
+    {
+      "epoch": 0.07536764705882353,
+      "grad_norm": 0.0,
+      "learning_rate": 4.9972055118691545e-06,
+      "loss": 1.5116,
+      "step": 41
+    },
+    {
+      "epoch": 0.07720588235294118,
+      "grad_norm": 0.0,
+      "learning_rate": 4.996845360660652e-06,
+      "loss": 1.7945,
+      "step": 42
+    },
+    {
+      "epoch": 0.07904411764705882,
+      "grad_norm": 0.0,
+      "learning_rate": 4.996463401014908e-06,
+      "loss": 1.6767,
+      "step": 43
+    },
+    {
+      "epoch": 0.08088235294117647,
+      "grad_norm": 0.0,
+      "learning_rate": 4.9960596362681054e-06,
+      "loss": 1.7024,
+      "step": 44
+    },
+    {
+      "epoch": 0.08272058823529412,
+      "grad_norm": 0.0,
+      "learning_rate": 4.9956340699468896e-06,
+      "loss": 1.7004,
+      "step": 45
+    },
+    {
+      "epoch": 0.08455882352941177,
+      "grad_norm": 0.0,
+      "learning_rate": 4.995186705768322e-06,
+      "loss": 1.5485,
+      "step": 46
+    },
+    {
+      "epoch": 0.08639705882352941,
+      "grad_norm": 0.0,
+      "learning_rate": 4.9947175476398606e-06,
+      "loss": 1.7182,
+      "step": 47
+    },
+    {
+      "epoch": 0.08823529411764706,
+      "grad_norm": 0.0,
+      "learning_rate": 4.994226599659319e-06,
+      "loss": 1.6924,
+      "step": 48
+    },
+    {
+      "epoch": 0.0900735294117647,
+      "grad_norm": 0.0,
+      "learning_rate": 4.993713866114829e-06,
+      "loss": 1.9756,
+      "step": 49
+    },
+    {
+      "epoch": 0.09191176470588236,
+      "grad_norm": 0.0,
+      "learning_rate": 4.993179351484811e-06,
+      "loss": 2.0407,
+      "step": 50
+    },
+    {
+      "epoch": 0.09375,
+      "grad_norm": 0.0,
+      "learning_rate": 4.9926230604379275e-06,
+      "loss": 1.8667,
+      "step": 51
+    },
+    {
+      "epoch": 0.09558823529411764,
+      "grad_norm": 0.0,
+      "learning_rate": 4.992044997833044e-06,
+      "loss": 1.8814,
+      "step": 52
+    },
+    {
+      "epoch": 0.0974264705882353,
+      "grad_norm": 0.0,
+      "learning_rate": 4.991445168719189e-06,
+      "loss": 1.9088,
+      "step": 53
+    },
+    {
+      "epoch": 0.09926470588235294,
+      "grad_norm": 0.0,
+      "learning_rate": 4.9908235783355075e-06,
+      "loss": 1.6814,
+      "step": 54
+    },
+    {
+      "epoch": 0.10110294117647059,
+      "grad_norm": 0.0,
+      "learning_rate": 4.990180232111217e-06,
+      "loss": 1.6273,
+      "step": 55
+    },
+    {
+      "epoch": 0.10294117647058823,
+      "grad_norm": 0.0,
+      "learning_rate": 4.989515135665558e-06,
+      "loss": 1.7085,
+      "step": 56
+    },
+    {
+      "epoch": 0.10477941176470588,
+      "grad_norm": 0.0,
+      "learning_rate": 4.988828294807746e-06,
+      "loss": 1.884,
+      "step": 57
+    },
+    {
+      "epoch": 0.10661764705882353,
+      "grad_norm": 0.0,
+      "learning_rate": 4.988119715536922e-06,
+      "loss": 1.7247,
+      "step": 58
+    },
+    {
+      "epoch": 0.10845588235294118,
+      "grad_norm": 0.0,
+      "learning_rate": 4.987389404042098e-06,
+      "loss": 1.7757,
+      "step": 59
+    },
+    {
+      "epoch": 0.11029411764705882,
+      "grad_norm": 0.0,
+      "learning_rate": 4.986637366702105e-06,
+      "loss": 1.745,
+      "step": 60
+    },
+    {
+      "epoch": 0.11213235294117647,
+      "grad_norm": 0.0,
+      "learning_rate": 4.985863610085534e-06,
+      "loss": 1.6955,
+      "step": 61
+    },
+    {
+      "epoch": 0.11397058823529412,
+      "grad_norm": 0.0,
+      "learning_rate": 4.985068140950683e-06,
+      "loss": 1.8484,
+      "step": 62
+    },
+    {
+      "epoch": 0.11580882352941177,
+      "grad_norm": 0.0,
+      "learning_rate": 4.984250966245495e-06,
+      "loss": 1.905,
+      "step": 63
+    },
+    {
+      "epoch": 0.11764705882352941,
+      "grad_norm": 0.0,
+      "learning_rate": 4.983412093107496e-06,
+      "loss": 1.9223,
+      "step": 64
+    },
+    {
+      "epoch": 0.11948529411764706,
+      "grad_norm": 0.0,
+      "learning_rate": 4.982551528863738e-06,
+      "loss": 1.8653,
+      "step": 65
+    },
+    {
+      "epoch": 0.1213235294117647,
+      "grad_norm": 0.0,
+      "learning_rate": 4.981669281030731e-06,
+      "loss": 1.7115,
+      "step": 66
+    },
+    {
+      "epoch": 0.12316176470588236,
+      "grad_norm": 0.0,
+      "learning_rate": 4.980765357314376e-06,
+      "loss": 1.7904,
+      "step": 67
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 0.0,
+      "learning_rate": 4.9798397656099005e-06,
+      "loss": 1.5778,
+      "step": 68
+    },
+    {
+      "epoch": 0.12683823529411764,
+      "grad_norm": 0.0,
+      "learning_rate": 4.978892514001792e-06,
+      "loss": 1.9114,
+      "step": 69
+    },
+    {
+      "epoch": 0.12867647058823528,
+      "grad_norm": 0.0,
+      "learning_rate": 4.977923610763719e-06,
+      "loss": 1.8529,
+      "step": 70
+    },
+    {
+      "epoch": 0.13051470588235295,
+      "grad_norm": 0.0,
+      "learning_rate": 4.976933064358467e-06,
+      "loss": 1.6901,
+      "step": 71
+    },
+    {
+      "epoch": 0.1323529411764706,
+      "grad_norm": 0.0,
+      "learning_rate": 4.975920883437862e-06,
+      "loss": 1.809,
+      "step": 72
+    },
+    {
+      "epoch": 0.13419117647058823,
+      "grad_norm": 0.0,
+      "learning_rate": 4.974887076842694e-06,
+      "loss": 1.9306,
+      "step": 73
+    },
+    {
+      "epoch": 0.13602941176470587,
+      "grad_norm": 0.0,
+      "learning_rate": 4.973831653602637e-06,
+      "loss": 1.8281,
+      "step": 74
+    },
+    {
+      "epoch": 0.13786764705882354,
+      "grad_norm": 0.0,
+      "learning_rate": 4.972754622936178e-06,
+      "loss": 1.7044,
+      "step": 75
+    },
+    {
+      "epoch": 0.13970588235294118,
+      "grad_norm": 0.0,
+      "learning_rate": 4.971655994250529e-06,
+      "loss": 1.6064,
+      "step": 76
+    },
+    {
+      "epoch": 0.14154411764705882,
+      "grad_norm": 0.0,
+      "learning_rate": 4.97053577714155e-06,
+      "loss": 1.7251,
+      "step": 77
+    },
+    {
+      "epoch": 0.14338235294117646,
+      "grad_norm": 0.0,
+      "learning_rate": 4.96939398139366e-06,
+      "loss": 1.979,
+      "step": 78
+    },
+    {
+      "epoch": 0.14522058823529413,
+      "grad_norm": 0.0,
+      "learning_rate": 4.968230616979755e-06,
+      "loss": 1.9523,
+      "step": 79
+    },
+    {
+      "epoch": 0.14705882352941177,
+      "grad_norm": 0.0,
+      "learning_rate": 4.967045694061122e-06,
+      "loss": 1.9131,
+      "step": 80
+    },
+    {
+      "epoch": 0.1488970588235294,
+      "grad_norm": 0.0,
+      "learning_rate": 4.965839222987348e-06,
+      "loss": 1.6283,
+      "step": 81
+    },
+    {
+      "epoch": 0.15073529411764705,
+      "grad_norm": 0.0,
+      "learning_rate": 4.9646112142962295e-06,
+      "loss": 1.6546,
+      "step": 82
+    },
+    {
+      "epoch": 0.15257352941176472,
+      "grad_norm": 0.0,
+      "learning_rate": 4.96336167871368e-06,
+      "loss": 1.9087,
+      "step": 83
+    },
+    {
+      "epoch": 0.15441176470588236,
+      "grad_norm": 0.0,
+      "learning_rate": 4.96209062715364e-06,
+      "loss": 1.8704,
+      "step": 84
+    },
+    {
+      "epoch": 0.15625,
+      "grad_norm": 0.0,
+      "learning_rate": 4.960798070717977e-06,
+      "loss": 1.9558,
+      "step": 85
+    },
+    {
+      "epoch": 0.15808823529411764,
+      "grad_norm": 0.0,
+      "learning_rate": 4.959484020696392e-06,
+      "loss": 1.8445,
+      "step": 86
+    },
+    {
+      "epoch": 0.15992647058823528,
+      "grad_norm": 0.0,
+      "learning_rate": 4.9581484885663175e-06,
+      "loss": 1.6393,
+      "step": 87
+    },
+    {
+      "epoch": 0.16176470588235295,
+      "grad_norm": 0.0,
+      "learning_rate": 4.956791485992823e-06,
+      "loss": 1.9478,
+      "step": 88
+    },
+    {
+      "epoch": 0.1636029411764706,
+      "grad_norm": 0.0,
+      "learning_rate": 4.955413024828504e-06,
+      "loss": 1.8037,
+      "step": 89
+    },
+    {
+      "epoch": 0.16544117647058823,
+      "grad_norm": 0.0,
+      "learning_rate": 4.9540131171133884e-06,
+      "loss": 1.7478,
+      "step": 90
+    },
+    {
+      "epoch": 0.16727941176470587,
+      "grad_norm": 0.0,
+      "learning_rate": 4.952591775074825e-06,
+      "loss": 1.7756,
+      "step": 91
+    },
+    {
+      "epoch": 0.16911764705882354,
+      "grad_norm": 0.0,
+      "learning_rate": 4.951149011127379e-06,
+      "loss": 1.7447,
+      "step": 92
+    },
+    {
+      "epoch": 0.17095588235294118,
+      "grad_norm": 0.0,
+      "learning_rate": 4.949684837872723e-06,
+      "loss": 1.6142,
+      "step": 93
+    },
+    {
+      "epoch": 0.17279411764705882,
+      "grad_norm": 0.0,
+      "learning_rate": 4.948199268099525e-06,
+      "loss": 1.8074,
+      "step": 94
+    },
+    {
+      "epoch": 0.17463235294117646,
+      "grad_norm": 0.0,
+      "learning_rate": 4.946692314783342e-06,
+      "loss": 1.7,
+      "step": 95
+    },
+    {
+      "epoch": 0.17647058823529413,
+      "grad_norm": 0.0,
+      "learning_rate": 4.9451639910865016e-06,
+      "loss": 1.6758,
+      "step": 96
+    },
+    {
+      "epoch": 0.17830882352941177,
+      "grad_norm": 0.0,
+      "learning_rate": 4.943614310357987e-06,
+      "loss": 1.5344,
+      "step": 97
+    },
+    {
+      "epoch": 0.1801470588235294,
+      "grad_norm": 0.0,
+      "learning_rate": 4.942043286133326e-06,
+      "loss": 1.6402,
+      "step": 98
+    },
+    {
+      "epoch": 0.18198529411764705,
+      "grad_norm": 0.0,
+      "learning_rate": 4.940450932134467e-06,
+      "loss": 1.8448,
+      "step": 99
+    },
+    {
+      "epoch": 0.18382352941176472,
+      "grad_norm": 0.0,
+      "learning_rate": 4.9388372622696605e-06,
+      "loss": 1.6571,
+      "step": 100
+    },
+    {
+      "epoch": 0.18566176470588236,
+      "grad_norm": 0.0,
+      "learning_rate": 4.937202290633337e-06,
+      "loss": 1.9318,
+      "step": 101
+    },
+    {
+      "epoch": 0.1875,
+      "grad_norm": 0.0,
+      "learning_rate": 4.935546031505991e-06,
+      "loss": 1.8587,
+      "step": 102
+    },
+    {
+      "epoch": 0.18933823529411764,
+      "grad_norm": 0.0,
+      "learning_rate": 4.933868499354043e-06,
+      "loss": 1.8227,
+      "step": 103
+    },
+    {
+      "epoch": 0.19117647058823528,
+      "grad_norm": 0.0,
+      "learning_rate": 4.932169708829725e-06,
+      "loss": 1.8896,
+      "step": 104
+    },
+    {
+      "epoch": 0.19301470588235295,
+      "grad_norm": 0.0,
+      "learning_rate": 4.930449674770947e-06,
+      "loss": 1.6666,
+      "step": 105
+    },
+    {
+      "epoch": 0.1948529411764706,
+      "grad_norm": 0.0,
+      "learning_rate": 4.928708412201169e-06,
+      "loss": 2.0114,
+      "step": 106
+    },
+    {
+      "epoch": 0.19669117647058823,
+      "grad_norm": 0.0,
+      "learning_rate": 4.926945936329266e-06,
+      "loss": 1.8712,
+      "step": 107
+    },
+    {
+      "epoch": 0.19852941176470587,
+      "grad_norm": 0.0,
+      "learning_rate": 4.925162262549405e-06,
+      "loss": 1.8027,
+      "step": 108
+    },
+    {
+      "epoch": 0.20036764705882354,
+      "grad_norm": 0.0,
+      "learning_rate": 4.923357406440896e-06,
+      "loss": 1.9823,
+      "step": 109
+    },
+    {
+      "epoch": 0.20220588235294118,
+      "grad_norm": 0.0,
+      "learning_rate": 4.921531383768071e-06,
+      "loss": 1.6381,
+      "step": 110
+    },
+    {
+      "epoch": 0.20404411764705882,
+      "grad_norm": 0.0,
+      "learning_rate": 4.919684210480134e-06,
+      "loss": 1.9495,
+      "step": 111
+    },
+    {
+      "epoch": 0.20588235294117646,
+      "grad_norm": 0.0,
+      "learning_rate": 4.917815902711029e-06,
+      "loss": 2.0251,
+      "step": 112
+    },
+    {
+      "epoch": 0.20772058823529413,
+      "grad_norm": 0.0,
+      "learning_rate": 4.915926476779297e-06,
+      "loss": 1.8135,
+      "step": 113
+    },
+    {
+      "epoch": 0.20955882352941177,
+      "grad_norm": 0.0,
+      "learning_rate": 4.914015949187934e-06,
+      "loss": 1.7443,
+      "step": 114
+    },
+    {
+      "epoch": 0.2113970588235294,
+      "grad_norm": 0.0,
+      "learning_rate": 4.912084336624243e-06,
+      "loss": 1.6857,
+      "step": 115
+    },
+    {
+      "epoch": 0.21323529411764705,
+      "grad_norm": 0.0,
+      "learning_rate": 4.910131655959697e-06,
+      "loss": 1.8796,
+      "step": 116
+    },
+    {
+      "epoch": 0.21507352941176472,
+      "grad_norm": 0.0,
+      "learning_rate": 4.908157924249781e-06,
+      "loss": 1.9533,
+      "step": 117
+    },
+    {
+      "epoch": 0.21691176470588236,
+      "grad_norm": 0.0,
+      "learning_rate": 4.906163158733851e-06,
+      "loss": 1.7924,
+      "step": 118
+    },
+    {
+      "epoch": 0.21875,
+      "grad_norm": 0.0,
+      "learning_rate": 4.904147376834979e-06,
+      "loss": 1.8991,
+      "step": 119
+    },
+    {
+      "epoch": 0.22058823529411764,
+      "grad_norm": 0.0,
+      "learning_rate": 4.9021105961598046e-06,
+      "loss": 1.8777,
+      "step": 120
+    },
+    {
+      "epoch": 0.22242647058823528,
+      "grad_norm": 0.0,
+      "learning_rate": 4.900052834498377e-06,
+      "loss": 1.7899,
+      "step": 121
+    },
+    {
+      "epoch": 0.22426470588235295,
+      "grad_norm": 0.0,
+      "learning_rate": 4.897974109824002e-06,
+      "loss": 1.8917,
+      "step": 122
+    },
+    {
+      "epoch": 0.2261029411764706,
+      "grad_norm": 0.0,
+      "learning_rate": 4.895874440293085e-06,
+      "loss": 1.73,
+      "step": 123
+    },
+    {
+      "epoch": 0.22794117647058823,
+      "grad_norm": 0.0,
+      "learning_rate": 4.8937538442449724e-06,
+      "loss": 1.8076,
+      "step": 124
+    },
+    {
+      "epoch": 0.22977941176470587,
+      "grad_norm": 0.0,
+      "learning_rate": 4.891612340201791e-06,
+      "loss": 1.6099,
+      "step": 125
+    },
+    {
+      "epoch": 0.23161764705882354,
+      "grad_norm": 0.0,
+      "learning_rate": 4.8894499468682865e-06,
+      "loss": 1.9381,
+      "step": 126
+    },
+    {
+      "epoch": 0.23345588235294118,
+      "grad_norm": 0.0,
+      "learning_rate": 4.887266683131659e-06,
+      "loss": 1.6964,
+      "step": 127
+    },
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 0.0,
+      "learning_rate": 4.885062568061399e-06,
+      "loss": 1.9401,
+      "step": 128
+    },
+    {
+      "epoch": 0.23713235294117646,
+      "grad_norm": 0.0,
+      "learning_rate": 4.882837620909121e-06,
+      "loss": 1.6888,
+      "step": 129
+    },
+    {
+      "epoch": 0.23897058823529413,
+      "grad_norm": 0.0,
+      "learning_rate": 4.880591861108397e-06,
+      "loss": 1.7796,
+      "step": 130
+    },
+    {
+      "epoch": 0.24080882352941177,
+      "grad_norm": 0.0,
+      "learning_rate": 4.878325308274583e-06,
+      "loss": 1.7957,
+      "step": 131
+    },
+    {
+      "epoch": 0.2426470588235294,
+      "grad_norm": 0.0,
+      "learning_rate": 4.876037982204649e-06,
+      "loss": 1.6231,
+      "step": 132
+    },
+    {
+      "epoch": 0.24448529411764705,
+      "grad_norm": 0.0,
+      "learning_rate": 4.873729902877009e-06,
+      "loss": 1.8064,
+      "step": 133
+    },
+    {
+      "epoch": 0.24632352941176472,
+      "grad_norm": 0.0,
+      "learning_rate": 4.871401090451342e-06,
+      "loss": 1.927,
+      "step": 134
+    },
+    {
+      "epoch": 0.24816176470588236,
+      "grad_norm": 0.0,
+      "learning_rate": 4.869051565268419e-06,
+      "loss": 1.7717,
+      "step": 135
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.0,
+      "learning_rate": 4.866681347849925e-06,
+      "loss": 1.5868,
+      "step": 136
+    },
+    {
+      "epoch": 0.25183823529411764,
+      "grad_norm": 0.0,
+      "learning_rate": 4.8642904588982785e-06,
+      "loss": 1.901,
+      "step": 137
+    },
+    {
+      "epoch": 0.2536764705882353,
+      "grad_norm": 0.0,
+      "learning_rate": 4.861878919296451e-06,
+      "loss": 1.9239,
+      "step": 138
+    },
+    {
+      "epoch": 0.2555147058823529,
+      "grad_norm": 0.0,
+      "learning_rate": 4.859446750107786e-06,
+      "loss": 2.088,
+      "step": 139
+    },
+    {
+      "epoch": 0.25735294117647056,
+      "grad_norm": 0.0,
+      "learning_rate": 4.856993972575813e-06,
+      "loss": 1.5303,
+      "step": 140
+    },
+    {
+      "epoch": 0.25919117647058826,
+      "grad_norm": 0.0,
+      "learning_rate": 4.854520608124063e-06,
+      "loss": 1.8925,
+      "step": 141
+    },
+    {
+      "epoch": 0.2610294117647059,
+      "grad_norm": 0.0,
+      "learning_rate": 4.8520266783558825e-06,
+      "loss": 1.8574,
+      "step": 142
+    },
+    {
+      "epoch": 0.26286764705882354,
+      "grad_norm": 0.0,
+      "learning_rate": 4.849512205054242e-06,
+      "loss": 1.6464,
+      "step": 143
+    },
+    {
+      "epoch": 0.2647058823529412,
+      "grad_norm": 0.0,
+      "learning_rate": 4.846977210181549e-06,
+      "loss": 1.8152,
+      "step": 144
+    },
+    {
+      "epoch": 0.2665441176470588,
+      "grad_norm": 0.0,
+      "learning_rate": 4.844421715879453e-06,
+      "loss": 1.5551,
+      "step": 145
+    },
+    {
+      "epoch": 0.26838235294117646,
+      "grad_norm": 0.0,
+      "learning_rate": 4.841845744468655e-06,
+      "loss": 1.7031,
+      "step": 146
+    },
+    {
+      "epoch": 0.2702205882352941,
+      "grad_norm": 0.0,
+      "learning_rate": 4.83924931844871e-06,
+      "loss": 1.724,
+      "step": 147
+    },
+    {
+      "epoch": 0.27205882352941174,
+      "grad_norm": 0.0,
+      "learning_rate": 4.836632460497832e-06,
+      "loss": 1.6675,
+      "step": 148
+    },
+    {
+      "epoch": 0.27389705882352944,
+      "grad_norm": 0.0,
+      "learning_rate": 4.833995193472697e-06,
+      "loss": 1.5296,
+      "step": 149
+    },
+    {
+      "epoch": 0.2757352941176471,
+      "grad_norm": 0.0,
+      "learning_rate": 4.831337540408239e-06,
+      "loss": 1.7336,
+      "step": 150
+    },
+    {
+      "epoch": 0.2775735294117647,
+      "grad_norm": 0.0,
+      "learning_rate": 4.828659524517455e-06,
+      "loss": 1.7736,
+      "step": 151
+    },
+    {
+      "epoch": 0.27941176470588236,
+      "grad_norm": 0.0,
+      "learning_rate": 4.825961169191196e-06,
+      "loss": 1.8912,
+      "step": 152
+    },
+    {
+      "epoch": 0.28125,
+      "grad_norm": 0.0,
+      "learning_rate": 4.8232424979979684e-06,
+      "loss": 1.5462,
+      "step": 153
+    },
+    {
+      "epoch": 0.28308823529411764,
+      "grad_norm": 0.0,
+      "learning_rate": 4.820503534683725e-06,
+      "loss": 1.7678,
+      "step": 154
+    },
+    {
+      "epoch": 0.2849264705882353,
+      "grad_norm": 0.0,
+      "learning_rate": 4.8177443031716545e-06,
+      "loss": 1.9841,
+      "step": 155
+    },
+    {
+      "epoch": 0.2867647058823529,
+      "grad_norm": 0.0,
+      "learning_rate": 4.814964827561981e-06,
+      "loss": 1.9354,
+      "step": 156
+    },
+    {
+      "epoch": 0.28860294117647056,
+      "grad_norm": 0.0,
+      "learning_rate": 4.812165132131746e-06,
+      "loss": 1.6513,
+      "step": 157
+    },
+    {
+      "epoch": 0.29044117647058826,
+      "grad_norm": 0.0,
+      "learning_rate": 4.809345241334598e-06,
+      "loss": 1.7552,
+      "step": 158
+    },
+    {
+      "epoch": 0.2922794117647059,
+      "grad_norm": 0.0,
+      "learning_rate": 4.806505179800583e-06,
+      "loss": 1.7143,
+      "step": 159
+    },
+    {
+      "epoch": 0.29411764705882354,
+      "grad_norm": 0.0,
+      "learning_rate": 4.803644972335925e-06,
+      "loss": 1.8868,
+      "step": 160
+    },
+    {
+      "epoch": 0.2959558823529412,
+      "grad_norm": 0.0,
+      "learning_rate": 4.800764643922806e-06,
+      "loss": 1.7209,
+      "step": 161
+    },
+    {
+      "epoch": 0.2977941176470588,
+      "grad_norm": 0.0,
+      "learning_rate": 4.797864219719161e-06,
+      "loss": 2.0387,
+      "step": 162
+    },
+    {
+      "epoch": 0.29963235294117646,
+      "grad_norm": 0.0,
+      "learning_rate": 4.794943725058441e-06,
+      "loss": 1.7266,
+      "step": 163
+    },
+    {
+      "epoch": 0.3014705882352941,
+      "grad_norm": 0.0,
+      "learning_rate": 4.792003185449406e-06,
+      "loss": 1.8065,
+      "step": 164
+    },
+    {
+      "epoch": 0.30330882352941174,
+      "grad_norm": 0.0,
+      "learning_rate": 4.789042626575895e-06,
+      "loss": 1.8573,
+      "step": 165
+    },
+    {
+      "epoch": 0.30514705882352944,
+      "grad_norm": 0.0,
+      "learning_rate": 4.786062074296602e-06,
+      "loss": 1.7878,
+      "step": 166
+    },
+    {
+      "epoch": 0.3069852941176471,
+      "grad_norm": 0.0,
+      "learning_rate": 4.783061554644853e-06,
+      "loss": 1.8467,
+      "step": 167
+    },
+    {
+      "epoch": 0.3088235294117647,
+      "grad_norm": 0.0,
+      "learning_rate": 4.780041093828376e-06,
+      "loss": 1.7535,
+      "step": 168
+    },
+    {
+      "epoch": 0.31066176470588236,
+      "grad_norm": 0.0,
+      "learning_rate": 4.777000718229072e-06,
+      "loss": 1.6498,
+      "step": 169
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 0.0,
+      "learning_rate": 4.773940454402789e-06,
+      "loss": 1.6728,
+      "step": 170
+    },
+    {
+      "epoch": 0.31433823529411764,
+      "grad_norm": 0.0,
+      "learning_rate": 4.770860329079083e-06,
+      "loss": 1.8933,
+      "step": 171
+    },
+    {
+      "epoch": 0.3161764705882353,
+      "grad_norm": 0.0,
+      "learning_rate": 4.7677603691609905e-06,
+      "loss": 1.7238,
+      "step": 172
+    },
+    {
+      "epoch": 0.3180147058823529,
+      "grad_norm": 0.0,
+      "learning_rate": 4.7646406017247895e-06,
+      "loss": 1.971,
+      "step": 173
+    },
+    {
+      "epoch": 0.31985294117647056,
+      "grad_norm": 0.0,
+      "learning_rate": 4.761501054019766e-06,
+      "loss": 1.8085,
+      "step": 174
+    },
+    {
+      "epoch": 0.32169117647058826,
+      "grad_norm": 0.0,
+      "learning_rate": 4.758341753467975e-06,
+      "loss": 1.9082,
+      "step": 175
+    },
+    {
+      "epoch": 0.3235294117647059,
+      "grad_norm": 0.0,
+      "learning_rate": 4.755162727663998e-06,
+      "loss": 1.6394,
+      "step": 176
+    },
+    {
+      "epoch": 0.32536764705882354,
+      "grad_norm": 0.0,
+      "learning_rate": 4.751964004374709e-06,
+      "loss": 2.0217,
+      "step": 177
+    },
+    {
+      "epoch": 0.3272058823529412,
+      "grad_norm": 0.0,
+      "learning_rate": 4.748745611539024e-06,
+      "loss": 1.8042,
+      "step": 178
+    },
+    {
+      "epoch": 0.3290441176470588,
+      "grad_norm": 0.0,
+      "learning_rate": 4.745507577267663e-06,
+      "loss": 2.1738,
+      "step": 179
+    },
+    {
+      "epoch": 0.33088235294117646,
+      "grad_norm": 0.0,
+      "learning_rate": 4.7422499298429e-06,
+      "loss": 1.8745,
+      "step": 180
+    },
+    {
+      "epoch": 0.3327205882352941,
+      "grad_norm": 0.0,
+      "learning_rate": 4.738972697718319e-06,
+      "loss": 1.7444,
+      "step": 181
+    },
+    {
+      "epoch": 0.33455882352941174,
+      "grad_norm": 0.0,
+      "learning_rate": 4.735675909518565e-06,
+      "loss": 1.9358,
+      "step": 182
+    },
+    {
+      "epoch": 0.33639705882352944,
+      "grad_norm": 0.0,
+      "learning_rate": 4.732359594039094e-06,
+      "loss": 1.5578,
+      "step": 183
+    },
+    {
+      "epoch": 0.3382352941176471,
+      "grad_norm": 0.0,
+      "learning_rate": 4.729023780245919e-06,
+      "loss": 1.6821,
+      "step": 184
+    },
+    {
+      "epoch": 0.3400735294117647,
+      "grad_norm": 0.0,
+      "learning_rate": 4.725668497275361e-06,
+      "loss": 1.8779,
+      "step": 185
+    },
+    {
+      "epoch": 0.34191176470588236,
+      "grad_norm": 0.0,
+      "learning_rate": 4.72229377443379e-06,
+      "loss": 1.7298,
+      "step": 186
+    },
+    {
+      "epoch": 0.34375,
+      "grad_norm": 0.0,
+      "learning_rate": 4.718899641197375e-06,
+      "loss": 1.8304,
+      "step": 187
+    },
+    {
+      "epoch": 0.34558823529411764,
+      "grad_norm": 0.0,
+      "learning_rate": 4.71548612721182e-06,
+      "loss": 1.741,
+      "step": 188
+    },
+    {
+      "epoch": 0.3474264705882353,
+      "grad_norm": 0.0,
+      "learning_rate": 4.712053262292111e-06,
+      "loss": 1.9535,
+      "step": 189
+    },
+    {
+      "epoch": 0.3492647058823529,
+      "grad_norm": 0.0,
+      "learning_rate": 4.70860107642225e-06,
+      "loss": 1.8692,
+      "step": 190
+    },
+    {
+      "epoch": 0.35110294117647056,
+      "grad_norm": 0.0,
+      "learning_rate": 4.7051295997549964e-06,
+      "loss": 1.8756,
+      "step": 191
+    },
+    {
+      "epoch": 0.35294117647058826,
+      "grad_norm": 0.0,
+      "learning_rate": 4.701638862611605e-06,
+      "loss": 1.869,
+      "step": 192
+    },
+    {
+      "epoch": 0.3547794117647059,
+      "grad_norm": 0.0,
+      "learning_rate": 4.698128895481557e-06,
+      "loss": 1.5358,
+      "step": 193
+    },
+    {
+      "epoch": 0.35661764705882354,
+      "grad_norm": 0.0,
+      "learning_rate": 4.694599729022297e-06,
+      "loss": 1.5597,
+      "step": 194
+    },
+    {
+      "epoch": 0.3584558823529412,
+      "grad_norm": 0.0,
+      "learning_rate": 4.691051394058965e-06,
+      "loss": 1.7232,
+      "step": 195
+    },
+    {
+      "epoch": 0.3602941176470588,
+      "grad_norm": 0.0,
+      "learning_rate": 4.687483921584124e-06,
+      "loss": 1.6854,
+      "step": 196
+    },
+    {
+      "epoch": 0.36213235294117646,
+      "grad_norm": 0.0,
+      "learning_rate": 4.683897342757493e-06,
+      "loss": 1.6543,
+      "step": 197
+    },
+    {
+      "epoch": 0.3639705882352941,
+      "grad_norm": 0.0,
+      "learning_rate": 4.680291688905674e-06,
+      "loss": 1.698,
+      "step": 198
+    },
+    {
+      "epoch": 0.36580882352941174,
+      "grad_norm": 0.0,
+      "learning_rate": 4.676666991521876e-06,
+      "loss": 1.6482,
+      "step": 199
+    },
+    {
+      "epoch": 0.36764705882352944,
+      "grad_norm": 0.0,
+      "learning_rate": 4.673023282265645e-06,
+      "loss": 1.5947,
+      "step": 200
+    },
+    {
+      "epoch": 0.3694852941176471,
+      "grad_norm": 0.0,
+      "learning_rate": 4.669360592962581e-06,
+      "loss": 1.6644,
+      "step": 201
+    },
+    {
+      "epoch": 0.3713235294117647,
+      "grad_norm": 0.0,
+      "learning_rate": 4.665678955604064e-06,
+      "loss": 1.9734,
+      "step": 202
+    },
+    {
+      "epoch": 0.37316176470588236,
+      "grad_norm": 0.0,
+      "learning_rate": 4.661978402346974e-06,
+      "loss": 1.7937,
+      "step": 203
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 0.0,
+      "learning_rate": 4.658258965513412e-06,
+      "loss": 1.9138,
+      "step": 204
+    },
+    {
+      "epoch": 0.37683823529411764,
+      "grad_norm": 0.0,
+      "learning_rate": 4.654520677590412e-06,
+      "loss": 1.8383,
+      "step": 205
+    },
+    {
+      "epoch": 0.3786764705882353,
+      "grad_norm": 0.0,
+      "learning_rate": 4.650763571229664e-06,
+      "loss": 1.7907,
+      "step": 206
+    },
+    {
+      "epoch": 0.3805147058823529,
+      "grad_norm": 0.0,
+      "learning_rate": 4.646987679247223e-06,
+      "loss": 1.588,
+      "step": 207
+    },
+    {
+      "epoch": 0.38235294117647056,
+      "grad_norm": 0.0,
+      "learning_rate": 4.643193034623229e-06,
+      "loss": 1.7127,
+      "step": 208
+    },
+    {
+      "epoch": 0.38419117647058826,
+      "grad_norm": 0.0,
+      "learning_rate": 4.6393796705016105e-06,
+      "loss": 1.721,
+      "step": 209
+    },
+    {
+      "epoch": 0.3860294117647059,
+      "grad_norm": 0.0,
+      "learning_rate": 4.635547620189802e-06,
+      "loss": 1.6846,
+      "step": 210
+    },
+    {
+      "epoch": 0.38786764705882354,
+      "grad_norm": 0.0,
+      "learning_rate": 4.631696917158449e-06,
+      "loss": 1.7172,
+      "step": 211
+    },
+    {
+      "epoch": 0.3897058823529412,
+      "grad_norm": 0.0,
+      "learning_rate": 4.62782759504112e-06,
+      "loss": 1.7209,
+      "step": 212
+    },
+    {
+      "epoch": 0.3915441176470588,
+      "grad_norm": 0.0,
+      "learning_rate": 4.623939687634009e-06,
+      "loss": 1.4935,
+      "step": 213
+    },
+    {
+      "epoch": 0.39338235294117646,
+      "grad_norm": 0.0,
+      "learning_rate": 4.620033228895639e-06,
+      "loss": 1.9397,
+      "step": 214
+    },
+    {
+      "epoch": 0.3952205882352941,
+      "grad_norm": 0.0,
+      "learning_rate": 4.616108252946568e-06,
+      "loss": 1.6881,
+      "step": 215
+    },
+    {
+      "epoch": 0.39705882352941174,
+      "grad_norm": 0.0,
+      "learning_rate": 4.612164794069096e-06,
+      "loss": 1.9585,
+      "step": 216
+    },
+    {
+      "epoch": 0.39889705882352944,
+      "grad_norm": 0.0,
+      "learning_rate": 4.608202886706953e-06,
+      "loss": 1.6473,
+      "step": 217
+    },
+    {
+      "epoch": 0.4007352941176471,
+      "grad_norm": 0.0,
+      "learning_rate": 4.6042225654650096e-06,
+      "loss": 1.8187,
+      "step": 218
+    },
+    {
+      "epoch": 0.4025735294117647,
+      "grad_norm": 0.0,
+      "learning_rate": 4.60022386510897e-06,
+      "loss": 1.8265,
+      "step": 219
+    },
+    {
+      "epoch": 0.40441176470588236,
+      "grad_norm": 0.0,
+      "learning_rate": 4.5962068205650674e-06,
+      "loss": 1.8966,
+      "step": 220
+    },
+    {
+      "epoch": 0.40625,
+      "grad_norm": 0.0,
+      "learning_rate": 4.592171466919762e-06,
+      "loss": 1.8687,
+      "step": 221
+    },
+    {
+      "epoch": 0.40808823529411764,
+      "grad_norm": 0.0,
+      "learning_rate": 4.588117839419432e-06,
+      "loss": 1.7952,
+      "step": 222
+    },
+    {
+      "epoch": 0.4099264705882353,
+      "grad_norm": 0.0,
+      "learning_rate": 4.584045973470067e-06,
+      "loss": 1.6071,
+      "step": 223
+    },
+    {
+      "epoch": 0.4117647058823529,
+      "grad_norm": 0.0,
+      "learning_rate": 4.579955904636959e-06,
+      "loss": 1.8199,
+      "step": 224
+    },
+    {
+      "epoch": 0.41360294117647056,
+      "grad_norm": 0.0,
+      "learning_rate": 4.5758476686443905e-06,
+      "loss": 1.8962,
+      "step": 225
+    },
+    {
+      "epoch": 0.41544117647058826,
+      "grad_norm": 0.0,
+      "learning_rate": 4.571721301375323e-06,
+      "loss": 1.5319,
+      "step": 226
+    },
+    {
+      "epoch": 0.4172794117647059,
+      "grad_norm": 0.0,
+      "learning_rate": 4.5675768388710855e-06,
+      "loss": 1.605,
+      "step": 227
+    },
+    {
+      "epoch": 0.41911764705882354,
+      "grad_norm": 0.0,
+      "learning_rate": 4.563414317331053e-06,
+      "loss": 1.673,
+      "step": 228
+    },
+    {
+      "epoch": 0.4209558823529412,
+      "grad_norm": 0.0,
+      "learning_rate": 4.559233773112343e-06,
+      "loss": 1.8094,
+      "step": 229
+    },
+    {
+      "epoch": 0.4227941176470588,
+      "grad_norm": 0.0,
+      "learning_rate": 4.5550352427294836e-06,
+      "loss": 1.4822,
+      "step": 230
+    },
+    {
+      "epoch": 0.42463235294117646,
+      "grad_norm": 0.0,
+      "learning_rate": 4.550818762854105e-06,
+      "loss": 1.6698,
+      "step": 231
+    },
+    {
+      "epoch": 0.4264705882352941,
+      "grad_norm": 0.0,
+      "learning_rate": 4.546584370314613e-06,
+      "loss": 1.697,
+      "step": 232
+    },
+    {
+      "epoch": 0.42830882352941174,
+      "grad_norm": 0.0,
+      "learning_rate": 4.542332102095871e-06,
+      "loss": 1.8328,
+      "step": 233
+    },
+    {
+      "epoch": 0.43014705882352944,
+      "grad_norm": 0.0,
+      "learning_rate": 4.538061995338875e-06,
+      "loss": 1.6596,
+      "step": 234
+    },
+    {
+      "epoch": 0.4319852941176471,
+      "grad_norm": 0.0,
+      "learning_rate": 4.533774087340431e-06,
+      "loss": 1.7157,
+      "step": 235
+    },
+    {
+      "epoch": 0.4338235294117647,
+      "grad_norm": 0.0,
+      "learning_rate": 4.529468415552829e-06,
+      "loss": 1.4717,
+      "step": 236
+    },
+    {
+      "epoch": 0.43566176470588236,
+      "grad_norm": 0.0,
+      "learning_rate": 4.52514501758351e-06,
+      "loss": 1.7363,
+      "step": 237
+    },
+    {
+      "epoch": 0.4375,
+      "grad_norm": 0.0,
+      "learning_rate": 4.520803931194747e-06,
+      "loss": 1.8573,
+      "step": 238
+    },
+    {
+      "epoch": 0.43933823529411764,
+      "grad_norm": 0.0,
+      "learning_rate": 4.5164451943033105e-06,
+      "loss": 1.9611,
+      "step": 239
+    },
+    {
+      "epoch": 0.4411764705882353,
+      "grad_norm": 0.0,
+      "learning_rate": 4.512068844980136e-06,
+      "loss": 1.9372,
+      "step": 240
+    },
+    {
+      "epoch": 0.4430147058823529,
+      "grad_norm": 0.0,
+      "learning_rate": 4.507674921449994e-06,
+      "loss": 1.4498,
+      "step": 241
+    },
+    {
+      "epoch": 0.44485294117647056,
+      "grad_norm": 0.0,
+      "learning_rate": 4.503263462091153e-06,
+      "loss": 1.642,
+      "step": 242
+    },
+    {
+      "epoch": 0.44669117647058826,
+      "grad_norm": 0.0,
+      "learning_rate": 4.49883450543505e-06,
+      "loss": 1.7529,
+      "step": 243
+    },
+    {
+      "epoch": 0.4485294117647059,
+      "grad_norm": 0.0,
+      "learning_rate": 4.494388090165947e-06,
+      "loss": 1.8263,
+      "step": 244
+    },
+    {
+      "epoch": 0.45036764705882354,
+      "grad_norm": 0.0,
+      "learning_rate": 4.489924255120597e-06,
+      "loss": 1.5046,
+      "step": 245
+    },
+    {
+      "epoch": 0.4522058823529412,
+      "grad_norm": 0.0,
+      "learning_rate": 4.485443039287907e-06,
+      "loss": 1.7404,
+      "step": 246
+    },
+    {
+      "epoch": 0.4540441176470588,
+      "grad_norm": 0.0,
+      "learning_rate": 4.48094448180859e-06,
+      "loss": 1.7201,
+      "step": 247
+    },
+    {
+      "epoch": 0.45588235294117646,
+      "grad_norm": 0.0,
+      "learning_rate": 4.476428621974833e-06,
+      "loss": 1.9917,
+      "step": 248
+    },
+    {
+      "epoch": 0.4577205882352941,
+      "grad_norm": 0.0,
+      "learning_rate": 4.471895499229946e-06,
+      "loss": 1.5859,
+      "step": 249
+    },
+    {
+      "epoch": 0.45955882352941174,
+      "grad_norm": 0.0,
+      "learning_rate": 4.467345153168018e-06,
+      "loss": 1.5362,
+      "step": 250
+    },
+    {
+      "epoch": 0.46139705882352944,
+      "grad_norm": 0.0,
+      "learning_rate": 4.462777623533577e-06,
+      "loss": 1.7275,
+      "step": 251
+    },
+    {
+      "epoch": 0.4632352941176471,
+      "grad_norm": 0.0,
+      "learning_rate": 4.458192950221237e-06,
+      "loss": 1.5027,
+      "step": 252
+    },
+    {
+      "epoch": 0.4650735294117647,
+      "grad_norm": 0.0,
+      "learning_rate": 4.4535911732753535e-06,
+      "loss": 1.9182,
+      "step": 253
+    },
+    {
+      "epoch": 0.46691176470588236,
+      "grad_norm": 0.0,
+      "learning_rate": 4.448972332889669e-06,
+      "loss": 1.8938,
+      "step": 254
+    },
+    {
+      "epoch": 0.46875,
+      "grad_norm": 0.0,
+      "learning_rate": 4.444336469406968e-06,
+      "loss": 1.6993,
+      "step": 255
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 0.0,
+      "learning_rate": 4.4396836233187195e-06,
+      "loss": 1.962,
+      "step": 256
+    },
+    {
+      "epoch": 0.4724264705882353,
+      "grad_norm": 0.0,
+      "learning_rate": 4.435013835264725e-06,
+      "loss": 1.9328,
+      "step": 257
+    },
+    {
+      "epoch": 0.4742647058823529,
+      "grad_norm": 0.0,
+      "learning_rate": 4.4303271460327655e-06,
+      "loss": 1.6516,
+      "step": 258
+    },
+    {
+      "epoch": 0.47610294117647056,
+      "grad_norm": 0.0,
+      "learning_rate": 4.425623596558243e-06,
+      "loss": 1.6439,
+      "step": 259
+    },
+    {
+      "epoch": 0.47794117647058826,
+      "grad_norm": 0.0,
+      "learning_rate": 4.420903227923823e-06,
+      "loss": 1.9226,
+      "step": 260
+    },
+    {
+      "epoch": 0.4797794117647059,
+      "grad_norm": 0.0,
+      "learning_rate": 4.416166081359077e-06,
+      "loss": 1.9026,
+      "step": 261
+    },
+    {
+      "epoch": 0.48161764705882354,
+      "grad_norm": 0.0,
+      "learning_rate": 4.411412198240119e-06,
+      "loss": 1.8662,
+      "step": 262
+    },
+    {
+      "epoch": 0.4834558823529412,
+      "grad_norm": 0.0,
+      "learning_rate": 4.406641620089252e-06,
+      "loss": 1.6995,
+      "step": 263
+    },
+    {
+      "epoch": 0.4852941176470588,
+      "grad_norm": 0.0,
+      "learning_rate": 4.401854388574595e-06,
+      "loss": 1.7047,
+      "step": 264
+    },
+    {
+      "epoch": 0.48713235294117646,
+      "grad_norm": 0.0,
+      "learning_rate": 4.397050545509726e-06,
+      "loss": 1.9081,
+      "step": 265
+    },
+    {
+      "epoch": 0.4889705882352941,
+      "grad_norm": 0.0,
+      "learning_rate": 4.392230132853316e-06,
+      "loss": 1.577,
+      "step": 266
+    },
+    {
+      "epoch": 0.49080882352941174,
+      "grad_norm": 0.0,
+      "learning_rate": 4.387393192708758e-06,
+      "loss": 1.6726,
+      "step": 267
+    },
+    {
+      "epoch": 0.49264705882352944,
+      "grad_norm": 0.0,
+      "learning_rate": 4.382539767323805e-06,
+      "loss": 1.8256,
+      "step": 268
+    },
+    {
+      "epoch": 0.4944852941176471,
+      "grad_norm": 0.0,
+      "learning_rate": 4.377669899090202e-06,
+      "loss": 1.6916,
+      "step": 269
+    },
+    {
+      "epoch": 0.4963235294117647,
+      "grad_norm": 0.0,
+      "learning_rate": 4.372783630543305e-06,
+      "loss": 1.6802,
+      "step": 270
+    },
+    {
+      "epoch": 0.49816176470588236,
+      "grad_norm": 0.0,
+      "learning_rate": 4.3678810043617215e-06,
+      "loss": 1.7817,
+      "step": 271
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.0,
+      "learning_rate": 4.362962063366933e-06,
+      "loss": 1.6981,
+      "step": 272
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1088,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 272,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.449404419238789e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb6b3cfbdb079e121acb85173a841d678600b5fa7045e83afa29653fd118a346
+size 7160