add model

.gitattributes

@@ -33,3 +33,8 @@ 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
+model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/gpfs/projects/bsc88/hf-models/fourth_epoch_bsc_7b_restart_mix1_all_fineweb_from_mix1_lr3e-5_lr3e-6_step68625_hf/",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.0",
+  "use_cache": true,
+  "vocab_size": 256000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.44.0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de6cd55ac2cd9af0f8b5bf869e48e1bfc9b897d487fe980fbbbbdd1cba6345ae
+size 4982973048

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adbc8a286a7f95213925072695848cbc1bef9c9c9215686b8ed62afc4f28900f
+size 4995660232

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eb79ac135e0333ec3da487bd73779d505090cac9069c61ddd10fcb3206ce67e
+size 3460482936

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69a355b8a5380f68bd5aa5d8fdc4b8c866e63ac5d1ed78d7fa8afcf59448e280
+size 2097152128

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 15536234496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": "<|im_end|>",
+  "pad_token": "<unk>",
+  "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:f055d86bd1a344221f15dcc85aaa96b6b80a616445504ef8fb5b74476e8140b4
+size 19092375

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa490e57cebce5cb1a0a5b1a5d3fa4de05aee53dc3a44791f1c3401db44d802d
+size 4813274

tokenizer_config.json

@@ -0,0 +1,1104 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<|reserved_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<|reserved_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<|reserved_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<|reserved_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<|reserved_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<|reserved_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<|reserved_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<|reserved_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<|reserved_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<|reserved_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<|reserved_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<|reserved_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<|reserved_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "19": {
+      "content": "<|reserved_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "20": {
+      "content": "<|reserved_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "21": {
+      "content": "<|reserved_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "22": {
+      "content": "<|reserved_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "23": {
+      "content": "<|reserved_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "24": {
+      "content": "<|reserved_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "25": {
+      "content": "<|reserved_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "26": {
+      "content": "<|reserved_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "27": {
+      "content": "<|reserved_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "28": {
+      "content": "<|reserved_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "29": {
+      "content": "<|reserved_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30": {
+      "content": "<|reserved_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "31": {
+      "content": "<|reserved_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32": {
+      "content": "<|reserved_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "33": {
+      "content": "<|reserved_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "34": {
+      "content": "<|reserved_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "35": {
+      "content": "<|reserved_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36": {
+      "content": "<|reserved_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "37": {
+      "content": "<|reserved_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "38": {
+      "content": "<|reserved_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "39": {
+      "content": "<|reserved_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "40": {
+      "content": "<|reserved_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "41": {
+      "content": "<|reserved_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "42": {
+      "content": "<|reserved_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "43": {
+      "content": "<|reserved_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "44": {
+      "content": "<|reserved_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "45": {
+      "content": "<|reserved_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "46": {
+      "content": "<|reserved_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "47": {
+      "content": "<|reserved_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "48": {
+      "content": "<|reserved_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49": {
+      "content": "<|reserved_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50": {
+      "content": "<|reserved_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "51": {
+      "content": "<|reserved_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "52": {
+      "content": "<|reserved_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "53": {
+      "content": "<|reserved_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "54": {
+      "content": "<|reserved_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "55": {
+      "content": "<|reserved_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "56": {
+      "content": "<|reserved_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57": {
+      "content": "<|reserved_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58": {
+      "content": "<|reserved_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "59": {
+      "content": "<|reserved_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "60": {
+      "content": "<|reserved_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "61": {
+      "content": "<|reserved_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "62": {
+      "content": "<|reserved_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "63": {
+      "content": "<|reserved_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64": {
+      "content": "<|reserved_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65": {
+      "content": "<|reserved_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "66": {
+      "content": "<|reserved_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "67": {
+      "content": "<|reserved_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "68": {
+      "content": "<|reserved_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "69": {
+      "content": "<|reserved_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "70": {
+      "content": "<|reserved_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "71": {
+      "content": "<|reserved_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "72": {
+      "content": "<|reserved_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "73": {
+      "content": "<|reserved_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "74": {
+      "content": "<|reserved_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "75": {
+      "content": "<|reserved_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "76": {
+      "content": "<|reserved_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "77": {
+      "content": "<|reserved_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "78": {
+      "content": "<|reserved_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "79": {
+      "content": "<|reserved_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "80": {
+      "content": "<|reserved_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "81": {
+      "content": "<|reserved_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "82": {
+      "content": "<|reserved_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "83": {
+      "content": "<|reserved_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "84": {
+      "content": "<|reserved_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "85": {
+      "content": "<|reserved_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "86": {
+      "content": "<|reserved_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "87": {
+      "content": "<|reserved_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "88": {
+      "content": "<|reserved_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "89": {
+      "content": "<|reserved_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "90": {
+      "content": "<|reserved_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "91": {
+      "content": "<|reserved_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92": {
+      "content": "<|reserved_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "93": {
+      "content": "<|reserved_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "94": {
+      "content": "<|reserved_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "95": {
+      "content": "<|reserved_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "96": {
+      "content": "<|reserved_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "97": {
+      "content": "<|reserved_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "98": {
+      "content": "<|reserved_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "99": {
+      "content": "<|reserved_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "<|reserved_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "<|reserved_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "<|reserved_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "<|reserved_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "\\r",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "105": {
+      "content": "▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "106": {
+      "content": "▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "107": {
+      "content": "▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "108": {
+      "content": "▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "109": {
+      "content": "▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "110": {
+      "content": "▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "111": {
+      "content": "▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "112": {
+      "content": "▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "113": {
+      "content": "▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "114": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "115": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "116": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "117": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "118": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "119": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "120": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "121": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "122": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "123": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "124": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "125": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "126": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "127": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "129": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "130": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "131": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "132": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "133": {
+      "content": "\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "134": {
+      "content": "\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] | trim + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "legacy": true,
+  "model_max_length": 8192,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,2376 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9984871406959153,
+  "eval_steps": 83,
+  "global_step": 330,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0030257186081694403,
+      "grad_norm": 28.69647459181808,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.1946,
+      "step": 1
+    },
+    {
+      "epoch": 0.006051437216338881,
+      "grad_norm": 46.535356376461294,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.2123,
+      "step": 2
+    },
+    {
+      "epoch": 0.009077155824508321,
+      "grad_norm": 26.580348193631924,
+      "learning_rate": 6e-06,
+      "loss": 1.1556,
+      "step": 3
+    },
+    {
+      "epoch": 0.012102874432677761,
+      "grad_norm": 42.77534282277984,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.0315,
+      "step": 4
+    },
+    {
+      "epoch": 0.015128593040847202,
+      "grad_norm": 16.275494364561833,
+      "learning_rate": 1e-05,
+      "loss": 0.876,
+      "step": 5
+    },
+    {
+      "epoch": 0.018154311649016642,
+      "grad_norm": 8.17885680137755,
+      "learning_rate": 1.2e-05,
+      "loss": 0.8625,
+      "step": 6
+    },
+    {
+      "epoch": 0.02118003025718608,
+      "grad_norm": 33.71594077895699,
+      "learning_rate": 1.4e-05,
+      "loss": 0.8587,
+      "step": 7
+    },
+    {
+      "epoch": 0.024205748865355523,
+      "grad_norm": 12.10712283931031,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.8204,
+      "step": 8
+    },
+    {
+      "epoch": 0.02723146747352496,
+      "grad_norm": 14.797023078319215,
+      "learning_rate": 1.8e-05,
+      "loss": 0.8517,
+      "step": 9
+    },
+    {
+      "epoch": 0.030257186081694403,
+      "grad_norm": 5.808283122077986,
+      "learning_rate": 2e-05,
+      "loss": 0.8194,
+      "step": 10
+    },
+    {
+      "epoch": 0.03328290468986384,
+      "grad_norm": 3.6048514956689637,
+      "learning_rate": 1.999951808959328e-05,
+      "loss": 0.8072,
+      "step": 11
+    },
+    {
+      "epoch": 0.036308623298033284,
+      "grad_norm": 3.53002370438567,
+      "learning_rate": 1.9998072404820648e-05,
+      "loss": 0.7756,
+      "step": 12
+    },
+    {
+      "epoch": 0.039334341906202726,
+      "grad_norm": 2.905740802249514,
+      "learning_rate": 1.9995663085020215e-05,
+      "loss": 0.7423,
+      "step": 13
+    },
+    {
+      "epoch": 0.04236006051437216,
+      "grad_norm": 3.4168458120510192,
+      "learning_rate": 1.9992290362407232e-05,
+      "loss": 0.7363,
+      "step": 14
+    },
+    {
+      "epoch": 0.0453857791225416,
+      "grad_norm": 2.761712792781197,
+      "learning_rate": 1.9987954562051724e-05,
+      "loss": 0.7546,
+      "step": 15
+    },
+    {
+      "epoch": 0.048411497730711045,
+      "grad_norm": 3.0818637598025327,
+      "learning_rate": 1.998265610184716e-05,
+      "loss": 0.7589,
+      "step": 16
+    },
+    {
+      "epoch": 0.05143721633888049,
+      "grad_norm": 3.118071353231242,
+      "learning_rate": 1.997639549247016e-05,
+      "loss": 0.7511,
+      "step": 17
+    },
+    {
+      "epoch": 0.05446293494704992,
+      "grad_norm": 3.2183269397087835,
+      "learning_rate": 1.9969173337331283e-05,
+      "loss": 0.7413,
+      "step": 18
+    },
+    {
+      "epoch": 0.057488653555219364,
+      "grad_norm": 4.661245042116266,
+      "learning_rate": 1.9960990332516875e-05,
+      "loss": 0.769,
+      "step": 19
+    },
+    {
+      "epoch": 0.060514372163388806,
+      "grad_norm": 3.7325903495658737,
+      "learning_rate": 1.995184726672197e-05,
+      "loss": 0.7762,
+      "step": 20
+    },
+    {
+      "epoch": 0.06354009077155824,
+      "grad_norm": 4.816863844430095,
+      "learning_rate": 1.9941745021174284e-05,
+      "loss": 0.7492,
+      "step": 21
+    },
+    {
+      "epoch": 0.06656580937972768,
+      "grad_norm": 4.136202257254184,
+      "learning_rate": 1.9930684569549265e-05,
+      "loss": 0.7481,
+      "step": 22
+    },
+    {
+      "epoch": 0.06959152798789713,
+      "grad_norm": 3.9111680915408664,
+      "learning_rate": 1.991866697787626e-05,
+      "loss": 0.75,
+      "step": 23
+    },
+    {
+      "epoch": 0.07261724659606657,
+      "grad_norm": 3.0125682686675646,
+      "learning_rate": 1.990569340443577e-05,
+      "loss": 0.7363,
+      "step": 24
+    },
+    {
+      "epoch": 0.07564296520423601,
+      "grad_norm": 2.9756894328848924,
+      "learning_rate": 1.989176509964781e-05,
+      "loss": 0.7089,
+      "step": 25
+    },
+    {
+      "epoch": 0.07866868381240545,
+      "grad_norm": 2.927900220452882,
+      "learning_rate": 1.9876883405951378e-05,
+      "loss": 0.7189,
+      "step": 26
+    },
+    {
+      "epoch": 0.08169440242057488,
+      "grad_norm": 3.1957652828807026,
+      "learning_rate": 1.9861049757675087e-05,
+      "loss": 0.7228,
+      "step": 27
+    },
+    {
+      "epoch": 0.08472012102874432,
+      "grad_norm": 3.0414085114978477,
+      "learning_rate": 1.9844265680898917e-05,
+      "loss": 0.7329,
+      "step": 28
+    },
+    {
+      "epoch": 0.08774583963691376,
+      "grad_norm": 2.9039201895797597,
+      "learning_rate": 1.982653279330712e-05,
+      "loss": 0.7043,
+      "step": 29
+    },
+    {
+      "epoch": 0.0907715582450832,
+      "grad_norm": 3.1835496461858503,
+      "learning_rate": 1.9807852804032306e-05,
+      "loss": 0.699,
+      "step": 30
+    },
+    {
+      "epoch": 0.09379727685325265,
+      "grad_norm": 2.6119206153518224,
+      "learning_rate": 1.9788227513490724e-05,
+      "loss": 0.7274,
+      "step": 31
+    },
+    {
+      "epoch": 0.09682299546142209,
+      "grad_norm": 2.389474693597407,
+      "learning_rate": 1.9767658813208725e-05,
+      "loss": 0.7027,
+      "step": 32
+    },
+    {
+      "epoch": 0.09984871406959153,
+      "grad_norm": 3.6204577668426294,
+      "learning_rate": 1.974614868564045e-05,
+      "loss": 0.6499,
+      "step": 33
+    },
+    {
+      "epoch": 0.10287443267776097,
+      "grad_norm": 2.7807778849597056,
+      "learning_rate": 1.9723699203976768e-05,
+      "loss": 0.7215,
+      "step": 34
+    },
+    {
+      "epoch": 0.1059001512859304,
+      "grad_norm": 3.2488604572997435,
+      "learning_rate": 1.9700312531945444e-05,
+      "loss": 0.7381,
+      "step": 35
+    },
+    {
+      "epoch": 0.10892586989409984,
+      "grad_norm": 2.8180508499440635,
+      "learning_rate": 1.96759909236026e-05,
+      "loss": 0.7036,
+      "step": 36
+    },
+    {
+      "epoch": 0.11195158850226929,
+      "grad_norm": 2.8951625696679515,
+      "learning_rate": 1.9650736723115476e-05,
+      "loss": 0.6799,
+      "step": 37
+    },
+    {
+      "epoch": 0.11497730711043873,
+      "grad_norm": 2.8052448064970017,
+      "learning_rate": 1.9624552364536472e-05,
+      "loss": 0.7312,
+      "step": 38
+    },
+    {
+      "epoch": 0.11800302571860817,
+      "grad_norm": 2.658771948223404,
+      "learning_rate": 1.9597440371568576e-05,
+      "loss": 0.7064,
+      "step": 39
+    },
+    {
+      "epoch": 0.12102874432677761,
+      "grad_norm": 33.37825731362895,
+      "learning_rate": 1.956940335732209e-05,
+      "loss": 0.7025,
+      "step": 40
+    },
+    {
+      "epoch": 0.12405446293494705,
+      "grad_norm": 2.5519953709353147,
+      "learning_rate": 1.9540444024062807e-05,
+      "loss": 0.7037,
+      "step": 41
+    },
+    {
+      "epoch": 0.12708018154311648,
+      "grad_norm": 2.4926261964588714,
+      "learning_rate": 1.9510565162951538e-05,
+      "loss": 0.7398,
+      "step": 42
+    },
+    {
+      "epoch": 0.13010590015128592,
+      "grad_norm": 3.17581775275039,
+      "learning_rate": 1.9479769653775107e-05,
+      "loss": 0.6861,
+      "step": 43
+    },
+    {
+      "epoch": 0.13313161875945537,
+      "grad_norm": 2.8350832824191015,
+      "learning_rate": 1.944806046466878e-05,
+      "loss": 0.7409,
+      "step": 44
+    },
+    {
+      "epoch": 0.1361573373676248,
+      "grad_norm": 3.013396547202102,
+      "learning_rate": 1.941544065183021e-05,
+      "loss": 0.6992,
+      "step": 45
+    },
+    {
+      "epoch": 0.13918305597579425,
+      "grad_norm": 2.4991790227079274,
+      "learning_rate": 1.9381913359224844e-05,
+      "loss": 0.6754,
+      "step": 46
+    },
+    {
+      "epoch": 0.1422087745839637,
+      "grad_norm": 2.371137405420411,
+      "learning_rate": 1.9347481818282927e-05,
+      "loss": 0.6601,
+      "step": 47
+    },
+    {
+      "epoch": 0.14523449319213314,
+      "grad_norm": 2.5608484924777684,
+      "learning_rate": 1.9312149347588035e-05,
+      "loss": 0.7101,
+      "step": 48
+    },
+    {
+      "epoch": 0.14826021180030258,
+      "grad_norm": 2.4369577435382603,
+      "learning_rate": 1.9275919352557242e-05,
+      "loss": 0.7177,
+      "step": 49
+    },
+    {
+      "epoch": 0.15128593040847202,
+      "grad_norm": 2.1725421335195834,
+      "learning_rate": 1.9238795325112867e-05,
+      "loss": 0.7132,
+      "step": 50
+    },
+    {
+      "epoch": 0.15431164901664146,
+      "grad_norm": 2.8175635584619747,
+      "learning_rate": 1.920078084334595e-05,
+      "loss": 0.6798,
+      "step": 51
+    },
+    {
+      "epoch": 0.1573373676248109,
+      "grad_norm": 7.970119121422135,
+      "learning_rate": 1.916187957117136e-05,
+      "loss": 0.6955,
+      "step": 52
+    },
+    {
+      "epoch": 0.16036308623298035,
+      "grad_norm": 3.3508509400766857,
+      "learning_rate": 1.9122095257974676e-05,
+      "loss": 0.6843,
+      "step": 53
+    },
+    {
+      "epoch": 0.16338880484114976,
+      "grad_norm": 3.375521052312449,
+      "learning_rate": 1.9081431738250815e-05,
+      "loss": 0.691,
+      "step": 54
+    },
+    {
+      "epoch": 0.1664145234493192,
+      "grad_norm": 4.070807581379976,
+      "learning_rate": 1.9039892931234434e-05,
+      "loss": 0.6731,
+      "step": 55
+    },
+    {
+      "epoch": 0.16944024205748864,
+      "grad_norm": 2.268801481261902,
+      "learning_rate": 1.8997482840522218e-05,
+      "loss": 0.677,
+      "step": 56
+    },
+    {
+      "epoch": 0.17246596066565809,
+      "grad_norm": 2.457387820783625,
+      "learning_rate": 1.895420555368697e-05,
+      "loss": 0.6922,
+      "step": 57
+    },
+    {
+      "epoch": 0.17549167927382753,
+      "grad_norm": 2.0435275180676875,
+      "learning_rate": 1.891006524188368e-05,
+      "loss": 0.6752,
+      "step": 58
+    },
+    {
+      "epoch": 0.17851739788199697,
+      "grad_norm": 2.2528990754516385,
+      "learning_rate": 1.8865066159447468e-05,
+      "loss": 0.7021,
+      "step": 59
+    },
+    {
+      "epoch": 0.1815431164901664,
+      "grad_norm": 2.8238943942406105,
+      "learning_rate": 1.881921264348355e-05,
+      "loss": 0.6953,
+      "step": 60
+    },
+    {
+      "epoch": 0.18456883509833585,
+      "grad_norm": 1.9948330242242918,
+      "learning_rate": 1.8772509113449243e-05,
+      "loss": 0.6248,
+      "step": 61
+    },
+    {
+      "epoch": 0.1875945537065053,
+      "grad_norm": 3.7523229521508163,
+      "learning_rate": 1.8724960070727974e-05,
+      "loss": 0.7073,
+      "step": 62
+    },
+    {
+      "epoch": 0.19062027231467474,
+      "grad_norm": 2.1680071456762455,
+      "learning_rate": 1.8676570098195443e-05,
+      "loss": 0.6827,
+      "step": 63
+    },
+    {
+      "epoch": 0.19364599092284418,
+      "grad_norm": 2.042062162285346,
+      "learning_rate": 1.862734385977792e-05,
+      "loss": 0.69,
+      "step": 64
+    },
+    {
+      "epoch": 0.19667170953101362,
+      "grad_norm": 2.2165386400934515,
+      "learning_rate": 1.8577286100002723e-05,
+      "loss": 0.6922,
+      "step": 65
+    },
+    {
+      "epoch": 0.19969742813918306,
+      "grad_norm": 2.2231810005372243,
+      "learning_rate": 1.8526401643540924e-05,
+      "loss": 0.7022,
+      "step": 66
+    },
+    {
+      "epoch": 0.2027231467473525,
+      "grad_norm": 2.423903019156615,
+      "learning_rate": 1.8474695394742345e-05,
+      "loss": 0.7159,
+      "step": 67
+    },
+    {
+      "epoch": 0.20574886535552195,
+      "grad_norm": 2.198025834687471,
+      "learning_rate": 1.8422172337162865e-05,
+      "loss": 0.7089,
+      "step": 68
+    },
+    {
+      "epoch": 0.2087745839636914,
+      "grad_norm": 2.0031914139514,
+      "learning_rate": 1.8368837533084092e-05,
+      "loss": 0.6897,
+      "step": 69
+    },
+    {
+      "epoch": 0.2118003025718608,
+      "grad_norm": 3.0386359279568405,
+      "learning_rate": 1.8314696123025456e-05,
+      "loss": 0.6727,
+      "step": 70
+    },
+    {
+      "epoch": 0.21482602118003025,
+      "grad_norm": 2.261529681141294,
+      "learning_rate": 1.825975332524873e-05,
+      "loss": 0.7021,
+      "step": 71
+    },
+    {
+      "epoch": 0.2178517397881997,
+      "grad_norm": 2.0495889362586808,
+      "learning_rate": 1.8204014435255136e-05,
+      "loss": 0.6882,
+      "step": 72
+    },
+    {
+      "epoch": 0.22087745839636913,
+      "grad_norm": 2.296340383646409,
+      "learning_rate": 1.8147484825274895e-05,
+      "loss": 0.6454,
+      "step": 73
+    },
+    {
+      "epoch": 0.22390317700453857,
+      "grad_norm": 2.0304893758901197,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 0.6804,
+      "step": 74
+    },
+    {
+      "epoch": 0.22692889561270801,
+      "grad_norm": 2.5133831251206344,
+      "learning_rate": 1.803207531480645e-05,
+      "loss": 0.7207,
+      "step": 75
+    },
+    {
+      "epoch": 0.22995461422087746,
+      "grad_norm": 2.1447445433471093,
+      "learning_rate": 1.797320653772707e-05,
+      "loss": 0.664,
+      "step": 76
+    },
+    {
+      "epoch": 0.2329803328290469,
+      "grad_norm": 2.028105828542751,
+      "learning_rate": 1.7913569286406606e-05,
+      "loss": 0.7106,
+      "step": 77
+    },
+    {
+      "epoch": 0.23600605143721634,
+      "grad_norm": 1.905594572089945,
+      "learning_rate": 1.785316930880745e-05,
+      "loss": 0.7199,
+      "step": 78
+    },
+    {
+      "epoch": 0.23903177004538578,
+      "grad_norm": 2.0681646724895195,
+      "learning_rate": 1.779201242640517e-05,
+      "loss": 0.6796,
+      "step": 79
+    },
+    {
+      "epoch": 0.24205748865355523,
+      "grad_norm": 1.8836218597127485,
+      "learning_rate": 1.773010453362737e-05,
+      "loss": 0.6715,
+      "step": 80
+    },
+    {
+      "epoch": 0.24508320726172467,
+      "grad_norm": 4.596541463949189,
+      "learning_rate": 1.7667451597285617e-05,
+      "loss": 0.6992,
+      "step": 81
+    },
+    {
+      "epoch": 0.2481089258698941,
+      "grad_norm": 2.0369793884589766,
+      "learning_rate": 1.7604059656000313e-05,
+      "loss": 0.7,
+      "step": 82
+    },
+    {
+      "epoch": 0.25113464447806355,
+      "grad_norm": 2.338455245767599,
+      "learning_rate": 1.7539934819618696e-05,
+      "loss": 0.6676,
+      "step": 83
+    },
+    {
+      "epoch": 0.25113464447806355,
+      "eval_loss": 0.6752901077270508,
+      "eval_runtime": 93.8585,
+      "eval_samples_per_second": 45.068,
+      "eval_steps_per_second": 0.714,
+      "step": 83
+    },
+    {
+      "epoch": 0.25416036308623297,
+      "grad_norm": 2.428048931609376,
+      "learning_rate": 1.747508326862597e-05,
+      "loss": 0.678,
+      "step": 84
+    },
+    {
+      "epoch": 0.25718608169440244,
+      "grad_norm": 2.0275496963886424,
+      "learning_rate": 1.7409511253549592e-05,
+      "loss": 0.695,
+      "step": 85
+    },
+    {
+      "epoch": 0.26021180030257185,
+      "grad_norm": 2.0508833034616156,
+      "learning_rate": 1.7343225094356857e-05,
+      "loss": 0.6928,
+      "step": 86
+    },
+    {
+      "epoch": 0.2632375189107413,
+      "grad_norm": 1.906095713213679,
+      "learning_rate": 1.727623117984575e-05,
+      "loss": 0.6578,
+      "step": 87
+    },
+    {
+      "epoch": 0.26626323751891073,
+      "grad_norm": 1.9381260380532637,
+      "learning_rate": 1.720853596702919e-05,
+      "loss": 0.6865,
+      "step": 88
+    },
+    {
+      "epoch": 0.2692889561270802,
+      "grad_norm": 2.044946626820364,
+      "learning_rate": 1.7140145980512684e-05,
+      "loss": 0.6637,
+      "step": 89
+    },
+    {
+      "epoch": 0.2723146747352496,
+      "grad_norm": 2.2577464480076745,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 0.705,
+      "step": 90
+    },
+    {
+      "epoch": 0.2753403933434191,
+      "grad_norm": 2.073404675641156,
+      "learning_rate": 1.7001308118985237e-05,
+      "loss": 0.6879,
+      "step": 91
+    },
+    {
+      "epoch": 0.2783661119515885,
+      "grad_norm": 2.0173586400260413,
+      "learning_rate": 1.6930873625456362e-05,
+      "loss": 0.6843,
+      "step": 92
+    },
+    {
+      "epoch": 0.2813918305597579,
+      "grad_norm": 2.0019518111223538,
+      "learning_rate": 1.685977111990193e-05,
+      "loss": 0.685,
+      "step": 93
+    },
+    {
+      "epoch": 0.2844175491679274,
+      "grad_norm": 2.439404052212247,
+      "learning_rate": 1.678800745532942e-05,
+      "loss": 0.6769,
+      "step": 94
+    },
+    {
+      "epoch": 0.2874432677760968,
+      "grad_norm": 2.000348467180862,
+      "learning_rate": 1.6715589548470187e-05,
+      "loss": 0.6792,
+      "step": 95
+    },
+    {
+      "epoch": 0.29046898638426627,
+      "grad_norm": 2.0229640481669877,
+      "learning_rate": 1.664252437911282e-05,
+      "loss": 0.7093,
+      "step": 96
+    },
+    {
+      "epoch": 0.2934947049924357,
+      "grad_norm": 1.9446179261078531,
+      "learning_rate": 1.6568818989430416e-05,
+      "loss": 0.6671,
+      "step": 97
+    },
+    {
+      "epoch": 0.29652042360060515,
+      "grad_norm": 2.088319167066672,
+      "learning_rate": 1.6494480483301836e-05,
+      "loss": 0.6709,
+      "step": 98
+    },
+    {
+      "epoch": 0.29954614220877457,
+      "grad_norm": 2.0371738606680427,
+      "learning_rate": 1.641951602562703e-05,
+      "loss": 0.6565,
+      "step": 99
+    },
+    {
+      "epoch": 0.30257186081694404,
+      "grad_norm": 2.039051091974588,
+      "learning_rate": 1.6343932841636455e-05,
+      "loss": 0.6774,
+      "step": 100
+    },
+    {
+      "epoch": 0.30559757942511345,
+      "grad_norm": 1.89072521062054,
+      "learning_rate": 1.6267738216194698e-05,
+      "loss": 0.6855,
+      "step": 101
+    },
+    {
+      "epoch": 0.3086232980332829,
+      "grad_norm": 1.9373416372844936,
+      "learning_rate": 1.6190939493098344e-05,
+      "loss": 0.6613,
+      "step": 102
+    },
+    {
+      "epoch": 0.31164901664145234,
+      "grad_norm": 2.4850609752400095,
+      "learning_rate": 1.6113544074368166e-05,
+      "loss": 0.6693,
+      "step": 103
+    },
+    {
+      "epoch": 0.3146747352496218,
+      "grad_norm": 1.8893955211292324,
+      "learning_rate": 1.6035559419535714e-05,
+      "loss": 0.6769,
+      "step": 104
+    },
+    {
+      "epoch": 0.3177004538577912,
+      "grad_norm": 1.9633433755541898,
+      "learning_rate": 1.5956993044924334e-05,
+      "loss": 0.6623,
+      "step": 105
+    },
+    {
+      "epoch": 0.3207261724659607,
+      "grad_norm": 2.004985996706271,
+      "learning_rate": 1.5877852522924733e-05,
+      "loss": 0.641,
+      "step": 106
+    },
+    {
+      "epoch": 0.3237518910741301,
+      "grad_norm": 1.8629977634675294,
+      "learning_rate": 1.579814548126514e-05,
+      "loss": 0.6458,
+      "step": 107
+    },
+    {
+      "epoch": 0.3267776096822995,
+      "grad_norm": 1.9494867289539974,
+      "learning_rate": 1.5717879602276123e-05,
+      "loss": 0.6418,
+      "step": 108
+    },
+    {
+      "epoch": 0.329803328290469,
+      "grad_norm": 1.8622891514920465,
+      "learning_rate": 1.5637062622150168e-05,
+      "loss": 0.6313,
+      "step": 109
+    },
+    {
+      "epoch": 0.3328290468986384,
+      "grad_norm": 1.9827293450600925,
+      "learning_rate": 1.5555702330196024e-05,
+      "loss": 0.6712,
+      "step": 110
+    },
+    {
+      "epoch": 0.3358547655068079,
+      "grad_norm": 2.4176703750653386,
+      "learning_rate": 1.547380656808797e-05,
+      "loss": 0.654,
+      "step": 111
+    },
+    {
+      "epoch": 0.3388804841149773,
+      "grad_norm": 1.9338933323273004,
+      "learning_rate": 1.5391383229110005e-05,
+      "loss": 0.6856,
+      "step": 112
+    },
+    {
+      "epoch": 0.34190620272314676,
+      "grad_norm": 2.0232362850746797,
+      "learning_rate": 1.5308440257395095e-05,
+      "loss": 0.6765,
+      "step": 113
+    },
+    {
+      "epoch": 0.34493192133131617,
+      "grad_norm": 1.9568056443475894,
+      "learning_rate": 1.5224985647159489e-05,
+      "loss": 0.676,
+      "step": 114
+    },
+    {
+      "epoch": 0.34795763993948564,
+      "grad_norm": 1.8861676872802784,
+      "learning_rate": 1.5141027441932217e-05,
+      "loss": 0.6497,
+      "step": 115
+    },
+    {
+      "epoch": 0.35098335854765506,
+      "grad_norm": 2.2756500221824787,
+      "learning_rate": 1.5056573733779848e-05,
+      "loss": 0.6743,
+      "step": 116
+    },
+    {
+      "epoch": 0.3540090771558245,
+      "grad_norm": 1.9139552054178928,
+      "learning_rate": 1.4971632662526545e-05,
+      "loss": 0.6471,
+      "step": 117
+    },
+    {
+      "epoch": 0.35703479576399394,
+      "grad_norm": 1.945783892355681,
+      "learning_rate": 1.4886212414969551e-05,
+      "loss": 0.6616,
+      "step": 118
+    },
+    {
+      "epoch": 0.3600605143721634,
+      "grad_norm": 2.3636500104137808,
+      "learning_rate": 1.4800321224090114e-05,
+      "loss": 0.6661,
+      "step": 119
+    },
+    {
+      "epoch": 0.3630862329803328,
+      "grad_norm": 1.9824827085817427,
+      "learning_rate": 1.4713967368259981e-05,
+      "loss": 0.6713,
+      "step": 120
+    },
+    {
+      "epoch": 0.3661119515885023,
+      "grad_norm": 2.215021731887088,
+      "learning_rate": 1.4627159170443504e-05,
+      "loss": 0.6658,
+      "step": 121
+    },
+    {
+      "epoch": 0.3691376701966717,
+      "grad_norm": 10.527580401090502,
+      "learning_rate": 1.4539904997395468e-05,
+      "loss": 0.6626,
+      "step": 122
+    },
+    {
+      "epoch": 0.3721633888048411,
+      "grad_norm": 2.649768108207238,
+      "learning_rate": 1.4452213258854684e-05,
+      "loss": 0.6578,
+      "step": 123
+    },
+    {
+      "epoch": 0.3751891074130106,
+      "grad_norm": 2.060396896527891,
+      "learning_rate": 1.436409240673342e-05,
+      "loss": 0.6584,
+      "step": 124
+    },
+    {
+      "epoch": 0.37821482602118,
+      "grad_norm": 2.012679002194894,
+      "learning_rate": 1.4275550934302822e-05,
+      "loss": 0.6953,
+      "step": 125
+    },
+    {
+      "epoch": 0.3812405446293495,
+      "grad_norm": 9.375765884143409,
+      "learning_rate": 1.4186597375374283e-05,
+      "loss": 0.6594,
+      "step": 126
+    },
+    {
+      "epoch": 0.3842662632375189,
+      "grad_norm": 1.9968667010149235,
+      "learning_rate": 1.4097240303476955e-05,
+      "loss": 0.6657,
+      "step": 127
+    },
+    {
+      "epoch": 0.38729198184568836,
+      "grad_norm": 1.9638652973708315,
+      "learning_rate": 1.4007488331031409e-05,
+      "loss": 0.6402,
+      "step": 128
+    },
+    {
+      "epoch": 0.3903177004538578,
+      "grad_norm": 2.6974851402436326,
+      "learning_rate": 1.391735010851956e-05,
+      "loss": 0.6999,
+      "step": 129
+    },
+    {
+      "epoch": 0.39334341906202724,
+      "grad_norm": 2.3946120322541145,
+      "learning_rate": 1.3826834323650899e-05,
+      "loss": 0.6929,
+      "step": 130
+    },
+    {
+      "epoch": 0.39636913767019666,
+      "grad_norm": 2.606665967226635,
+      "learning_rate": 1.3735949700525164e-05,
+      "loss": 0.6406,
+      "step": 131
+    },
+    {
+      "epoch": 0.39939485627836613,
+      "grad_norm": 125.89612873667855,
+      "learning_rate": 1.3644704998791501e-05,
+      "loss": 0.6678,
+      "step": 132
+    },
+    {
+      "epoch": 0.40242057488653554,
+      "grad_norm": 3.514135273140995,
+      "learning_rate": 1.3553109012804162e-05,
+      "loss": 0.6687,
+      "step": 133
+    },
+    {
+      "epoch": 0.405446293494705,
+      "grad_norm": 4.240922776003794,
+      "learning_rate": 1.346117057077493e-05,
+      "loss": 0.658,
+      "step": 134
+    },
+    {
+      "epoch": 0.4084720121028744,
+      "grad_norm": 2.1855195011412922,
+      "learning_rate": 1.3368898533922202e-05,
+      "loss": 0.6677,
+      "step": 135
+    },
+    {
+      "epoch": 0.4114977307110439,
+      "grad_norm": 2.463546469392426,
+      "learning_rate": 1.3276301795616937e-05,
+      "loss": 0.6627,
+      "step": 136
+    },
+    {
+      "epoch": 0.4145234493192133,
+      "grad_norm": 2.133545623738071,
+      "learning_rate": 1.3183389280525497e-05,
+      "loss": 0.6928,
+      "step": 137
+    },
+    {
+      "epoch": 0.4175491679273828,
+      "grad_norm": 2.535405634645763,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 0.644,
+      "step": 138
+    },
+    {
+      "epoch": 0.4205748865355522,
+      "grad_norm": 2.1936138643866223,
+      "learning_rate": 1.2996652769962567e-05,
+      "loss": 0.686,
+      "step": 139
+    },
+    {
+      "epoch": 0.4236006051437216,
+      "grad_norm": 1.9156629913412506,
+      "learning_rate": 1.2902846772544625e-05,
+      "loss": 0.6528,
+      "step": 140
+    },
+    {
+      "epoch": 0.4266263237518911,
+      "grad_norm": 1.902537792043501,
+      "learning_rate": 1.2808760992712923e-05,
+      "loss": 0.6542,
+      "step": 141
+    },
+    {
+      "epoch": 0.4296520423600605,
+      "grad_norm": 2.0509718747044197,
+      "learning_rate": 1.2714404498650743e-05,
+      "loss": 0.6259,
+      "step": 142
+    },
+    {
+      "epoch": 0.43267776096822996,
+      "grad_norm": 3.364345349502592,
+      "learning_rate": 1.2619786384633374e-05,
+      "loss": 0.6699,
+      "step": 143
+    },
+    {
+      "epoch": 0.4357034795763994,
+      "grad_norm": 3.6100731074556656,
+      "learning_rate": 1.252491577015158e-05,
+      "loss": 0.6583,
+      "step": 144
+    },
+    {
+      "epoch": 0.43872919818456885,
+      "grad_norm": 1.8986778970529314,
+      "learning_rate": 1.242980179903264e-05,
+      "loss": 0.6519,
+      "step": 145
+    },
+    {
+      "epoch": 0.44175491679273826,
+      "grad_norm": 2.0039061587882623,
+      "learning_rate": 1.2334453638559057e-05,
+      "loss": 0.6701,
+      "step": 146
+    },
+    {
+      "epoch": 0.44478063540090773,
+      "grad_norm": 2.0871498766669467,
+      "learning_rate": 1.2238880478584987e-05,
+      "loss": 0.6336,
+      "step": 147
+    },
+    {
+      "epoch": 0.44780635400907715,
+      "grad_norm": 2.260892934011929,
+      "learning_rate": 1.2143091530650508e-05,
+      "loss": 0.6655,
+      "step": 148
+    },
+    {
+      "epoch": 0.4508320726172466,
+      "grad_norm": 1.9595683172138556,
+      "learning_rate": 1.2047096027093798e-05,
+      "loss": 0.6342,
+      "step": 149
+    },
+    {
+      "epoch": 0.45385779122541603,
+      "grad_norm": 1.8964347487859918,
+      "learning_rate": 1.1950903220161286e-05,
+      "loss": 0.6447,
+      "step": 150
+    },
+    {
+      "epoch": 0.4568835098335855,
+      "grad_norm": 2.0465943957039325,
+      "learning_rate": 1.185452238111591e-05,
+      "loss": 0.6398,
+      "step": 151
+    },
+    {
+      "epoch": 0.4599092284417549,
+      "grad_norm": 2.2749337860012186,
+      "learning_rate": 1.1757962799343548e-05,
+      "loss": 0.6228,
+      "step": 152
+    },
+    {
+      "epoch": 0.4629349470499244,
+      "grad_norm": 1.9360234732478145,
+      "learning_rate": 1.1661233781457655e-05,
+      "loss": 0.6271,
+      "step": 153
+    },
+    {
+      "epoch": 0.4659606656580938,
+      "grad_norm": 6.391362683845854,
+      "learning_rate": 1.156434465040231e-05,
+      "loss": 0.6102,
+      "step": 154
+    },
+    {
+      "epoch": 0.4689863842662632,
+      "grad_norm": 2.6964140732000597,
+      "learning_rate": 1.1467304744553618e-05,
+      "loss": 0.6381,
+      "step": 155
+    },
+    {
+      "epoch": 0.4720121028744327,
+      "grad_norm": 2.040478374694881,
+      "learning_rate": 1.1370123416819683e-05,
+      "loss": 0.6891,
+      "step": 156
+    },
+    {
+      "epoch": 0.4750378214826021,
+      "grad_norm": 2.5024088180061996,
+      "learning_rate": 1.1272810033739134e-05,
+      "loss": 0.68,
+      "step": 157
+    },
+    {
+      "epoch": 0.47806354009077157,
+      "grad_norm": 5.034110912343636,
+      "learning_rate": 1.1175373974578378e-05,
+      "loss": 0.6357,
+      "step": 158
+    },
+    {
+      "epoch": 0.481089258698941,
+      "grad_norm": 1.8088504044607232,
+      "learning_rate": 1.1077824630427593e-05,
+      "loss": 0.6596,
+      "step": 159
+    },
+    {
+      "epoch": 0.48411497730711045,
+      "grad_norm": 1.9005713985258568,
+      "learning_rate": 1.098017140329561e-05,
+      "loss": 0.6198,
+      "step": 160
+    },
+    {
+      "epoch": 0.48714069591527986,
+      "grad_norm": 1.9342848652449698,
+      "learning_rate": 1.0882423705203698e-05,
+      "loss": 0.6396,
+      "step": 161
+    },
+    {
+      "epoch": 0.49016641452344933,
+      "grad_norm": 2.829885337118367,
+      "learning_rate": 1.0784590957278452e-05,
+      "loss": 0.6673,
+      "step": 162
+    },
+    {
+      "epoch": 0.49319213313161875,
+      "grad_norm": 1.9563381110322227,
+      "learning_rate": 1.0686682588843737e-05,
+      "loss": 0.6378,
+      "step": 163
+    },
+    {
+      "epoch": 0.4962178517397882,
+      "grad_norm": 2.456309042364747,
+      "learning_rate": 1.058870803651189e-05,
+      "loss": 0.6297,
+      "step": 164
+    },
+    {
+      "epoch": 0.49924357034795763,
+      "grad_norm": 1.929682148235842,
+      "learning_rate": 1.0490676743274181e-05,
+      "loss": 0.6579,
+      "step": 165
+    },
+    {
+      "epoch": 0.5022692889561271,
+      "grad_norm": 2.1866586377485624,
+      "learning_rate": 1.0392598157590687e-05,
+      "loss": 0.6704,
+      "step": 166
+    },
+    {
+      "epoch": 0.5022692889561271,
+      "eval_loss": 0.6389465928077698,
+      "eval_runtime": 89.0761,
+      "eval_samples_per_second": 47.488,
+      "eval_steps_per_second": 0.752,
+      "step": 166
+    },
+    {
+      "epoch": 0.5052950075642966,
+      "grad_norm": 2.7293134459227932,
+      "learning_rate": 1.0294481732479635e-05,
+      "loss": 0.6475,
+      "step": 167
+    },
+    {
+      "epoch": 0.5083207261724659,
+      "grad_norm": 2.1860750738467973,
+      "learning_rate": 1.0196336924606282e-05,
+      "loss": 0.6845,
+      "step": 168
+    },
+    {
+      "epoch": 0.5113464447806354,
+      "grad_norm": 1.9577090354755105,
+      "learning_rate": 1.0098173193371498e-05,
+      "loss": 0.6386,
+      "step": 169
+    },
+    {
+      "epoch": 0.5143721633888049,
+      "grad_norm": 1.7813398109730993,
+      "learning_rate": 1e-05,
+      "loss": 0.6397,
+      "step": 170
+    },
+    {
+      "epoch": 0.5173978819969742,
+      "grad_norm": 2.044986488285846,
+      "learning_rate": 9.901826806628505e-06,
+      "loss": 0.6212,
+      "step": 171
+    },
+    {
+      "epoch": 0.5204236006051437,
+      "grad_norm": 1.769516031150374,
+      "learning_rate": 9.80366307539372e-06,
+      "loss": 0.6136,
+      "step": 172
+    },
+    {
+      "epoch": 0.5234493192133132,
+      "grad_norm": 6.456975961949371,
+      "learning_rate": 9.705518267520369e-06,
+      "loss": 0.6348,
+      "step": 173
+    },
+    {
+      "epoch": 0.5264750378214826,
+      "grad_norm": 2.5315009637312036,
+      "learning_rate": 9.607401842409318e-06,
+      "loss": 0.6428,
+      "step": 174
+    },
+    {
+      "epoch": 0.529500756429652,
+      "grad_norm": 2.988285644385764,
+      "learning_rate": 9.50932325672582e-06,
+      "loss": 0.6335,
+      "step": 175
+    },
+    {
+      "epoch": 0.5325264750378215,
+      "grad_norm": 1.914633603140675,
+      "learning_rate": 9.41129196348811e-06,
+      "loss": 0.6446,
+      "step": 176
+    },
+    {
+      "epoch": 0.5355521936459909,
+      "grad_norm": 2.1586892262096753,
+      "learning_rate": 9.313317411156265e-06,
+      "loss": 0.6875,
+      "step": 177
+    },
+    {
+      "epoch": 0.5385779122541604,
+      "grad_norm": 2.09973624901808,
+      "learning_rate": 9.215409042721553e-06,
+      "loss": 0.6286,
+      "step": 178
+    },
+    {
+      "epoch": 0.5416036308623298,
+      "grad_norm": 2.1121991469118373,
+      "learning_rate": 9.117576294796307e-06,
+      "loss": 0.6086,
+      "step": 179
+    },
+    {
+      "epoch": 0.5446293494704992,
+      "grad_norm": 2.970101791108074,
+      "learning_rate": 9.019828596704394e-06,
+      "loss": 0.6201,
+      "step": 180
+    },
+    {
+      "epoch": 0.5476550680786687,
+      "grad_norm": 2.797557758822073,
+      "learning_rate": 8.922175369572407e-06,
+      "loss": 0.666,
+      "step": 181
+    },
+    {
+      "epoch": 0.5506807866868382,
+      "grad_norm": 1.9321335437019027,
+      "learning_rate": 8.824626025421625e-06,
+      "loss": 0.5977,
+      "step": 182
+    },
+    {
+      "epoch": 0.5537065052950075,
+      "grad_norm": 1.971967748577256,
+      "learning_rate": 8.72718996626087e-06,
+      "loss": 0.6201,
+      "step": 183
+    },
+    {
+      "epoch": 0.556732223903177,
+      "grad_norm": 3.0984688964644103,
+      "learning_rate": 8.629876583180322e-06,
+      "loss": 0.6142,
+      "step": 184
+    },
+    {
+      "epoch": 0.5597579425113465,
+      "grad_norm": 2.623594180878439,
+      "learning_rate": 8.532695255446384e-06,
+      "loss": 0.6123,
+      "step": 185
+    },
+    {
+      "epoch": 0.5627836611195158,
+      "grad_norm": 1.9333898094978612,
+      "learning_rate": 8.43565534959769e-06,
+      "loss": 0.6169,
+      "step": 186
+    },
+    {
+      "epoch": 0.5658093797276853,
+      "grad_norm": 1.765583174562486,
+      "learning_rate": 8.338766218542348e-06,
+      "loss": 0.5971,
+      "step": 187
+    },
+    {
+      "epoch": 0.5688350983358548,
+      "grad_norm": 2.0010679040329427,
+      "learning_rate": 8.242037200656455e-06,
+      "loss": 0.6574,
+      "step": 188
+    },
+    {
+      "epoch": 0.5718608169440242,
+      "grad_norm": 4.98264842883333,
+      "learning_rate": 8.145477618884092e-06,
+      "loss": 0.6182,
+      "step": 189
+    },
+    {
+      "epoch": 0.5748865355521936,
+      "grad_norm": 1.8354394720905292,
+      "learning_rate": 8.04909677983872e-06,
+      "loss": 0.6295,
+      "step": 190
+    },
+    {
+      "epoch": 0.5779122541603631,
+      "grad_norm": 1.7610448288238965,
+      "learning_rate": 7.952903972906205e-06,
+      "loss": 0.6034,
+      "step": 191
+    },
+    {
+      "epoch": 0.5809379727685325,
+      "grad_norm": 1.9152183775112974,
+      "learning_rate": 7.856908469349495e-06,
+      "loss": 0.6349,
+      "step": 192
+    },
+    {
+      "epoch": 0.583963691376702,
+      "grad_norm": 1.975212156731082,
+      "learning_rate": 7.761119521415017e-06,
+      "loss": 0.6311,
+      "step": 193
+    },
+    {
+      "epoch": 0.5869894099848714,
+      "grad_norm": 13.200664607058753,
+      "learning_rate": 7.66554636144095e-06,
+      "loss": 0.6415,
+      "step": 194
+    },
+    {
+      "epoch": 0.5900151285930408,
+      "grad_norm": 2.5875429359472633,
+      "learning_rate": 7.570198200967363e-06,
+      "loss": 0.6507,
+      "step": 195
+    },
+    {
+      "epoch": 0.5930408472012103,
+      "grad_norm": 2.593631327870592,
+      "learning_rate": 7.4750842298484205e-06,
+      "loss": 0.6313,
+      "step": 196
+    },
+    {
+      "epoch": 0.5960665658093798,
+      "grad_norm": 2.276110525495816,
+      "learning_rate": 7.380213615366627e-06,
+      "loss": 0.6519,
+      "step": 197
+    },
+    {
+      "epoch": 0.5990922844175491,
+      "grad_norm": 1.8935451273928605,
+      "learning_rate": 7.285595501349259e-06,
+      "loss": 0.6174,
+      "step": 198
+    },
+    {
+      "epoch": 0.6021180030257186,
+      "grad_norm": 2.2562062680826993,
+      "learning_rate": 7.191239007287082e-06,
+      "loss": 0.6373,
+      "step": 199
+    },
+    {
+      "epoch": 0.6051437216338881,
+      "grad_norm": 2.0887824983462786,
+      "learning_rate": 7.097153227455379e-06,
+      "loss": 0.6684,
+      "step": 200
+    },
+    {
+      "epoch": 0.6081694402420574,
+      "grad_norm": 2.067806827035956,
+      "learning_rate": 7.003347230037434e-06,
+      "loss": 0.6458,
+      "step": 201
+    },
+    {
+      "epoch": 0.6111951588502269,
+      "grad_norm": 2.2400710241102555,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 0.6224,
+      "step": 202
+    },
+    {
+      "epoch": 0.6142208774583964,
+      "grad_norm": 3.530109217003973,
+      "learning_rate": 6.816610719474503e-06,
+      "loss": 0.6029,
+      "step": 203
+    },
+    {
+      "epoch": 0.6172465960665658,
+      "grad_norm": 1.9437166356375082,
+      "learning_rate": 6.723698204383067e-06,
+      "loss": 0.6237,
+      "step": 204
+    },
+    {
+      "epoch": 0.6202723146747352,
+      "grad_norm": 4.601296861932386,
+      "learning_rate": 6.631101466077801e-06,
+      "loss": 0.6101,
+      "step": 205
+    },
+    {
+      "epoch": 0.6232980332829047,
+      "grad_norm": 1.7734035043229037,
+      "learning_rate": 6.538829429225068e-06,
+      "loss": 0.6144,
+      "step": 206
+    },
+    {
+      "epoch": 0.6263237518910741,
+      "grad_norm": 3.3875264361334065,
+      "learning_rate": 6.446890987195842e-06,
+      "loss": 0.6263,
+      "step": 207
+    },
+    {
+      "epoch": 0.6293494704992436,
+      "grad_norm": 1.837402458317683,
+      "learning_rate": 6.355295001208504e-06,
+      "loss": 0.651,
+      "step": 208
+    },
+    {
+      "epoch": 0.632375189107413,
+      "grad_norm": 1.8127137816199999,
+      "learning_rate": 6.2640502994748375e-06,
+      "loss": 0.6031,
+      "step": 209
+    },
+    {
+      "epoch": 0.6354009077155824,
+      "grad_norm": 2.222119352037505,
+      "learning_rate": 6.173165676349103e-06,
+      "loss": 0.6341,
+      "step": 210
+    },
+    {
+      "epoch": 0.6384266263237519,
+      "grad_norm": 2.0517413682681878,
+      "learning_rate": 6.082649891480441e-06,
+      "loss": 0.6012,
+      "step": 211
+    },
+    {
+      "epoch": 0.6414523449319214,
+      "grad_norm": 1.743000217931073,
+      "learning_rate": 5.9925116689685925e-06,
+      "loss": 0.612,
+      "step": 212
+    },
+    {
+      "epoch": 0.6444780635400907,
+      "grad_norm": 1.893932549286191,
+      "learning_rate": 5.902759696523046e-06,
+      "loss": 0.6139,
+      "step": 213
+    },
+    {
+      "epoch": 0.6475037821482602,
+      "grad_norm": 1.7655154916634883,
+      "learning_rate": 5.813402624625722e-06,
+      "loss": 0.6045,
+      "step": 214
+    },
+    {
+      "epoch": 0.6505295007564297,
+      "grad_norm": 2.3122722500829185,
+      "learning_rate": 5.724449065697182e-06,
+      "loss": 0.6283,
+      "step": 215
+    },
+    {
+      "epoch": 0.653555219364599,
+      "grad_norm": 2.07646899358201,
+      "learning_rate": 5.635907593266578e-06,
+      "loss": 0.6011,
+      "step": 216
+    },
+    {
+      "epoch": 0.6565809379727685,
+      "grad_norm": 1.974337195806504,
+      "learning_rate": 5.54778674114532e-06,
+      "loss": 0.6322,
+      "step": 217
+    },
+    {
+      "epoch": 0.659606656580938,
+      "grad_norm": 1.7797760085297933,
+      "learning_rate": 5.460095002604533e-06,
+      "loss": 0.6271,
+      "step": 218
+    },
+    {
+      "epoch": 0.6626323751891074,
+      "grad_norm": 1.8906339851795884,
+      "learning_rate": 5.3728408295565e-06,
+      "loss": 0.6392,
+      "step": 219
+    },
+    {
+      "epoch": 0.6656580937972768,
+      "grad_norm": 1.7408037225823225,
+      "learning_rate": 5.286032631740023e-06,
+      "loss": 0.6153,
+      "step": 220
+    },
+    {
+      "epoch": 0.6686838124054463,
+      "grad_norm": 1.7150384120846642,
+      "learning_rate": 5.199678775909889e-06,
+      "loss": 0.5994,
+      "step": 221
+    },
+    {
+      "epoch": 0.6717095310136157,
+      "grad_norm": 2.4913211552340067,
+      "learning_rate": 5.1137875850304545e-06,
+      "loss": 0.6101,
+      "step": 222
+    },
+    {
+      "epoch": 0.6747352496217852,
+      "grad_norm": 1.783893713744158,
+      "learning_rate": 5.0283673374734546e-06,
+      "loss": 0.6318,
+      "step": 223
+    },
+    {
+      "epoch": 0.6777609682299546,
+      "grad_norm": 1.7107399741480709,
+      "learning_rate": 4.943426266220156e-06,
+      "loss": 0.6129,
+      "step": 224
+    },
+    {
+      "epoch": 0.680786686838124,
+      "grad_norm": 1.836722334744728,
+      "learning_rate": 4.858972558067784e-06,
+      "loss": 0.5994,
+      "step": 225
+    },
+    {
+      "epoch": 0.6838124054462935,
+      "grad_norm": 2.108359381810314,
+      "learning_rate": 4.775014352840512e-06,
+      "loss": 0.615,
+      "step": 226
+    },
+    {
+      "epoch": 0.686838124054463,
+      "grad_norm": 2.4528528203456386,
+      "learning_rate": 4.691559742604906e-06,
+      "loss": 0.6218,
+      "step": 227
+    },
+    {
+      "epoch": 0.6898638426626323,
+      "grad_norm": 2.9562372553126677,
+      "learning_rate": 4.608616770889998e-06,
+      "loss": 0.6055,
+      "step": 228
+    },
+    {
+      "epoch": 0.6928895612708018,
+      "grad_norm": 2.23721294737496,
+      "learning_rate": 4.526193431912038e-06,
+      "loss": 0.6297,
+      "step": 229
+    },
+    {
+      "epoch": 0.6959152798789713,
+      "grad_norm": 2.948141809060743,
+      "learning_rate": 4.444297669803981e-06,
+      "loss": 0.6631,
+      "step": 230
+    },
+    {
+      "epoch": 0.6989409984871406,
+      "grad_norm": 2.7688260603953614,
+      "learning_rate": 4.362937377849832e-06,
+      "loss": 0.6086,
+      "step": 231
+    },
+    {
+      "epoch": 0.7019667170953101,
+      "grad_norm": 1.9975679057945175,
+      "learning_rate": 4.282120397723879e-06,
+      "loss": 0.6059,
+      "step": 232
+    },
+    {
+      "epoch": 0.7049924357034796,
+      "grad_norm": 2.0441528068066583,
+      "learning_rate": 4.2018545187348645e-06,
+      "loss": 0.612,
+      "step": 233
+    },
+    {
+      "epoch": 0.708018154311649,
+      "grad_norm": 1.7827953299318366,
+      "learning_rate": 4.12214747707527e-06,
+      "loss": 0.6223,
+      "step": 234
+    },
+    {
+      "epoch": 0.7110438729198184,
+      "grad_norm": 1.910631194940744,
+      "learning_rate": 4.043006955075667e-06,
+      "loss": 0.6216,
+      "step": 235
+    },
+    {
+      "epoch": 0.7140695915279879,
+      "grad_norm": 2.2327872483205664,
+      "learning_rate": 3.964440580464286e-06,
+      "loss": 0.6363,
+      "step": 236
+    },
+    {
+      "epoch": 0.7170953101361573,
+      "grad_norm": 1.8553908596509907,
+      "learning_rate": 3.8864559256318375e-06,
+      "loss": 0.6121,
+      "step": 237
+    },
+    {
+      "epoch": 0.7201210287443268,
+      "grad_norm": 1.8523636314789427,
+      "learning_rate": 3.8090605069016596e-06,
+      "loss": 0.6496,
+      "step": 238
+    },
+    {
+      "epoch": 0.7231467473524962,
+      "grad_norm": 1.9267223174964587,
+      "learning_rate": 3.7322617838053066e-06,
+      "loss": 0.6221,
+      "step": 239
+    },
+    {
+      "epoch": 0.7261724659606656,
+      "grad_norm": 2.5477420067834733,
+      "learning_rate": 3.6560671583635467e-06,
+      "loss": 0.6533,
+      "step": 240
+    },
+    {
+      "epoch": 0.7291981845688351,
+      "grad_norm": 2.086091207989975,
+      "learning_rate": 3.58048397437297e-06,
+      "loss": 0.6557,
+      "step": 241
+    },
+    {
+      "epoch": 0.7322239031770046,
+      "grad_norm": 1.7198590873048778,
+      "learning_rate": 3.505519516698165e-06,
+      "loss": 0.6089,
+      "step": 242
+    },
+    {
+      "epoch": 0.735249621785174,
+      "grad_norm": 1.7451800185500015,
+      "learning_rate": 3.4311810105695875e-06,
+      "loss": 0.5903,
+      "step": 243
+    },
+    {
+      "epoch": 0.7382753403933434,
+      "grad_norm": 1.827742556162237,
+      "learning_rate": 3.3574756208871862e-06,
+      "loss": 0.6189,
+      "step": 244
+    },
+    {
+      "epoch": 0.7413010590015129,
+      "grad_norm": 1.738634389252119,
+      "learning_rate": 3.284410451529816e-06,
+      "loss": 0.6098,
+      "step": 245
+    },
+    {
+      "epoch": 0.7443267776096822,
+      "grad_norm": 2.4650262506220617,
+      "learning_rate": 3.2119925446705824e-06,
+      "loss": 0.622,
+      "step": 246
+    },
+    {
+      "epoch": 0.7473524962178517,
+      "grad_norm": 1.9057562551451306,
+      "learning_rate": 3.140228880098074e-06,
+      "loss": 0.6213,
+      "step": 247
+    },
+    {
+      "epoch": 0.7503782148260212,
+      "grad_norm": 1.7767572926898476,
+      "learning_rate": 3.069126374543643e-06,
+      "loss": 0.6103,
+      "step": 248
+    },
+    {
+      "epoch": 0.7534039334341907,
+      "grad_norm": 1.7615575905509537,
+      "learning_rate": 2.998691881014765e-06,
+      "loss": 0.5892,
+      "step": 249
+    },
+    {
+      "epoch": 0.7534039334341907,
+      "eval_loss": 0.6087134480476379,
+      "eval_runtime": 88.9685,
+      "eval_samples_per_second": 47.545,
+      "eval_steps_per_second": 0.753,
+      "step": 249
+    },
+    {
+      "epoch": 0.75642965204236,
+      "grad_norm": 1.9054940488072203,
+      "learning_rate": 2.9289321881345257e-06,
+      "loss": 0.6151,
+      "step": 250
+    },
+    {
+      "epoch": 0.7594553706505295,
+      "grad_norm": 1.7961329037995988,
+      "learning_rate": 2.859854019487318e-06,
+      "loss": 0.6122,
+      "step": 251
+    },
+    {
+      "epoch": 0.762481089258699,
+      "grad_norm": 2.008011636688375,
+      "learning_rate": 2.791464032970812e-06,
+      "loss": 0.6134,
+      "step": 252
+    },
+    {
+      "epoch": 0.7655068078668684,
+      "grad_norm": 1.802889816029653,
+      "learning_rate": 2.723768820154251e-06,
+      "loss": 0.606,
+      "step": 253
+    },
+    {
+      "epoch": 0.7685325264750378,
+      "grad_norm": 1.7123288009118462,
+      "learning_rate": 2.656774905643147e-06,
+      "loss": 0.599,
+      "step": 254
+    },
+    {
+      "epoch": 0.7715582450832073,
+      "grad_norm": 1.872010012601884,
+      "learning_rate": 2.5904887464504115e-06,
+      "loss": 0.6122,
+      "step": 255
+    },
+    {
+      "epoch": 0.7745839636913767,
+      "grad_norm": 1.7931604063599083,
+      "learning_rate": 2.5249167313740307e-06,
+      "loss": 0.6184,
+      "step": 256
+    },
+    {
+      "epoch": 0.7776096822995462,
+      "grad_norm": 5.906281110948661,
+      "learning_rate": 2.4600651803813057e-06,
+      "loss": 0.6212,
+      "step": 257
+    },
+    {
+      "epoch": 0.7806354009077155,
+      "grad_norm": 1.796522835609395,
+      "learning_rate": 2.395940343999691e-06,
+      "loss": 0.6275,
+      "step": 258
+    },
+    {
+      "epoch": 0.783661119515885,
+      "grad_norm": 2.502567467661614,
+      "learning_rate": 2.332548402714385e-06,
+      "loss": 0.6131,
+      "step": 259
+    },
+    {
+      "epoch": 0.7866868381240545,
+      "grad_norm": 1.7721464863028324,
+      "learning_rate": 2.26989546637263e-06,
+      "loss": 0.6312,
+      "step": 260
+    },
+    {
+      "epoch": 0.789712556732224,
+      "grad_norm": 2.7446340546388903,
+      "learning_rate": 2.207987573594833e-06,
+      "loss": 0.6305,
+      "step": 261
+    },
+    {
+      "epoch": 0.7927382753403933,
+      "grad_norm": 1.8224754193860417,
+      "learning_rate": 2.146830691192553e-06,
+      "loss": 0.5943,
+      "step": 262
+    },
+    {
+      "epoch": 0.7957639939485628,
+      "grad_norm": 2.039467832689681,
+      "learning_rate": 2.086430713593397e-06,
+      "loss": 0.6301,
+      "step": 263
+    },
+    {
+      "epoch": 0.7987897125567323,
+      "grad_norm": 10.038334257050249,
+      "learning_rate": 2.02679346227293e-06,
+      "loss": 0.6251,
+      "step": 264
+    },
+    {
+      "epoch": 0.8018154311649016,
+      "grad_norm": 1.77925140677465,
+      "learning_rate": 1.967924685193552e-06,
+      "loss": 0.5986,
+      "step": 265
+    },
+    {
+      "epoch": 0.8048411497730711,
+      "grad_norm": 1.8193241378693117,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 0.6426,
+      "step": 266
+    },
+    {
+      "epoch": 0.8078668683812406,
+      "grad_norm": 1.7632326770584787,
+      "learning_rate": 1.8525151747251058e-06,
+      "loss": 0.5756,
+      "step": 267
+    },
+    {
+      "epoch": 0.81089258698941,
+      "grad_norm": 1.7943311933481843,
+      "learning_rate": 1.7959855647448642e-06,
+      "loss": 0.6144,
+      "step": 268
+    },
+    {
+      "epoch": 0.8139183055975794,
+      "grad_norm": 1.7517176357017044,
+      "learning_rate": 1.7402466747512704e-06,
+      "loss": 0.6105,
+      "step": 269
+    },
+    {
+      "epoch": 0.8169440242057489,
+      "grad_norm": 2.0420002751411577,
+      "learning_rate": 1.6853038769745466e-06,
+      "loss": 0.6167,
+      "step": 270
+    },
+    {
+      "epoch": 0.8199697428139183,
+      "grad_norm": 1.675277078717734,
+      "learning_rate": 1.6311624669159064e-06,
+      "loss": 0.5983,
+      "step": 271
+    },
+    {
+      "epoch": 0.8229954614220878,
+      "grad_norm": 1.8699956812574887,
+      "learning_rate": 1.577827662837136e-06,
+      "loss": 0.5887,
+      "step": 272
+    },
+    {
+      "epoch": 0.8260211800302572,
+      "grad_norm": 1.942186575025359,
+      "learning_rate": 1.5253046052576559e-06,
+      "loss": 0.6227,
+      "step": 273
+    },
+    {
+      "epoch": 0.8290468986384266,
+      "grad_norm": 1.7140913453292885,
+      "learning_rate": 1.4735983564590784e-06,
+      "loss": 0.5889,
+      "step": 274
+    },
+    {
+      "epoch": 0.8320726172465961,
+      "grad_norm": 1.8602199384237519,
+      "learning_rate": 1.4227138999972801e-06,
+      "loss": 0.6156,
+      "step": 275
+    },
+    {
+      "epoch": 0.8350983358547656,
+      "grad_norm": 1.7357383944516909,
+      "learning_rate": 1.3726561402220818e-06,
+      "loss": 0.6231,
+      "step": 276
+    },
+    {
+      "epoch": 0.8381240544629349,
+      "grad_norm": 2.049034834900203,
+      "learning_rate": 1.3234299018045615e-06,
+      "loss": 0.5762,
+      "step": 277
+    },
+    {
+      "epoch": 0.8411497730711044,
+      "grad_norm": 1.8899426483696566,
+      "learning_rate": 1.2750399292720284e-06,
+      "loss": 0.6271,
+      "step": 278
+    },
+    {
+      "epoch": 0.8441754916792739,
+      "grad_norm": 1.7902118508514344,
+      "learning_rate": 1.2274908865507595e-06,
+      "loss": 0.5865,
+      "step": 279
+    },
+    {
+      "epoch": 0.8472012102874432,
+      "grad_norm": 1.7796598756657644,
+      "learning_rate": 1.1807873565164507e-06,
+      "loss": 0.5966,
+      "step": 280
+    },
+    {
+      "epoch": 0.8502269288956127,
+      "grad_norm": 1.998204889741657,
+      "learning_rate": 1.1349338405525368e-06,
+      "loss": 0.6121,
+      "step": 281
+    },
+    {
+      "epoch": 0.8532526475037822,
+      "grad_norm": 1.8591997510503189,
+      "learning_rate": 1.0899347581163222e-06,
+      "loss": 0.5947,
+      "step": 282
+    },
+    {
+      "epoch": 0.8562783661119516,
+      "grad_norm": 2.091403547509914,
+      "learning_rate": 1.045794446313031e-06,
+      "loss": 0.6099,
+      "step": 283
+    },
+    {
+      "epoch": 0.859304084720121,
+      "grad_norm": 5.552258074388298,
+      "learning_rate": 1.0025171594777872e-06,
+      "loss": 0.6001,
+      "step": 284
+    },
+    {
+      "epoch": 0.8623298033282905,
+      "grad_norm": 1.984667974599296,
+      "learning_rate": 9.601070687655667e-07,
+      "loss": 0.6214,
+      "step": 285
+    },
+    {
+      "epoch": 0.8653555219364599,
+      "grad_norm": 1.9108222703571809,
+      "learning_rate": 9.185682617491865e-07,
+      "loss": 0.6326,
+      "step": 286
+    },
+    {
+      "epoch": 0.8683812405446294,
+      "grad_norm": 1.7777131621422688,
+      "learning_rate": 8.779047420253239e-07,
+      "loss": 0.6071,
+      "step": 287
+    },
+    {
+      "epoch": 0.8714069591527988,
+      "grad_norm": 1.7623805284409448,
+      "learning_rate": 8.381204288286415e-07,
+      "loss": 0.6189,
+      "step": 288
+    },
+    {
+      "epoch": 0.8744326777609682,
+      "grad_norm": 1.7371506833039154,
+      "learning_rate": 7.992191566540519e-07,
+      "loss": 0.5895,
+      "step": 289
+    },
+    {
+      "epoch": 0.8774583963691377,
+      "grad_norm": 1.8174334539956483,
+      "learning_rate": 7.612046748871327e-07,
+      "loss": 0.6241,
+      "step": 290
+    },
+    {
+      "epoch": 0.8804841149773072,
+      "grad_norm": 2.152708215011433,
+      "learning_rate": 7.240806474427598e-07,
+      "loss": 0.6081,
+      "step": 291
+    },
+    {
+      "epoch": 0.8835098335854765,
+      "grad_norm": 1.9524519551038517,
+      "learning_rate": 6.878506524119644e-07,
+      "loss": 0.5908,
+      "step": 292
+    },
+    {
+      "epoch": 0.886535552193646,
+      "grad_norm": 4.280045389112553,
+      "learning_rate": 6.525181817170756e-07,
+      "loss": 0.593,
+      "step": 293
+    },
+    {
+      "epoch": 0.8895612708018155,
+      "grad_norm": 1.7830376473459097,
+      "learning_rate": 6.180866407751595e-07,
+      "loss": 0.6492,
+      "step": 294
+    },
+    {
+      "epoch": 0.8925869894099848,
+      "grad_norm": 1.7849324700948386,
+      "learning_rate": 5.845593481697931e-07,
+      "loss": 0.5877,
+      "step": 295
+    },
+    {
+      "epoch": 0.8956127080181543,
+      "grad_norm": 1.7200906987170332,
+      "learning_rate": 5.519395353312195e-07,
+      "loss": 0.5976,
+      "step": 296
+    },
+    {
+      "epoch": 0.8986384266263238,
+      "grad_norm": 2.523328519492762,
+      "learning_rate": 5.20230346224897e-07,
+      "loss": 0.6417,
+      "step": 297
+    },
+    {
+      "epoch": 0.9016641452344932,
+      "grad_norm": 1.7332890626025772,
+      "learning_rate": 4.894348370484648e-07,
+      "loss": 0.6123,
+      "step": 298
+    },
+    {
+      "epoch": 0.9046898638426626,
+      "grad_norm": 1.7313495120885292,
+      "learning_rate": 4.5955597593719593e-07,
+      "loss": 0.6123,
+      "step": 299
+    },
+    {
+      "epoch": 0.9077155824508321,
+      "grad_norm": 1.9089514092546682,
+      "learning_rate": 4.305966426779118e-07,
+      "loss": 0.6209,
+      "step": 300
+    },
+    {
+      "epoch": 0.9107413010590015,
+      "grad_norm": 1.7209932552420357,
+      "learning_rate": 4.025596284314259e-07,
+      "loss": 0.5757,
+      "step": 301
+    },
+    {
+      "epoch": 0.913767019667171,
+      "grad_norm": 1.875857005840312,
+      "learning_rate": 3.7544763546352834e-07,
+      "loss": 0.597,
+      "step": 302
+    },
+    {
+      "epoch": 0.9167927382753404,
+      "grad_norm": 2.170147189258584,
+      "learning_rate": 3.492632768845261e-07,
+      "loss": 0.6199,
+      "step": 303
+    },
+    {
+      "epoch": 0.9198184568835098,
+      "grad_norm": 1.932298321660113,
+      "learning_rate": 3.2400907639740243e-07,
+      "loss": 0.5874,
+      "step": 304
+    },
+    {
+      "epoch": 0.9228441754916793,
+      "grad_norm": 1.9060668531244895,
+      "learning_rate": 2.996874680545603e-07,
+      "loss": 0.602,
+      "step": 305
+    },
+    {
+      "epoch": 0.9258698940998488,
+      "grad_norm": 2.876936994230681,
+      "learning_rate": 2.7630079602323447e-07,
+      "loss": 0.6068,
+      "step": 306
+    },
+    {
+      "epoch": 0.9288956127080181,
+      "grad_norm": 1.6979020112569279,
+      "learning_rate": 2.5385131435955e-07,
+      "loss": 0.59,
+      "step": 307
+    },
+    {
+      "epoch": 0.9319213313161876,
+      "grad_norm": 1.7392856626246644,
+      "learning_rate": 2.3234118679127615e-07,
+      "loss": 0.5997,
+      "step": 308
+    },
+    {
+      "epoch": 0.9349470499243571,
+      "grad_norm": 1.805002057886788,
+      "learning_rate": 2.117724865092774e-07,
+      "loss": 0.6114,
+      "step": 309
+    },
+    {
+      "epoch": 0.9379727685325264,
+      "grad_norm": 1.8063850245594506,
+      "learning_rate": 1.921471959676957e-07,
+      "loss": 0.6309,
+      "step": 310
+    },
+    {
+      "epoch": 0.9409984871406959,
+      "grad_norm": 1.7781982924325161,
+      "learning_rate": 1.734672066928822e-07,
+      "loss": 0.6006,
+      "step": 311
+    },
+    {
+      "epoch": 0.9440242057488654,
+      "grad_norm": 1.8021342311499136,
+      "learning_rate": 1.5573431910108404e-07,
+      "loss": 0.5949,
+      "step": 312
+    },
+    {
+      "epoch": 0.9470499243570348,
+      "grad_norm": 1.6024335443693254,
+      "learning_rate": 1.3895024232491338e-07,
+      "loss": 0.5801,
+      "step": 313
+    },
+    {
+      "epoch": 0.9500756429652042,
+      "grad_norm": 1.9581264928414572,
+      "learning_rate": 1.231165940486234e-07,
+      "loss": 0.6268,
+      "step": 314
+    },
+    {
+      "epoch": 0.9531013615733737,
+      "grad_norm": 1.7315183379261287,
+      "learning_rate": 1.0823490035218986e-07,
+      "loss": 0.6055,
+      "step": 315
+    },
+    {
+      "epoch": 0.9561270801815431,
+      "grad_norm": 2.2785089633330364,
+      "learning_rate": 9.43065955642275e-08,
+      "loss": 0.6048,
+      "step": 316
+    },
+    {
+      "epoch": 0.9591527987897126,
+      "grad_norm": 2.1203864893122013,
+      "learning_rate": 8.133302212373961e-08,
+      "loss": 0.618,
+      "step": 317
+    },
+    {
+      "epoch": 0.962178517397882,
+      "grad_norm": 1.7790483418175567,
+      "learning_rate": 6.931543045073708e-08,
+      "loss": 0.5928,
+      "step": 318
+    },
+    {
+      "epoch": 0.9652042360060514,
+      "grad_norm": 1.787018555262936,
+      "learning_rate": 5.8254978825718065e-08,
+      "loss": 0.5936,
+      "step": 319
+    },
+    {
+      "epoch": 0.9682299546142209,
+      "grad_norm": 2.023165603430636,
+      "learning_rate": 4.815273327803183e-08,
+      "loss": 0.5966,
+      "step": 320
+    },
+    {
+      "epoch": 0.9712556732223904,
+      "grad_norm": 1.744400598145924,
+      "learning_rate": 3.900966748312862e-08,
+      "loss": 0.6196,
+      "step": 321
+    },
+    {
+      "epoch": 0.9742813918305597,
+      "grad_norm": 2.6734084131681017,
+      "learning_rate": 3.082666266872036e-08,
+      "loss": 0.6032,
+      "step": 322
+    },
+    {
+      "epoch": 0.9773071104387292,
+      "grad_norm": 2.5457151249929115,
+      "learning_rate": 2.3604507529843e-08,
+      "loss": 0.6207,
+      "step": 323
+    },
+    {
+      "epoch": 0.9803328290468987,
+      "grad_norm": 48.615098546656974,
+      "learning_rate": 1.7343898152841765e-08,
+      "loss": 0.6019,
+      "step": 324
+    },
+    {
+      "epoch": 0.983358547655068,
+      "grad_norm": 1.7393804404319622,
+      "learning_rate": 1.2045437948275952e-08,
+      "loss": 0.5871,
+      "step": 325
+    },
+    {
+      "epoch": 0.9863842662632375,
+      "grad_norm": 1.934884937544193,
+      "learning_rate": 7.70963759277099e-09,
+      "loss": 0.5849,
+      "step": 326
+    },
+    {
+      "epoch": 0.989409984871407,
+      "grad_norm": 1.7879449709638233,
+      "learning_rate": 4.336914979787832e-09,
+      "loss": 0.625,
+      "step": 327
+    },
+    {
+      "epoch": 0.9924357034795764,
+      "grad_norm": 1.778813518283478,
+      "learning_rate": 1.9275951793518154e-09,
+      "loss": 0.6118,
+      "step": 328
+    },
+    {
+      "epoch": 0.9954614220877458,
+      "grad_norm": 3.4972680132091467,
+      "learning_rate": 4.819104067199653e-10,
+      "loss": 0.6033,
+      "step": 329
+    },
+    {
+      "epoch": 0.9984871406959153,
+      "grad_norm": 1.8469038074218784,
+      "learning_rate": 0.0,
+      "loss": 0.6178,
+      "step": 330
+    },
+    {
+      "epoch": 0.9984871406959153,
+      "step": 330,
+      "total_flos": 551924772372480.0,
+      "train_loss": 0.14928891153046578,
+      "train_runtime": 940.1371,
+      "train_samples_per_second": 44.997,
+      "train_steps_per_second": 0.351
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 330,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 83,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 551924772372480.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2df6a2f148bfe6db0dcca9fbb16b2761f7b4a59ca98eff55f49482d830e93860
+size 7032